Yao-Wei Wang
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
Yao-Wei Wang has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Wen-An Zhang
Zhejiang University of Technology
5 shared publications - Min Wu
China University of Geosciences
3 shared publications - Caoyuan Gu
College of Information and Engineering, Zhejiang University of Technology, Hangzhou, China
2 shared publications - Chengda Lu
China University of Geosciences
2 shared publications - Li Yu
Department of Automation, Zhejiang University of Technology, Hangzhou, China
2 shared publications - Qi Wu
College of Information Engineering, Zhejiang University of Technology, Hangzhou, China
2 shared publications
Latest Publications
- 5 June 2026
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 37 (23) , 236105
Physics-guided learnable wavelet filtering network for small-sample fault diagnosis with application to band saw blades
Intelligent fault diagnosis of metal band saw blades is challenged by the intricate entanglement of fault patterns in industrial scenarios, where limited samples impede deep networks from learning class-specific discriminative boundaries, and black-box decision mechanisms preclude the traceability of misdiagnosis origins. To address the coupling of multi-fault categories and the deficiency of interpretability, a physics-guided learnable wavelet filtering attention network is proposed, in which physical prior knowledge is leveraged to guide adaptive feature extraction and fault decoupling. Specifically, an adaptive Morlet wavelet filter is designed to explicitly extract fault-related physical features through time–frequency impact, thereby endowing the feature extraction process with interpretability. Subsequently, an adaptive residual hybrid wavelet network is constructed, wherein a dual-path architecture of discrete wavelets and convolutions is adopted to deeply mine multi-scale features and alleviate the information bottleneck induced by physical filtering. Furthermore, a cross-category filtering strategy is incorporated, by which the multi-class classification task is implicitly decoupled through category competition mechanisms, compelling the network to learn discriminative feature representations. Experiments demonstrate that the proposed method achieves significantly superior diagnostic accuracy under small-sample conditions compared to existing approaches, yielding an average fault diagnosis accuracy of 96.8% on the gearbox dataset and 89.92% on the band saw blade dataset, while its generalization capability and full-process interpretability are validated through the physical semantic analysis of filter parameters and feature visualization.
- 5 June 2026
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 37 (23) , 236105
Physics-guided learnable wavelet filtering network for small-sample fault diagnosis with application to band saw blades
Intelligent fault diagnosis of metal band saw blades is challenged by the intricate entanglement of fault patterns in industrial scenarios, where limited samples impede deep networks from learning class-specific discriminative boundaries, and black-box decision mechanisms preclude the traceability of misdiagnosis origins. To address the coupling of multi-fault categories and the deficiency of interpretability, a physics-guided learnable wavelet filtering attention network is proposed, in which physical prior knowledge is leveraged to guide adaptive feature extraction and fault decoupling. Specifically, an adaptive Morlet wavelet filter is designed to explicitly extract fault-related physical features through time–frequency impact, thereby endowing the feature extraction process with interpretability. Subsequently, an adaptive residual hybrid wavelet network is constructed, wherein a dual-path architecture of discrete wavelets and convolutions is adopted to deeply mine multi-scale features and alleviate the information bottleneck induced by physical filtering. Furthermore, a cross-category filtering strategy is incorporated, by which the multi-class classification task is implicitly decoupled through category competition mechanisms, compelling the network to learn discriminative feature representations. Experiments demonstrate that the proposed method achieves significantly superior diagnostic accuracy under small-sample conditions compared to existing approaches, yielding an average fault diagnosis accuracy of 96.8% on the gearbox dataset and 89.92% on the band saw blade dataset, while its generalization capability and full-process interpretability are validated through the physical semantic analysis of filter parameters and feature visualization.
- 11 November 2025
- Published by Elsevier in Control Engineering Practice
- Vol. 167
A fully-actuated system approach based synchronization control of networked multi-motor motion systems
- 11 November 2025
- Published by Elsevier in Control Engineering Practice
- Vol. 167
A fully-actuated system approach based synchronization control of networked multi-motor motion systems
- 28 September 2025
- Published by Elsevier in Control Engineering Practice
- Vol. 165
High-precision tracking control for high-order fully actuated motion control systems with deadzone nonlinearity
- 28 September 2025
- Published by Elsevier in Control Engineering Practice
- Vol. 165
High-precision tracking control for high-order fully actuated motion control systems with deadzone nonlinearity
- 9 September 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 70 (7) , 7216-7224
Learning-Enabled Output-Feedback-MPC-Based Synchronization Tracking Control of Multiaxis Motion Systems
The unknown and time-varying model parameters and measurement noises impose great influence on the high-precision synchronization tracking control performance of multiaxis motion systems (MAMSs). To deal with the influence of the factors on the high-precision synchronization tracking control performance in MAMSs, a learning-enabled output-feedback model-predictive control (MPC) strategy for MAMSs is proposed in this article. First, an efficient learning mechanism is introduced to capture the unknown and slow time-varying behavior of the system parameters. Then, considering both the existence of the measurement noises and the unavailability of the velocity signals in system and synchronization coupling errors, the learning-enabled output-feedback-MPC-based synchronization tracking controller is designed to achieve the high-precision synchronization tracking control of the MAMSs. The stability of the overall synchronization tracking system with the proposed learning procedure is analyzed. Finally, simulations and experiments are performed on the four-motor motion system to demonstrate the practicability and effectiveness of the proposed control strategy.
- 9 September 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 70 (7) , 7216-7224
Learning-Enabled Output-Feedback-MPC-Based Synchronization Tracking Control of Multiaxis Motion Systems
The unknown and time-varying model parameters and measurement noises impose great influence on the high-precision synchronization tracking control performance of multiaxis motion systems (MAMSs). To deal with the influence of the factors on the high-precision synchronization tracking control performance in MAMSs, a learning-enabled output-feedback model-predictive control (MPC) strategy for MAMSs is proposed in this article. First, an efficient learning mechanism is introduced to capture the unknown and slow time-varying behavior of the system parameters. Then, considering both the existence of the measurement noises and the unavailability of the velocity signals in system and synchronization coupling errors, the learning-enabled output-feedback-MPC-based synchronization tracking controller is designed to achieve the high-precision synchronization tracking control of the MAMSs. The stability of the overall synchronization tracking system with the proposed learning procedure is analyzed. Finally, simulations and experiments are performed on the four-motor motion system to demonstrate the practicability and effectiveness of the proposed control strategy.
- 22 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 69 (9) , 9419-9428
Tube-Based Adaptive Model Predictive Control for Deviation Correction in Vertical Drilling Process
The build-up rate of the bottom hole assembly (BHA) fluctuates violently during the deviation correction in the vertical drilling process due to the mutation of stratum, low operation accuracy of the BHA, etc. As a result, the uncertainty of the build-up rate of the BHA has great influence on the performance of correction control and the quality of the drilling trajectory. To deal with this control problem, a tube-based adaptive model predictive control (MPC) method is developed in this article. By dividing the trajectory extension model into two lower order models, the calculability of the disturbance invariant set of the tube-based MPC controller is ensured. Meanwhile, the bootstrap sampling method with a sliding window is used to estimate the range of the uncertainty online to reduce the conservativeness of the controller based on practical drilling data. Moreover, rules and a small interim deviation are introduced to adjust the parameters adaptively to decrease the curvature of the drilling trajectory and the calculation time. Simulations and hardware-in-the-loop experiment tests are carried out to illustrate the effectiveness of the control method. The results show that the proposed method completes the drilling task with a higher quality of trajectory and needs less time for calculation.
- 22 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 69 (9) , 9419-9428
Tube-Based Adaptive Model Predictive Control for Deviation Correction in Vertical Drilling Process
The build-up rate of the bottom hole assembly (BHA) fluctuates violently during the deviation correction in the vertical drilling process due to the mutation of stratum, low operation accuracy of the BHA, etc. As a result, the uncertainty of the build-up rate of the BHA has great influence on the performance of correction control and the quality of the drilling trajectory. To deal with this control problem, a tube-based adaptive model predictive control (MPC) method is developed in this article. By dividing the trajectory extension model into two lower order models, the calculability of the disturbance invariant set of the tube-based MPC controller is ensured. Meanwhile, the bootstrap sampling method with a sliding window is used to estimate the range of the uncertainty online to reduce the conservativeness of the controller based on practical drilling data. Moreover, rules and a small interim deviation are introduced to adjust the parameters adaptively to decrease the curvature of the drilling trajectory and the calculation time. Simulations and hardware-in-the-loop experiment tests are carried out to illustrate the effectiveness of the control method. The results show that the proposed method completes the drilling task with a higher quality of trajectory and needs less time for calculation.
- 25 August 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 69 (8) , 8317-8324
Equivalent-Input-Disturbance-Based Position Synchronization Control of Networked Multiaxis Motion System
Synchronization control is an essential technique in networked multiaxis motion systems (NMAMSs). However, the compound disturbances caused by the delay-induced uncertainty and external disturbances such as system coupling and load mutation have great influence on performance of the motion control systems. The purpose of this article is to propose an equivalent-input-disturbance (EID)-based position synchronization control strategy for NMAMSs to solve the influence of compound disturbances on synchronization control performance in NMAMSs. First, a position synchronization error model is established for the NMAMSs, and the delay-induced uncertainty is treated as a network disturbance. Next, the EID is designed to suppress the overall effect. Then, an EID-based synchronization controller is designed to achieve both position synchronization and disturbance rejection. The effect of the compound disturbances in the synchronization performance is significantly reduced. Finally, simulations and experiments on a position synchronization control platform of a four-motor system are presented to demonstrate the effectiveness and superiority of the proposed method.
- 25 August 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 69 (8) , 8317-8324
Equivalent-Input-Disturbance-Based Position Synchronization Control of Networked Multiaxis Motion System
Synchronization control is an essential technique in networked multiaxis motion systems (NMAMSs). However, the compound disturbances caused by the delay-induced uncertainty and external disturbances such as system coupling and load mutation have great influence on performance of the motion control systems. The purpose of this article is to propose an equivalent-input-disturbance (EID)-based position synchronization control strategy for NMAMSs to solve the influence of compound disturbances on synchronization control performance in NMAMSs. First, a position synchronization error model is established for the NMAMSs, and the delay-induced uncertainty is treated as a network disturbance. Next, the EID is designed to suppress the overall effect. Then, an EID-based synchronization controller is designed to achieve both position synchronization and disturbance rejection. The effect of the compound disturbances in the synchronization performance is significantly reduced. Finally, simulations and experiments on a position synchronization control platform of a four-motor system are presented to demonstrate the effectiveness and superiority of the proposed method.
- 1 June 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Control of Network Systems
- Vol. 7 (4) , 1746-1756
A Linear Active Disturbance Rejection Control Approach to Position Synchronization Control for Networked Interconnected Motion System
This paper investigates the position synchronization control problem for networked interconnected motion systems (NIMSs). First, a position synchronization error model is established for the interconnected motion system, and the delay-induced uncertainty, the adjacent coupling between subsystems and the external disturbances are lumped together as a total disturbance in the system model. Next, the linear extended state observer (LESO) is designed to estimate the total disturbance and the system state simultaneously. Then, a LESO based synchronization controller is designed to achieve both position synchronization and disturbance rejection. The effect of the network-induced delay in the synchronization performance is significantly reduced. Finally, experiments on a position synchronization control platform of an interconnected four motor system are presented to demonstrate the effectiveness and superiority of the proposed method.
- 1 June 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Control of Network Systems
- Vol. 7 (4) , 1746-1756
A Linear Active Disturbance Rejection Control Approach to Position Synchronization Control for Networked Interconnected Motion System
This paper investigates the position synchronization control problem for networked interconnected motion systems (NIMSs). First, a position synchronization error model is established for the interconnected motion system, and the delay-induced uncertainty, the adjacent coupling between subsystems and the external disturbances are lumped together as a total disturbance in the system model. Next, the linear extended state observer (LESO) is designed to estimate the total disturbance and the system state simultaneously. Then, a LESO based synchronization controller is designed to achieve both position synchronization and disturbance rejection. The effect of the network-induced delay in the synchronization performance is significantly reduced. Finally, experiments on a position synchronization control platform of an interconnected four motor system are presented to demonstrate the effectiveness and superiority of the proposed method.
- 7 May 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 16 (1) , 248-257
GESO-Based Position Synchronization Control of Networked Multiaxis Motion System
This paper studies the position synchronization control problem for networked multi-axis motion systems (NMAMSs). First, a position synchronization error model is established for the multi-axis motion system, and the uncertainty induced by the network-induced delay is modeled as an additive disturbance of the system. Second, the delay-induced uncertainty and the external disturbances such as load torque variation are lumped together as a total disturbance in the system model. Based on the established position synchronization error model, a generalized extended state observer (GESO) is designed to estimate the lumped disturbance and system states simultaneously. Then, the GESO based synchronization controller is designed to achieve the objective of position synchronization and disturbance rejection, and the effect of the network-induced delay in the synchronization performance is significantly reduced. Moreover, an input-to-state stability condition is presented for the position synchronization system. Finally, experiments on a four motors position synchronization control platform are presented to demonstrate the effectiveness and superiority of the proposed method.
- 7 May 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 16 (1) , 248-257
GESO-Based Position Synchronization Control of Networked Multiaxis Motion System
This paper studies the position synchronization control problem for networked multi-axis motion systems (NMAMSs). First, a position synchronization error model is established for the multi-axis motion system, and the uncertainty induced by the network-induced delay is modeled as an additive disturbance of the system. Second, the delay-induced uncertainty and the external disturbances such as load torque variation are lumped together as a total disturbance in the system model. Based on the established position synchronization error model, a generalized extended state observer (GESO) is designed to estimate the lumped disturbance and system states simultaneously. Then, the GESO based synchronization controller is designed to achieve the objective of position synchronization and disturbance rejection, and the effect of the network-induced delay in the synchronization performance is significantly reduced. Moreover, an input-to-state stability condition is presented for the position synchronization system. Finally, experiments on a four motors position synchronization control platform are presented to demonstrate the effectiveness and superiority of the proposed method.