Fault Diagnosis Method of Modularized BP Neural Network Circuit Based on Fault Propagation

Abstract

The invention provides a modular BP neural network circuit fault diagnosis method based on fault propagation, and belongs to the technical field of fault diagnosis and positioning of electronic systems. The present invention determines the test nodes of each sub-circuit on the basis of circuit module division, and uses the characteristic parameter data of the test nodes as a data source for fault diagnosis; establishes a modular anomaly detection model based on the data source based on circuit simulation, and analyzes fault propagation , establish a modular BP neural network model; when the actual circuit fails, use the modular anomaly detection model for primary positioning to determine the faulty sub-circuit, and then use the BP neural network model of the target sub-circuit for secondary positioning to identify the fault mode . The present invention performs fault location through a model established offline, has strong expansibility, and has a wide application range; realizes online real-time fault diagnosis of large-scale digital-analog hybrid circuits, especially for the situation of fault propagation, and has extremely high fault positioning accuracy.

Description

technical field [0001] The invention belongs to the technical field of fault diagnosis and location of electronic systems, and in particular relates to a fault diagnosis method for a modularized BP neural network circuit based on fault propagation. Background technique [0002] In recent years, with the increase in the scale and complexity of digital-analog hybrid circuits, especially in the application fields of aviation, aerospace, military and national defense, circuit reliability has received more and more attention. As an important means of maintaining circuit reliability, fault diagnosis has become a research hotspot. Circuit fault diagnosis methods mentioned in many literatures include: fault dictionary, nearest neighbor, rule-based and SVM fault classification model, etc., which are only put into practice in analog circuits, and due to the intricate nonlinear mapping relationship of complex circuits, resulting in Diagnosis is poor. The BP neural network has been pr...

AI Technical Summary

Problems solved by technology

Among them, when establishing the BP neural network of each sub-circuit, all the measurable nodes are used, and the node redundancy is high. The direct use of node voltage to represent the node information cannot perfectly represent the fault information of the circuit. Propagated circuits are less accurate

In the document "Bearing Fault Detection Combined with Anomaly Detection Algorithm", a two-step fault diagnosis method based on a combination of anomaly detection algorithm is proposed. As a fault detector, the anomaly detection model can only be used to detect whether the circuit is faulty, and cannot reduce The scope of the fault source of the circuit; SVM is used as a fault classifier to locate the fault on the basis of determining the fault in the circuit. This method is actually equivalent to a single-step fault diagnosis method for real-time monitoring of the circuit, and is not suitable for fault diagnosis of large-scale circuits. , and does not take into account the complex situation of fault propagation

Images