Network-Constrained Data-Driven Control of High-Speed Rail Systems
Adaptive and Learning-Based Approaches
- 1st Edition - January 1, 2026
- Authors: Deqing Huang, Wei Yu
- Language: English
- Paperback ISBN:9 7 8 - 0 - 4 4 3 - 4 8 9 9 4 - 5
- eBook ISBN:9 7 8 - 0 - 4 4 3 - 4 8 9 9 5 - 2
Network-Constrained Data-Driven Control of High-Speed Rail Systems addresses the critical challenges in high-speed railway (HSR) operational control systems, focusing on enhanc… Read more
Network-Constrained Data-Driven Control of High-Speed Rail Systems addresses the critical challenges in high-speed railway (HSR) operational control systems, focusing on enhancing safety, efficiency, and automation in an era of rapid network expansion. Railway systems face limitations in automatic driving capabilities and decentralized control, relying heavily on manual adjustments and outdated communication infrastructure like GSM-R (limited to 9.6 kbit/s speeds and 400 ms delays). Network-Constrained Data-Driven Control of High-Speed Rail Systems introduces a transformative framework for data-driven adaptive control and multi-train cooperative control under dynamic network constraints. It integrates next-generation 5G-R communication to enable real-time train-to-train (T2T) coordination, reducing dependency on fixed infrastructure and addressing vulnerabilities like faded channels and interference. By combining rigorous theoretical analysis with simulations, the book proposes solutions to improve operational precision, resilience against disruptions, and transportation capacity. This resource is helpful for researchers, engineers, and graduate students in high speed railway control systems, offering innovative strategies to advance autonomous operations and meet the demands of high-density, high-speed rail networks
- Presents a data-driven adaptive and learning control framework for high-speed trains under network constraints
- Discusses the theory and method of multi-train cooperative control in detail: particularly how to realize real-time information interaction and dynamic adjustment between trains with the support of train-to-train communication
- Discusses the influence of network constraints (such as fading measurement, malicious attacks, etc.) on train cooperative control, and proposes a series of compensation strategies
- The book not only focuses on current high-speed rail control technology, but also forward-looking discussion of future high-speed rail communication and control technology, such as the application of 5G-R communication system and autonomous driving technology
Academic researchers engaged in research on control theory, data-driven control, adaptive control, and high-speed train systems
1. Introduction
1.1 HST Operation Control System
1.2 Communication Network Subsystem
1.3 Operation Control Methods for HSTs
1.4 Coordination for MHSTs
1.5 Conclusions
1.6 Outline of the Book
2. Preliminaries
2.1 Directed Graph
2.2 Dynamic Linearization Method
3. Coordinated MFAC of MHSTs Under Faded Channels and DoS Attacks
3.1 Introduction
3.2 Preliminaries and Problem Formulations
3.3 Main Results
3.4 Extension to the Compensation Scheme
3.5 Extension to the Switching Topologies
3.6 Numerical Test
3.7 Conclusions
4. DD Consensus of MHSTs Via Random Topologies with Recovery Mechanism
4.1 Introduction
4.2 Problem Formulation
4.3 Main Results
4.4 Simulation Test
4.5 Conclusions
5. Weighted T2T Communication-Based DD Consensus of MHSTs Under DA
5.1 Introduction
5.2 Problem Formulation
5.3 Main Results
5.4 Some Extended Consideration
5.5 Simulation Test
5.6 Conclusions
6. Active Quantizer-Based DMFAC for MHSTs Against Sensor Bias
6.1 Introduction
6.2 Problem Formulation
6.3 Main Results
6.4 Simulation Test
6.5 Conclusions
7. HOIM Based Data-Driven ILC of HSTs Subject to Faded Channels
7.1 Introduction
7.2 Problem Formulation
7.3 Main Results
7.4 Simulation Results
7.5 Conclusions
8. Fading-Based Coordinated MFAILC of MHSTs Against DoS Attacks
8.1 Introduction
8.2 Problem Formulation
8.3 Stability Analysis
8.4 Extension Results
8.5 Numerical Simulation
8.6 Conclusions
9. Attack Recovery-Based DMFAILC for MHSTs with Fading Compensation
9.1 Introduction
9.2 Preliminaries and Problem Formulation
9.3 Main Results
9.4 Simulation Test
9.5 Conclusions
10. Event-Triggered DMFAILC for MHSTs with Switching Topologies
10.1 Introduction
10.2 Main Results
10.3 Extension to Iteration-Varying Graph of MHSTs
10.4 Numerical Examples
10.5 Conclusions
11. DMFAILC for MHSTs under Weighted Communication and Saturations
11.1 Introduction
11.2 Preliminaries
11.3 Problem Formulation
11.4 Main Results
11.5 Simulation Test
11.6 Conclusions
12. DMFAILC for MHSTs Considering Quantizations and Measurement Bias
12.1 Introduction
12.2 Problem Formulation
12.3 Main Results
12.4 HIL Simulations
12.5 Conclusions References
1.1 HST Operation Control System
1.2 Communication Network Subsystem
1.3 Operation Control Methods for HSTs
1.4 Coordination for MHSTs
1.5 Conclusions
1.6 Outline of the Book
2. Preliminaries
2.1 Directed Graph
2.2 Dynamic Linearization Method
3. Coordinated MFAC of MHSTs Under Faded Channels and DoS Attacks
3.1 Introduction
3.2 Preliminaries and Problem Formulations
3.3 Main Results
3.4 Extension to the Compensation Scheme
3.5 Extension to the Switching Topologies
3.6 Numerical Test
3.7 Conclusions
4. DD Consensus of MHSTs Via Random Topologies with Recovery Mechanism
4.1 Introduction
4.2 Problem Formulation
4.3 Main Results
4.4 Simulation Test
4.5 Conclusions
5. Weighted T2T Communication-Based DD Consensus of MHSTs Under DA
5.1 Introduction
5.2 Problem Formulation
5.3 Main Results
5.4 Some Extended Consideration
5.5 Simulation Test
5.6 Conclusions
6. Active Quantizer-Based DMFAC for MHSTs Against Sensor Bias
6.1 Introduction
6.2 Problem Formulation
6.3 Main Results
6.4 Simulation Test
6.5 Conclusions
7. HOIM Based Data-Driven ILC of HSTs Subject to Faded Channels
7.1 Introduction
7.2 Problem Formulation
7.3 Main Results
7.4 Simulation Results
7.5 Conclusions
8. Fading-Based Coordinated MFAILC of MHSTs Against DoS Attacks
8.1 Introduction
8.2 Problem Formulation
8.3 Stability Analysis
8.4 Extension Results
8.5 Numerical Simulation
8.6 Conclusions
9. Attack Recovery-Based DMFAILC for MHSTs with Fading Compensation
9.1 Introduction
9.2 Preliminaries and Problem Formulation
9.3 Main Results
9.4 Simulation Test
9.5 Conclusions
10. Event-Triggered DMFAILC for MHSTs with Switching Topologies
10.1 Introduction
10.2 Main Results
10.3 Extension to Iteration-Varying Graph of MHSTs
10.4 Numerical Examples
10.5 Conclusions
11. DMFAILC for MHSTs under Weighted Communication and Saturations
11.1 Introduction
11.2 Preliminaries
11.3 Problem Formulation
11.4 Main Results
11.5 Simulation Test
11.6 Conclusions
12. DMFAILC for MHSTs Considering Quantizations and Measurement Bias
12.1 Introduction
12.2 Problem Formulation
12.3 Main Results
12.4 HIL Simulations
12.5 Conclusions References
- Edition: 1
- Published: January 1, 2026
- Language: English
DH
Deqing Huang
Professor Deqing Huang received the B.S. and Ph.D. degrees from Sichuan University, Chengdu, China, in 2002 and 2007, respectively, and the second Ph.D. degree with a major in control engineering from the Department of Electrical and Computer Engineering, National University of Singapore (NUS), Singapore, in 2011. From January 2010 to February 2013, he was a Research Fellow with the Department of Electrical and Computer Engineering, NUS. From March 2013 to January 2016, he was a Research Associate with the Department of Aeronautics, Imperial College London, London, U.K. In January 2016, he joined the Department of Electronic and Information Engineering, Southwest Jiaotong University, Chengdu, China, as a Professor and the Department Head. His current research interests include modern control theory, artificial intelligence, and fault diagnosis as well as robotics
Affiliations and expertise
Southwest Jiaotong University, ChinaWY
Wei Yu
Dr Wei Yu received the B.S. degree in rail transportation signal and control from Henan Polytechnic University, Jiaozuo, China, in 2018, the M.S. degree in control science and engineering from the School of Electric Engineering and Automation, Henan Polytechnic University, Jiaozuo, China, in 2021 and the Ph.D. degree in control science and engineering with Southwest Jiaotong University, Chengdu, China, in 2024. He is currently conducting Boya postdoctoral research at Peking University. His research interests include high-speed train control, data-driven control, iterative learning control and networked system control
Affiliations and expertise
Southwest Jiaotong University, China