Quanning Xu
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
Quanning Xu has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
Guangrui Wen
5 shared publicationsXuefeng Chen
4 shared publicationsShulong Gu
3 shared publications- Xinrong Zhang
Key Laboratory of Expressway Construction Machinery of Shaanxi Province, Chang’an University, Xi’an 710064, China
3 shared publications - Xueyun Li
Hubei Key Laboratory of Advanced Technology for Automotive Components, Wuhan University of Technology, Wuhan, China
3 shared publications Yu Su
3 shared publications
Latest Publications
- 3 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75 (00189456) , 1-14
Digital Twin-Driven Stacked Multiwavelet Domain Adaptation Network for Interpretable Intelligent Transfer Fault Diagnosis
Advanced fault diagnosis algorithms are essential for maintaining the smooth operation and effective health management of modern manufacturing systems. However, constructing comprehensive and high-quality training datasets remains a major challenge in real-world industrial environments. By leveraging the abundant virtual resources available in modern manufacturing systems, digital twin technology provides an innovative solution to the problem of data scarcity. This paper proposes an interpretable transfer diagnosis framework based on digital twin technology and multi-wavelet feature fusion. The main contributions of this work are summarized as follows: 1) A virtual entity is developed using a six-degree-of-freedom bearing dynamics model, and virtual-physical interaction is established via a multi-objective particle swarm optimization algorithm. 2) A stacked multi-wavelet domain adaptation network is constructed, integrating three distinct wavelet kernel convolutions for time-frequency feature extraction. Additionally, a hybrid attention mechanism is introduced to dynamically assign weights, achieving a balance between interpretability and diagnostic performance. 3) The generalization capability is enhanced by combining multi-kernel maximum mean discrepancy (MK-MMD) loss with adversarial learning, thereby effectively optimizing knowledge transfer. Extensive evaluations on two benchmark datasets demonstrate that the proposed framework delivers high diagnostic accuracy and strong interpretability, providing reliable decision support for industrial applications.
- 3 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75 (00189456) , 1-14
Digital Twin-Driven Stacked Multiwavelet Domain Adaptation Network for Interpretable Intelligent Transfer Fault Diagnosis
Advanced fault diagnosis algorithms are essential for maintaining the smooth operation and effective health management of modern manufacturing systems. However, constructing comprehensive and high-quality training datasets remains a major challenge in real-world industrial environments. By leveraging the abundant virtual resources available in modern manufacturing systems, digital twin technology provides an innovative solution to the problem of data scarcity. This paper proposes an interpretable transfer diagnosis framework based on digital twin technology and multi-wavelet feature fusion. The main contributions of this work are summarized as follows: 1) A virtual entity is developed using a six-degree-of-freedom bearing dynamics model, and virtual-physical interaction is established via a multi-objective particle swarm optimization algorithm. 2) A stacked multi-wavelet domain adaptation network is constructed, integrating three distinct wavelet kernel convolutions for time-frequency feature extraction. Additionally, a hybrid attention mechanism is introduced to dynamically assign weights, achieving a balance between interpretability and diagnostic performance. 3) The generalization capability is enhanced by combining multi-kernel maximum mean discrepancy (MK-MMD) loss with adversarial learning, thereby effectively optimizing knowledge transfer. Extensive evaluations on two benchmark datasets demonstrate that the proposed framework delivers high diagnostic accuracy and strong interpretability, providing reliable decision support for industrial applications.
- 28 December 2025
- Published by Elsevier in Computers & Industrial Engineering
- Vol. 213
Virtual-physical mapping network-driven digital twin for intelligent fault diagnosis with imbalanced samples
- 28 December 2025
- Published by Elsevier in Computers & Industrial Engineering
- Vol. 213
Virtual-physical mapping network-driven digital twin for intelligent fault diagnosis with imbalanced samples
- 24 October 2025
- Published by Elsevier in Advanced Engineering Informatics
- Vol. 69
Deep digital twin-powered large vision-language model for multi-scenario industrial fault diagnosis
- 24 October 2025
- Published by Elsevier in Advanced Engineering Informatics
- Vol. 69
Deep digital twin-powered large vision-language model for multi-scenario industrial fault diagnosis
- 25 January 2025
- Published by SAGE Publications in Journal of Vibration and Control
- Vol. 32 (7-8) , 1550-1571
Robust path-tracking control for intelligent vehicles considering human–vehicle multi-factors
Human–machine co-driving refers to a technological architecture in which human driver and automated system control vehicle sharing and cooperate to accomplish driving tasks. The architecture could solve the safety and ethical dilemmas of autonomous vehicles, which is an innovative method to improve vehicle intelligence. To realize high-precision and safe path-tracking control, this paper proposes a parallel steering sharing human–machine co-driving framework based on constraint-following controller and driving weight allocation module. First, a parallel human–machine co-driving control framework is established, which uses a two-point preview driver model and constraint-following controller to represent the human driver and automated system, respectively. Second, the underactuated characteristics of front steering vehicles are analyzed. A multiple-constraint path-tracking robust controller is designed based on constraint-following control approach, which considers the multi-source uncertainty and multiple constraints of real road conditions. Third, a multi-factor driving weight allocation module is constructed, which considers human–machine characteristics and cooperation performance. Finally, the effectiveness of the proposed method is verified by CarSim–MATLAB/Simulink joint simulation under three different case studies. This paper creatively synthesizes the vehicle uncertainty, multiple path-tracking constraints, and human–machine cooperation performance, and provides a new idea for human–machine co-driving vehicles to realize robust and safe path-tracking control.
- 25 January 2025
- Published by SAGE Publications in Journal of Vibration and Control
- Vol. 32 (7-8) , 1550-1571
Robust path-tracking control for intelligent vehicles considering human–vehicle multi-factors
Human–machine co-driving refers to a technological architecture in which human driver and automated system control vehicle sharing and cooperate to accomplish driving tasks. The architecture could solve the safety and ethical dilemmas of autonomous vehicles, which is an innovative method to improve vehicle intelligence. To realize high-precision and safe path-tracking control, this paper proposes a parallel steering sharing human–machine co-driving framework based on constraint-following controller and driving weight allocation module. First, a parallel human–machine co-driving control framework is established, which uses a two-point preview driver model and constraint-following controller to represent the human driver and automated system, respectively. Second, the underactuated characteristics of front steering vehicles are analyzed. A multiple-constraint path-tracking robust controller is designed based on constraint-following control approach, which considers the multi-source uncertainty and multiple constraints of real road conditions. Third, a multi-factor driving weight allocation module is constructed, which considers human–machine characteristics and cooperation performance. Finally, the effectiveness of the proposed method is verified by CarSim–MATLAB/Simulink joint simulation under three different case studies. This paper creatively synthesizes the vehicle uncertainty, multiple path-tracking constraints, and human–machine cooperation performance, and provides a new idea for human–machine co-driving vehicles to realize robust and safe path-tracking control.
- 26 September 2024
- Published by Elsevier in Computers in Industry
- Vol. 164
Dual channel visible graph convolutional neural network for microleakage monitoring of pipeline weld homalographic cracks
- 26 September 2024
- Published by Elsevier in Computers in Industry
- Vol. 164
Dual channel visible graph convolutional neural network for microleakage monitoring of pipeline weld homalographic cracks
- 4 January 2024
- Published by SAGE Publications in Journal of Vibration and Control
- Vol. 30 (21-22) , 5132-5148
Shared control for human–machine co-driving vehicles based on constraint-following approach
To ensure the human–machine co-driving vehicle path-tracking accuracy, as well as to diminish the effects of vehicle underactuated characteristics and undesirable driver operation, a parallel shared control framework is proposed in this paper. By structuring a rational driving weights allocation module, the framework enables cooperative driving between the driver and automated system. First, for the front steering vehicle, a robust path-tracking controller is proposed using the constraint-following approach. The system uncertainty is decomposed into matched and non-matched uncertainties. As the non-matched portions are orthogonal to the constraint-following geometric space, they will not affect control performance. Therefore, the constraint-following control (CFC) is designed to handle the path-tracking equality constraint, initial state deviations, and matched uncertainties. Second, a fuzzy rule-based driving weights allocation module is proposed. According to the lateral deviation and the relative accuracy of the steering angle, the allocation module adjusts the driving weight of the driver and automated system to improve the vehicle condition. Finally, the simulation results show that the framework can effectively reduce the emergence caused by the driver or automated system, and significantly improve the path-tracking performance. Additionally, as the controller exhibits sufficient robustness, it can handle multiple sources of uncertainty in vehicle systems.
- 4 January 2024
- Published by SAGE Publications in Journal of Vibration and Control
- Vol. 30 (21-22) , 5132-5148
Shared control for human–machine co-driving vehicles based on constraint-following approach
To ensure the human–machine co-driving vehicle path-tracking accuracy, as well as to diminish the effects of vehicle underactuated characteristics and undesirable driver operation, a parallel shared control framework is proposed in this paper. By structuring a rational driving weights allocation module, the framework enables cooperative driving between the driver and automated system. First, for the front steering vehicle, a robust path-tracking controller is proposed using the constraint-following approach. The system uncertainty is decomposed into matched and non-matched uncertainties. As the non-matched portions are orthogonal to the constraint-following geometric space, they will not affect control performance. Therefore, the constraint-following control (CFC) is designed to handle the path-tracking equality constraint, initial state deviations, and matched uncertainties. Second, a fuzzy rule-based driving weights allocation module is proposed. According to the lateral deviation and the relative accuracy of the steering angle, the allocation module adjusts the driving weight of the driver and automated system to improve the vehicle condition. Finally, the simulation results show that the framework can effectively reduce the emergence caused by the driver or automated system, and significantly improve the path-tracking performance. Additionally, as the controller exhibits sufficient robustness, it can handle multiple sources of uncertainty in vehicle systems.
- 1 February 2023
- Published by SAGE Publications in Journal of Vibration and Control
- Vol. 30 (3-4) , 890-905
Optimal robust path tracking control for multi-constrained underactuated vehicles based on uncertainty orthogonal decomposition
In this article, an optimal robust constraint-following control is proposed for the underactuated vehicle path tracking problem. First, an underactuated dynamic model is established according to Udwadia–Kalaba (UK) equation, and the system uncertainty is decomposed into matching and mismatching portions based on the system geometric characteristics. The mismatching uncertainty is orthogonal to task space; thus, its influence on system stability is eliminated. Second, the diffeomorphism method is used to creatively set inequality and equality constraints into new equality constraints, and a robust control method for front steering vehicles with parameter-tunable is proposed. Third, an optimal design scheme is proposed for the tunable parameters to minimize the comprehensive index of system performance and control cost. Carsim-Simulink co-simulation shows the effectiveness of the proposed optimal robust control. This article creatively solves the problem of optimal robust control for path tracking of multi-constrained underactuated vehicles.
- 1 February 2023
- Published by SAGE Publications in Journal of Vibration and Control
- Vol. 30 (3-4) , 890-905
Optimal robust path tracking control for multi-constrained underactuated vehicles based on uncertainty orthogonal decomposition
In this article, an optimal robust constraint-following control is proposed for the underactuated vehicle path tracking problem. First, an underactuated dynamic model is established according to Udwadia–Kalaba (UK) equation, and the system uncertainty is decomposed into matching and mismatching portions based on the system geometric characteristics. The mismatching uncertainty is orthogonal to task space; thus, its influence on system stability is eliminated. Second, the diffeomorphism method is used to creatively set inequality and equality constraints into new equality constraints, and a robust control method for front steering vehicles with parameter-tunable is proposed. Third, an optimal design scheme is proposed for the tunable parameters to minimize the comprehensive index of system performance and control cost. Carsim-Simulink co-simulation shows the effectiveness of the proposed optimal robust control. This article creatively solves the problem of optimal robust control for path tracking of multi-constrained underactuated vehicles.