基于SOM的电静压伺服机构油滤堵塞故障诊断

SOM-based Fault Diagnosis of the Filter Blockage in Electro-Hydrostatic Actuator

以电静压伺服机构(EHA)为研究对象,对该机构特有的油滤堵塞故障模式进行故障诊断.首先在AMESim系统中建立EHA的仿真模型,并根据油滤堵塞程度划分故障状态;然后以仿真中作动器的位移、电机转速和电机电流(指非输入电流)为特征值,建立基于自组织特征映射神经网络的EHA故障诊断模型,并以神经元反馈分布作为故障标识,进行故障诊断;最后利用样机的实测数据建立EHA的故障诊断模型,验证所提出方法的可行性.研究结果可应用到其他故障模式中.

As a new type of servo drive device, electro-hydraulic actuator(EHA) has been successfully applied in the aerospace field abroad. In this paper, EHA is taken as the research object, and fault diagnosis research is carried out according to the specific oil filter blockage fault mode of the mechanism. Firstly, the simulation model of EHA is established in AMESim, and the fault state is divided according to the degree of oil filter blockage. Then, taking the actuator displacement, motor speed and input current (non-input current) as the eigenvalues, an EHA fault diagnosis model based on self-organizing feature maps (SOM) is established, and a neuron feedback cloud image is used as a fault identification mark for fault diagnosis. Finally, the EHA fault diagnosis model is established by using the measured data of the system prototype, which verifies the feasibility of the proposed method. The exploratory research results can also be applied to other fault modes.