Change search
Link to record
Permanent link

Direct link
Alternative names
Publications (10 of 96) Show all publications
Shen, J., Zhang, X., Mylly, N. & Lin, J. (2023). A Critical Review of Lighting Design and Asset Management Strategies. Illuminating Practices and Lessons Learned for Swedish Public Libraries. Journal of Physics, Conference Series, 2654(1), 012139-012139
Open this publication in new window or tab >>A Critical Review of Lighting Design and Asset Management Strategies. Illuminating Practices and Lessons Learned for Swedish Public Libraries
2023 (English)In: Journal of Physics, Conference Series, ISSN 1742-6588, E-ISSN 1742-6596, Vol. 2654, no 1, p. 012139-012139Article in journal (Refereed) Published
Abstract [en]

Most lighting is only designed to meet the visual needs in most public library environments in Sweden. Although lighting-related impacts are relevant to six Unite Nations sustainability goals, some important lighting considerations, such as circadian phase disruption, mode and productivity impact, and energy-efficient operation, are missing in current lighting operating practices. Moreover, most of the current lighting asset management practice in public buildings remains "fix it if only it breaks". With respect to people-centric health factors, visual index, and lighting asset energy-efficient operation, this study sublimates lighting into a new perspective. Finally, the suggested comprehensive lighting operating strategies integrating digital twins can help designers and operators in defining the optimal design/control strategy in public-built environments, like public library. Digital twin-based decision-making is expected to be applied to lighting design and control in public spaces that improves visual acuity and comfort, positively impact mood and productivity, and provides recommendations on engagement principles under Environment Social Governance (ESG) framework to asset manager/operators.

National Category
Architecture
Research subject
Operation and Maintenance Engineering
Identifiers
urn:nbn:se:ltu:diva-103364 (URN)10.1088/1742-6596/2654/1/012139 (DOI)2-s2.0-85181166180 (Scopus ID)
Note

Full text license: CC BY

Available from: 2023-12-19 Created: 2023-12-19 Last updated: 2024-02-23
Zhang, L., Fan, Q., Lin, J., Zhang, Z., Yan, X. & Li, C. (2023). A nearly end-to-end deep learning approach to fault diagnosis of wind turbine gearboxes under nonstationary conditions. Engineering applications of artificial intelligence, 119, Article ID 105735.
Open this publication in new window or tab >>A nearly end-to-end deep learning approach to fault diagnosis of wind turbine gearboxes under nonstationary conditions
Show others...
2023 (English)In: Engineering applications of artificial intelligence, ISSN 0952-1976, E-ISSN 1873-6769, Vol. 119, article id 105735Article in journal (Refereed) Published
Abstract [en]

Fault diagnosis of wind turbine gearboxes is crucial in ensuring wind farms’ reliability and safety. However, nonstationary working conditions, such as load change or speed regulation, may result in an accuracy deterioration of many existing fault diagnosis approaches. To overcome the issue, this research proposes a nearly end-to-end deep learning approach to fault diagnosis of wind turbine gearboxes using vibration signals. Concretely, we adopt Empirical Mode Decomposition (EMD) to decompose vibration signals into a series of Intrinsic Mode Functions (IMFs). Then, the multi-channel IMFs are fed into a 1D Convolutional Neural Network (CNN) for automatic feature learning and fault classification. Since EMD is a signal processing technique requiring no prior knowledge, the model architecture can be viewed as nearly end-to-end. The proposed approach was validated in a real-world dataset; it proved deep learning models have an overwhelming advantage in representation capacity over traditional shallow models. It also demonstrated that the introduction of EMD as a preprocessing step improves both the training efficiency and the generalization ability of a deep model, thus leading to a better fault diagnosis efficacy under variable working conditions.

Place, publisher, year, edition, pages
Elsevier, 2023
Keywords
Fault diagnosis, Deep learning, End-to-end learning, Empirical mode decomposition, Convolutional neural network
National Category
Other Mechanical Engineering
Research subject
Operation and Maintenance
Identifiers
urn:nbn:se:ltu:diva-95176 (URN)10.1016/j.engappai.2022.105735 (DOI)000912326600001 ()2-s2.0-85144823492 (Scopus ID)
Note

Validerad;2023;Nivå 2;2023-03-21 (joosat);

Funder: National Natural Science Foundation of China (71801045); DGUT, China (GC300502-46); Department of Education of Guangdong in China (2021ZDJS083)

Available from: 2023-01-05 Created: 2023-01-05 Last updated: 2023-04-21Bibliographically approved
Li, X., Li, Y., Yan, K., Shao, H. & Lin, J. (. (2023). Intelligent fault diagnosis of bevel gearboxes using semi-supervised probability support matrix machine and infrared imaging. Reliability Engineering & System Safety, 230, Article ID 108921.
Open this publication in new window or tab >>Intelligent fault diagnosis of bevel gearboxes using semi-supervised probability support matrix machine and infrared imaging
Show others...
2023 (English)In: Reliability Engineering & System Safety, ISSN 0951-8320, E-ISSN 1879-0836, Vol. 230, article id 108921Article in journal (Refereed) Published
Abstract [en]

Fault diagnosis is of great significance to ensure the reliability and safety of complex bevel gearbox systems. Most existing intelligent fault diagnosis approaches of bevel gearboxes are designed with vibration monitoring. However, the collected vibration data are vulnerable to noise pollution and machinery operating conditions. Besides, traditional fault diagnosis models highly rely on numerous labeled samples, and neglect the high cost of label annotation in real-world applications. Therefore, a novel fault diagnosis approach based on semi-supervised probability support matrix machine (SPSMM) and infrared imaging is proposed for bevel gearboxes in this paper, which has the following properties. Firstly, SPSMM classifies 2D matrix data directly without vectorization, thus fully utilizing the spatial information in infrared images. Secondly, a probability output strategy is designed for SPSMM to calculate the posterior class probability estimation of matrix inputs, and consequently enhance the diagnostic accuracy and robustness of the model. Thirdly, a semi-supervised learning (SSL) framework is proposed for SPSMM to carry out sample transfer from the unlabeled sample pool to the labeled sample pool, which can effectively alleviate the problem of insufficient labeled samples. The superiority of the proposed diagnosis approach is demonstrated with an infrared imaging dataset of a bevel gearbox.

Place, publisher, year, edition, pages
Elsevier, 2023
Keywords
Intelligent fault diagnosis, Support matrix machine, Probability output strategy, Semi-supervised learning, Infrared imaging
National Category
Reliability and Maintenance
Research subject
Operation and Maintenance
Identifiers
urn:nbn:se:ltu:diva-93823 (URN)10.1016/j.ress.2022.108921 (DOI)000892062100002 ()2-s2.0-85141328619 (Scopus ID)
Note

Validerad;2022;Nivå 2;2022-11-25 (hanlid);

Funder: National Key Research and Development of China (2020YFB1712100); National Natural Science Foundation of China (51905160, 52204178); MOE AcRF Tier 1 (A-0008299-00-00, A-0008552-01-00); BIM-Geospatial Thrust in the Center of 5G Digital Building Technology, National University of Singapore

Available from: 2022-11-05 Created: 2022-11-05 Last updated: 2023-05-08Bibliographically approved
Zhang, L., Zhang, J., Peng, Y. & Lin, J. (2022). Intra-Domain Transfer Learning for Fault Diagnosis with Small Samples. Applied Sciences, 12(14), Article ID 7032.
Open this publication in new window or tab >>Intra-Domain Transfer Learning for Fault Diagnosis with Small Samples
2022 (English)In: Applied Sciences, E-ISSN 2076-3417, Vol. 12, no 14, article id 7032Article in journal (Refereed) Published
Abstract [en]

The concept of deep transfer learning has spawned broad research into fault diagnosis with small samples. A considerable covariate shift between the source and target domains, however, could result in negative transfer and lower fault diagnosis task accuracy. To alleviate the adverse impacts of negative transfer, this research proposes an intra-domain transfer learning strategy that makes use of knowledge from a data-abundant source domain that is akin to the target domain. Concretely, a pre-trained model in the source domain is built via a vanilla transfer from an off-the-shelf inter-domain deep neural network. The model is then transferred to the target domain using shallow-layer freezing and finetuning with those small samples. In a case study involving rotating machinery, where we tested the proposed strategy, we saw improved performance in both training efficiency and prediction accuracy. To demystify the learned neural network, we propose a heat map visualization method using a channel-wise average over the final convolutional layer and up-sampling with interpolation. The findings revealed that the most active neurons coincide with the corresponding fault characteristics.

Place, publisher, year, edition, pages
MDPI, 2022
Keywords
fault diagnosis, transfer learning, time-frequency spectrum, small samples, heat map
National Category
Other Engineering and Technologies not elsewhere specified
Research subject
Operation and Maintenance
Identifiers
urn:nbn:se:ltu:diva-92242 (URN)10.3390/app12147032 (DOI)000833882400001 ()2-s2.0-85137365305 (Scopus ID)
Note

Validerad;2022;Nivå 2;2022-08-11 (hanlid);

Funder: National Science Foundation of China, NSFC (71801045); DGUT (GC300502-46)

Available from: 2022-07-26 Created: 2022-07-26 Last updated: 2022-09-20Bibliographically approved
Xiao, Y., Shao, H., Min, Z., Cao, H., Chen, X. & Lin, J. (. (2022). Multiscale dilated convolutional subdomain adaptation network with attention for unsupervised fault diagnosis of rotating machinery cross operating conditions. Measurement, 204, Article ID 112146.
Open this publication in new window or tab >>Multiscale dilated convolutional subdomain adaptation network with attention for unsupervised fault diagnosis of rotating machinery cross operating conditions
Show others...
2022 (English)In: Measurement, ISSN 0263-2241, E-ISSN 1873-412X, Vol. 204, article id 112146Article in journal (Refereed) Published
Abstract [en]

Unsupervised cross-domain fault diagnosis research of rotating machinery has significant implications. However, some issues remain to be solved. For example, convolutional neural network cannot capture discriminative information in vibration signals from different scales. In addition, the extracted features should be selected to enhance informative features and suppress redundant features. Finally, global domain adaptation methods may cause different subdomains of source and target domains to be too close. To address these challenges, this paper proposes a multiscale dilated convolutional subdomain adaptation network with attention. Firstly, a multiscale dilated convolutional module is developed to extract fault features at different scales. Secondly, a squeeze-and-excitation attention mechanism is built to assign channel-level weights to these features. Finally, local maximum mean discrepancy is constructed to adapt corresponding subdomains of the two domains. The proposed method is applied to perform various unsupervised cross-domain fault diagnosis tasks, and the experimental results demonstrate its superior diagnostic performance.

Place, publisher, year, edition, pages
Elsevier, 2022
Keywords
Multiscale features, Attention mechanism, Subdomain adaptation, Unsupervised cross-domain, Rotating machinery fault diagnosis
National Category
Reliability and Maintenance Computer Sciences
Research subject
Operation and Maintenance
Identifiers
urn:nbn:se:ltu:diva-93824 (URN)10.1016/j.measurement.2022.112146 (DOI)000881770500003 ()2-s2.0-85141266906 (Scopus ID)
Note

Validerad;2022;Nivå 2;2022-11-25 (hanlid);

Funder: National Natural Science Foundation of China (51905160); Natural Science Fund for Excellent Young Scholars of Hunan Province (2021JJ20017)

Available from: 2022-11-05 Created: 2022-11-05 Last updated: 2023-05-08Bibliographically approved
Vila Forteza, M., Galar, D., Lin, J. & Liyanage, J. P. (2022). New paradigms in Maintenance, operation, and health management of rotating machinery large fleets. The effect of Industry 4.0. In: 18th International Conference on Condition Monitoring and Asset Management (CM 2022): . Paper presented at The Eighteenth International Conference on Condition Monitoring and Asset Management (CM2022), London, United Kingdom, June 7-9, 2022 (pp. 311-321). British Institute of Non-Destructive Testing (BINDT)
Open this publication in new window or tab >>New paradigms in Maintenance, operation, and health management of rotating machinery large fleets. The effect of Industry 4.0
2022 (English)In: 18th International Conference on Condition Monitoring and Asset Management (CM 2022), British Institute of Non-Destructive Testing (BINDT) , 2022, p. 311-321Conference paper, Published paper (Refereed)
Abstract [en]

Rotating machinery belong to the category of major equipment in many large industries as oil refineries. When such assets are installed in an industrial plant, they are expected to perform with minimal faults and failures guaranteeing that the plant can be operated within pre-defined reliability, safety, availability, and performance specifications. This paper provides an insight into current practices when dealing with large fleets of rotating machines in an Industry 4.0 context and what opportunities and challenges are encountered towards improving their safe operation and reliability by taking advantage of the development of new technologies.

Bearing in mind that centrifugal pumps are the most common rotating machines in oil refineries, this paper is specially focused in this case, but its guidelines can be applied to all types of rotating equipment installed in an industrial plant.

Place, publisher, year, edition, pages
British Institute of Non-Destructive Testing (BINDT), 2022
National Category
Other Civil Engineering Production Engineering, Human Work Science and Ergonomics
Research subject
Operation and Maintenance
Identifiers
urn:nbn:se:ltu:diva-95283 (URN)2-s2.0-85145884033 (Scopus ID)
Conference
The Eighteenth International Conference on Condition Monitoring and Asset Management (CM2022), London, United Kingdom, June 7-9, 2022
Note

ISBN för värdpublikation: 978-1-7138-6227-7

Available from: 2023-01-16 Created: 2023-01-16 Last updated: 2023-01-16Bibliographically approved
Xin, T., Yang, Y., Zheng, X., Lin, J., Wang, S. & Wang, P. (2022). Time Series Recovery Using Adjacent Channel Data Based on LSTM: A Case Study of Subway Vibrations. Applied Sciences, 12(22), Article ID 11497.
Open this publication in new window or tab >>Time Series Recovery Using Adjacent Channel Data Based on LSTM: A Case Study of Subway Vibrations
Show others...
2022 (English)In: Applied Sciences, E-ISSN 2076-3417, Vol. 12, no 22, article id 11497Article in journal (Refereed) Published
Abstract [en]

Multi-sensor technology has been widely applied in the condition monitoring of rail transit. In practice, the data of some channels in the high channel counts are often abnormal or lost due to the abnormality and damage of the sensors, thus resulting in a large amount of data waste. A method for the data recovery of lost channels by using adjacent channel data is proposed to solve this problem. Based on the LSTM network algorithm, a data recovery model is established based on the “sequence-to-sequence” regression analysis of adjacent channel data. Taking the measured vibration data of a subway as an example, the network is trained with multi-channel measured data to recover the lost channel data of time-series characteristics. The results show that this multi-channel data recovery model is feasible, and the accuracy is up to 98%. This method can also further reduce the number of channels that need to be collected.

Place, publisher, year, edition, pages
MDPI, 2022
Keywords
multi-channel data, time-series recovery, neural network, regression analysis, data recovery, time domain, frequency domain
National Category
Signal Processing
Research subject
Operation and Maintenance
Identifiers
urn:nbn:se:ltu:diva-94135 (URN)10.3390/app122211497 (DOI)000887061600001 ()2-s2.0-85142849504 (Scopus ID)
Note

Validerad;2022;Nivå 2;2022-11-21 (sofila);

Funder: Beijing Nova Program (Z191100001119126); the Shanghai Key Laboratory of Rail Infrastructure Durability and System Safety (R202101); the Fundamental Research Funds for the Central Universities (2020JBM049); the 111 Project (B20040)

Available from: 2022-11-17 Created: 2022-11-17 Last updated: 2023-05-08Bibliographically approved
Shao, H., Lin, J., Zhang, L., Galar, D. & Kumar, U. (2021). A novel approach of multisensory fusion to collaborative fault diagnosis in maintenance. Information Fusion, 74, 65-76
Open this publication in new window or tab >>A novel approach of multisensory fusion to collaborative fault diagnosis in maintenance
Show others...
2021 (English)In: Information Fusion, ISSN 1566-2535, E-ISSN 1872-6305, Vol. 74, p. 65-76Article in journal (Refereed) Published
Abstract [en]

Collaborative fault diagnosis can be facilitated by multisensory fusion technologies, as these can give more reliable results with a more complete data set. Although deep learning approaches have been developed to overcome the problem of relying on subjective experience in conventional fault diagnosis, there are two remaining obstacles to collaborative efficiency: integration of multisensory data and fusion of maintenance strategies. To overcome these obstacles, we propose a novel two-part approach: a stacked wavelet auto-encoder structure with a Morlet wavelet function for multisensory data fusion and a flexible weighted assignment of fusion strategies. Taking a planetary gearbox as an example, we use noisy vibration signals from multisensors to test the diagnosis performance of the proposed approach. The results demonstrate that it can provide more accurate and reliable fault diagnosis results than other approaches.

Place, publisher, year, edition, pages
Elsevier, 2021
Keywords
Collaborative maintenance, Prognostics and health management, Multi-sensor information fusion, fault diagnosis, Stacked wavelet auto-encoder, Planetary gearbox
National Category
Other Civil Engineering
Research subject
Operation and Maintenance
Identifiers
urn:nbn:se:ltu:diva-83400 (URN)10.1016/j.inffus.2021.03.008 (DOI)000659136200005 ()2-s2.0-85103775860 (Scopus ID)
Note

Validerad;2021;Nivå 2;2021-04-19 (johcin);

Finansiär: National Natural Science Foundation of China (51905160, 71801045); the Natural Science Foundation of Hunan Province (2020JJ5072); National Key Research and Development Program of China (2020YFB1712103); Fundamental Research Funds for the Central Universities (531118010335); Research start-up funds of DGUT (GC300502-46)

Available from: 2021-03-25 Created: 2021-03-25 Last updated: 2022-10-28Bibliographically approved
Zhong, Y., Gao, L., Cai, X., An, B., Zhang, Z., Lin, J. & Qin, Y. (2021). An Improved Cohesive Zone Model for Interface Mixed-Mode Fractures of Railway Slab Tracks. Applied Sciences, 11(1), Article ID 456.
Open this publication in new window or tab >>An Improved Cohesive Zone Model for Interface Mixed-Mode Fractures of Railway Slab Tracks
Show others...
2021 (English)In: Applied Sciences, E-ISSN 2076-3417, Vol. 11, no 1, article id 456Article in journal (Refereed) Published
Abstract [en]

The interface crack of a slab track is a fracture of mixed-mode that experiences a complex loading–unloading–reloading process. A reasonable simulation of the interaction between the layers of slab tracks is the key to studying the interface crack. However, the existing models of interface disease of slab track have problems, such as the stress oscillation of the crack tip and self-repairing, which do not simulate the mixed mode of interface cracks accurately. Aiming at these shortcomings, we propose an improved cohesive zone model combined with an unloading/reloading relationship based on the original Park–Paulino–Roesler (PPR) model in this paper. It is shown that the improved model guaranteed the consistency of the cohesive constitutive model and described the mixed-mode fracture better. This conclusion is based on the assessment of work-of-separation and the simulation of the mixed-mode bending test. Through the test of loading, unloading, and reloading, we observed that the improved unloading/reloading relationship effectively eliminated the issue of self-repairing and preserved all essential features. The proposed model provides a tool for the study of interface cracking mechanism of ballastless tracks and theoretical guidance for the monitoring, maintenance, and repair of layer defects, such as interfacial cracks and slab arches.

Place, publisher, year, edition, pages
MDPI, 2021
Keywords
railway slab track, interface mixed-mode fracture, cohesive zone model, unloading/reloading relationship
National Category
Other Civil Engineering
Research subject
Operation and Maintenance Engineering
Identifiers
urn:nbn:se:ltu:diva-82335 (URN)10.3390/app11010456 (DOI)000605811600001 ()2-s2.0-85099770996 (Scopus ID)
Note

Validerad;2021;Nivå 2;2021-01-28 (johcin);

Finansiär: Fundamental Research Funds for the Central Universities (2019JBM080), National Natural Science Foundation of China (51908031, U1734206), China Postdoctoral Science Foundation (2020M670126)

Available from: 2021-01-13 Created: 2021-01-13 Last updated: 2023-10-28Bibliographically approved
Zhang, L., Lin, J., Shao, H., Zhang, Z., Yan, X. & Long, J. (2021). End-To-End Unsupervised Fault Detection Using A Flow-Based Model. Reliability Engineering & System Safety, 215, Article ID 107805.
Open this publication in new window or tab >>End-To-End Unsupervised Fault Detection Using A Flow-Based Model
Show others...
2021 (English)In: Reliability Engineering & System Safety, ISSN 0951-8320, E-ISSN 1879-0836, Vol. 215, article id 107805Article in journal (Refereed) Published
Abstract [en]

Fault detection has been extensively studied in both academia and industry. The rareness of faulty samples in the real world restricts the use of many supervised models, and the reliance on domain expertise for feature engineering raises Other barriers. For this reason, this paper proposes an unsupervised, end-to-end approach to fault detection based on a flow-based model, the Nonlinear Independent Components Estimation (NICE) model. A NICE model models a target distribution via a sequence of invertible transformations to a prior distribution in the latent space. We prove that, under certain conditions, the L2-norm of normal samples’ latent codes in a trained NICE model is Chi-distributed. This facilitates the use of hypothesis testing for fault detection purpose. Concretely, we first apply Zero-phase Component Analysis to decorrelate the data of normal states. The whitened data are fed to a NICE model for training, in a maximum likelihood sense. At the testing stage, samples whose L2-norm of latent codes fail in the hypothesis testing are suspected of being generated by different mechanisms and hence regarded as potential faults. The proposed approach was validated on two datasets of vibration signals; it proved superior to several alternatives. We also show the use of NICE, a type of generative model, can produce real-like vibration signals because of the model's bijective nature.

Place, publisher, year, edition, pages
Elsevier, 2021
Keywords
Prognostics and health management, Fault detection, Deep learning, Unsupervised learning, Flow-based models
National Category
Software Engineering
Research subject
Operation and Maintenance
Identifiers
urn:nbn:se:ltu:diva-84635 (URN)10.1016/j.ress.2021.107805 (DOI)000690283800019 ()2-s2.0-85107630379 (Scopus ID)
Note

Validerad;2021;Nivå 2;2021-06-18 (johcin);

Forskningsfinansiärer: National Natural Science Foundation of China (71801045, 71801046, 51905160); the Research start-up funds of DGUT (GC300502-46); the Natural Science Foundation of Hunan Province (2020JJ5072); the National Key Research and Development Program of China (2020YFB1712103); the Fundamental Research Funds for the Central Universities (531118010335)

Available from: 2021-05-26 Created: 2021-05-26 Last updated: 2022-10-28Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0002-7458-6820

Search in DiVA

Show all publications