Wei Shi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Wei Shi has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Aihua Liao
Shanghai University of Engineering Science
3 shared publications - Kailin Bi
Shanghai University of Engineering Science
2 shared publications DingYu Hu
Shanghai University of Engineering Science
1 shared publicationDingyu Hu
School of Urban Rail Transportation, Shanghai University of Engineering Science, Shanghai 201620, People’s Republic of China
1 shared publication- Dingyu Hu
Shanghai University of Engineering Science
1 shared publication Jun Fang
School of Urban Rail Transportation, Shanghai University of Engineering Science, Shanghai 201620, People’s Republic of China
1 shared publication
Latest Publications
- 6 October 2026
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 37 (40) , 405105
A novel multi-sensor fault diagnosis framework based on PPS feature selection and K -means initialized particle swarm classifier using MiniRocket feature extraction
Acoustic sensors and microphone array technologies are widely used in industrial condition monitoring and fault diagnosis, and their reliability directly affects monitoring stability and equipment safety. However, existing acoustic sensor fault diagnosis methods under complex operating conditions still face limitations, including insufficient feature representation, reliance on handcrafted features, high computational cost, and difficulty in real-time deployment. To address these issues, this paper proposes a lightweight acoustic sensor fault identification method for complex operating conditions, enabling prior hard-fault removal, fine-grained soft-fault classification, and efficient feature selection. First, an anomaly identification mechanism integrating statistical screening and adaptive decision-making is developed to rapidly detect and remove explicit hard-fault samples using multidimensional statistical features, ensuring reliable inputs for subsequent diagnosis. Second, MiniRocket is used to map the screened acoustic time-series signals into high-dimensional features, enhancing fault representation. Then, the Predictive Power Score is introduced to evaluate and select discriminative core features, reducing feature redundancy, inference latency, and computational burden. Finally, K -means-based initial partitioning is combined with a granular-ball classifier, where local geometric coverage and a relaxation factor enable robust soft-fault classification. The proposed method balances accuracy, robustness, interpretability, and efficiency, providing an effective solution for lightweight intelligent diagnosis of acoustic sensor faults in complex industrial environments.
- 6 October 2026
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 37 (40) , 405105
A novel multi-sensor fault diagnosis framework based on PPS feature selection and K -means initialized particle swarm classifier using MiniRocket feature extraction
Acoustic sensors and microphone array technologies are widely used in industrial condition monitoring and fault diagnosis, and their reliability directly affects monitoring stability and equipment safety. However, existing acoustic sensor fault diagnosis methods under complex operating conditions still face limitations, including insufficient feature representation, reliance on handcrafted features, high computational cost, and difficulty in real-time deployment. To address these issues, this paper proposes a lightweight acoustic sensor fault identification method for complex operating conditions, enabling prior hard-fault removal, fine-grained soft-fault classification, and efficient feature selection. First, an anomaly identification mechanism integrating statistical screening and adaptive decision-making is developed to rapidly detect and remove explicit hard-fault samples using multidimensional statistical features, ensuring reliable inputs for subsequent diagnosis. Second, MiniRocket is used to map the screened acoustic time-series signals into high-dimensional features, enhancing fault representation. Then, the Predictive Power Score is introduced to evaluate and select discriminative core features, reducing feature redundancy, inference latency, and computational burden. Finally, K -means-based initial partitioning is combined with a granular-ball classifier, where local geometric coverage and a relaxation factor enable robust soft-fault classification. The proposed method balances accuracy, robustness, interpretability, and efficiency, providing an effective solution for lightweight intelligent diagnosis of acoustic sensor faults in complex industrial environments.
- 1 June 2026
- Published by IOP Publishing in Engineering Research Express
- Vol. 8 (12) , 125518
Multi-scale signal transformer for rolling bearing fault diagnosis under variable conditions
Deep learning has shown promise in bearing fault diagnosis but often suffers from performance degradation under non-stationary conditions due to the difficulty in capturing time-varying fault characteristics. This study proposes a multi-scale signal transformer (MSSiT) to enhance diagnostic robustness under variable conditions. The architecture incorporates a multi-scale convolutional embedding module, leveraging multi-scale dilated convolutions and efficient channel attention to refine discriminative signal representations. Following convolution-based patch embedding for efficient tokenization, an alternating global–local scale self-attention mechanism and a multi-scale feed-forward network are employed. These modules utilize multi-scale depthwise convolutions to bolster local perception while maintaining a lightweight parameter count. Case studies on four datasets substantiate that MSSiT consistently outperforms five representative methods in cross-speed, cross-load, variable-speed tasks and cross-lateral-load tasks, demonstrating improved cross-condition diagnostic performance under the evaluated variable-condition scenarios.
- 1 June 2026
- Published by IOP Publishing in Engineering Research Express
- Vol. 8 (12) , 125518
Multi-scale signal transformer for rolling bearing fault diagnosis under variable conditions
Deep learning has shown promise in bearing fault diagnosis but often suffers from performance degradation under non-stationary conditions due to the difficulty in capturing time-varying fault characteristics. This study proposes a multi-scale signal transformer (MSSiT) to enhance diagnostic robustness under variable conditions. The architecture incorporates a multi-scale convolutional embedding module, leveraging multi-scale dilated convolutions and efficient channel attention to refine discriminative signal representations. Following convolution-based patch embedding for efficient tokenization, an alternating global–local scale self-attention mechanism and a multi-scale feed-forward network are employed. These modules utilize multi-scale depthwise convolutions to bolster local perception while maintaining a lightweight parameter count. Case studies on four datasets substantiate that MSSiT consistently outperforms five representative methods in cross-speed, cross-load, variable-speed tasks and cross-lateral-load tasks, demonstrating improved cross-condition diagnostic performance under the evaluated variable-condition scenarios.
- 12 May 2026
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 37 (21)
A self-supervised learning framework integrating prior knowledge and simulation data for rolling bearing fault diagnosis with few-shot and imbalanced data
The compound problem of few-shot and data imbalance remains a major obstacle in rolling bearing fault diagnosis. To address this issue, this paper proposes IMSSiT-SSL, a self-supervised learning framework that integrates prior knowledge with simulation data-driven approaches. Unlabeled simulation datasets are used for self-supervised pre-training through two physics-informed pretext tasks: a kurtosis-guided masked reconstruction task that selectively masks high-kurtosis segments to force the model to capture intrinsic fault features, and a characteristic indicator-based pseudo-label prediction task that explicitly embeds domain expert knowledge into the representation learning process. This dual-task pre-training strategy alleviates the few-shot challenge while directing the model's attention toward fault-relevant impact segments, improving the physical interpretability of feature extraction. Subsequently, a small amount of labeled data is used for fine-tuning, where an adaptive boundary-regularized dual focal loss (ABR-DFL) is introduced to encourage the model to focus on discriminating minority class samples, thus mitigating the negative effects of imbalanced data. Experimental results demonstrate that the proposed method achieves G-mean improvements of 3.07%–20.62% over competing methods across various imbalance ratios, and maintains a diagnostic accuracy of 98.78% under cross-speed few-shot conditions with only 30 labeled samples per class.
- 12 May 2026
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 37 (21)
A self-supervised learning framework integrating prior knowledge and simulation data for rolling bearing fault diagnosis with few-shot and imbalanced data
The compound problem of few-shot and data imbalance remains a major obstacle in rolling bearing fault diagnosis. To address this issue, this paper proposes IMSSiT-SSL, a self-supervised learning framework that integrates prior knowledge with simulation data-driven approaches. Unlabeled simulation datasets are used for self-supervised pre-training through two physics-informed pretext tasks: a kurtosis-guided masked reconstruction task that selectively masks high-kurtosis segments to force the model to capture intrinsic fault features, and a characteristic indicator-based pseudo-label prediction task that explicitly embeds domain expert knowledge into the representation learning process. This dual-task pre-training strategy alleviates the few-shot challenge while directing the model's attention toward fault-relevant impact segments, improving the physical interpretability of feature extraction. Subsequently, a small amount of labeled data is used for fine-tuning, where an adaptive boundary-regularized dual focal loss (ABR-DFL) is introduced to encourage the model to focus on discriminating minority class samples, thus mitigating the negative effects of imbalanced data. Experimental results demonstrate that the proposed method achieves G-mean improvements of 3.07%–20.62% over competing methods across various imbalance ratios, and maintains a diagnostic accuracy of 98.78% under cross-speed few-shot conditions with only 30 labeled samples per class.
- 9 February 2020
- Published by Wiley in IEEJ Transactions on Electrical and Electronic Engineering
- Vol. 15 (5) , 751-756
Online Estimation Method for Permanent Magnet Temperature of High‐Density Permanent Magnet Synchronous Motor
Since it can be difficult to directly estimate the temperature of permanent magnets (PM) in high‐density permanent magnet motor rotors, this paper proposes a method based on lumped parameter thermal networks (LPTN) for online estimation of PM temperature. Firstly, a parameter model is established that contains a four‐node thermal network model and a loss model. For the online estimation, an extended Kalman filter algorithm with fading factor is used to dynamically update the thermal network parameter model in order to estimate the PM temperature. The simulation and experimental results show that the parameter model can quickly converge to a value that is close to the true value. Therefore, this online estimation method for PM temperature can accurately monitor the PM temperature online without increasing the required motor hardware; thus not affecting the motor operation. © 2020 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.
- 9 February 2020
- Published by Wiley in IEEJ Transactions on Electrical and Electronic Engineering
- Vol. 15 (5) , 751-756
Online Estimation Method for Permanent Magnet Temperature of High‐Density Permanent Magnet Synchronous Motor
Since it can be difficult to directly estimate the temperature of permanent magnets (PM) in high‐density permanent magnet motor rotors, this paper proposes a method based on lumped parameter thermal networks (LPTN) for online estimation of PM temperature. Firstly, a parameter model is established that contains a four‐node thermal network model and a loss model. For the online estimation, an extended Kalman filter algorithm with fading factor is used to dynamically update the thermal network parameter model in order to estimate the PM temperature. The simulation and experimental results show that the parameter model can quickly converge to a value that is close to the true value. Therefore, this online estimation method for PM temperature can accurately monitor the PM temperature online without increasing the required motor hardware; thus not affecting the motor operation. © 2020 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.
- 6 June 2014
- Published by Wiley in IEEJ Transactions on Electrical and Electronic Engineering
- Vol. 9 (5) , 555-562
Multiobjective optimum design method with anti‐demagnetization of high‐density permanent magnet synchronous motor
This paper presents a method of multiobjective optimization design with anti‐demagnetization aiming at the problem of irreversible demagnetization in high‐density permanent magnet synchronous motors (PMSMs) due to temperature and external magnetic field, at the same time considering the volume of permanent magnets and cost, torque ripple, and core loss. In the first step, a two‐dimensional magnetic network model is used to rapidly assess the basic design parameters and its ability to avenge the anti‐demagnetization of the PMSM. In the second step, the finite element method (FEM) is used to design the key parts of motor, and regression models that solve the model of the multiobjective problem are built based on the simulation experiment data. On this basis, multiobjective optimization result using genetic algorithm is used that can achieve a fast and efficiently global optimal solution. © 2014 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.
- 6 June 2014
- Published by Wiley in IEEJ Transactions on Electrical and Electronic Engineering
- Vol. 9 (5) , 555-562
Multiobjective optimum design method with anti‐demagnetization of high‐density permanent magnet synchronous motor
This paper presents a method of multiobjective optimization design with anti‐demagnetization aiming at the problem of irreversible demagnetization in high‐density permanent magnet synchronous motors (PMSMs) due to temperature and external magnetic field, at the same time considering the volume of permanent magnets and cost, torque ripple, and core loss. In the first step, a two‐dimensional magnetic network model is used to rapidly assess the basic design parameters and its ability to avenge the anti‐demagnetization of the PMSM. In the second step, the finite element method (FEM) is used to design the key parts of motor, and regression models that solve the model of the multiobjective problem are built based on the simulation experiment data. On this basis, multiobjective optimization result using genetic algorithm is used that can achieve a fast and efficiently global optimal solution. © 2014 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.