Method for diagnosing failures of analog circuit based on heterogeneous information fusion

Abstract

The invention discloses a method for diagnosing failures of an analog circuit based on heterogeneous information fusion. The method comprises the following steps: measuring a temperature variation value of a circuit element to be diagnosed; calculating an optimum gate valve value of the variation value of working temperature of each element; integrating the temperature variation value of an element more than the optimum gate valve value into a failure domain phi, and calculating by a temperature membership grade model to acquire a temperature evidence value of each element; applying an actuating signal to a circuit to be diagnosed to measure voltage of a measurable point; inputting information of the voltage of the measurable point into a BP neural network to carry out primary diagnosis so as to acquire an evidence value of voltage of the measurable point; and fusing the evidence value of temperature and the evidence value of voltage by a heterogeneous information fusion system, acquiring an associated weight coefficient, identifying the weight coefficient and unifying the weight coefficient, and regulating and carrying out D-S fusion on the two types of the evidence values to determine a failure element. The method solves the problem of inaccurate judgment caused by deficiency of feature information and incompatible heterogeneous information in failure diagnosis of the analog circuit, and improves the accuracy of the failure diagnosis.

Description

technical field [0001] The invention relates to an analog circuit diagnosis method, in particular to an analog circuit fault diagnosis method based on heterogeneous information fusion. Background technique [0002] After more than 40 years of development in analog circuit fault diagnosis research, great progress has been made. However, with the continuous improvement of circuit complexity and integration, it is difficult to find a sufficient number of accessible nodes in actual tests. In particular, there are fewer measurable nodes in large-scale and complex circuits, and the topology of the actual circuit is far from ideal. The topology and measurable points of the circuit restrict the applicability of the circuit diagnosis method. And the diversity of fault phenomena makes it difficult for existing diagnosis methods to solve the diagnosis problems of actual circuits. [0003] The application of information fusion technology provides the possibility to solve many problems ...

AI Technical Summary

Problems solved by technology

Although this theory has been widely used, especially in pattern recognition, target recognition, etc., there are still many problems in the application of fault diagnosis: 1. Due to the low robustness of this method, it is often A small change in the value of a single piece of evidence will cause a drastic change in the combined result; 2. The fusion of conflicting evidence values ​​is often contrary to intuition and fact, which is obviously unreasonable; 3. When one piece of evidence is completely inconsistent with multiple pieces of evidence, the combination There is a veto

Especially for the diagnosis of large-scale circuit systems, due to the influence of sensors, circuit complexity and other factors, it is not realistic to obtain ideal and accurate evidence itself

Images