论文部分内容阅读
为避免电机制动失效对驾驶安全的影响,提出了一种基于驾驶员意图识别的电动汽车电机制动失效监控系统。根据控制要求,将系统的硬件部分分为电源电路、信号采集调理电路、故障监测电路和故障处理电路并进行了设计。将驾驶员制动意图分为缓慢制动、紧急制动、正常制动。利用k-medoids聚类算法对数据进行离散化处理,利用双层隐形马尔科夫模型对驾驶员的制动操作意图进行识别。提出基于模糊推理的失效等级进行判断方法,并根据不同失效等级制订了车辆响应方式。利用Simulink与Simplorer对控制系统进行联合仿真,并对系统进行了试验验证。结果表明,该控制策略能正确识别驾驶员的制动操作意图,正确判断故障等级,并据此作出正确响应,可保证车辆制动时的安全性、操控性,实现既定的控制要求。
In order to avoid the influence of motor brake failure on driving safety, a braking failure monitoring system for electric vehicle based on driver’s intention is proposed. According to the control requirements, the hardware part of the system is divided into power supply circuit, signal acquisition and conditioning circuit, fault monitoring circuit and fault handling circuit and designed. The driver’s brake intent is divided into slow braking, emergency braking, normal braking. The k-medoids clustering algorithm was used to discretize the data, and the invisible Markov model was used to identify the driver’s intention of braking operation. Put forward the judgment method of the failure level based on fuzzy inference, and formulate the vehicle response method according to different failure levels. Simulink and Simplorer were used to simulate the control system and the system was tested. The results show that the control strategy can correctly identify the intention of the driver’s brake operation, correctly judge the fault level, and make the correct response accordingly to ensure the safety and controllability of the vehicle during braking, and realize the established control requirements.