Adaptive fault-tolerant automatic train operation using RBF neural networks

详细信息    查看全文

• 作者：Shigen Gao (1)
  Hairong Dong (1)
  Bin Ning (1)
  Yao Chen (2)
  Xubin Sun (2)
  
  1. State Key Laboratory of Rail Traffic Control and Safety ; Beijing Jiaotong University ; Beijing ; 100044 ; China
  2. School of Electronic and Information Engineering ; Beijing Jiaotong University ; Beijing ; 100044 ; China
  
• 关键词：Intelligent transportation system ; Automatic train operation ; Fault ; tolerant control ; RBF neural network
• 刊名：Neural Computing & Applications
• 出版年：2015
• 出版时间：January 2015
• 年：2015
• 卷：26
• 期：1
• 页码：141-149
• 全文大小：904 KB
• 参考文献：1. Pascoe R, Eichorn N (2009) What is communication-based train control. IEEE Veh Technol Mag 4(4):16鈥?1 CrossRef
  2. Dong H, Ning B, Cai B, Hou Z (2010) Automatic train control system development and simulation for high-speed railways. IEEE Circuits Syst Mag 10(2):6鈥?8 CrossRef
  3. Chen X, Zhang Y, Huang H (2010) Train speed control algorithm based on PID controller and single-neuron PID controller. Proc Second WRI Glob Congr Intell Syst 1:107鈥?10
  4. Dong H, Gao B, Ning B, Zhang Y (2010) Fuzzy-PID soft switching speed control of automatic train operation system. Control Decis 25(5):794鈥?96, 800
  5. Wang Y, Luo R, Yu Z, Ning B (2012) Study on ATO control algorithm with consideration of ATP speed limits. J Railw Soc 34(5):59鈥?4
  6. Luo R, Wang Y, Yu Z, Tang T (2012) Adaptive stopping control of urban rail vehicle. J Railw Soc 34(4):64鈥?8
  7. Yasunobu S, Miyamoto S, Ihara H (1983) Fuzzy control for automatic train operation system. In: Proceedings of 4th IFAC/IFIP/IFRS international conference on transportation systems, pp 33鈥?9
  8. Yasunobu S, Miyamoto S, Takaoka T, Ohshima H (1984) Application of predictive fuzzy control to automatic train operation controller. Proc IECON 84:657鈥?62
  9. Chang C, Xu D (2000) Differential evolution based tuning of fuzzy automatic train operation for mass rapid transit system. IEE Proc Electr Power Appl 147(3):206鈥?12 CrossRef
  10. Dong H, Gao S, Ning B, Li L (2013) Extended fuzzy logic controllers for high speed train. Neural Comput Appl 22(2):321鈥?28 CrossRef
  11. Howlett P (1996) Optimal strategies for the control of a train. Automatica 32(4):519鈥?32 CrossRef
  12. Howlett P, Cheng J (1997) Optimal driving strategies for a train on a track with continuously varying gradient. J Aust Math Soc Ser B Electron 38:388鈥?10 CrossRef
  13. Howlett P, Milroy I, Pudney P (1994) Energy-efficient train control. Control Eng Pract 2(2):193鈥?00 CrossRef
  14. Howlett P, Pudney P, Vu X (2009) Local energy minimization in optimal train control. Automatica 45(11):2692鈥?698 CrossRef
  15. Liu R, Golovitcher I (2003) Energy-efficient operation of rail vehicles. Transp Res Part A 37:917鈥?32
  16. Yang C, Sun Y (2001) Mixed \({\cal H {\cal _{2}}/{\cal H} \cal _{\infty }}\) cruise controller design for high speed train. Int J Control 74(9):905鈥?20 CrossRef
  17. Wang C, Tang T, Luo R (2013) Study on iterative learning control in automatic train operation. J Railw Soc 35(3):48鈥?2
  18. Zhang X, Parisini T, Polycarpou MM (2004) Adaptive fault-tolerant control of nonlinear uncertain systems: an information-based diagnostic approach. IEEE Trans Autom Control 49(8):1259鈥?274 CrossRef
  19. Gao X, Ovaska S, Wang X, Chow M (2008) A neural networks-based negative selection algorithm in fault diagnosis. Neural Comput Appl 17(1):91鈥?8 CrossRef
  20. Zargany F, Shahbazian M, Rad H (2013) Multi-sensor fault tolerant measurement based on Tagaki鈥揝ugeno fuzzy model. Neural Comput Appl. doi:10.1007/s00521-012-1328-0
  21. Wu Y, Sun F, Zheng J, Song Q (2010) A robust training algorithm of discrete-time MIMO RNN and application in fault tolerant control of robotic system. Neural Comput Appl 19(7):1013鈥?027 CrossRef
  22. Zhuan X, Xia X (2010) Fault-tolerant control of heavy-haul trains. Veh Syst Dyn 48(6):705鈥?35 CrossRef
  23. Zhuan X, Xia X (2008) Speed regulation with measured output feedback in the control of heavy haul trains. Automatica 44(1):242鈥?47 CrossRef
  24. Tao T, Xu H (2013) Fault-tolerant control of high-speed trains with uncertain parameters and actuator failures using control reallocation and adaptive control. J Inf Comput Sci 10(7):1959鈥?977 CrossRef
  25. Zhuan X, Xia X (2006) Cruise control scheduling of heavy haul trains. IEEE Trans Control Syst Technol 14(4):757鈥?66 CrossRef
  26. Zhou K, Doyle J, Glover K (1995) Robust and optimal control. Prentice Hall, NJ
  27. Polycarpou M (1996) Stable adaptive neural control scheme for nonlinear systems. IEEE Trans Autom Control 41(3):447鈥?51 CrossRef
  28. Khalil H (2001) Nonlinear systems, 3rd edn. Prentice Hall, NJ
  29. Spong MW (1992) On the robust control of robot manipulators. IEEE Trans Autom Control 37(11):1782鈥?786 CrossRef
  30. Dawson DM, Carroll JJ, Schneider M (1994) Integrator backstepping control of a brush DC motor turning a robotic load. IEEE Trans Control Syst Technol 2(3):233鈥?44 CrossRef
  31. Ioannou P, Kokotovic PV (1983) Adaptive systems with reduced models, Lecture notes in control and information sciences. 47, Springer, New York
  32. Ioannou P, Kokotovic PV (1984) Instability analysis and improvement of robustness of adaptive control. Automatica 20(5):583鈥?94 CrossRef
  33. Ioannou P, Sun J (1996) Robust adaptive control. Prentice Hall, NJ
  
• 刊物类别：Computer Science
• 刊物主题：Simulation and Modeling
  
• 出版者：Springer London
• ISSN：1433-3058

文摘

In order to accommodate actuator failures which are unknown in amplitude and time, adaptive fault-tolerant control schemes are proposed for automatic train operation system. Firstly a basic design scheme on the basis of direct adaptive control is considered. It is demonstrated that, when actuator failures occur, asymptotical speed and position tracking are guaranteed. Then a new user-friendly control scheme is proposed which can eliminate the undesirable chattering phenomenon, which is the defect of the previous method. Simulation results verify the effectiveness of established theoretical results that satisfactory speed tracking and position tracking can be guaranteed in the presence of uncertain actuator failures in automatic train operation systems.