基于高阶谱分析的混合电路故障诊断专家系统的设计

Design of Experts System for Mixed-signal Circuits Fault Diagnosis Based on Higher-order Spectrum Analysis

混合电路故障诊断是当前对电路故障诊断的一个热点问题,文中从分析混合电路特点入手,利用高阶谱中的双谱技术分析、处理和提取电路状态的故障信息特征,然后设计和采用以径向基神经网络作为故障模式的训练和识别器,建立一个故障诊断专家系统,最后以一个功率电路作为例子进行了仿真验证,结果表明,对电路的故障诊断准确率达到95%以上。

Fault diagnosing for mixed-signal circuits is a hotspot in circuits fault diagnosis. It is the first step to analyze the characters of mixed-signal circuits. Afterwards, the faulty circuit information feature was analyzed, processed and extracted by hi-spectrum analy sis. In the sequel, The fault modes were trained and recognized by a Radial Basis Function Neural Network （RBFNN） and a experts system is built. Finally, a power circuit was simulated to validate the arithmetic. The results show that the fault location accuracy is up to 95%.