Wei Yu
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
Research Subjects
Wei Yu has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Deqing Huang
Southwest Jiaotong University
9 shared publications - Xuhui Bu
Henan Polytechnic University
7 shared publications Zhongsheng Hou
School of Automation, Qingdao University, Qingdao, China
3 shared publicationsAng Zheng
School of Electrical Engineering and the Key Laboratory of Railway Industry of Advanced Energy Traction and Comprehensive Energy Conservation, Southwest Jiaotong University, Chengdu, China
2 shared publications- Luanhui Li
Southwest Jiaotong University
2 shared publications - Yong Chen
School of Information Science and Technology, Southwest Jiaotong University, Chengdu, China
2 shared publications
Latest Publications
- 29 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 23 (15455955) , 8967-8978
Adaptive T–S Fuzzy Control for HSTs Against Composite Adversarial Scenarios: A Parallel Switching Strategy
This paper investigates resilient state estimation and control for high-speed train (HST) systems with nonlinear dynamics and adversarially corrupted measurements. A Takagi–Sugeno fuzzy model is used to approximate the nonlinear resistances, based on which an adaptive fuzzy observer (AFO) is developed to estimate the states under bounded false-data injection (FDI), man-in-the-middle (MITM), and malware-induced gain-removal attacks. To enhance robustness under compound or high-intensity attacks, an adaptive fuzzy predictor (AFP) operates in parallel with the observer and freezes its parameters once a residual-based health indicator is violated. The resulting observer/predictor output is integrated into an adaptive fuzzy sliding-mode controller (AFSMC), whose robust term compensates for approximation uncertainties and prediction mismatch during predictor-driven operation. A composite Lyapunov analysis establishes uniformly ultimately bounded closed-loop signals. Simulations on a nonlinear HST model validate that the proposed framework significantly improves estimation resilience and tracking performance under various hybrid cyberattacks.
- 29 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 23 (15455955) , 8967-8978
Adaptive T–S Fuzzy Control for HSTs Against Composite Adversarial Scenarios: A Parallel Switching Strategy
This paper investigates resilient state estimation and control for high-speed train (HST) systems with nonlinear dynamics and adversarially corrupted measurements. A Takagi–Sugeno fuzzy model is used to approximate the nonlinear resistances, based on which an adaptive fuzzy observer (AFO) is developed to estimate the states under bounded false-data injection (FDI), man-in-the-middle (MITM), and malware-induced gain-removal attacks. To enhance robustness under compound or high-intensity attacks, an adaptive fuzzy predictor (AFP) operates in parallel with the observer and freezes its parameters once a residual-based health indicator is violated. The resulting observer/predictor output is integrated into an adaptive fuzzy sliding-mode controller (AFSMC), whose robust term compensates for approximation uncertainties and prediction mismatch during predictor-driven operation. A composite Lyapunov analysis establishes uniformly ultimately bounded closed-loop signals. Simulations on a nonlinear HST model validate that the proposed framework significantly improves estimation resilience and tracking performance under various hybrid cyberattacks.
- 15 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (1) , 544-554
High-Order Internal Model-Based Data-Driven Iterative Learning Control of High-Speed Railways Subject to Faded Channels
This study investigates the high-order internal model (HOIM) based data-driven iterative learning control of HSRs subject to faded channels. Firstly, the nonlinear train dynamics are converted into an input/output data-based model by using a linearization approach. Then, the HOIM of the desired speed trajectories is introduced and the fading channel is used to model the unreliable transmission network. Next, the model free adaptive iterative learning control (MFAILC) strategy is implemented based on the train input and faded output information, and the theoretical convergence analysis of the speed error is carried out. Eventually, the validity of the MFAILC scheme is checked in simulation by applying the CRH-380 HSRs on a StarSim hardware-in-loop semi-physical platform.
- 15 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (1) , 544-554
High-Order Internal Model-Based Data-Driven Iterative Learning Control of High-Speed Railways Subject to Faded Channels
This study investigates the high-order internal model (HOIM) based data-driven iterative learning control of HSRs subject to faded channels. Firstly, the nonlinear train dynamics are converted into an input/output data-based model by using a linearization approach. Then, the HOIM of the desired speed trajectories is introduced and the fading channel is used to model the unreliable transmission network. Next, the model free adaptive iterative learning control (MFAILC) strategy is implemented based on the train input and faded output information, and the theoretical convergence analysis of the speed error is carried out. Eventually, the validity of the MFAILC scheme is checked in simulation by applying the CRH-380 HSRs on a StarSim hardware-in-loop semi-physical platform.
- 21 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (2) , 1804-1813
Coordinated Model Free Adaptive Control for Multiple High-Speed Trains Against False Data Injection Attacks and Input Constraints
The coordination of multiple high-speed trains (MHSTs) is considered an effective means to enhance train tracking accuracy and operational efficiency. In this study, the model free adaptive control (MFAC) of MHSTs under false data injection attacks (FDIAs) and input limits is investigated within the framework of data-driven control. The advantage of this control scheme lies in its ability to mitigate performance degradation caused by model inaccuracies. Firstly, a dynamic model for MHSTs is established and then transformed into an equivalent linearized form that solely relies on input and output (I/O) data. Secondly, considering power limitations in the traction network and external FDIAs during direct train-to-train (T2T) communication, a data-driven coordinated MFAC scheme for MHSTs is developed. Finally, the effectiveness of the controller, coordination performance among MHSTs, as well as the impact of external constraints on MHSTs are verified through numerical simulations.
- 21 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (2) , 1804-1813
Coordinated Model Free Adaptive Control for Multiple High-Speed Trains Against False Data Injection Attacks and Input Constraints
The coordination of multiple high-speed trains (MHSTs) is considered an effective means to enhance train tracking accuracy and operational efficiency. In this study, the model free adaptive control (MFAC) of MHSTs under false data injection attacks (FDIAs) and input limits is investigated within the framework of data-driven control. The advantage of this control scheme lies in its ability to mitigate performance degradation caused by model inaccuracies. Firstly, a dynamic model for MHSTs is established and then transformed into an equivalent linearized form that solely relies on input and output (I/O) data. Secondly, considering power limitations in the traction network and external FDIAs during direct train-to-train (T2T) communication, a data-driven coordinated MFAC scheme for MHSTs is developed. Finally, the effectiveness of the controller, coordination performance among MHSTs, as well as the impact of external constraints on MHSTs are verified through numerical simulations.
- 27 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (12) , 22996-23006
An Alignment-Condition-Based Iterative Learning Controller for High-Speed Trains With Norm-Bounded Uncertainties
A novel iterative learning control (ILC) strategy is developed for displacement and velocity tracking control of high-speed trains (HSTs) across all operational phases. In practical operations, HSTs encounter complex nonlinear uncertainties, such as variations in coupler forces and aerodynamic resistance, which are more appropriately characterized by norm-bounded models rather than traditional Lipschitz continuous disturbances. To capture these effects accurately, a multi-particle dynamic model of HSTs with norm-bounded uncertainties is formulated, considering the coupler dynamics, mechanical resistance, and aerodynamic resistance acting upon different carriages. Based on this model, a robust ILC scheme, together with an associated parameter updating law, is designed to ensure precise tracking control despite the presence of nonlinear uncertainties. Furthermore, the classical resetting condition in conventional ILC frameworks is replaced by a practical alignment condition that better reflects the continuous operation characteristics of HSTs. A composite energy function (CEF) is constructed to rigorously prove the convergence of control errors. Real-time hardware-in-the-loop (HIL) simulations are conducted to validate the effectiveness of the proposed method. The proposed strategy achieves effective tracking control and stability across traction, cruising, coasting, and full braking stages.
- 27 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (12) , 22996-23006
An Alignment-Condition-Based Iterative Learning Controller for High-Speed Trains With Norm-Bounded Uncertainties
A novel iterative learning control (ILC) strategy is developed for displacement and velocity tracking control of high-speed trains (HSTs) across all operational phases. In practical operations, HSTs encounter complex nonlinear uncertainties, such as variations in coupler forces and aerodynamic resistance, which are more appropriately characterized by norm-bounded models rather than traditional Lipschitz continuous disturbances. To capture these effects accurately, a multi-particle dynamic model of HSTs with norm-bounded uncertainties is formulated, considering the coupler dynamics, mechanical resistance, and aerodynamic resistance acting upon different carriages. Based on this model, a robust ILC scheme, together with an associated parameter updating law, is designed to ensure precise tracking control despite the presence of nonlinear uncertainties. Furthermore, the classical resetting condition in conventional ILC frameworks is replaced by a practical alignment condition that better reflects the continuous operation characteristics of HSTs. A composite energy function (CEF) is constructed to rigorously prove the convergence of control errors. Real-time hardware-in-the-loop (HIL) simulations are conducted to validate the effectiveness of the proposed method. The proposed strategy achieves effective tracking control and stability across traction, cruising, coasting, and full braking stages.
- 10 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 74 (12) , 18733-18742
Adaptive Neural Network Identification-Based Operating Control for High-Speed Trains Under Unknown Dynamic Disturbance
This study investigates the adaptive neural network (NN) identification-based operating control problem for high-speed trains (HSTs) in the presence of unknown dynamic disturbance. Firstly, the train states are monitored by a high-order sliding mode (HOSM) observer, thereby relaxing the assumption of complete knowledge about the train states. Simultaneously, two NNs are employed to identify the unknown dynamics and enhance the approximation accuracy. Subsequently, an adaptive output-feedback controller is developed by combining the observed train states with approximated unknown dynamics, wherein a leakage term is introduced to suppress the accumulated parameter estimation errors and improve the train adaptability to uncertainty. Next, stability analysis demonstrates the convergence of the identified parameters and the tracking performance of HSTs towards the reference displacement and velocity trajectories. Finally, the proposed approach is validated by the simulation results obtained from the real-time hardware-in-the-loop (HIL) test platforms.
- 10 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 74 (12) , 18733-18742
Adaptive Neural Network Identification-Based Operating Control for High-Speed Trains Under Unknown Dynamic Disturbance
This study investigates the adaptive neural network (NN) identification-based operating control problem for high-speed trains (HSTs) in the presence of unknown dynamic disturbance. Firstly, the train states are monitored by a high-order sliding mode (HOSM) observer, thereby relaxing the assumption of complete knowledge about the train states. Simultaneously, two NNs are employed to identify the unknown dynamics and enhance the approximation accuracy. Subsequently, an adaptive output-feedback controller is developed by combining the observed train states with approximated unknown dynamics, wherein a leakage term is introduced to suppress the accumulated parameter estimation errors and improve the train adaptability to uncertainty. Next, stability analysis demonstrates the convergence of the identified parameters and the tracking performance of HSTs towards the reference displacement and velocity trajectories. Finally, the proposed approach is validated by the simulation results obtained from the real-time hardware-in-the-loop (HIL) test platforms.
- 2 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Control Systems Technology
- Vol. 32 (6) , 2298-2309
Data-Driven Security Consensus Tracking of Multiple High-Speed Trains Under Random Topologies With Data Recovery Mechanism
Inspired by the challenges in improving train efficiency, this study investigates the consensus tracking of multiple high-speed trains (MHSTs) under random denial-of-service (DoS) attacks. First, a linearization method is used to linearize the nonlinear dynamic model of MHSTs with external running resistance. Second, the strategy of DoS attackers is elaborated on by using random variables obeying Bernoulli distributions. After establishing a data recovery mechanism, a security model-free adaptive control (MFAC) scheme is presented for MHSTs that is fully data-driven and independent of any model information or structural data of train groups. The effectiveness of this approach is theoretically analyzed without requiring accurate system modeling. Finally, the validity of MFAC and the impact of DoS attacks on MHSTs are evaluated through simulations involving G1868 HSTs between Guiyang North and Kaili South.
- 2 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Control Systems Technology
- Vol. 32 (6) , 2298-2309
Data-Driven Security Consensus Tracking of Multiple High-Speed Trains Under Random Topologies With Data Recovery Mechanism
Inspired by the challenges in improving train efficiency, this study investigates the consensus tracking of multiple high-speed trains (MHSTs) under random denial-of-service (DoS) attacks. First, a linearization method is used to linearize the nonlinear dynamic model of MHSTs with external running resistance. Second, the strategy of DoS attackers is elaborated on by using random variables obeying Bernoulli distributions. After establishing a data recovery mechanism, a security model-free adaptive control (MFAC) scheme is presented for MHSTs that is fully data-driven and independent of any model information or structural data of train groups. The effectiveness of this approach is theoretically analyzed without requiring accurate system modeling. Finally, the validity of MFAC and the impact of DoS attacks on MHSTs are evaluated through simulations involving G1868 HSTs between Guiyang North and Kaili South.
- 29 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 18 (15566013) , 1449-1460
Event-Triggered Data-Driven Control for Nonlinear Systems Under Frequency-Duration-Constrained DoS Attacks
This paper addresses the event-triggered model free adaptive control (MFAC) problem for unknown nonlinear systems under denial-of-service (DoS) attacks, where the design and analysis are discussed under the data-driven framework. Firstly, by using the novel pseudo partial derivative, the nonlinear systems are converted into an equivalent data-relationship model. Then, the DoS attacks are described as limited by their frequency and duration, and without any more specific assumptions about the attack structure or strategy. Next, a novel event-triggered MFAC scheme is proposed. By employing the Lyapunov stability theory, the stability performance is analyzed. Furthermore, a compensation algorithm is designed to against the adverse impact brought by the DoS attacks. Finally, simulations including a numerical example and a load frequency control (LFC) example for multi-area power systems are given to demonstrate the validity and applicability of the proposed schemes.
- 29 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 18 (15566013) , 1449-1460
Event-Triggered Data-Driven Control for Nonlinear Systems Under Frequency-Duration-Constrained DoS Attacks
This paper addresses the event-triggered model free adaptive control (MFAC) problem for unknown nonlinear systems under denial-of-service (DoS) attacks, where the design and analysis are discussed under the data-driven framework. Firstly, by using the novel pseudo partial derivative, the nonlinear systems are converted into an equivalent data-relationship model. Then, the DoS attacks are described as limited by their frequency and duration, and without any more specific assumptions about the attack structure or strategy. Next, a novel event-triggered MFAC scheme is proposed. By employing the Lyapunov stability theory, the stability performance is analyzed. Furthermore, a compensation algorithm is designed to against the adverse impact brought by the DoS attacks. Finally, simulations including a numerical example and a load frequency control (LFC) example for multi-area power systems are given to demonstrate the validity and applicability of the proposed schemes.
- 17 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 23 (11) , 20965-20977
Nonuniform Sampling Control for Multibody High-Speed Train Systems With Quantization Mechanisms via Stochastic Faded Channels
This paper studies the dissipative control problem of the multibody high-speed train (HST) systems with nonuniform sampling mechanisms and logarithmic quantizers, in which the transmitted signals are subject to random fading phenomenon. The tracking error dynamic model of HST is firstly established and the logarithmic quantizers for both the input and output (I/O) signals are designed. The faded I/O signals are described by the Rice fading model, in which the mathematical expectation and variance are given in advance. Then, based on the Lyapunov-Krasovskii functional approach with the consideration of time-varying delay, sufficient conditions are derived to ensure the convergence of tracking error and that HST is strictly dissipative. Further, the design method of the gain matrix is obtained by employing the linear matrix inequalities (LMI) techniques and a compensation algorithm is designed to offset the adverse effect brought by the fading measurements. Finally, the effectiveness of the proposed controller is verified by a numerical example from Japan Shinkansen HST.
- 17 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 23 (11) , 20965-20977
Nonuniform Sampling Control for Multibody High-Speed Train Systems With Quantization Mechanisms via Stochastic Faded Channels
This paper studies the dissipative control problem of the multibody high-speed train (HST) systems with nonuniform sampling mechanisms and logarithmic quantizers, in which the transmitted signals are subject to random fading phenomenon. The tracking error dynamic model of HST is firstly established and the logarithmic quantizers for both the input and output (I/O) signals are designed. The faded I/O signals are described by the Rice fading model, in which the mathematical expectation and variance are given in advance. Then, based on the Lyapunov-Krasovskii functional approach with the consideration of time-varying delay, sufficient conditions are derived to ensure the convergence of tracking error and that HST is strictly dissipative. Further, the design method of the gain matrix is obtained by employing the linear matrix inequalities (LMI) techniques and a compensation algorithm is designed to offset the adverse effect brought by the fading measurements. Finally, the effectiveness of the proposed controller is verified by a numerical example from Japan Shinkansen HST.
- 10 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 9 (4) , 2910-2921
Security Data-Driven Control for Nonlinear Systems Subject to Deception and False Data Injection Attacks
This paper studies the security data-driven control problem for a class of nonlinear systems with completely unknown dynamics under the deception attacks (DA) and false data injection attacks (FDIA) via faded channels. Firstly, the fading phenomenon is formulated by the Rice fading model, which obeys the Gaussian distribution with a known mathematical expectation and variance. DA could invert the direction of I/O data and FDIA may result in false injection data with zero-mean Gaussian white noise. Then, by employing the compact form dynamic linearization method, the security model free adaptive controller (MFAC) is designed, which does not involve the model or structure information of the system. Next, the system stability is analyzed, and the compensation scheme with an increasing gain is proposed to counteract the adverse effect brought by faded channels. A numerical simulation and a load frequency control (LFC) example for multi-area power systems illustrate the validity of the proposed schemes.
- 10 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 9 (4) , 2910-2921
Security Data-Driven Control for Nonlinear Systems Subject to Deception and False Data Injection Attacks
This paper studies the security data-driven control problem for a class of nonlinear systems with completely unknown dynamics under the deception attacks (DA) and false data injection attacks (FDIA) via faded channels. Firstly, the fading phenomenon is formulated by the Rice fading model, which obeys the Gaussian distribution with a known mathematical expectation and variance. DA could invert the direction of I/O data and FDIA may result in false injection data with zero-mean Gaussian white noise. Then, by employing the compact form dynamic linearization method, the security model free adaptive controller (MFAC) is designed, which does not involve the model or structure information of the system. Next, the system stability is analyzed, and the compensation scheme with an increasing gain is proposed to counteract the adverse effect brought by faded channels. A numerical simulation and a load frequency control (LFC) example for multi-area power systems illustrate the validity of the proposed schemes.