基于RVM和相空间重构的模拟电路PHM研究

Research on Analog Circuit PHM Based on RVM and Phase Space Reconstruction

摘要:

针对模拟电路健康管理的特点，提出了一种基于RVM的模拟电路故障诊断和预测方法。首先对模拟电路作蒙特卡罗分析得到输出频域响应，然后利用小波分解与重构方法提取模拟电路的故障特征，最后用相关向量机分别对电路进行了单一故障和双故障的诊断研究。接着，对电路进行参数分析，得到不同参数值下的输出响应，计算其与电路无故障标准响应的欧氏距离作为故障特征，并以此表征电路元件健康值，结合相空间重构方法，得到相关向量机的输入输出样本，随后训练学习并实现对各个时间点元件的健康值变化轨迹进行预测。仿真结果表明，该方法在小样本情况下，诊断和预测效果好，适用于健康管理中实时预测，具有较好的实用性。

Abstract:

Aimed at the characteristics of Prognostic and health management(PHM) in analog circuits，a new method for analog circuit fault diagnostics and prediction based on relevance vector machine(RVM) is proposed in this paper. Firstly, getting frequency domain response by the Monte Carlo Analysis of Analog Circuits, fault features are extracted by wavelet decomposition and reconstruction to make single-fault and double fault diagnosis utilizing relevance vector machine, combining the phase space reconstruction method, the health value of circuit components is represented through calculating the Euclidean distance between output of standard and different parameter analysis, and the trend of health value trajectory with respect to time points can be predicted by training samples of inputs and outputs of RVM, the proposed approach is appropriate for real time prediction in PHM. Simulation results validate the good practicability and effectiveness of the proposed method.