摘要
动车组转向架的健康状态直接关系到到动车组的行车安全,基于健康评估方法获取其健康状态及时制定维护计划可以有效降低其维护费用.动车组转向架健康状态评估时应用了模糊层次分析法以及BP神经网络,其模糊矩阵的特征向量用遗传算法进行求解,获取动车组转向架系统关键部件健康状态的权重,以及基于转向架系统评价指标的健康状态样本数据.构建BP神经网络,用转向架健康状态样本数据作为神经网络训练集,优化神经网络结构参数.通过实际测试数据对神经网络评估效果进行检验,完成了动车组转向架健康评估方法的智能化,支持了动车组转向架的维护决策.
The health status of EMU bogies is directly related to the driving safety of EMU.To obtain the health status of EMU bogies based on the health assessment method and make the maintenance plan in time can effectively reduce the maintenance cost.The fuzzy analytic hierarchy process and BP neural network are used in the evaluation of EMU bogie health state.The eigenvector of the fuzzy matrix is solved by genetic algorithm to obtain the weight of the health state of the key components of EMU bogie system and the health state sample data based on the evaluation index of bogie system.The BP neural network is constructed,and the bogie health state sample data is used as the training set of the neural network to optimize the structural parameters of the neural network.Through the actual test data to test the evaluation effect of neural network,the intelligent evaluation method of EMU bogie health is completed,which supports the maintenance decision of EMU bogie.
作者
邢成梁
李忠学
XING Cheng-liang;LI Zhong-xue(School of Mechanical and Electrical Engineering,Lanzhou Jiaotong University,Lanzhou 730070,China)
出处
《数学的实践与认识》
2022年第11期122-131,共10页
Mathematics in Practice and Theory
