Zhe Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zhe Chen has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Yonghua Li
Zhan Tianyou College(CRRC College), Dalian Jiaotong University
4 shared publications Denglong Wang
College of locomotive and rolling stock Engineering, Dalian Jiaotong University, Dalian, China
2 shared publicationsQi Gong
Zhan Tianyou Honors College (College of China Railway Rolling Stock Corporation) Dalian Jiaotong University Dalian China
2 shared publications- Chaoqun Hu
College of locomotive and rolling stock Engineering, Dalian Jiaotong University, Dalian, China
1 shared publication - Denglong Wang
College of Locomotive and Rolling Stock Engineering, Dalian Jiaotong University 1 , Dalian 116000, China
1 shared publication Fan Yang
Zhan Tianyou Honors College (College of China Railway Rolling Stock Corporation) Dalian Jiaotong University Dalian China
1 shared publication
Latest Publications
- 9 April 2026
- Published by Wiley in Quality and Reliability Engineering International
Remaining Useful Life Prediction Method Based on an Improved Wiener Process Considering Multiple Performance Indicators Correlations
To improve the accuracy of remaining useful life (RUL) prediction under complex multi‐indicator dependencies, this paper proposes an RUL prediction method that integrates multi‐indicator correlation modeling with an enhanced Wiener process. Kendall rank correlation is used to identify key performance indicators that are highly related to equipment lifespan, thereby reducing the influence of redundant variables on dependency modeling. C‐Vine Copula model is employed to jointly model higher‐order dependencies among multiple degradation features, with the optimal Copula type for each pair of indicators automatically selected based on the AIC criterion, enabling flexible characterization of complex nonlinear and asymmetric interdependencies. Based on the joint modeling results, principal component analysis is used to fuse high‐dimensional health indicators, extracting a comprehensive indicator that effectively reflects the overall health condition of the equipment. In degradation modeling, machine learning methods are introduced by employing long short‐term memory networks to adaptively fit the drift coefficient, and the Wiener process is used to characterize prediction uncertainty, thereby enabling dynamic modeling of the fused health indicator degradation trajectory and probabilistic prediction of the remaining useful life.
- 9 April 2026
- Published by Wiley in Quality and Reliability Engineering International
Remaining Useful Life Prediction Method Based on an Improved Wiener Process Considering Multiple Performance Indicators Correlations
To improve the accuracy of remaining useful life (RUL) prediction under complex multi‐indicator dependencies, this paper proposes an RUL prediction method that integrates multi‐indicator correlation modeling with an enhanced Wiener process. Kendall rank correlation is used to identify key performance indicators that are highly related to equipment lifespan, thereby reducing the influence of redundant variables on dependency modeling. C‐Vine Copula model is employed to jointly model higher‐order dependencies among multiple degradation features, with the optimal Copula type for each pair of indicators automatically selected based on the AIC criterion, enabling flexible characterization of complex nonlinear and asymmetric interdependencies. Based on the joint modeling results, principal component analysis is used to fuse high‐dimensional health indicators, extracting a comprehensive indicator that effectively reflects the overall health condition of the equipment. In degradation modeling, machine learning methods are introduced by employing long short‐term memory networks to adaptively fit the drift coefficient, and the Wiener process is used to characterize prediction uncertainty, thereby enabling dynamic modeling of the fused health indicator degradation trajectory and probabilistic prediction of the remaining useful life.
- 28 October 2025
- Published by SAGE Publications in Journal of Vibration and Control
A method for predicting the remaining service life of equipment considering the dual effects of degradation and random shocks
In engineering practice, equipment experiences expected degradation while also being affected by random shocks. A method for predicting the remaining useful life (RUL) of equipment considering both degradation and random shocks has been proposed for equipment degraded by random shocks during operation. Firstly, a comprehensive degradation model is constructed to characterize the equipment degradation process. This model employs a nonlinear Wiener process to identify the continuous degradation process, a normal distribution to describe the impact of random shocks on the amount of equipment degradation, and a compound Poisson process with a time-varying shock frequency is used to characterize the effects of random shocks on degradation levels. This general formulation reduces to the traditional case with a constant shock frequency, while the time-varying form better reflects real-world operating behavior where shocks occur less frequently in the early stage and more frequently in the later stage of degradation. Secondly, the RUL prediction accounts for device heterogeneity and uncertainty, yielding an approximate analytical RUL distribution, with model parameters estimated via maximum likelihood estimation. Finally, the influence of different parameters in the model on the RUL prediction results is verified through numerical simulation, validating the effectiveness of the proposed method, and the engineering application value of the proposed method is demonstrated through bearing examples. Compared with existing methods, this method has higher estimation accuracy and can quantify prediction uncertainty. It has certain theoretical significance for solving the problem of RUL prediction for equipment affected by random shocks.
- 28 October 2025
- Published by SAGE Publications in Journal of Vibration and Control
A method for predicting the remaining service life of equipment considering the dual effects of degradation and random shocks
In engineering practice, equipment experiences expected degradation while also being affected by random shocks. A method for predicting the remaining useful life (RUL) of equipment considering both degradation and random shocks has been proposed for equipment degraded by random shocks during operation. Firstly, a comprehensive degradation model is constructed to characterize the equipment degradation process. This model employs a nonlinear Wiener process to identify the continuous degradation process, a normal distribution to describe the impact of random shocks on the amount of equipment degradation, and a compound Poisson process with a time-varying shock frequency is used to characterize the effects of random shocks on degradation levels. This general formulation reduces to the traditional case with a constant shock frequency, while the time-varying form better reflects real-world operating behavior where shocks occur less frequently in the early stage and more frequently in the later stage of degradation. Secondly, the RUL prediction accounts for device heterogeneity and uncertainty, yielding an approximate analytical RUL distribution, with model parameters estimated via maximum likelihood estimation. Finally, the influence of different parameters in the model on the RUL prediction results is verified through numerical simulation, validating the effectiveness of the proposed method, and the engineering application value of the proposed method is demonstrated through bearing examples. Compared with existing methods, this method has higher estimation accuracy and can quantify prediction uncertainty. It has certain theoretical significance for solving the problem of RUL prediction for equipment affected by random shocks.
- 30 August 2025
- Published by SAGE Publications in Journal of Vibration and Control
- Vol. 32 (17-18) , 5405-5420
Rolling bearing fault diagnosis method based on improved gramian angular difference field and SPPF-MsCNN
Aiming at the problem that the 2D image of the input deep learning model has lost edge information, which leads to the low accuracy of rolling bearing fault diagnosis, a fault diagnosis method based on improved gramian angular difference field (GADF) image and spatial pyramid pooling-fast (SPPF) to optimize multi-scale sliding convolutional neural network (SPPF-MsCNN) model is proposed. First, the high-frequency components of the bearing vibration signals are enhanced using the tangent sigmoid function, and GADF images are generated. Then, features are extracted using a multi-scale parallel convolution approach. Finally, introducing spatial pyramid pooling-fast avoids the feature loss issue caused by max pooling and average pooling. The experimental results demonstrate that the model achieves excellent fault recognition performance across different datasets. Furthermore, the proposed method effectively addresses the problem of low diagnostic accuracy caused by edge loss in 2D images. In addition, noise resistance experiments evaluate the robustness of the model under noisy conditions, while ablation studies confirm the rationality of the model architecture.
- 30 August 2025
- Published by SAGE Publications in Journal of Vibration and Control
- Vol. 32 (17-18) , 5405-5420
Rolling bearing fault diagnosis method based on improved gramian angular difference field and SPPF-MsCNN
Aiming at the problem that the 2D image of the input deep learning model has lost edge information, which leads to the low accuracy of rolling bearing fault diagnosis, a fault diagnosis method based on improved gramian angular difference field (GADF) image and spatial pyramid pooling-fast (SPPF) to optimize multi-scale sliding convolutional neural network (SPPF-MsCNN) model is proposed. First, the high-frequency components of the bearing vibration signals are enhanced using the tangent sigmoid function, and GADF images are generated. Then, features are extracted using a multi-scale parallel convolution approach. Finally, introducing spatial pyramid pooling-fast avoids the feature loss issue caused by max pooling and average pooling. The experimental results demonstrate that the model achieves excellent fault recognition performance across different datasets. Furthermore, the proposed method effectively addresses the problem of low diagnostic accuracy caused by edge loss in 2D images. In addition, noise resistance experiments evaluate the robustness of the model under noisy conditions, while ablation studies confirm the rationality of the model architecture.
- 25 July 2024
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 35 (10) , 106132
Remaining useful life prediction method based on stacked autoencoder and generalized wiener process for degrading bearing
Remaining useful life (RUL) prediction using deep learning networks primarily produces point estimates of RUL, but capturing the inherent uncertainty in RUL prediction is difficult. The use of the stochastic process approach can reflect the uncertainty in RUL predictions. However, the amount of data generated during equipment operation cannot be effectively utilized. This paper aims to propose an adaptive RUL prediction method tailored for extensive datasets and prediction uncertainty, effectively harnessing the strengths of deep learning methods in managing massive data and stochastic process techniques in quantifying uncertainties. RUL prediction method, based on stacked autoencoder (SAE) combined with Generalized Wiener Process, employs SAE to extract profound underlying features from the monitoring signals. Principal component analysis (PCA) is then used to select highly trending features as inputs. The output of PCA accurately reflects health status. A Generalized Wiener Process is used to construct a model for the evolution of the health indicators. The estimation values for the model parameters are determined using the Maximum Likelihood Estimation method. Furthermore, an adaptive update is performed based on Bayesian theory. Utilizing the sense of the first hitting time concept, the Probability Density Function for RUL prediction is derived accurately. Finally, the effectiveness and superiority of the proposed method is verified using numerical simulations and experimental studies of bearing degradation data. The method improves the life prediction accuracy while reducing the prediction uncertainty.
- 25 July 2024
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 35 (10) , 106132
Remaining useful life prediction method based on stacked autoencoder and generalized wiener process for degrading bearing
Remaining useful life (RUL) prediction using deep learning networks primarily produces point estimates of RUL, but capturing the inherent uncertainty in RUL prediction is difficult. The use of the stochastic process approach can reflect the uncertainty in RUL predictions. However, the amount of data generated during equipment operation cannot be effectively utilized. This paper aims to propose an adaptive RUL prediction method tailored for extensive datasets and prediction uncertainty, effectively harnessing the strengths of deep learning methods in managing massive data and stochastic process techniques in quantifying uncertainties. RUL prediction method, based on stacked autoencoder (SAE) combined with Generalized Wiener Process, employs SAE to extract profound underlying features from the monitoring signals. Principal component analysis (PCA) is then used to select highly trending features as inputs. The output of PCA accurately reflects health status. A Generalized Wiener Process is used to construct a model for the evolution of the health indicators. The estimation values for the model parameters are determined using the Maximum Likelihood Estimation method. Furthermore, an adaptive update is performed based on Bayesian theory. Utilizing the sense of the first hitting time concept, the Probability Density Function for RUL prediction is derived accurately. Finally, the effectiveness and superiority of the proposed method is verified using numerical simulations and experimental studies of bearing degradation data. The method improves the life prediction accuracy while reducing the prediction uncertainty.