基于BP网络的容差模拟电路故障诊断研究

Fault diagnosis of analog circuit with tolerances based on back-propagation neural networks

传统模拟故障诊断多采用K故障诊断法,即在已知拓扑结构和元件参数的标称值前提下,不必对故障进行模拟,就可以计算出各元件发生故障的统一特征,找出故障位置。但对于有容差干扰的电路检测速度将会变慢,甚至影响检测效果的可靠性。鉴于此,引进BP神经网络,将K故障诊断法与BP网络相结合,用于容差模拟电路故障检测,其方法具有实时诊断性和鲁棒性特点。故障诊断实例和计算机仿真结果证明,本文所提出的观点是可行的。

Tradition fault diagnosis of analog circuits always uses the k-fauh diagnosis method, according to the topology of the circuit and the parameters of component, and the common characteristic of fault can be located. However, for the circuits with tolerances, fault feature values are influenced by tolerance, which will make the contributions of faults to the two values ambiguous and the testing process slow. Under this situation, fault location results may not be so accurate and sometimes may lead to false diagnosis. In this paper,an approach is proposed based on the K-fault diagnosis method and artificial backward propagation neural network to settle the problems mentioned above. Simulation results indicate that the method is robust and fast for fault diagnosis of analog circuits with tolerances.