基于无模型自适应控制的高速列车ATO控制器

ATO Controller for High-speed Train Based on Model-Free Adaptive Control

针对高速列车在多变复杂环境运行时,传统控制器出现的动力学模型不匹配和司机操作存在安全隐患的问题,提出一种基于无模型自适应控制(Model-Free Adaptive Control, MFAC)的高速列车自动驾驶控制器设计方案。首先,构建全格式动态数据列车模型,将列车的非线性特性转移到伪梯度中;其次,根据全格式动态数据列车模型设计无模型自适应控制律和列车控车原理,通过列车运行数据估计伪梯度,构建ATO控制器;最后,使用"兰州西—西宁"的动车组运行数据进行仿真,得到MFAC控制器作用下的速度追踪误差为0.254km/h,列车加速度冲击率区间主要分布于[0,0.1)中,约占总步长的83.8%,并与模糊自适应PID(ProportionIntegral-Derivative)在速度追踪、位移追踪和舒适度方面做了对比,结果表明该控制器的性能更优。

In view of the problems of dynamic model mismatch of traditional controller and potential safety hazards of driver operation when the high-speed train operated in a changeable and complex environment, a high speed train automatic driving controller design scheme based on model-free adaptive control(MFAC) was proposed. Firstly, a full-format dynamic data train model to transfer the nonlinear characteristics of the train to the pseudo gradient was constructed;Secondly, according to the full-format dynamic data train model, the model-free adaptive control law and the train control principle were designed, and with the pseudo gradient estimated through the train operation data, the ATO controller was constructed;Finally, "Lanzhouxi-Xining" EMU operating data was used for simulation. The result shows that: speed tracking error under the action of the MFAC controller is 0.254 km/h, and the train acceleration impact rate is mainly distributed in [0, 0.1), accounting for about 83.8% of the total step length. By compared with fuzzy adaptive PID(proportion-integral-derivative) in terms of speed tracking, displacement tracking, and comfort, the performance of the proposed controller is proved better.