基于驱动端电流检测的电磁阀故障诊断研究  

The Fault Diagnosis of Electromagnetic Valves Based on Driving Current Detection

作　　者：刘志浩[1] 高钦和[1] 牛海龙[1] 管文良[1] 李璟玥 

机构地区：[1]第二炮兵工程大学兵器发射理论与技术国家重点学科实验室,陕西西安710025

出　　处：《兵工学报》2014年第7期1083-1090,共8页Acta Armamentarii

摘　　要：提出基于驱动端电流检测的电磁阀故障诊断方法,研究了电磁阀驱动端电流特性及故障阀电流特征分析和识别方法。利用AMEsim软件搭建电磁阀的机、电、液模型,分析其驱动端电流与阀芯位移的关系;采集正常、弹簧断裂、阀芯轻微卡滞和阀芯完全卡死4种状态下的电流信号,分析不同状态的电流特征;针对驱动端电流为直流阶跃信号的特点,选取电流变化率为特征曲线,采用"能量-故障"的诊断方法,利用3层小波包分解对信号进行重构,并提取相应频带能量作为特征向量;利用前馈反向传播(BP)神经网络对提取的特征向量,对电磁换向阀模式识别和故障诊断。实验结果表明:基于"能量-故障"的诊断方法能较好地区分电磁阀的不同状态,并且经过训练的BP神经网络能够准确判别电磁阀的正常、弹簧断裂和阀芯卡死3种状态。The fault diagnosis of electromagnetic valves based on driving end current detection is proposed. The current characteristics of the faulted electromagnetic valves and the failure signal are analyzed. The four conditions of the valve are detected, including normal state, spring break state, spool seizure and un-resetting state. Variation trend is the character signal on terms of the direct-current char- acteristic. For the trait of the current signal, the wavelet packet decomposition is used to distill the corresponding frequent band energy as feature vector. The feature database is combined with the each frequent band energy which is produced after reconfiguration. The feedforward-back propagation network is used to identify the fault type of the electromagnetic valves. The result shows that the diagnosis method of energyfault can distinguish the different conditions of the electromagnetic valves,and the feedforward-back propagation network after training can identify the 3 fault conditions. The method is an effective assistant method for the maintenance of the electromagnetic valves, which can be widely used for the fault diagnosis of other electromagnetic valves.

关 键 词：仪器仪表技术 电磁换向阀 电流检测 AMESIM 故障诊断 小波包分析 前馈反向传播神经网络 

分 类 号：TH137.523[机械工程—机械制造及自动化]