论文部分内容阅读
电动汽车电机故障因素多,可靠性分析需要大样本数据,为准确预测电机的故障时间,建立了故障率较高元件的故障树模型,给出了其可靠性计算式,并将基于小样本数据的灰色算法引入到电机可靠性计算中,利用传统和改进灰色模型进行仿真分析。为了进一步提高预测精度,以两种灰色模型为基础,利用粒子群算法的全局寻优能力,提出了以均方差最小为目标函数的优化模型,对电机故障时间进行预测,并利用两组实测数据进行了验证。结果表明,优化算法的相对平均误差分别为3.36%和5.05%,相对误差最大值分别为5.62%和8.41%。该结果验证了所提算法的有效性,为电动汽车电机的故障预测提供了理论依据。
In order to accurately predict the fault time of a motor, a fault tree model of a component with a high failure rate is established, and its reliability calculation formula is given. Based on the small sample data The gray algorithm is introduced into the reliability calculation of the motor. The traditional gray model and the improved gray model are used in the simulation analysis. In order to further improve the prediction accuracy, based on the two gray models and using the global optimization ability of particle swarm optimization, an optimization model with minimum mean square error as objective function is proposed to predict the motor failure time. Two sets of measured data Verified. The results show that the relative average error of the optimized algorithm is 3.36% and 5.05% respectively, and the maximum relative error is 5.62% and 8.41% respectively. The result verifies the validity of the proposed algorithm and provides a theoretical basis for the fault prediction of the electric vehicle motor.