Lijuan Shen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Lijuan Shen has a total of 44 co-authors. Here are the top co-authors by number of shared publications:
- Ancha Xu
Zhejiang Gongshang University
3 shared publications - Fode Zhang
Center of Statistical Research, School of Statistics, Southwestern University of Finance and Economics, Chengdu, China
3 shared publications - Qiuzhuang Sun
College of Integrative Studies, Singapore Management University, Singapore
3 shared publications - Yan Shen
Department of Statistics and Data Sciences, School of Economics, Xiamen University
3 shared publications - Yincai Tang
KLATASDS-MOE, School of Statistics, East China Normal University, Shanghai, China
3 shared publications - Bingxin Yan
Department of Industrial Systems Engineering and Management, National University of Singapore, Singapore
2 shared publications
Latest Publications
- Open Access
- 8 October 2026
- Published by Elsevier in SSRN Electronic Journal
SECI-DA: Physics-Enforced Diffusion Augmentation for Cross-Domain Bearing Fault Diagnosis
Intelligent bearing fault diagnosis under cross-domain few-shot conditions faces three intertwined challenges: limited labeled data in the target domain, distribution shift across working conditions, and the lack of physical constraints in generative augmentation. To address these challenges jointly, we propose a unified framework that combines physics-guided diffusion augmentation with momentum contrastive domain adaptation. Specifically, we introduce a physics-grounded Spectral Energy Concentration Index (SECI), a differentiable and speed-aware metric that quantifies the harmonic concentration of fault-frequency components. SECI is used as a gradient-based guidance signal to steer diffusion sampling toward physically meaningful synthetic samples, while a class-conditional guidance schedule prevents spurious fault-frequency injection into the healthy class. For open-set scenarios, we further develop a fused scoring strategy based on embedding distance and a SECI-adaptive quantile threshold to robustly reject unknown faults. Experiments on the Paderborn Dataset and RFWB Dataset across closed-set, open-set, and few-shot settings demonstrate consistent improvements over recent state-of-the-art baselines.
- 8 October 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessSECI-DA: Physics-Enforced Diffusion Augmentation for Cross-Domain Bearing Fault Diagnosis
Intelligent bearing fault diagnosis under cross-domain few-shot conditions faces three intertwined challenges: limited labeled data in the target domain, distribution shift across working conditions, and the lack of physical constraints in generative augmentation. To address these challenges jointly, we propose a unified framework that combines physics-guided diffusion augmentation with momentum contrastive domain adaptation. Specifically, we introduce a physics-grounded Spectral Energy Concentration Index (SECI), a differentiable and speed-aware metric that quantifies the harmonic concentration of fault-frequency components. SECI is used as a gradient-based guidance signal to steer diffusion sampling toward physically meaningful synthetic samples, while a class-conditional guidance schedule prevents spurious fault-frequency injection into the healthy class. For open-set scenarios, we further develop a fused scoring strategy based on embedding distance and a SECI-adaptive quantile threshold to robustly reject unknown faults. Experiments on the Paderborn Dataset and RFWB Dataset across closed-set, open-set, and few-shot settings demonstrate consistent improvements over recent state-of-the-art baselines.
- 2 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Reliability
- Vol. 75 (00189529) , 97-111
Order-Preserving Kernel Contrastive Learning With Applications to Cross-Domain RUL Prediction
Cross-domain remaining useful life prediction is a critical task for industrial applications, and existing domain adaptation (DA) techniques typically focus on mitigating domain shift by learning domain-invariant features. These methods help transfer knowledge from a labeled source domain to an unlabeled target domain, thus improving prediction accuracy and robustness. However, the alignment strategies used are often coarse-grained, which can lead to the disruption of inherent temporal dependencies in degradation data. In this article, we introduce the novel order-preserving kernel contrastive (OPKC) learning, which leverages the concept that samples with smaller label differences should exhibit higher kernel similarities in the reproducing Kernel Hilbert space (RKHS), irrespective of their domain origin. This kernel-enhanced, regression-aware contrastive learning technique enables fine-grained instance-level pairwise alignment between the source and target domains, ensuring that label difference information is preserved while maintaining the temporal order information inherent in the data. In addition, OPKC can be seamlessly integrated with adversarial DA methods to further enhance both prediction performance and training stability. Extensive experiments on two widely used industrial benchmark datasets demonstrate that the proposed framework significantly outperforms state-of-the-art transfer learning and contrastive learning methods, achieving relative improvement of 16.9% on the PHM 2012 dataset and 13.2% on the C-MAPSS dataset.
- 2 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Reliability
- Vol. 75 (00189529) , 97-111
Order-Preserving Kernel Contrastive Learning With Applications to Cross-Domain RUL Prediction
Cross-domain remaining useful life prediction is a critical task for industrial applications, and existing domain adaptation (DA) techniques typically focus on mitigating domain shift by learning domain-invariant features. These methods help transfer knowledge from a labeled source domain to an unlabeled target domain, thus improving prediction accuracy and robustness. However, the alignment strategies used are often coarse-grained, which can lead to the disruption of inherent temporal dependencies in degradation data. In this article, we introduce the novel order-preserving kernel contrastive (OPKC) learning, which leverages the concept that samples with smaller label differences should exhibit higher kernel similarities in the reproducing Kernel Hilbert space (RKHS), irrespective of their domain origin. This kernel-enhanced, regression-aware contrastive learning technique enables fine-grained instance-level pairwise alignment between the source and target domains, ensuring that label difference information is preserved while maintaining the temporal order information inherent in the data. In addition, OPKC can be seamlessly integrated with adversarial DA methods to further enhance both prediction performance and training stability. Extensive experiments on two widely used industrial benchmark datasets demonstrate that the proposed framework significantly outperforms state-of-the-art transfer learning and contrastive learning methods, achieving relative improvement of 16.9% on the PHM 2012 dataset and 13.2% on the C-MAPSS dataset.
- 1 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Reliability
- Vol. 74 (3) , 4091-4105
A Physical-Statistical Framework on Complex Mechanical System Fault Isolation
Supervisory control and data acquisition (SCADA) data from a complex mechanical system, such as a high-speed train power bogie, nonpower bogie, and wind turbine, are widely used for anomaly detection and fault isolation. The SCADA data include measurements of process variables and exogenous covariates for key components in the system. The process variables refer to the performance characteristics of the key component while the exogenous covariates are working loads or working conditions of the complex mechanical system. Dominated by such physical mechanisms as dynamic motion laws of the system, there are complex relationships between the process variables and covariates, that complicate anomaly detection and fault isolation. To solve this problem, we propose a framework that integrates physical knowledge and statistical learning. We first build a spline model to capture the relationship between process variables and exogenous covariates. To make the model interpretable, we use physical knowledge to impose constraints on the model parameters. We then conduct anomaly detection at a system level based on the physical-statistical regression model. Once an anomaly is detected, we propose a Lasso-based method to isolate the faulty components. Our fault isolation method does not require historical failure data or knowing the true number of faulty components. Real-world case studies on power bogies from high-speed trains illustrate the advantages of our framework: the best benchmark achieves at least 2.50% lower F1-score in anomaly detection and 6.01% lower F1-score in fault isolation compared to our method.
- 1 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Reliability
- Vol. 74 (3) , 4091-4105
A Physical-Statistical Framework on Complex Mechanical System Fault Isolation
Supervisory control and data acquisition (SCADA) data from a complex mechanical system, such as a high-speed train power bogie, nonpower bogie, and wind turbine, are widely used for anomaly detection and fault isolation. The SCADA data include measurements of process variables and exogenous covariates for key components in the system. The process variables refer to the performance characteristics of the key component while the exogenous covariates are working loads or working conditions of the complex mechanical system. Dominated by such physical mechanisms as dynamic motion laws of the system, there are complex relationships between the process variables and covariates, that complicate anomaly detection and fault isolation. To solve this problem, we propose a framework that integrates physical knowledge and statistical learning. We first build a spline model to capture the relationship between process variables and exogenous covariates. To make the model interpretable, we use physical knowledge to impose constraints on the model parameters. We then conduct anomaly detection at a system level based on the physical-statistical regression model. Once an anomaly is detected, we propose a Lasso-based method to isolate the faulty components. Our fault isolation method does not require historical failure data or knowing the true number of faulty components. Real-world case studies on power bogies from high-speed trains illustrate the advantages of our framework: the best benchmark achieves at least 2.50% lower F1-score in anomaly detection and 6.01% lower F1-score in fault isolation compared to our method.
- 9 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Reliability
- Vol. 74 (3) , 3871-3883
RUL Prediction With Cross-Domain Adaptation Based on Reproducing Kernel Hilbert Space
Data-driven methods for predicting remaining useful life (RUL) have received considerable attention in the field of degradation data analysis. The transfer learning (TL) method offers new possibilities for RUL tasks in various operational settings. However, in many engineering applications, challenges in TL arise mainly from the scarcity or high cost of labeled data in the target domain, coupled with incomplete degradation of RUL samples within the target domain. This article proposes an innovative model named deep cross-domain transfer learning for interpretable prediction The model effectively harnesses the advantages of domain adaptation (DA) techniques in mitigating domain distribution disparities and also uses the exceptional visualization capabilities inherent in the variational autoencoder (VAE) model. This method integrates the VAE framework with regression networks and utilizes DA techniques to align feature spaces, achieving cross-domain RUL prediction with unlabeled target domain data and cross-domain visualization of the entire degradation process. The reproducing kernel Hilbert space is considered in domain adaption to control the complexity of hypothesis space. The effectiveness of the proposed method is demonstrated by analyzing the real C-MAPSS dataset.
- 9 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Reliability
- Vol. 74 (3) , 3871-3883
RUL Prediction With Cross-Domain Adaptation Based on Reproducing Kernel Hilbert Space
Data-driven methods for predicting remaining useful life (RUL) have received considerable attention in the field of degradation data analysis. The transfer learning (TL) method offers new possibilities for RUL tasks in various operational settings. However, in many engineering applications, challenges in TL arise mainly from the scarcity or high cost of labeled data in the target domain, coupled with incomplete degradation of RUL samples within the target domain. This article proposes an innovative model named deep cross-domain transfer learning for interpretable prediction The model effectively harnesses the advantages of domain adaptation (DA) techniques in mitigating domain distribution disparities and also uses the exceptional visualization capabilities inherent in the variational autoencoder (VAE) model. This method integrates the VAE framework with regression networks and utilizes DA techniques to align feature spaces, achieving cross-domain RUL prediction with unlabeled target domain data and cross-domain visualization of the entire degradation process. The reproducing kernel Hilbert space is considered in domain adaption to control the complexity of hypothesis space. The effectiveness of the proposed method is demonstrated by analyzing the real C-MAPSS dataset.
- 1 August 2024
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 35 (10) , 106138
A novel RUL prediction method for rolling bearings based on dynamic control chart and adaptive incremental filtering
Degradation of rolling bearings typically consists of two stages: a stable stage (Stage I) characterized by stable fluctuations in the health indicator (HI), and a degradation stage (Stage II) where early damage leads to HI degradation, eventually reaching the failure threshold. Therefore, to achieve remaining useful life prediction for bearings, three aspects should be studied: (1) degradation modeling; (2) inter stage change point identification; (3) degradation state updating. Firstly, a two-stage degradation model is constructed by simultaneously considering inherent randomness, individual differences, and measurement errors. Then, a dynamic statistical process control (SPC) method is proposed to identify the change point from Stage I to Stage II. The SPC is designed to dynamically control limits based on the bearing’s condition monitoring data to prevent false alarms. An adaptive incremental filtering is proposed to update the degradation states by simultaneously considering the state increment and the dynamics of the system noise and measurement noise. The effectiveness of the proposed method is validated on 16 004 bearing test data and XJTU-SY bearing data. Results show that the proposed method can accuracy identify the change point and improve the accuracy of the prediction result during stage II.
- 1 August 2024
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 35 (10) , 106138
A novel RUL prediction method for rolling bearings based on dynamic control chart and adaptive incremental filtering
Degradation of rolling bearings typically consists of two stages: a stable stage (Stage I) characterized by stable fluctuations in the health indicator (HI), and a degradation stage (Stage II) where early damage leads to HI degradation, eventually reaching the failure threshold. Therefore, to achieve remaining useful life prediction for bearings, three aspects should be studied: (1) degradation modeling; (2) inter stage change point identification; (3) degradation state updating. Firstly, a two-stage degradation model is constructed by simultaneously considering inherent randomness, individual differences, and measurement errors. Then, a dynamic statistical process control (SPC) method is proposed to identify the change point from Stage I to Stage II. The SPC is designed to dynamically control limits based on the bearing’s condition monitoring data to prevent false alarms. An adaptive incremental filtering is proposed to update the degradation states by simultaneously considering the state increment and the dynamics of the system noise and measurement noise. The effectiveness of the proposed method is validated on 16 004 bearing test data and XJTU-SY bearing data. Results show that the proposed method can accuracy identify the change point and improve the accuracy of the prediction result during stage II.
- 1 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Reliability
- Vol. 74 (3) , 3911-3925
Physics-Enhanced NMF Toward Anomaly Detection in Rotating Mechanical Systems
With the advancements in sensor technology, it is now possible to measure and record a multitude of features that reflect the health condition of complex systems. These measurements are stored in a sizable data matrix, enabling the detection of anomalies. Nevertheless, the presence of this large data matrix poses a significant computational burden. The dimension-reduction methods, such as non-negative matrix factorization (NMF), can efficiently reduce computational burden. However, their pure data-driven nature can lead to overfitting and biases in anomaly detection results. To address this shortcoming, we propose a physics-enhanced NMF (PNMF) method by incorporating physical knowledge into NMF with the help of graph technique. The graph technique organizes measurements and features into two graph objects, respectively, and the physical knowledge guides the formation of edges between nodes in the graph. This allows the PNMF to capture not only the data-driven patterns but also the physical structure inherent in the system. The closed-form update algorithm is developed for the PNMF model, which can guarantee the convergence of parameters estimation. The superior performance of the PNMF model in detecting anomalies is demonstrated by comparing prevailing methods in both public datasets and real-world applications.
- 1 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Reliability
- Vol. 74 (3) , 3911-3925
Physics-Enhanced NMF Toward Anomaly Detection in Rotating Mechanical Systems
With the advancements in sensor technology, it is now possible to measure and record a multitude of features that reflect the health condition of complex systems. These measurements are stored in a sizable data matrix, enabling the detection of anomalies. Nevertheless, the presence of this large data matrix poses a significant computational burden. The dimension-reduction methods, such as non-negative matrix factorization (NMF), can efficiently reduce computational burden. However, their pure data-driven nature can lead to overfitting and biases in anomaly detection results. To address this shortcoming, we propose a physics-enhanced NMF (PNMF) method by incorporating physical knowledge into NMF with the help of graph technique. The graph technique organizes measurements and features into two graph objects, respectively, and the physical knowledge guides the formation of edges between nodes in the graph. This allows the PNMF to capture not only the data-driven patterns but also the physical structure inherent in the system. The closed-form update algorithm is developed for the PNMF model, which can guarantee the convergence of parameters estimation. The superior performance of the PNMF model in detecting anomalies is demonstrated by comparing prevailing methods in both public datasets and real-world applications.
- 9 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Reliability
- Vol. 73 (2) , 912-921
Degradation Modeling and RUL Prediction in Dynamic Environments Using a Wiener Process With an Autoregressive Rate
Since the degradation process is dependent on the environmental stresses, degrading products operating under dynamic environments can have time-varying degradation rates. Existing studies generally exploit a random walk to model the time-varying degradation rate, considering the randomness of the environmental effects. The random walk is not stationary, while the real environments, although dynamic, are often stationary. The degradation process under a stationary environment would have a stationary degradation rate. Therefore, instead of the random walk, we propose to model the stochastic degradation rate by an autoregressive model. The autoregressive rate can accommodate the randomness and stationarity of the environmental effects. Conditional on the autoregressive degradation rate, a Wiener process is used to model the degradation process. We develop an Expectation-Maximization algorithm to perform maximum likelihood estimation of model parameters. Moreover, to facilitate remaining useful life prediction, we derive the explicit probability density function for the remaining useful life (RUL). We validate the proposed model by a simulation study and justify the applicability and performance of the proposed model by two real degradation datasets.
- 9 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Reliability
- Vol. 73 (2) , 912-921
Degradation Modeling and RUL Prediction in Dynamic Environments Using a Wiener Process With an Autoregressive Rate
Since the degradation process is dependent on the environmental stresses, degrading products operating under dynamic environments can have time-varying degradation rates. Existing studies generally exploit a random walk to model the time-varying degradation rate, considering the randomness of the environmental effects. The random walk is not stationary, while the real environments, although dynamic, are often stationary. The degradation process under a stationary environment would have a stationary degradation rate. Therefore, instead of the random walk, we propose to model the stochastic degradation rate by an autoregressive model. The autoregressive rate can accommodate the randomness and stationarity of the environmental effects. Conditional on the autoregressive degradation rate, a Wiener process is used to model the degradation process. We develop an Expectation-Maximization algorithm to perform maximum likelihood estimation of model parameters. Moreover, to facilitate remaining useful life prediction, we derive the explicit probability density function for the remaining useful life (RUL). We validate the proposed model by a simulation study and justify the applicability and performance of the proposed model by two real degradation datasets.
- 7 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Reliability
- Vol. 73 (1) , 560-575
Robust Estimation and Selection for Degradation Modeling With Inhomogeneous Increments
The evaluation of long-lifetime and high-reliability products has attracted much attention. Stochastic degradation modeling is one of the most popular methods. The classical stochastic processes are frequently employed to discuss degradation trajectories. Most current work assumes that the underlying probability model of a degradation process is known or fixed in the estimation and model selection procedures. However, the ground-truth degradation model is usually unavailable in engineering applications. This article proposes a feasible parameter estimation and model selection procedure by measuring the distribution divergence among the nonparametric estimated model and some candidate models. In the proposed methods, it is not necessary to assume the availability of a ground-true model, which is replaced by a nonparametric estimated model. The proposed methodologies are suitable for restricted independent and nonidentically distributed samples. We discuss the large sample property of the suggested estimators. We report the Monte Carlo simulation study and practical data analysis to demonstrate our methods.
- 7 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Reliability
- Vol. 73 (1) , 560-575
Robust Estimation and Selection for Degradation Modeling With Inhomogeneous Increments
The evaluation of long-lifetime and high-reliability products has attracted much attention. Stochastic degradation modeling is one of the most popular methods. The classical stochastic processes are frequently employed to discuss degradation trajectories. Most current work assumes that the underlying probability model of a degradation process is known or fixed in the estimation and model selection procedures. However, the ground-truth degradation model is usually unavailable in engineering applications. This article proposes a feasible parameter estimation and model selection procedure by measuring the distribution divergence among the nonparametric estimated model and some candidate models. In the proposed methods, it is not necessary to assume the availability of a ground-true model, which is replaced by a nonparametric estimated model. The proposed methodologies are suitable for restricted independent and nonidentically distributed samples. We discuss the large sample property of the suggested estimators. We report the Monte Carlo simulation study and practical data analysis to demonstrate our methods.
- 9 August 2023
- Published by Wiley in Quality and Reliability Engineering International
- Vol. 40 (1) , 388-405
Maintenance optimization of a two‐component series system considering masked causes of failure
Maintenance planning of two‐component systems has been extensively studied in recent decades. In the literature, most studies assume that the failure cause of a two‐component system is self‐announcing. In some real applications, the failure cause is masked, and a diagnosis with professional equipment is needed to reveal the failed component. This study investigates a preventive replacement policy of a two‐component series system considering masked causes of failure. When an unexpected failure occurs, we can carry out a diagnosis to reveal the failed component and replace it subsequently, or we can directly replace the whole system without diagnosis. Meanwhile, when we carry out a preventive replacement on a component, the other component can be replaced opportunistically. We formulate the problem as a semi‐Markov decision process, and prove the existence of the stationary optimal policy. The optimal preventive replacement age thresholds for each component and the corresponding optimal maintenance actions upon each failure are jointly obtained to minimize the long‐term average maintenance cost per time unit. A comprehensive numerical study is provided to illustrate the effectiveness of our proposed model.
- 9 August 2023
- Published by Wiley in Quality and Reliability Engineering International
- Vol. 40 (1) , 388-405
Maintenance optimization of a two‐component series system considering masked causes of failure
Maintenance planning of two‐component systems has been extensively studied in recent decades. In the literature, most studies assume that the failure cause of a two‐component system is self‐announcing. In some real applications, the failure cause is masked, and a diagnosis with professional equipment is needed to reveal the failed component. This study investigates a preventive replacement policy of a two‐component series system considering masked causes of failure. When an unexpected failure occurs, we can carry out a diagnosis to reveal the failed component and replace it subsequently, or we can directly replace the whole system without diagnosis. Meanwhile, when we carry out a preventive replacement on a component, the other component can be replaced opportunistically. We formulate the problem as a semi‐Markov decision process, and prove the existence of the stationary optimal policy. The optimal preventive replacement age thresholds for each component and the corresponding optimal maintenance actions upon each failure are jointly obtained to minimize the long‐term average maintenance cost per time unit. A comprehensive numerical study is provided to illustrate the effectiveness of our proposed model.
- Top Cited Papers
- 18 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Reliability
- Vol. 73 (1) , 399-412
Fast Bayesian Inference of Reparameterized Gamma Process With Random Effects
In the field of reliability engineering, the gamma process plays an important role in modeling degradation processes. However, extracting lifetime information from product degradation observations has long been suffering from both ineffective modeling techniques and inefficient statistical inference methods. To overcome these challenges, we propose a reparameterized gamma process with random effects in this article. Compared with the classical gamma process, the proposed model has a more intuitive physical interpretation. In addition, statistical inference for the model can be readily done through the variational Bayesian algorithm. Combining with the Gauss–Hermite quadrature and the Laplace approximation, the algorithm yields closed-form variational posteriors for the proposed model. Its superiority over two other inference methods (expectation maximization and Monte Carlo Markov Chain) in terms of computational efficiency and estimation accuracy is demonstrated by simulation.
- 18 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Reliability
- Vol. 73 (1) , 399-412
Top Cited PapersFast Bayesian Inference of Reparameterized Gamma Process With Random Effects
In the field of reliability engineering, the gamma process plays an important role in modeling degradation processes. However, extracting lifetime information from product degradation observations has long been suffering from both ineffective modeling techniques and inefficient statistical inference methods. To overcome these challenges, we propose a reparameterized gamma process with random effects in this article. Compared with the classical gamma process, the proposed model has a more intuitive physical interpretation. In addition, statistical inference for the model can be readily done through the variational Bayesian algorithm. Combining with the Gauss–Hermite quadrature and the Laplace approximation, the algorithm yields closed-form variational posteriors for the proposed model. Its superiority over two other inference methods (expectation maximization and Monte Carlo Markov Chain) in terms of computational efficiency and estimation accuracy is demonstrated by simulation.