时变工况下电静压伺服机构性能退化监测方法研究  

Performance Degradation Monitoring of Electro-hydrostatic Actuator Under Time-varying Testing Conditions

作　　者：马行健 贺青川[1] 刘慧[2] 赵守军[2] 潘骏[1] MA Xing-jian;HE Qing-chuan;LIU Hui;ZHAO Shou-jun;PAN Jun(National and Local Joint Engineering Research Center of Reliability Analysis and testing for Mechanical and Electrical Products,Zhejiang Sci-Tech University,Hangzhou,Zhejiang 310018;Beijing Institute of Precision Mechatronics and Controls,Beijing 100076)

机构地区：[1]浙江理工大学机电产品可靠性分析与测试国家地方联合工程研究中心,浙江杭州310018 [2]北京精密机电控制设备研究所,北京100076

出　　处：《液压与气动》2023年第5期17-25,共9页Chinese Hydraulics & Pneumatics

基　　金：国家自然科学基金(51875529);浙江省科技创新领军人才项目(2021R52036);装备预先研究领域基金(80902010302)。

摘　　要：针对缺乏时变工况下电静压伺服机构性能退化监测方法,在地面摇摆测试过程中难以预测性能退化程度,进而影响火箭健康状态评估准确性的问题,提出了一种利用人工神经网络进行电静压伺服机构性能退化监测的方法。通过对电静压伺服机构的系统建模与性能退化机理分析,确定了性能退化表征参数;通过分析不同性能退化阶段与正常状态下的特征参量相对偏离程度的方法构建了健康因子;提出了基于可控参数的前馈神经网络进行健康因子监测的方法。利用地面摇摆实验平台进行了验证,结果表明:所构建的健康因子具有较强的性能退化程度表征能力;所提监测方法对解决时变工况下电静压伺服机构性能退化监测问题是有效的。To solve the problem how to monitor the performance degradation of an Electro-Hydrostatic Actuator(EHA)under time-varying test conditions and improve,a performance degradation monitoring method based on Artificial neural network(ANN)is proposed,which can help to improve the accuracy of residual useful life prediction of the EHA and also the launch vehicle.The performance degradation parameters of the EHA are identified by degradation mechanism analysis.The calculation method of Health Indicator(HI)is proposed by analyzing the relative deviation of the monitoring performance parameters by comparing those parameters under degradation phase and health state.The monitoring method of the HI under time-varying testing conditions based on feedforward neural network(FFNN)is proposed.The test results indicated that the proposed new method can be used to monitor performance degradation of the under time-varying testing conditions.

关 键 词：电静压伺服机构(EHA) 时变工况 前馈神经网络(FFNN) 性能退化 

分 类 号：TH137[机械工程—机械制造及自动化]