摘要
高速动车组运行环境复杂多变,其运行过程需在牵引、制动和惰行工况中多次切换,难以建立有效的控制模型实现动车组安全、正点、高效运行。借鉴ANFIS在复杂系统建模的优势,结合动车组牵引/制动特性曲线和实际运行数据,建立高速动车组运行过程多工况ANFIS模型,设计相应的动车组运行速度控制器。与基于全局ANFIS模型和基于线性多模型的控制对比试验表明:基于多工况ANFIS模型的高速动车组运行控制具有更高的精度和控制效果,保障了动车组在各种工况下的安全运行。
High-speed electric multiple unit(HSEMU) is a complex dynamic nonlinear system whose operating conditions switch frequently among traction, braking and coasting. To enhance the running performances of HSEMU, a technical running model should be designed. By applying the advantages of adaptive neuro-fuzzy inference system(ANFIS) in complex system modeling, this paper proposed a multiple operating conditions(MOC)-ANFIS model of HSEMU combining with traction/braking characteristic curves and real running data of HSEMU. Then based on the MOC-ANFIS model, a speed controller was designed to realize a safe, punctual and efficient running of HSEMU. Comparative experiments with global ANFIS model based controller and linear multiple model based controller demonstrate that the presented controller based on MOC-ANFIS model delivers higher accuracy and control effect in improving the running performances of HSEMU in each operating condition.
引文
[1] DONG H R,NING B,CAI B G,et al.Automatic Train Control System Development and Simulation for High-speed Railways[J].IEEE Circuits and System Magazine,2010,10(2):6-18.
[2] LI D Y,SONG Y D,CAI W C.Neuro-adaptive Fault-tolerant Approach for Active Suspension Control of High-speed Trains[J].IEEE Transactions on Intelligent Transportation Systems,2015,16(5):2446-2456.
[3] 余进,钱清泉,何正友.两级模糊神经网络在高速列车ATO 系统中的应用研究[J].铁道学报,2008,30(5):52-56.YU Jin,QIAN Qingquan,HE Zhengyou.Research on Application of Two-degree Fuzzy Neural Network in ATO of High Speed Train[J].Journal of the China Railway Society,2008,30(5):52-56.
[4] YANG C D,SUN Y P.Mixed H2/H∞ Cruise Controller Design for High Speed Train[J].International Journal of Control,2010,74(9):905-920.
[5] SONG Q,SONG Y D,CAI W C.Adaptive Backstepping Control of Train Systems with Traction/Braking Dynamics and Uncertain Resistive Forces[J].Vehicle System Dynamics:International Journal of Vehicle Mechanics and Mobility,2011,49(9):1441-1454.
[6] 衷路生,颜争,杨辉,等.数据驱动的高速列车子空间预测控制[J].铁道学报,2013,35(4):77-83.ZHONG Lusheng,YAN Zheng,YANG Hui,et al.Predictive Control of High-speed Train Based on Data Driven Subspace Approach[J].Journal of the China Railway Society,2013,35(4):77-83.
[7] 杨辉,张坤鹏,王昕,等.高速列车多模型广义预测控制方法[J].铁道学报,2011,33(8):80-87.YANG Hui,ZHANG Kunpeng,WANG Xin,et al.Multiple Models Generalized Predictive Control Method of High-speed Train[J].Journal of the China Railway Society,2011,33(8):80-87.
[8] KE B R,LIN C L,LAI C W.Optimization of Train-speed Trajectory and Control for Mass Rapid Transit Systems[J].Control Engineering Practice,2011,19(7):675-687.
[9] SONG Q,SONG Y D.Data-based Fault-tolerant Control of High-speed Trains with Traction/Braking Notch Nonlinearities and Actuator Failures[J].IEEE Transactions on Neural Networks,2011,22(12):2250-2261.
[10] WANG Y J,SONG Y D,GAO H,et al.Distributed Fault-tolerant Control of Virtually and Physically Interconnected Systems with Application to High-speed Trains under Traction/Braking Failures[J].IEEE Transactions on Intelligent Transportation Systems,2016,17(2):535-545.
[11] 杨辉,张芳,刘鸿恩,等.基于自适应LSSVM模型的动车组运行速度控制[J].铁道学报,2015,37(9):62-68.YANG Hui,ZHANG Fang,LIU Hongen,et al.Speed Control of Electric Multiple Unit Via a LSSVM Model[J].Journal of the China Railway Society,2015,37(9):62-68.
[12] JANG J S R.ANFIS:Adaptive-network-based Fuzzy Inference System[J].IEEE Transactions on Systems,Man,and Cybernetics,1993,23(3):665-685.
[13] YANG H,FU Y T,ZHANG K P,et al.Speed Tracking Control Using an ANFIS Model for High-speed Electric Multiple Unit[J].Control Engineering Practice,2014,23(1):57-65.
[14] FU Y T,YANG H,WANG D H.Real-time Optimal Control of Tracking Running for High-speed Electric Multiple Unit[J].Information Sciences,2017,376(10):202-215.
[15] CHOU M,XIA X.Optimal Cruise Control of Heavy-haul Trains Equipped with Electronically Controlled Pneumatic Brake System[J].Control Engineering Practice,2007,15(5):511-519.
[16] JANG J S R,SUN C T.Neuro-fuzzy Modeling and Control[J].Proceedings of the IEEE,1995,83(3):378-406.
[17] CHEN M Y.A Hybrid ANFIS Model for Business Failure Prediction Utilizing Particle Swarm Optimization and Subtractive Clustering[J].Information Science,2013,220(20):180-195.
[18] CLARKE D W,SCATTOLINI R.Constrained Receding-Horizon Predictive Control[J].IEE Proceedings D (Control Theory and Applications),1991,138(4):347-354.
[19] NARENDRA K S,BALAKRISHMAN J.Adaptive Control Using Multiple Models[J].IEEE Transactions on Automatic Control,1997,42(2):171-187.
[20] CLARKE D W,MOHTADI C,TUFFS P S.Generalized Predictive Control-Part I the Basic Algorithm[J].Automatica,1987,23(2):137-148.