汽车防抱死制动系统神经网络自适应控制

针对汽车ABS系统在冰雪等湿滑不平的路面上制动效能下降的情况,本文在对ABS制动特性进行分析的基础上,建立了其数学模型,提出了一种基于神经网络的汽车ABS系统自适应控制方案。控制器由标称控制律和补偿控制律组成,并在Matlab/Simulink环境中进行仿真模拟。为检验控制策略合理性和控制软件可行性以及自主设计ECU的可靠性,进行了装车对比试验。理论分析和仿真计算、试验结果均证明:本文提出的控制策略具有更好的控制效果和鲁棒性,汽车在不良路面上的制动效能也得到明显改善。

An Adaptive Robust Control for Automobile Antilock Braking System Based on Neural Network

The braking effectiveness of antilock braking system(ABS) could be degraded for rough road conditions(e.g.,icy/snowy roads).This paper explores a neuro-adaptive control design method for ABS in which a new control scheme consisting of both neuro and adaptive units is proposed.The neuro unit is the main tracking controller used to mimic an ideal controller to cope with disturbances and coupled dynamics due to road condition variations;and the adaptive unit is included to compensate for the difference between the ideal controller and the neuro controller.Unlike traditional NN based method,there is no need to analytically estimate the upper bound on the reconstruction error and uncertainties in the proposed approach.Both theoretical analysis and simulation studies verify the effectiveness of the control algorithms.