Change search
Link to record
Permanent link

Direct link
BETA
Alternative names
Publications (10 of 80) Show all publications
Shao, H., Lin, J., Zhang, L. & Wei, M. (2020). Compound fault diagnosis for a rolling bearing using adaptive DTCWPT with higher order spectra. Quality Engineering
Open this publication in new window or tab >>Compound fault diagnosis for a rolling bearing using adaptive DTCWPT with higher order spectra
2020 (English)In: Quality Engineering, ISSN 0898-2112, E-ISSN 1532-4222Article in journal (Refereed) Epub ahead of print
Abstract [en]

Fault diagnosis plays a vital role in prognostics and health management. Researchers have devoted their efforts in enhancing the accuracy of fault diagnosis. However, diagnosis of compound faults in complex systems is still a challenging task. The problem lies in the coupling of multiple signals, which may conceal the characteristics of compound faults. Taking a rolling bearing as an example, this study aims to boost the accuracy of compound fault diagnosis through a novel feature extraction approach to making the fault characteristics more discriminative. The approach proposes an adaptive dual-tree complex wavelet packet transform (DTCWPT) with higher order spectra analysis. To flexibly and best match the characteristics of the measured vibration signals under analysis, DTCWPT is first adaptively determined by the minimum singular value decomposition entropy. Then, higher order spectra analysis is performed on the decomposed frequency sensitive band for feature extraction and enhancement. The proposed approach is used to analyze experimental signals of a bearing’s compound faults and found effective.

Place, publisher, year, edition, pages
Taylor & Francis, 2020
Keywords
Adaptive dual-tree complex wavelet packet, compound faults, prognostics and health management, rolling bearing, singular value decomposition
National Category
Other Civil Engineering
Research subject
Operation and Maintenance
Identifiers
urn:nbn:se:ltu:diva-78978 (URN)10.1080/08982112.2020.1749654 (DOI)
Available from: 2020-05-25 Created: 2020-05-25 Last updated: 2020-05-27
Chi, Z., Lin, J., Chen, R. & Huang, S. (2020). Data-driven approach to study the polygonization of high-speed railway train wheel-sets using field data of China’s HSR train. Measurement, 149, Article ID 107022.
Open this publication in new window or tab >>Data-driven approach to study the polygonization of high-speed railway train wheel-sets using field data of China’s HSR train
2020 (English)In: Measurement, ISSN 0263-2241, E-ISSN 1873-412X, Vol. 149, article id 107022Article in journal (Refereed) Published
Abstract [en]

Environmental factors, like seasonality, have been proved to exert significant impact on reliability of China high-speed rail train wheels in this article. Most studies on polygonization of train wheels are based on physical models, mathematical models or simulation systems. Normally, characteristics and mechanisms of wheel polygonization are studied under ideal conditions without considering the impact of the environment. However, in practical use, there are many irregular wear wheels and irregular wear cannot be explained by theoretical models with assumptions of ideal conditions. We look at two possible factors in polygonization: seasonality and proximity to engines. Our analysis of field data shows the environmental factor has more impact on wheel polygonization than the mechanical factor. Based on the Bayesian models, the mean time to failure of the wheels under different operation conditions is conducted. A case study of China’s HSR train wheels is conducted to confirm the finding. The case study shows the degree of polygonal wear is much more severe in summer than other seasons. The finding may give a totally new research perspective on polygonization of train wheels. We use Bayesian analysis because this method is useful for small and incomplete data sets. We propose three Bayesian data-driven models.

Place, publisher, year, edition, pages
Elsevier, 2020
Keywords
railway safety, prognostics and health management, mean time to failure, Bayesian methods, polygonization, wheel-sets
National Category
Other Civil Engineering
Research subject
Operation and Maintenance
Identifiers
urn:nbn:se:ltu:diva-75933 (URN)10.1016/j.measurement.2019.107022 (DOI)000490131400013 ()2-s2.0-85072207003 (Scopus ID)
Note

Validerad;2019;Nivå 2;2019-09-23 (johcin)

Available from: 2019-09-10 Created: 2019-09-10 Last updated: 2019-11-06Bibliographically approved
Ma, S., Gao, L., Liu, X. & Lin, J. (2020). Deep Learning for Track Quality Evaluation of High-Speed Railway Based on Vehicle-Body Vibration Prediction. IEEE Access, 7, 185099-185107
Open this publication in new window or tab >>Deep Learning for Track Quality Evaluation of High-Speed Railway Based on Vehicle-Body Vibration Prediction
2020 (English)In: IEEE Access, E-ISSN 2169-3536, Vol. 7, p. 185099-185107Article in journal (Refereed) Published
Abstract [en]

Track quality evaluation is fundamental for track maintenance. Around the world, track geometry standards are established to evaluate track quality. However, these standards may not be capable of detecting some abnormal track geometry conditions that can cause considerable vehicle-body vibration. And people gradually realized that track quality evaluation should be based not only on track geometry but also on vehicle performance. Vehicle-body vibration prediction is beneficial for locating potential track geometry defects, and the predicted accelerations can be used as an auxiliary index for assessing track quality. For this purpose, this paper gives a method to predict vehicle-body vibration based on deep learning, which represents one of the newest areas in artificial intelligence. By integrating convolutional neural network (CNN) and long short-term memory (LSTM), a CNN-LSTM model is proposed to make accurate and point-wise prediction. To achieve the optimal performance and explore the internal mechanism of the model, structural configurations and inner states are extensively studied. CNN-LSTM can take advantage of the powerful feature extraction capacity of CNN and LSTM, and outperforms the fully-connected neural network and the plain LSTM on the experimental data of a high-speed railway. In detail, CNN-LSTM has superior performance in predicting vertical vehicle-body vibration below 10 Hz and lateral vehicle-body vibration below 1 Hz. Moreover, analysis shows that the predicted vehicle-body acceleration can act as a performance-based evaluation index of track quality.

Place, publisher, year, edition, pages
IEEE, 2020
Keywords
Track quality evaluation, track geometry, vehicle-body vibration, convolutional neural network (CNN), long short-term memory (LSTM), CNN-LSTM
National Category
Other Civil Engineering
Research subject
Operation and Maintenance
Identifiers
urn:nbn:se:ltu:diva-77232 (URN)10.1109/ACCESS.2019.2960537 (DOI)000510021700054 ()2-s2.0-85077963564 (Scopus ID)
Note

Validerad;2020;Nivå 2;2020-02-17 (johcin)

Available from: 2019-12-20 Created: 2019-12-20 Last updated: 2020-04-16Bibliographically approved
He, Z., Shao, H., Wang, P., Lin, J. (., Cheng, J. & Yang, Y. (2020). Deep transfer multi-wavelet auto-encoder for intelligent fault diagnosis of gearbox with few target training samples. Knowledge-Based Systems, 191, Article ID 105313.
Open this publication in new window or tab >>Deep transfer multi-wavelet auto-encoder for intelligent fault diagnosis of gearbox with few target training samples
Show others...
2020 (English)In: Knowledge-Based Systems, ISSN 0950-7051, E-ISSN 1872-7409, Vol. 191, article id 105313Article in journal (Refereed) Published
Abstract [en]

Lack of typical fault samples remains a huge challenge for intelligent fault diagnosis of gearbox. In this paper, a novel approach named deep transfer multi-wavelet auto-encoder is presented for gearbox intelligent fault diagnosis with few training samples. Firstly, new-type deep multi-wavelet auto-encoder is designed for learning important features of the collected vibration signals of gearbox. Secondly, high-quality auxiliary samples are selected based on similarity measure to well pre-train a source model sharing similar characteristics with the target domain. Thirdly, parameter knowledge acquired from the source model is transferred to target model using very few target training samples. Transfer diagnosis cases for different fault severities and compound faults of gearbox confirm the feasibility of the proposed approach even if the working conditions have significant changes.

Place, publisher, year, edition, pages
Elsevier, 2020
Keywords
Deep transfer multi-wavelet auto-encode, Gearbox fault, Transfer diagnosis, Variable working conditions, Few target training samples
National Category
Other Civil Engineering
Research subject
Operation and Maintenance
Identifiers
urn:nbn:se:ltu:diva-77568 (URN)10.1016/j.knosys.2019.105313 (DOI)000517663200035 ()2-s2.0-85076527537 (Scopus ID)
Note

Validerad;2020;Nivå 2;2020-03-02 (alebob)

Available from: 2020-01-30 Created: 2020-01-30 Last updated: 2020-04-01Bibliographically approved
He, Z., Shao, H., Lin, J., Cheng, J. & Yang, Y. (2020). Transfer fault diagnosis of bearing installed in different machines using enhanced deep auto-encoder. Measurement, 152, Article ID 107393.
Open this publication in new window or tab >>Transfer fault diagnosis of bearing installed in different machines using enhanced deep auto-encoder
Show others...
2020 (English)In: Measurement, ISSN 0263-2241, E-ISSN 1873-412X, Vol. 152, article id 107393Article in journal (Refereed) Published
Abstract [en]

The collected vibration data with labeled information from bearing is far insufficient in engineering practice, which is challenging for training an intelligent diagnosis model. For this purpose, enhanced deep transfer auto-encoder is proposed for fault diagnosis of bearing installed in different machines. First, scaled exponential linear unit is used to improve the quality of the mapped vibration data collected from bearing. Second, nonnegative constraint is adopted for modifying the loss function to improve reconstruction effect. Then, the parameter knowledge of the well-trained source model is transferred to the target model. Finally, target training samples with limited labeled information are adopted for fine-tuning the target model to match the characteristics of the target testing samples. The proposed approach is applied for analyzing the measured vibration signals of bearings installed in different machines. The analysis results show that the proposed approach holds better transfer diagnosis performance compared with the existing approaches.

Place, publisher, year, edition, pages
Elsevier, 2020
Keywords
Enhanced deep auto-encoder model, Transfer diagnosis, Limited labeled information, Bearing fault, Different machines
National Category
Infrastructure Engineering Other Civil Engineering
Research subject
Operation and Maintenance
Identifiers
urn:nbn:se:ltu:diva-77569 (URN)10.1016/j.measurement.2019.107393 (DOI)2-s2.0-85076849611 (Scopus ID)
Note

Validerad;2020;Nivå 2;2020-02-18 (johcin)

Available from: 2020-01-30 Created: 2020-01-30 Last updated: 2020-04-23Bibliographically approved
Liu, B., Lin, J., Zhang, L. & Kumar, U. (2019). A Dynamic Prescriptive Maintenance Model Considering System Aging and Degradation. IEEE Access, 7, 94941-94943, Article ID 8762155.
Open this publication in new window or tab >>A Dynamic Prescriptive Maintenance Model Considering System Aging and Degradation
2019 (English)In: IEEE Access, E-ISSN 2169-3536, Vol. 7, p. 94941-94943, article id 8762155Article in journal (Refereed) Published
Abstract [en]

This paper develops a dynamic maintenance strategy for a system subject to aging and degradation. The influence of degradation level and aging on system failure rate is modeled in an additive way. Based on the observed degradation level at the inspection, repair or replacement is carried out upon the system. Previous researches assume that repair will always lead to an improvement in the health condition of the system. However, in our study, repair reduces the system age but on the other hand, increases the degradation level. Considering the two-fold influence of maintenance actions, we perform reliability analysis on system reliability as a first step. The evolution of system reliability serves as a foundation for establishing the maintenance model. The optimal maintenance strategy is achieved by minimizing the long-run cost rate in terms of the repair cycle. At each inspection, the parameters of the degradation processes are updated with maximum a posteriori estimation when a new observation arrives. The effectiveness of the proposed model is illustrated through a case study of locomotive wheel-sets. The maintenance model considers the influence of degradation and aging on system failure and dynamically determines the optimal inspection time, which is more flexible than traditional stationary maintenance strategies and can provide better performance in the field.

Place, publisher, year, edition, pages
IEEE, 2019
Keywords
Aging and degradation process, dynamic maintenance strategy, locomotive wheel-sets, prescriptive maintenance, sequential schedule
National Category
Other Civil Engineering
Research subject
Operation and Maintenance
Identifiers
urn:nbn:se:ltu:diva-75614 (URN)10.1109/ACCESS.2019.2928587 (DOI)000478676600061 ()2-s2.0-85070235312 (Scopus ID)
Note

Validerad;2019;Nivå 2;2019-08-20 (svasva)

Available from: 2019-08-20 Created: 2019-08-20 Last updated: 2019-08-28Bibliographically approved
Zhang, L., Lin, J., Liu, B., Zhang, Z., Yan, X. & Wei, M. (2019). A Review on Deep Learning Applications in Prognostics and Health Management. IEEE Access, 7, 162415-162438
Open this publication in new window or tab >>A Review on Deep Learning Applications in Prognostics and Health Management
Show others...
2019 (English)In: IEEE Access, E-ISSN 2169-3536, Vol. 7, p. 162415-162438Article, review/survey (Refereed) Published
Abstract [en]

Deep learning has attracted intense interest in Prognostics and Health Management (PHM), because of its enormous representing power, automated feature learning capability and best-in-class performance in solving complex problems. This paper surveys recent advancements in PHM methodologies using deep learning with the aim of identifying research gaps and suggesting further improvements. After a brief introduction to several deep learning models, we review and analyze applications of fault detection, diagnosis and prognosis using deep learning. The survey validates the universal applicability of deep learning to various types of input in PHM, including vibration, imagery, time-series and structured data. It also reveals that deep learning provides a one-fits-all framework for the primary PHM subfields: fault detection uses either reconstruction error or stacks a binary classifier on top of the network to detect anomalies; fault diagnosis typically adds a soft-max layer to perform multi-class classification; prognosis adds a continuous regression layer to predict remaining useful life. The general framework suggests the possibility of transfer learning across PHM applications. The survey reveals some common properties and identifies the research gaps in each PHM subfield. It concludes by summarizing some major challenges and potential opportunities in the domain.

Place, publisher, year, edition, pages
IEEE, 2019
Keywords
Condition-based maintenance, deep learning, fault detection, fault diagnosis, prognosis
National Category
Other Civil Engineering
Research subject
Operation and Maintenance
Identifiers
urn:nbn:se:ltu:diva-76709 (URN)10.1109/ACCESS.2019.2950985 (DOI)000497169800116 ()
Note

Validerad;2019;Nivå 2;2019-11-25 (johcin)

Available from: 2019-11-15 Created: 2019-11-15 Last updated: 2019-12-09Bibliographically approved
Chen, J., Zhou, D., Guo, Z., Lin, J., LYU, C. & LU, C. (2019). An Active Learning Method Based on Uncertainty and Complexity for Gearbox Fault Diagnosis. IEEE Access, 7, 9022-9031
Open this publication in new window or tab >>An Active Learning Method Based on Uncertainty and Complexity for Gearbox Fault Diagnosis
Show others...
2019 (English)In: IEEE Access, E-ISSN 2169-3536, Vol. 7, p. 9022-9031Article in journal (Refereed) Published
Abstract [en]

It is crucial to implement an effective and accurate fault diagnosis of a gearbox for mechanical systems. However, being composed of many mechanical parts, a gearbox has a variety of failure modes resulting in the difficulty of accurate fault diagnosis. Moreover, it is easy to obtain raw vibration signals from real gearbox applications, but it requires significant costs to label them, especially for multi-fault modes. These issues challenge the traditional supervised learning methods of fault diagnosis. To solve these problems, we develop an active learning strategy based on uncertainty and complexity. Therefore, a new diagnostic method for a gearbox is proposed based on the present active learning, empirical mode decomposition-singular value decomposition (EMD-SVD) and random forests (RF). First, the EMD-SVD is used to obtain feature vectors from raw signals. Second, the proposed active learning scheme selects the most valuable unlabeled samples, which are then labeled and added to the training data set. Finally, the RF, trained by the new training data, is employed to recognize the fault modes of a gearbox. Two cases are studied based on experimental gearbox fault diagnostic data, and a supervised learning method, as well as other active learning methods, are compared. The results show that the proposed method outperforms the two common types of methods, thus validating its effectiveness and superiority.

Place, publisher, year, edition, pages
IEEE, 2019
Keywords
Active learning, gearbox fault diagnosis, uncertainty and complexity, supervised learning
National Category
Engineering and Technology Other Civil Engineering
Research subject
Operation and Maintenance
Identifiers
urn:nbn:se:ltu:diva-72603 (URN)10.1109/ACCESS.2019.2890979 (DOI)000456910200001 ()2-s2.0-85060708128 (Scopus ID)
Note

Validerad;2019;Nivå 2;2019-01-29 (svasva)

Available from: 2019-01-17 Created: 2019-01-17 Last updated: 2019-02-11Bibliographically approved
An, B., Gao, L., Xin, T. & Lin, J. (2019). An approach to evaluate wheel-rail match properties considering the flexibility of ballastless track: Comparison of rigid and flexible track models in wheel-rail profile matching. International Journal of COMADEM, 22(3), 5-13
Open this publication in new window or tab >>An approach to evaluate wheel-rail match properties considering the flexibility of ballastless track: Comparison of rigid and flexible track models in wheel-rail profile matching
2019 (English)In: International Journal of COMADEM, ISSN 1363-7681, Vol. 22, no 3, p. 5-13Article in journal (Refereed) Published
Abstract [en]

Many different wheel/rail profiles are used in the China high-speed railway, and vehicle operation safety and comfort will decrease if the inappropriate wheel-rail profile pair is used. To solve the problem of estimating the wheel-rail match, many numerical models, including vehicle system dynamic models and wheel-rail rolling contact models, have been established to analyse the wheel-rail dynamic responses. Both methods have less consideration of the flexibility and vibration characteristics of ballastless track, leading to deviations in the calculation of middle and high frequency vibration. This paper proposes a vehicle-flexible track coupling model and compares it with the vehicle dynamic model (vehicle-rigid track model). In the rigid track model, only the track irregularities are considered in the track module; the vibrations and deformations of rails, track slab and the foundation are considered in the flexible track model. Taking Chinese CRH3 series wheel profile S1002CN and rail profile CHN60 as examples and considering different track excitations, the two models are compared. The wheel-rail interaction forces, wheel-rail wear depths, wear volumes and vehicle accelerations are chosen as analysis indices for the comparative study.

The results show that the wheel-rail forces of the flexible track model are larger than the rigid track model in the frequency range from 70 to 120Hz, while they decrease obviously in the frequency range above 150Hz. The differences in wear depths and volumes between the two models exceed 10%. Therefore, the flexible track model should be considered when studying the match properties of different wheel-rail pairs.

Place, publisher, year, edition, pages
COMADEM International, 2019
Keywords
High-speed railway, Wheel-rail profile matching, Flexible track, Vehicle-track coupling interaction
National Category
Infrastructure Engineering Other Civil Engineering
Research subject
Operation and Maintenance
Identifiers
urn:nbn:se:ltu:diva-75757 (URN)
Note

Validerad;2019;Nivå 1;2019-09-03 (johcin)

Available from: 2019-08-29 Created: 2019-08-29 Last updated: 2019-09-03Bibliographically approved
Cai, B., Kong, X., Liu, Y., Lin, J., Yuan, X., Xu, H. & Ji, R. (2019). Application of Bayesian Networks in Reliability Evaluation. IEEE Transactions on Industrial Informatics, 15(4), 2146-2157
Open this publication in new window or tab >>Application of Bayesian Networks in Reliability Evaluation
Show others...
2019 (English)In: IEEE Transactions on Industrial Informatics, ISSN 1551-3203, E-ISSN 1941-0050, Vol. 15, no 4, p. 2146-2157Article in journal (Refereed) Published
Abstract [en]

The Bayesian network (BN) is a powerful model for probabilistic knowledge representation and inference and is increasingly used in the field of reliability evaluation. This paper presents a bibliographic review of BNs that have been proposed for reliability evaluation in the last decades. Studies are classified from the perspective of the objects of reliability evaluation, i.e., hardware, structures, software, and humans. For each classification, the construction and validation of a BN-based reliability model are emphasized. The general procedural steps for BN-based reliability evaluation, including BN structure modeling, BN parameter modeling, BN inference, and model verification and validation, are investigated. Current gaps and challenges in reliability evaluation with BNs are explored, and a few upcoming research directions that are of interest to reliability researchers are identified.

Place, publisher, year, edition, pages
IEEE, 2019
Keywords
Software reliability, Hardware, Software, Object oriented modeling, Power system reliability, Reliability engineering
National Category
Other Civil Engineering
Research subject
Operation and Maintenance
Identifiers
urn:nbn:se:ltu:diva-71739 (URN)10.1109/TII.2018.2858281 (DOI)000467095500029 ()
Note

Validerad;2019;Nivå 2;2019-04-12 (oliekm)

Available from: 2018-11-23 Created: 2018-11-23 Last updated: 2019-06-17Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0002-7458-6820

Search in DiVA

Show all publications