Ändra sökning
Avgränsa sökresultatet
3456789 251 - 300 av 1446
RefereraExporteraLänk till träfflistan
Permanent länk
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Träffar per sida
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sortering
  • Standard (Relevans)
  • Författare A-Ö
  • Författare Ö-A
  • Titel A-Ö
  • Titel Ö-A
  • Publikationstyp A-Ö
  • Publikationstyp Ö-A
  • Äldst först
  • Nyast först
  • Skapad (Äldst först)
  • Skapad (Nyast först)
  • Senast uppdaterad (Äldst först)
  • Senast uppdaterad (Nyast först)
  • Disputationsdatum (tidigaste först)
  • Disputationsdatum (senaste först)
  • Standard (Relevans)
  • Författare A-Ö
  • Författare Ö-A
  • Titel A-Ö
  • Titel Ö-A
  • Publikationstyp A-Ö
  • Publikationstyp Ö-A
  • Äldst först
  • Nyast först
  • Skapad (Äldst först)
  • Skapad (Nyast först)
  • Senast uppdaterad (Äldst först)
  • Senast uppdaterad (Nyast först)
  • Disputationsdatum (tidigaste först)
  • Disputationsdatum (senaste först)
Markera
Maxantalet träffar du kan exportera från sökgränssnittet är 250. Vid större uttag använd dig av utsökningar.
  • 251.
    Fornlöf, Veronica
    et al.
    University of Skövde.
    Galar, Diego
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Syberfeldt, Anna
    University of Skövde.
    Almgren, torgny
    GKN Aerospace Engine Systems, Trollhättan.
    On-Condition Parts Versus Life Limited Parts: A Trade off in Aircraft Engines2016Ingår i: Current Trends in Reliability, Availability, Maintainability and Safety: An Industry Perspective / [ed] Uday Kumar; Alireza Ahmadi; Ajit Kumar Verma; Prabhakar Varde, Encyclopedia of Global Archaeology/Springer Verlag, 2016, s. 253-262Konferensbidrag (Refereegranskat)
    Abstract [en]

    Maintaining an aircraft engine is both complex and time consuming since an aircraft is an advanced system with high demands on safety and reliability. Each maintenance occasion must be as effective as possible and the maintenance need to be executed without performing excessive maintenance. The aim of this paper is to describe the essence of aircraft engine maintenance and to point out the potential for improvement within the maintenance planning by improving the remaining life predictions of the On-Condition parts, i.e. parts that are not given a fixed life limit.

  • 252.
    Frenne, Nicklas
    et al.
    Luleå tekniska universitet.
    Johansson, Örjan
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Acoustic time histories from vibrating surfaces of a diesel engine2006Ingår i: Applied Acoustics, ISSN 0003-682X, E-ISSN 1872-910X, Vol. 67, nr 3, s. 230-248Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    An experiment on a diesel engine provides for validation of a method that retrieves source strength spectra, source strength time histories and sound pressure time histories of the engine's complex partial sources. The method is based on empirical transfer function measurements and inverse matrix calculations briefly described in the article. Different simplifying source models were selected by comparison of calculated and measured auto spectra. The results show: (1) indication of time efficient measurements of source strength spectra, (2) the importance of correct source models in the case of separated source strength time histories, and (3) spectra of separated sound pressure time histories. Listening tests reported that it is possible to detect well differentiated sounds of the partial sources as a result of the method.

  • 253.
    Fuqing, Yuan
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Failure diagnostics using support vector machine2011Doktorsavhandling, sammanläggning (Övrigt vetenskapligt)
    Abstract [en]

    Failure diagnostics is an important part of condition monitoring aiming to identify incipient failures in early stages. Accurate and efficient failure diagnostics can guarantee that the operator makes the correct maintenance decision, thereby reducing the maintenance costs and improving system availability. The Support Vector Machine (SVM) is discussed in this thesis with the purpose of efficiently diagnosing failure. The SVM utilizes the kernel method to transform input data from a lower dimensional space to a higher dimensional space. In the higher dimensional space, the hitherto linearly non separable patterns can be linearly separated, without compromising the computational cost. This facilitates failure diagnostics as in the higher dimensional space, the existing failure or incipient failure is more identifiable. The SVM uses the maximal margin method to overcome the “overfitting” problem. This problem makes the model fit special data sets. The maximal margin method also makes it suitable for solving small sample size problems. In this thesis, the SVM is compared with another well known technique, the Artificial Neural Network (ANN). In the comparative study, the SVM performs better than the ANN. However, as the performance of the SVM critically depends on the parameters of the kernel function, this thesis proposes using an Ant Colony Optimization (ACO) method to obtain the optimal parameters. The ACO optimized SVM is applied to diagnose the electric motor in a railway system. The Support Vector Regression (SVR) is an extension of the SVM. In this thesis, SVR is combined with a time-series to forecast reliability. Finally, to improve the SVM performance, the thesis proposes a multiple kernel SVM. The SVM is an excellent pattern recognition technique. However, to obtain an accurate diagnostics performance, one has to extract the appropriate features. This thesis discusses the features extracted from the time domain and uses the SVM to diagnose failure for a bearing. Another case in this thesis is presented, namely failure diagnostics for an electric motor installed in a railway’s crossing and switching system; in this case, the features are extracted from the power consumption signal. In short, the thesis discuses the use of the SVM in failure diagnostics. Theoretically, the SVM is an excellent classifier or regressor possessing a solid theoretical foundation. Practically, the SVM performs well in failure diagnostics, as shown in the cases presented. Finally, as failure diagnostics critically relies on feature extraction, this thesis considers feature extraction from the time domain.

  • 254.
    Fuqing, Yuan
    et al.
    Tromsø University.
    Barabadi, Abbas
    Tromsø University.
    Lu, J.M.
    Department of Engineering and Safety, UiT The Arctic University of Norway, Tromsø.
    Garmabaki, Amir
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik. Islamic Azad University.
    Performance Evaluation for Maximum Likelihood and Moment Parameter Estimation Methods on Classical Two Weibull Distribution2015Ingår i: 2015 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM): Singapore, 6-9 Dec. 2015, Piscataway, NJ: IEEE Communications Society, 2015, s. 802-806, artikel-id 7385758Konferensbidrag (Refereegranskat)
    Abstract [en]

    The two-parameter Weibull distribution is the most widely used distribution in reliability engineering. Parameter estimation is a key issue to apply the Weibull to practical engineering. This paper aims to compare the performance of the maximum parameter estimation method (MLE) and the moment parameter method. It firstly investigates some mathematical properties such as solution uniqueness, estimator's equivariance and the confidence interval, that are important to practice. Later on their performances have been evaluated by using simulation. In the simulation, data sets ranged from extreme small to large have been considered. Weibull distribution with increasing, constant and deceasing failure rate have been chosen in the simulation to ensure the simulation's results concrete.

  • 255.
    Fuqing, Yuan
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Kumar, Uday
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser.
    A cost model for repairable system considering multi-failure type over finite time horizon2011Ingår i: International Journal of Pedagogy, Innovation and New Technologies, ISSN 0973-1318, E-ISSN 2392-0092, Vol. 7, nr 2, s. 186-194Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    In general, downtime of a system can be attributed due to multiple failure categories and repair costs for each failure categories can be different. Many of these failure types are repaired to a state which can be called as bad as old and such repair actions are termed as “minimal repair”. Many system or components are replaced after a certain number of such minimal repair actions. In this study, we intend to prove that if the system failure process can be described by NHPP (Non Homogenous Poisson Process), then each failure category can also be modelled by NHPP. Based on this, a cost model is developed by using the decomposition of the NHPP and renewal theory. Using the cost model, a model is developed to obtain the optimal number of minimum repair action every failure category. Since it is not possible to find any analytical solution, solution to the renewal function, an approximate approach is introduced to obtain numerical solution. Finally, a numerical example is presented to demonstrate the method.

  • 256.
    Fuqing, Yuan
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Kumar, Uday
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    A general imperfect repair model considering time-dependent repair effectiveness2012Ingår i: IEEE Transactions on Reliability, ISSN 0018-9529, E-ISSN 1558-1721, Vol. 61, nr 1, s. 95-100Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Kijima I and Kijima II models are two important imperfect repair models in literature. These two models use one constant parameter to represent the degree of repair, which is called Repair Effectiveness (RE) in this paper. We developed a more general imperfect repair model by extending the constant RE to a time-dependent function based on the virtual age process, where the Kijima models are special cases of the new model. A simulation method is developed to estimate the cumulative number of failures for the new model, and a Bayesian inference method is proposed to select the best imperfect repair model. Finally, to demonstrate the new model, a numerical example is provided. From this example, the new model shows a more accurate mean and a narrower confidence interval than that of the Non-Homogeneous Poisson Processes, and Kijima I and Kijima II models.

  • 257.
    Fuqing, Yuan
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Kumar, Uday
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Anomaly detection using support vector machines on overhead contact wire2013Konferensbidrag (Övrigt vetenskapligt)
    Abstract [en]

    This paper describes an anomaly detection method on the Overhead Contact Wire (OCW) in electrified railway system. The fundamental basic of contact wire is described. Their mechanical property and thermal property are discussed. The principle of the current collection through the overhead wire is described in brief. Some classical mechanic dynamic models between the pantograph and overhead contact wire are presented. Concentrating on the anomaly detection using vertical acceleration signal, this paper proposes a support vector regression based method to detect the anomaly detection on the surface of the overhead contact wire. The Support Vector Regression (SVR) is used to model the dependency between vertical acceleration and the other factor such as uplift, train speed, height of the wire. Correlation is used to find the significant factors which influence the vertical acceleration. The SVR model is used to de-trend the vertical acceleration signal. The statistical model is proposed to find the anomaly points on the contact wire.

  • 258.
    Fuqing, Yuan
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Kumar, Uday
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Kernelized proportional intensity model for repairable systems considering piecewise operating conditions2012Ingår i: IEEE Transactions on Reliability, ISSN 0018-9529, E-ISSN 1558-1721, Vol. 61, nr 3, s. 618-624Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    The proportional intensity model (PIM) has been used to model the intensity function of repairable systems taking non-time factors, such as operating conditions, and repair history, into consideration. This paper develops a kernelized PIM (KPIM) by combining the PIM and the kernel method to consider a scenario where a repairable system experiences piecewise operating conditions. The kernel method is used to approximate the PIM covariate function nonlinearly. An approach based on the regularized likelihood function is proposed to obtain the optimal parameters for the KPIM. A numerical example is provided to demonstrate the KPIM model, and the parameter estimation approach

  • 259. Fuqing, Yuan
    et al.
    Kumar, Uday
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Predicting time to failure using support vector regression2010Ingår i: Proceedings of the 1st international workshop and congress on eMaintenance, Luleå tekniska universitet, 2010, s. 223-226Konferensbidrag (Refereegranskat)
    Abstract [en]

    Support Vector Machine (SVM) is a new but prospective technique which has been used in pattern recognition, data mining, etc. Taking the advantage of Kernel function, maximum margin and Lanrangian optimization method, SVM has high application potential in reliability data analysis. This paper introduces the principle and some concepts of SVM. One extension of regular SVM named Support Vector Regression (SVR) is discussed. SVR is dedicated to solve continuous problem. This paper uses SVR to predict reliability for repairable system. Taking an equipment from Swedish railway industry as a case, it is shown that the SVR can predict (Time to Failure) TTF accurately and its prediction performance can outperform Artificial Neural Network (ANN).

  • 260.
    Fuqing, Yuan
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Kumar, Uday
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Proportional Intensity Model considering imperfect repair for repairable systems2013Ingår i: International Journal of Pedagogy, Innovation and New Technologies, ISSN 0973-1318, E-ISSN 2392-0092, Vol. 9, nr 2, s. 163-174Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    The Proportional Intensity Model (PIM) extends the classical Proportional Hazard Model (PHM) in order to deal with repairable systems. This paper develops a more general PIM model which uses the imperfect model as baseline function. By using the imperfect model, the effectiveness of repair has been taken into account, without assuming an "as-bad-as-old" or an "as-good-as-new" scheme. Moreover, the effectiveness of other factors, such as the environmental conditions and the repair history, is considered as covariant in this PIM. In order to solve the large number parameters estimation problem, a Bayesian inference method is proposed. The Markov Chain Monte Carlo (MCMC) method is used to compute the posterior distribution for the Bayesian method. The Bayesian Information Criterion (BIC) is employed to perform model selection, namely, selecting the baseline function and remove the nuisance factors in this paper. In the final, a numerical example is provided to demonstrate the proposed model and method.

  • 261. Fuqing, Yuan
    et al.
    Kumar, Uday
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Replacement policy for repairable system under various failure types with finite time horizon2009Konferensbidrag (Övrigt vetenskapligt)
    Abstract [en]

    The repairable system suffers various type of failure and each failure type has different repair cost. Assume the failure process of the system as Non-homogenous Poisson Process (NHPP). The system is replaced after it experienced a predetermined number of minimal repairs. Considering finite time horizon, the paper proposes a replacement model for the system. It firstly proves that the failure process of each type of failure also follows NHPP. Then it develops a model to estimate the total cost which covers minimal repair cost for each type of failure and system replacement cost. To obtain the numerical solution, the paper introduces a numerical approach to approximate renewal function and a nonlinear programming model is developed. A numerical example is presented eventually.

  • 262. Fuqing, Yuan
    et al.
    Kumar, Uday
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Statistical index development from time domain for rolling element bearings2014Ingår i: International Journal of Pedagogy, Innovation and New Technologies, ISSN 0973-1318, E-ISSN 2392-0092, Vol. 10, nr 3, s. 313-324Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Feature extraction is crucial to efficiently diagnose fault. This paper discusses a number of time-domain statistical features, including Kurtosis or the Crest Factor, the Mean by Deviation Ratio (MDR), and Symbolized Sequence Shannon Entropy (SSSE). The SSSE reflects the spatial distribution of the signal which is complementary with the statistical features. A new feature, Normalized Normal Negative Likelihood (NNNL), is used to improve the Normal Negative Likelihood (NNL). A Separation Index (SI) called the Extended SI (ESI) evaluates the performance of each feature and to remove noise feature. The Multi-Class Support Vector Machine (MSVM) recognizes bearing defect patterns. A numerical case is presented to demonstrate these features, their feature subset selection method and the pattern recognition method. The MSVM is used to detect three different types of bearing defects: defects in the inner race, outer race and bearing ball

  • 263.
    Fuqing, Yuan
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Kumar, Uday
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Galar, Diego
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    A comparative study of artificial neural networks and support vector machine for fault diagnosis2013Ingår i: International Journal of Pedagogy, Innovation and New Technologies, ISSN 0973-1318, E-ISSN 2392-0092, Vol. 9, nr 1, s. 49-60Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Fault detection is a crucial step in condition based maintenance requiring. The importance of fault diagnosis necessitates an efficient and effective failure pattern identification method. Artificial Neural Networks (ANN) and Support Vector Machines (SVM) emerging as prospective pattern recognition techniques in fault diagnosis have been showing its adaptability, flexibility and efficiency. Regardless of variants of the two techniques, this paper discusses the principle of the two techniques, and discusses their theoretical similarity and difference. Eventually using the commonest ANN, SVM, a case study is presented for fault diagnosis using a wide used bearing data. Their performances are compared in terms of accuracy, computational cost and stability

  • 264.
    Fuqing, Yuan
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Kumar, Uday
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Galar, Diego
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    An adaptive multiple kernel method-based support vector machine used for classication2013Ingår i: International Journal of Condition Monitoring, ISSN 0019-6398, E-ISSN 2047-6426, Vol. 3, nr 1, s. 8-15Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Classification is an important technique used for condition monitoring. Extensive research has been carried out on classification and numerous techniques have been developed. The support vector machine (SVM) is one of these techniques; it has excellent classification capacity and is widely used. The effectiveness of the SVM depends on the selection of the kernel function, so to maximise performance this paper proposes using an adaptive multiple kernel SVM (AMK-SVM). Using AMK, many heterogeneous features, such as continuous, categorical, logical etc, can be merged. Instead of predefining the parameters of kernel functions as with other multiple kernel SVMs, this method can adapt its parameters to data automatically through kernel alignment. The paper offers two numerical examples: one with benchmarking data to test the feasibility and performance of the approach (for this case a two-layer neural network and two single kernel SVMs are applied to the same datasets to compare their performance with the AMK-SVM); the other example uses the AMK-SVM to discriminate a healthy bearing from a defective bearing

  • 265.
    Fuqing, Yuan
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Kumar, Uday
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Galar, Diego
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Failure detection using support vector machine and artificial neural networks: a comparative study2011Ingår i: The Eighth International Conference on Condition Monitoring and Machinery Failure Prevention Technologies: St. David's Hotel, Cardiff, Wales, 20 - 22 June 2011 ; CM2011/MFPT2011, Longborough, Glos.: Coxmoor Publishing Co. , 2011, Vol. 1, s. 189-201Konferensbidrag (Refereegranskat)
  • 266.
    Fuqing, Yuan
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Kumar, Uday
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Galar, Diego
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Failure diagnosis of railway assets using support vector machine and ant colony optimization method2012Ingår i: International Journal of COMADEM, ISSN 1363-7681, Vol. 15, nr 2, s. 3-10Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Support Vector Machine (SVM) is an excellent technique for pattern recognition. This paper uses a multi-class SVM as a classifier to solve a multi-class classification problem for fault diagnosis. As the pre-defined parameters in the SVM influence the performance of the classification, this paper uses the heuristic Ant Colony Optimization (ACO) algorithm to find the optimal parameters. This multi-class SVM and ACO are applied to the fault diagnosis of an electric motor used in a railway system. A case study illustrates how efficient the ACO is in finding the optimal parameters. By using the optimal parameters from the ACO, the accuracy of the performed diagnosis on the electric motor is found to be highest.

  • 267.
    Fuqing, Yuan
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Kumar, Uday
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser.
    Galar, Diego
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser.
    Reliability prediction using support vector regression2010Ingår i: International Journal of Systems Assurance Engineering and Management, ISSN 0975-6809, E-ISSN 0976-4348, Vol. 1, nr 3, s. 263-268Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Reliability prediction of machinery is crucial to schedule overhauls, spare parts replacement and maintenance interventions. Many AI tools have been used in order to provide these predictions for the industry. Support vector regression (SVR) is a nonlinear regression technique extended from support vector machine. SVR can fit data flexibly and it has a wide variety of applications. This paper utilizes SVR combining time series to predict the next failure time based on historical failure data. To solve the parameter selection problem a method has been proposed. This method approximates the widely used leave-one-out method. To bound the prediction error, a confidence interval is proposed based on the non-homogeneous poisson process. A numerical case from the mining industry is presented to demonstrate the developed approach.

  • 268.
    Fuqing, Yuan
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Kumar, Uday
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Krishna, B. Misra
    Complex system reliability evaluation using support vector machine for incomplete data-set2011Ingår i: International Journal of Pedagogy, Innovation and New Technologies, ISSN 0973-1318, E-ISSN 2392-0092, Vol. 7, nr 1, s. 32-42Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Support Vector Machine (SVM) is an artificial intelligence technique that has been successfully used in data classification problems, taking advantage of its learning capacity. In systems modelled as networks, SVM has been used to classify the state of a network as failed or operating to approximate the network reliability. Due to the lack of information, or high computational complexity, the complete analytical expression of system states may be impossible to obtain, that is to say, only incomplete data-set can be obtained. Using these incomplete data-sets, depending on amount of missed data-set, this paper proposes two different approaches named rough approximation method and simulation based method to evaluate system reliability. SVM is used to make the incomplete data-set complete. Simulation technique is also employed in the so called simulation based approximation method. Several examples are presented to illustrate the approaches.

  • 269. Fuqing, Yuan
    et al.
    Kumar, Uday
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    S, Claudio M. Rocco
    Facultad de Ingeniería, Universidad Central de Venezuela.
    Misra, Krishna B.
    RAMS Consultants.
    Complex system reliability evaluation using support vector machine2010Konferensbidrag (Övrigt vetenskapligt)
    Abstract [en]

    Support Vector Machine (SVM) is a data mining technique that has been successfully used in classification problems, starting from a known training data set (TDS). In systems modeled as networks, SVM has been used to classify the state of a network as failed or operating and jointly combined in a Monte Carlo sampling approach to approximate the network reliability. The analytical expression of the binary function (failed/operating) produced by SVM is difficult to be understood, since it generally involves the evaluation of non-linear operators, which consider a subset of the TDS, called Support Vectors (SV) and sampled system states. In this paper a different approach is proposed to assess system reliability. Information about path and cut sets is obtained directly from SV, without considering the analytical expression of the binary function produced by SVM. From here the system reliability is approximated directly. Several examples illustrate the approach.

  • 270.
    Galar, Diego
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Editorial Special Issue on Developments and Applications in Maintenance Performance2013Ingår i: International Journal of Strategic Engineering Asset Management (IJSEAM), ISSN 1759-9733, E-ISSN 1759-9741, Vol. 1, nr 3, s. 225-227Artikel i tidskrift (Refereegranskat)
  • 271.
    Galar, Diego
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Reliability and maintenance programs in nuclear power plants2011Konferensbidrag (Refereegranskat)
  • 272.
    Galar, Diego
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Berges, Luis
    University of Zaragoza.
    Application of dynamic benchmarking of rotating machinery for eMaintenance2010Ingår i: Proceedings of the 1st international workshop and congress on eMaintenance, Luleå tekniska universitet, 2010, s. 227-233Konferensbidrag (Refereegranskat)
    Abstract [en]

    The vibration analysis and condition monitoring technology is based on comparison of measurements obtained with benchmarks suggested by manufacturers or standards. In this case, the references provided by current rules are static and independent of parameters such as age or environmental conditions in which the machine is analyzed.New communication technologies allow the integration of eMaintenance systems, production and real-time data or the result of vibration routes. The integration of all these data allows Data mining and extraction of parameters to be incorporated into decision-making typical of CBM, such as repairs, downtime, overhauls etc.This paper proposes the use of indicators that result from data mining as a reference dynamic, not static as proposed by the standard. The application of these references to the decision making process of the maintenance manager avoids unnecessary repairs caused by false alarms and thus prolongs the life of the equipment, resulting in the improvement of parameters such as the MTBF, in a eMaintenance system.

  • 273.
    Galar, Diego
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Berges, Luis
    Universidad de Zaragoza.
    Lambán, Ma Pilar
    Universidad de Zaragoza.
    Tormos, Bernardo
    Universidad Politécnica de Valencia.
    The measurement of maintenance function efficiency through financial KPIS2014Ingår i: Dyna, ISSN 0012-7353, Vol. 81, nr 184, s. 102-109Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    The measurement of the performance in the maintenance function has produced large sets of indicators that due to their nature and disparity in criteria and objectives have been grouped in different subsets lately, emphasizing the set of financial indicators. To generate these indicators properly is necessary to have accurate input data. Hence in this paper we propose a comprehensive model of consensus between the different stakeholders involved in the maintenance function. This will bring about the accurate determination of the maintenance costs of an organization

  • 274.
    Galar, Diego
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Berges, Luis
    University of Zaragoza.
    Lambán, Pilar
    University of Zaragoza.
    Huertas-Talón, Jose Luis
    University of Zaragoza.
    Tormos, Bernardo
    UPV.
    Cálculo de la vida útil remanente mediante trayectorias móviles entre hiperplanos de máquinas de de soporte vectorial2013Ingår i: Interciencia, ISSN 0378-1844, Vol. 38, nr 8, s. 556-562Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    We propose a new method for predicting remaining useful life ( RUL ) classifiers inspired by support vector machines ( SVM). Historical data of condition of a system during its lifetime are used to create a classification by hyperplanes in SVM. To estimate the RUL of a system , the degradation rate was assessed by calculating the minimum distance defined based on the degradation pathways , ie , the progressive approach hyperplane segregates information from both good and bad for different time horizons.One can estimate the final life of a specific component , or the information in the RUL of a population be calculated by aggregating multiple RUL estimates using a density estimation method . The degradation of a system is affected by many unknown factors , besides complicating degradation behaviors , difficult to collect quality data.Due to lack of knowledge and incomplete measurements , normally lacks important information on the context of the data collected . Therefore historical data of the system with a variety of degradation patterns are grouped , with the search for a global model RUL prediction is extremely difficult. This leads them to seek advanced forecasting techniques beyond traditional models. The proposed model develops an effective RUL prediction method that addresses multiple challenges in forecasting complex systems. The similarities between degradation pathways can be contrasted to enrich existing methodologies prognosis.

  • 275.
    Galar, Diego
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Berges, Luis
    University of Zaragoza.
    Lambán, Pilar
    University of Zaragoza.
    Tormos, Bernardo
    UPV.
    La medición de la eficiencia de la función mantenimiento a través de KPIs financieros2014Ingår i: Dyna, ISSN 0012-7353, Vol. 81, nr 184, s. 102-109Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    The measurement of the performance in the maintenance function has produced large sets of indicators that due to their nature and disparity in criteria and objectives have been grouped in different subsets lately, emphasizing the set of financial indicators. To generate these indicators properly is necessary to have accurate input data. Hence in this paper we propose a comprehensive model of consensus between the different stakeholders involved in the maintenance function. This will bring about the accurate determination of the maintenance costs of an organization.

  • 276.
    Galar, Diego
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Fuqing, Yuan
    Department of Engineering and Safety, University of Tromsø, Tromsø, Norway.
    Harmonic and Inter-harmonic Analysis on Power Signal from Railway Traction Systems2017Ingår i: International Journal of COMADEM, ISSN 1363-7681, Vol. 20, nr 2, s. 3-10Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    A thorough investigation of wave velocity effects to the accuracy of damage location in a two dimensional source location algorithm of acoustic emission technique was carried out with pencil lead breaks (PLB) tests on a steel plate (SS400). Several AE signal propagation modes were investigated along with the experimental averaging values of wave velocity. Results show that the appropriate consideration of velocity mode in damage location is an important factor in reducing the errors of damage source location in acoustic emission technique.

  • 277.
    Galar, Diego
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Ghodrati, Behzad
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Fusion of CMMS Data and CM Data - a real need for maintenance: Part 22012Ingår i: Maintworld, ISSN 1798-7024, E-ISSN 1799-8670, nr 3, s. 40-43Artikel i tidskrift (Övrigt vetenskapligt)
  • 278.
    Galar, Diego
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Ghodrati, Behzad
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Fusion of CMMS data and CM data: a real need for maintenance (part I)2012Ingår i: Maintworld, ISSN 1798-7024, E-ISSN 1799-8670, nr 2, s. 42-45Artikel i tidskrift (Övrigt vetenskapligt)
    Abstract [en]

    Maintenance can be considered as an information processing system. Therefore, thedevelopment of future maintenance information systems is one of the most importantcurrent research problems to model the effects of automatic condition monitoringsystems enabled by embedded electronics and software.

  • 279.
    Galar, Diego
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Gustafson, Anna
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Tormos, Bernardo
    Berges, Luis
    Podejmowanie decyzji eksploatacyjnych w oparciu o fuzje{ogonek} różnego typu danych2012Ingår i: Eksploatacja i niezawodnosc - Maintenance and Reliability, ISSN 1507-2711, Vol. 14, nr 2, s. 135-144Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Over the last decade, system integration is applied more as it allows organizations to streamline business processes. A recent development in the asset engineering management is to leverage the investment already made in process control systems. This allows the operations, maintenance, and process control teams to monitor and determine new alarm level based on the physical condition data of the critical machines. Condition-based maintenance (CBM) is a maintenance philosophy based on this massive data collection, wherein equipment repair or replacement decisions depend on the current and projected future health of the equipment. Since, past research has been dominated by condition monitoring techniques for specific applications; the maintenance community lacks a generic CBM implementation method based on data mining of such vast amount of collected data. The methodology would be relevant across different domains. It is necessary to integrate Condition Monitoring (CM) data with management data from CMMS (Computer Maintenance Management Systems) which contains information, such as: component failures, failure information related data, servicing or repairs, and inventory control and so on. These systems are the core of traditional scheduled maintenance practices and rely on bulk observations from historical data to make modifications to regulated maintenance actions. The most obvious obstacle in the integration of CMMS, process and CM data is the disparate nature of the data types involved, and there have benn several attempts to remedy this problem. Although, there have been many recent efforts to collect and maintain large repositories of these types of data, there have been relatively few studies to identify the ways these to datasets could be related. This paper attempts to fulfill that need by proposing a combined data mining-based methodology for CBM considering CM data and Historical Maintenance Management data. It shows a system integration of physical and management data that also supports business intelligence and data mining where data sets can be combined in non-traditional ways.

  • 280.
    Galar, Diego
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Johansson, Carl-Anders
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Mouzoune, A.
    Mohammed V University.
    Taibi, S.
    Mohammed V University.
    Risk Based Maintenance policies for SMART devices2013Ingår i: Proceedings of International Conference Life Cycle Engineering and Management ICDQM-2013 / [ed] Ljubisa Papic, Prijevor: Research Center of Dependability and Quality Management DQM , 2013, Vol. 2, s. 470-486Konferensbidrag (Refereegranskat)
  • 281.
    Galar, Diego
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Johansson, Carl-Anders
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Mouzoune, A.
    Ecole Mohammadia d'ingénieurs, Mohammed V University – Agdal, Rabat.
    Taibi, S.
    Ecole Mohammadia d'ingénieurs, Mohammed V University – Agdal, Rabat.
    Risk Based Maintenance policies for SMART devices2013Ingår i: Communications in Dependability and Quality Management, ISSN 1450-7196, Vol. 16, nr 3, s. 15-28Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Maintenance activities are commonly organized into scheduled and unscheduled actions. Scheduled maintenance is undertaken during pre-programmed inspections. Such maintenance operations try to minimize the risk of deterioration based on a priori knowledge of failure mechanisms and their timing. However, in complex systems it is not always possible to schedule maintenance actions to mitigate all undesired effects, and SMART systems, which monitor selected parameters, propose actions to correct any deviation in normal behavior. Maintenance decisions must be made on the basis of accepted risk. Performed or not performed scheduled tasks as well as deferred corrective actions can have positive or negative consequences for the company, technicians and machines. These three risks should be properly assessed and prioritized as a function of the goals to be achieved. This paper focuses on how best practices in risk assessment for human safety can be successfully transferred to risk assessment for asset integrity.

  • 282.
    Galar, Diego
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Kans, Mirka
    Department of Mechanical Engineering, Linnaeus University, Växjö.
    The Impact of Maintenance 4.0 and Big Data Analytics within Strategic Asset Management2017Ingår i: Proceedings of MPMM 2016: 6th International Conference on Maintenance Performance Measurement and Management, 28 November 2016, Luleå, Sweden / [ed] Diego Galar, Dammika Seneviratne, Luleå: Luleå tekniska universitet, 2017, s. 96-104Konferensbidrag (Refereegranskat)
    Abstract [en]

    The latest industrial revolution is manifested by smart and networking equipment. Realizing the full value of these machineries, and other business assets, has become increasingly important. Strategic asset management faces managerial, technical as well as methodological challenges, of which some could be reduced or overcome by applying technological solutions such as Internet of things, cloud computing, cyber-physical systems and big data analytics. This paper outlines the impact of the emerging technologies in the area of strategic management with special emphasis on the analytics as service provider for the maintenance functions.

  • 283.
    Galar, Diego
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Kans, Mirka
    Linnaeus University.
    Schmidt, Bernard
    University of Skövde.
    Big Data in Asset Management: Knowledge Discovery in Asset Data by the Means of Data Mining2016Ingår i: Proceedings of the 10th World Congress on Engineering Asset Management (WCEAM 2015) / [ed] Kari T. Koskinen; Helena Kortelainen; Jussi Aaltonen; Teuvo Uusitalo; Kari Komonen; Joseph Mathew; Jouko Laitinen, Encyclopedia of Global Archaeology/Springer Verlag, 2016, s. 161-171Konferensbidrag (Refereegranskat)
    Abstract [en]

    Assets are complex mixes of complex systems, built from components which, over time, may fail. The ability to quickly and efficiently determine the cause of failures and propose optimum maintenance decisions, while minimizing the need for human intervention is necessary. Thus, for complex assets, much information needs to be captured and mined to assess the overall condition of the whole system. Therefore the integration of asset information is required to get an accurate health assessment of the whole system, and determine the probability of a shutdown or slowdown. Moreover, the data collected are not only huge but often dispersed across independent systems that are difficult to access, fuse and mine due to disparate nature and granularity. If the data from these independent systems are combined into a common correlated data source, this new set of information could add value to the individual data sources by the means of data mining. This paper proposes a knowledge discovery process based on CRISP-DM for failure diagnosis using big data sets. The process is exemplified by applying it on railway infrastructure assets. The proposed framework implies a progress beyond the state of the art in the development of Big Data technologies in the fields of Knowledge Discovery algorithms from heterogeneous data sources, scalable data structures, real-time communications and visualizations techniques.

  • 284.
    Galar, Diego
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Kumar, Uday
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    SMART bearing: from sensing to actuation2013Ingår i: Proceedings of the 12th IMEKO TC10 Workshop on Technical Diagnostics: New Perspectives in Measurements, Tools and Techniques for Industrial Applications, Florence, Italy: IMEKO , 2013, s. 21-30Konferensbidrag (Refereegranskat)
    Abstract [en]

    A Centre has been created within Lulea University of Technology (LTU), with support from SKF, to examine the opportunities presented by developments in sensing and communication technologies in adding sensing and analysis functionality to rolling element bearings. One of the goals is the development of an artefact which closes the loop from sensing to actuation and taking advantage of all existing IT, mechanical and maintenance technologies.

  • 285.
    Galar, Diego
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Kumar, Uday
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Berges, Luis
    Department Design engineering and manufacturing, University of Zaragoza.
    Sandborn, Peter
    CAlCe Center for Advanced life Cycle engineering, University of Maryland.
    The need for aggregated indicators in performance asset management2014Ingår i: Eksploatacja i niezawodnosc - Maintenance and Reliability, ISSN 1507-2711, Vol. 16, nr 1, s. 120-127Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Composite indicators formed when individual Indicators are compiled into a single index. A composite indicator should ideally measure multidimensional concepts that cannot be captured by a single index. Since asset management is multidisciplinary,composite indicators would be helpful. This paper describes a method of monitoring a complex entity in a processing plant. In this scenario, a composite use index from a combination of lower level use indices and weighting values. Each use index contains status information on one aspect of the lower level entities, and each weighting value corresponds to one lower level entity. The resulting composite indicator can be a decision-making tool for asset managers.

  • 286.
    Galar, Diego
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Kumar, Uday
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Fuqing, Yuan
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    RUL prediction using moving trajectories between SVM hyper planes2012Ingår i: 2012 proceedings: Annual Reliability and Maintainability Symposium (RAMS 2011) : Reno, Nv 23-26 Jan. 2012, Piscataway, NJ: IEEE Communications Society, 2012Konferensbidrag (Refereegranskat)
    Abstract [en]

    With increasing amounts of data being generated by businesses and researchers, there is a need for fast, accurate and robust algorithms for data analysis. Improvements in database's technology, computing performance and artificial intelligence have contributed to the development of intelligent data analysis. The primary aim of data mining is knowledge discovery, i.e. patterns in the data that lead to better understanding of the data generating process and to useful predictions. The knowledge that becomes available through data mining enables an asset owner to make important decisions about life cycle costs in advance. In maintenance field, CMMS (Computer maintenance management system) and CM (Condition Monitoring) are the most popular software available in the industries. Since first one stores all historical data, maintenance actions, events and ma nufacturer recommendations, second one collects and stores all critical physical parameters (vibration, temperature.) to be monitored in a regular time basis. However, converting these data into useful information is a challenge. The degradation process of a system may be affected by many unknown factors, such as unidentified fault modes, unmeasured operational conditions, engineering variance, environmental conditions, etc. These unknown factors not only complicate the degradation behaviors of the system, but also make it difficult to collect quality data. Due to lack of knowledge and incomplete measurements, certain important con text information (e.g. fault modes, operational conditions) of the collected data will be missing. Therefore, historical data of the system with a large variety of degradation patterns will be mixed together. With such data, learning a global model for Remaining Useful Life (RUL) prediction becomes extremely hard since the end user does not have enough and good-quality data to model properly the system. This has led us to look for advanced RUL prediction techniques beyond the traditional RUL prediction models. The degradation process for many engineering systems, especially mechanical systems, is irreversible unless the condition is recovered by effective maintenance actions. The irreversible degradation process does not necessarily imply that the observed features will exhibit a monotonic progression pattern during degradation. Such progression pattern is sometimes hard to model using parametric methods. Considering a degradation process involving no or limited maintenance, the process may compose of a sequence of irreversible stages (either discrete or continuous) from new to be worn out, which can be implicitly expressed by the trajectory of the measured condition data or features. Therefore, the RUL of the system can be estimated if its future degradation trend can be projected from those historical instances. In this paper, a novel RUL prediction method inspired by feature maps and SVM classifiers is proposed. The historical instances of a system with life-time condition data are used to create a classification by SVM hyper planes. For a test instance of the same system, whose RUL is going to be estimated, degradation speed is evaluated by computing the minimal distance defined based on the degradation trajectories, i.e. the approach of the system to the hyper plane that segregates good and bad condition data at a different time horizon. Therefore, the final RUL of a specific component can be estimated, and global RUL information can then be obtained by aggregating the multiple RUL estimations using a density estimation method. Proposed model develops an effective RUL prediction method that addresses multiple challenges in complex system prognostics, where many parameters are unknown. Similarities between degradation trajectories can be checked in order to enrich existing methodologies in prognostic's applications. Existing CM data for bearings will be used to verify the model.

  • 287.
    Galar, Diego
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Kumar, Uday
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Juuso, Esko
    University of Oulu.
    Lahdelma, Sulo
    University of Oulu.
    Fusion of maintenance and control data: a need for the process2012Ingår i: Proceedings of 18th World Conference on Nondestructive Testing: April 2012, Durban, South Africa, 2012Konferensbidrag (Refereegranskat)
    Abstract [en]

    A process control system deals with disperse information sources mostly related with operation and maintenance issues. For integration purposes, a data collection and distribution system based on the concept of cloud computing is proposed to collect data or information pertaining to the assets of a process plant from various sources or functional areas of the plant inc1uding, for example, the process control functional areas, the maintenance functional areas and the process performance monitoring functional areas. This data and information is manipulated in a coordinated manner by the cloud using XML for data exchange, and is redistributed to other applications where is used to perform overall better or more optimal control, maintenance and business activities. From maintenance point of view, the benefit is that information or data may be collected by maintenance functions pertaining to the health, variability, performance or utilization of an asset. The end user, i.e. operators and maintainers are also considered. A user interface becomes necessary in order to enable users to access and manipulate the data and optimize plant operation. Furthermore, applications, such as work order generation applications may automatically generate work orders, parts or supplies orders, etc. based on events occurring within the plant due to this integration of data and creation of new knowledge as a consequence of such process.

  • 288.
    Galar, Diego
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Kumar, Uday
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Lee, J.
    NSFI/UCR Center for Intelligent Maintenance System (IMS), University of Cincinnati.
    Zhao, W.
    NSFI/UCR Center for Intelligent Maintenance System (IMS), University of Cincinnati.
    Remaining useful life estimation using time trajectory tracking and support vector machines2012Ingår i: 25th International Congress on Condition Monitoring and Diagnostic Engineering (COMADEM 2012): 18–20 June 2012, Huddersfield, UK, IOP Publishing Ltd , 2012, artikel-id 012063Konferensbidrag (Refereegranskat)
    Abstract [en]

    In this paper, a novel RUL prediction method inspired by feature maps and SVM classifiers is proposed. The historical instances of a system with life-time condition data are used to create a classification by SVM hyper planes. For a test instance of the same system, whose RUL is to be estimated, degradation speed is evaluated by computing the minimal distance defined based on the degradation trajectories, i.e. the approach of the system to the hyper plane that segregates good and bad condition data at different time horizon. Therefore, the final RUL of a specific component can be estimated and global RUL information can then be obtained by aggregating the multiple RUL estimations using a density estimation method.

  • 289.
    Galar, Diego
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Kumar, Uday
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Lee, Jay
    Center for Intelligent Maintenance Systems (IMS), Cincinnati, OH.
    Zhao, Wenyu
    Center for Intelligent Maintenance Systems (IMS), Cincinnati, OH.
    Remaining useful life estimation using time trajectory tracking and support vector machines2012Ingår i: International Journal of COMADEM, ISSN 1363-7681, Vol. 15, nr 3, s. 2-8Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    In this paper, a novel RUL prediction method inspired by feature maps and SVM classifiers is proposed. The historical instances of a system with life-time condition data are used to create a classification by SVM hyper planes. To test the system's RUL, degradation speed is evaluated by computing the minimal distance based on the degradation trajectories, i.e. the approach of the system to the hyper plane that segregates good and bad condition data on a different time horizon. The final RUL of a specific component can be estimated and global RUL information can be obtained by aggregating the multiple RUL estimations using a density estimation method

  • 290.
    Galar, Diego
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Kumar, Uday
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Parida, Aditya
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Maintenance audits: elements of the metric2012Ingår i: Mantenimiento, ISSN 0214-4344Artikel i tidskrift (Övrigt vetenskapligt)
  • 291.
    Galar, Diego
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Kumar, Uday
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Parida, Aditya
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Berges, Luis
    University of Saragossa.
    Auditorias de mantenimiento2011Ingår i: Ingenieria y Gestion de Mantenimiento, ISSN 1695-3754, Vol. 16, nr 76, s. 16-29Artikel i tidskrift (Refereegranskat)
  • 292.
    Galar, Diego
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Kumar, Uday
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Sandborn, P.
    CAlCe Center for Advanced life Cycle engineering, University of Maryland.
    Morant, Amparo
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    O&M efficiency model: A dependability approach2012Ingår i: 25th International Congress on Condition Monitoring and Diagnostic Engineering (COMADEM 2012): 18–20 June 2012, Huddersfield, UK, IOP Publishing Ltd , 2012, artikel-id 012111Konferensbidrag (Refereegranskat)
    Abstract [en]

    The occurrence of equipment failures is one of the main causes of inefficiency. These events increase the operational costs and give rise to a loss of revenues or in the worst case they can even produce an accident with significant damages to people and the environment. The efficiency of the operation of an industrial installation in a given period of time has been defined use the ratio of the Dependability level achieved by the installation in a specified period of time and the sum of the corresponding Dependability and Undependability costs. The aim of this paper is the development of a methodology for the calculation of operating costs in industrial facilities that addresses the difficulty of performing a simple, homogeneous and objective evaluation of the operational efficiency of the industrial facility. The main obstacle to this evaluation is the lack of a method for quantifying Dependability, which to date has always been considered a purely qualitative characteristic.

  • 293.
    Galar, Diego
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Kumar, Uday
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Villarejo, Roberto
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Johansson, Carl-Anders
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Hybrid prognosis for railway health assessment: an information fusion approach for PHM deployment2013Ingår i: PHM2013: 2013 Prognostic and System Health Management: Milan 8-11 September 2013 / [ed] Enrico Zio; Piero Baraldi, AIDIC Servizi S.r.l. , 2013, s. 769-774Konferensbidrag (Refereegranskat)
    Abstract [en]

    Many railway assets suffer increasing wear and tear during operation. Prognostics can assist diagnosis by assessing the current health of a system and predicting its remaining life based on features that capture the gradual degradation in a system's operational capabilities. Prognostics are critical to improve safety, plan successful work, schedule maintenance, and reduce maintenance costs and down time. Unlike fault diagnosis, prognosis is a relatively new area, but it has become an important part of Condition-based Maintenance (CBM) of systems. As there are many prognostic techniques, usage must be attuned to particular applications. Broadly stated, prognostic methods are either data-driven or model-based. Each has advantages and disadvantages; consequently, they are often combined in hybrid applications. A approach hybrid model can combine some or all model types (data-driven, and phenomenological); thus, more complete information can be gathered, leading to more accurate recognition of the fault state. This approach is especially relevant in railway systems where the maintainer and operator know some of the failure mechanisms, but the complexity of the infrastructure and rolling stock is huge that there is no way to develop a complete model-based approach. Therefore, hybrid models are extremely useful for accurately estimating the Remaining Useful Life (RUL) of railway systems. The paper addresses the process of data aggregation into a hybrid model to get RUL values within logical confidence intervals so that the life cycle of railway assets can be managed and optimised

  • 294.
    Galar, Diego
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Morant, Amparo
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Integration of production data in CM for non-stationary machinery: a data fusion approach2012Ingår i: Condition Monitoring of Machinery in Non-Stationary Operations: Proceedings of the Second International Conference "Condition Monitoring of Machinery in Non-Stationnary Operations" CMMNO’2012, Berlin: Springer Berlin/Heidelberg, 2012, s. 403-414Kapitel i bok, del av antologi (Refereegranskat)
    Abstract [en]

    A process control system deals with disperse information sources mostly related with operation and maintenance issues. For integration purposes, a data collection and distribution system based on the concept of cloud computing is proposed to collect data or information pertaining to the assets of a process plant from various sources or functional areas of the plant inc1uding, for example, the process control functional areas, the maintenance functional areas and the process performance monitoring functional areas. This data and information is manipulated in a coordinated manner by the cloud using XML for data exchange and is redistributed to other applications where is used to perform overall better or more optimal control, maintenance and business activities. From maintenance point of view, the benefit is that information or data may be collected by maintenance functions pertaining to the health, variability, performance or utilization of an asset. The end user, i.e. operators and maintainers are also considered. A user interface becomes necessary in order to enable users to access and manipulate the data and optimize plant operation. Furthermore, applications, such as work order generation applications may automatically generate work orders, parts or supplies orders, etc. based on events occurring within the plant due to this integration of data and creation of new knowledge as a consequence of such process

  • 295.
    Galar, Diego
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Naeem, Hassan Bin
    Schunnesson, Håkan
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Geoteknologi.
    Berges, Luis
    Department of Design Engineering and Manufacturing, University of Zaragoza.
    Tormos, Bernardo
    CMT-Motores Térmicos, Universitat Politècnica de València.
    Fusion of Operations, Event-Log and Maintenance Data: A Case Study for Optimising Availability of Mining Shovels2014Ingår i: Mine Planning and Equipment Selection: Proceedings of the 22nd MPES Conference, Dresden, Germany, 14th – 19th October 2013 / [ed] Carsten Drebenstedt; Raj Singhal, Switzerland: Encyclopedia of Global Archaeology/Springer Verlag, 2014, Vol. IX, s. 1173-1194Konferensbidrag (Refereegranskat)
    Abstract [en]

    The modern mining industry is highly mechanised and relies on massive, multimillion-dollar pieces of equipment to achieve production targets. In an increasingly challenging international economic climate, mining operations are reliant on economies of scale to remain competitive. To maximise revenue, it is imperative that at each stage of the mining process, equipment is operating optimally without preventable and unnecessary interruptions. As a result, the focus of all mining operations is to increase equipment uptime and utilisation.The data used for this investigation have been sourced from the Aitik mine, a large open pit copper mine in Northern Sweden. In the loading area, power shovels load trucks with blasted material for transport, either to the crushers or to the waste dumps. The Aitik mine employs various computer-aided applications to track and maintain mobile mining equipment like the shovels. These applications also serve as chronological operational and maintenance databases for the equipment. This paper’s study of six mining shovels is based on the analysis of three data types: historical maintenance data from CMMS Maximo, operational data from mine management system Cat® MineStarTM, and event-log data from individual shovels.The results indicate that such a synthesis is viable. A regular time-lapse integration of the diverse data types displays potential and could prove helpful in achieving overall improvements in maintenance.

  • 296.
    Galar, Diego
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Palo, Mikael
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Horenbeek, Adriaan Van
    Centre for Industrial management, KU Leuven.
    Printelon, Liliane M.
    Centre for Industrial management, KU Leuven.
    Integration of disparate data sources to perform maintenance prognosis and optimal decision making2012Ingår i: Insight (Northampton), ISSN 1354-2575, E-ISSN 1754-4904, Vol. 54, nr 8, s. 440-445Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Prognosis can be defined as the course of predicting a failure of equipment or a component in advance, whereas prognostication refers to the act of prediction. The three main branches of condition-based maintenance are diagnosis, prognosis and treatment-prognosis; however, prognosis is admittedly the most difficult. Also, this area has been the least described in literature and the knowledge about it in a maintenance management context is still poorly systematised. To this day, formal professional attention to prognosis, in the field of maintenance management and engineering in the everyday care of machinery, is often relegated to a secondary status, although the availability of prognostic information can considerably improve (for example reduce costs and maximise uptime) the performance of machinery and maintenance processes. Ideally, assessment of a prognosis of remaining useful life should be deliberate and explicit. In order to support the maintenance crew in the achievement of this objective, an increasing amount of prognostic information is available. Over the last decade, system integration has grown in popularity as it allows organisations to streamline business processes. It is necessary to integrate management data from computer maintenance management systems (CMMS) with condition monitoring (CM) systems and finally supervisory control and data acquisition (SCADA) and other control systems, widely used in production but seldom with a usage in asset diagnosis and prognosis. The most obvious obstacle in the integration of these data is the disparate nature of the data types involved; moreover, several attempts to remedy this problem have fizzled out. Although there have been many recent efforts to collect and maintain large repositories of these types of data, there have been relatively few studies to identify the ways these datasets could be related and linked for prognosis and maintenance decision making. After identifying what and how to predict incipient failures and developing a corresponding prognosis, maintenance engineers must consider how to communicate the prediction. In this activity, once again, technicians' psychosocial attributes and values may influence how they discuss prognoses with asset managers. Regardless of whether prognostic assessments are subjective or objective, however, technicians should consider two major points. Firstly, the maintenance crew should clarify in their own minds the link, if any, between their prognostic assessment and their consequent decision making. Secondly, they should consider the ways that they and their assets might benefit from explicitly discussing how the prognostic assessment is linked with diagnostics and preventive maintenance recommendations. These and other steps that maintenance engineers should take in incorporating prognostic information into their decision making are discussed in this paper. The objective is to give an overview of how the integration of disparate data sources, commonly available in industry, can be achieved for maintenance prognosis and optimal decision making.

  • 297.
    Galar, Diego
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Parida, Aditya
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Gustafson, Anna
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Berges, Luis
    University of Zaragoza.
    Use of vibration monitoring and analysis as KPIs in paper industry2011Ingår i: Proceedings of the 24th International Congress on Condition Monitoring and Diagnosis Engineering Management: COMADEM 2011 / [ed] Maneesh Singh; Raj B.K.N. Rao; J.P. Liyanage, COMADEM International, 2011, s. 135-147Konferensbidrag (Refereegranskat)
    Abstract [en]

    The use of automated systems for monitoring or surveillance of the condition of machinery for an industrial plant is becoming more common. Variables or indicators are transmitted to a database connected "on line" with such systems, allowing us to correctly track the condition parameters included in the PdM (Predictive Maintenance) Program. A practical example of an installation of 500 measuring points in a paper mill is presented in this paper. Paper mill plants show a wide variety of defects and conditions related to problems in rotating machinery bearings, gears, low speed operation, variable speed machine due to harsh conditions in the environment for elements of the installation and other adverse factors. Therefore, the vibration analyses are presented as physical indicators of the technical system for this type of machinery, on which the maintenance performance metrics are built. The article concludes presenting the "state of the art in data transmission to remote facilities engineering, for predictive diagnostic in order to detect potential problems in machinery which facilitate decisionmaking process in maintenance departments. These systems allow the rapid construction of the KPIs at different hierarchical levels. Therefore an approach to decision making based on the Maintenance methodology has been developed as a result of technological advances in the collection of physical data

  • 298.
    Galar, Diego
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Parida, Aditya
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Kumar, Uday
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Baglee, D.
    School of Computing and Technology, University of Sunderland.
    Morant, Amparo
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    The measurement of maintenance function efficiency through financial KPIs2012Ingår i: 25th International Congress on Condition Monitoring and Diagnostic Engineering (COMADEM 2012): 18–20 June 2012, Huddersfield, UK, IOP Publishing Ltd , 2012, artikel-id 012112Konferensbidrag (Refereegranskat)
    Abstract [en]

    The measurement of the performance in the maintenance function has produced large sets of indicators that due to their nature and disparity in criteria and objectives have been grouped in different subsets lately, emphasizing the set of financial indicators. The generation of these indicators demands data collection of high reliability that is only made possible through a model of costs adapted to the special casuistry of the maintenance function, characterized by the occultism of these costs.

  • 299.
    Galar, Diego
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Parida, Aditya
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Kumar, Uday
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Stenström, Christer
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Berges, Luis
    Manufacturing Engineering and Advanced Metrology Group, Aragon Institute of Engineering Research (13A), University of Zaragoza.
    Maintenance metrics: a hierarchical model of balanced scorecard2011Ingår i: 2011 IEEE International Conference on Quality and Reliability: ICQR 2011 : Bangkok, 14 September 2011-17 September 2011, Piscataway, NJ: IEEE Communications Society, 2011, s. 67-74Konferensbidrag (Refereegranskat)
    Abstract [en]

    The system of performance measurement of maintenance function should cover all processes related to it within the organization. There must be an interconnection between the different indicators, so the numbers can be interpreted in order to reach a good conclusion for decision making. This premise implies a hierarchy of indicators needed in a dual way. First, it will require maintenance indicators to be segmented according to the areas of influence for the rest of the organization, posed by interactions with finance department, human resources, purchasing, and, of course, with production in the seeking of compliance with corporate objectives. Simultaneously, these indicators correspond to different levels in the organization and therefore they will be segmented according to the hierarchical position of end users.

  • 300.
    Galar, Diego
    et al.
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Parida, AdityaLuleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.Schunnesson, HåkanLuleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Geoteknologi.Kumar, UdayLuleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    MPMM 2011: Maintenance Performance Measurement & Management: Conference Proceedings2011Samlingsverk (redaktörskap) (Övrigt vetenskapligt)
3456789 251 - 300 av 1446
RefereraExporteraLänk till träfflistan
Permanent länk
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf