基于改进PSO-BP神经网络的挖掘机液压系统故障诊断  

Fault Diagnosis of Excavator Hydraulic System Based on Improved PSO-BP Neural Network

作　　者：郭京峰 GUO Jingfeng(China Railway 16th Bureau Group fourth Engineering Co.,Ltd.,Beijing 101400)

机构地区：[1]中铁十六局集团第四工程有限公司,北京101400

出　　处：《现代制造技术与装备》2024年第11期37-39,共3页Modern Manufacturing Technology and Equipment

摘　　要：由于现行方法在挖掘机液压系统故障诊断中存在一定不足,无法达到预期效果,提出基于改进粒子群优化算法(ParticleSwarmOptimization,PSO)-反向传播(BackPropagation,BP)神经网络的挖掘机液压系统故障诊断方法。采用无线传感器采集液压系统数据,对采集的数据进行预处理,利用PSO对BP神经网络进行迭代训练、优化网络参数,利用改进BP神经网络挖掘液压系统数据,识别诊断系统故障。实验结果表明,所提方法的平均绝对误差百分比不超过1%,漏诊比例也不超过1%,能够实现对挖掘机液压系统故障的精准诊断。Due to the shortcomings of the current method in fault diagnosis of excavator hydraulic system,the expected diagnosis effect can not be achieved,a fault diagnosis method of excavator hydraulic system based on the improved Particle Swarm Optimization(PSO)-Back Propagation(BP)neural network is proposed.The wireless sensor is used to collect the data of the hydraulic system,and the collected data is pre-processed.PSO is used to iteratively train the BP neural network and optimize the network parameters.The improved BP neural network is used to mine the data of the hydraulic system and identify and diagnose the system faults.The experimental results show that the average absolute error of the proposed method is less than 1%,and the proportion of missed diagnosis is less than 1%,which can realize the accurate diagnosis of the excavator hydraulic system fault.

关 键 词：改进粒子群优化算法(PSO) 反向传播(BP)神经网络 挖掘机 液压系统 故障诊断 

分 类 号：TU621[建筑科学—建筑技术科学] TP18[自动化与计算机技术—控制理论与控制工程]