Analog circuit fault diagnosis method based on artificial immunity diagnosis network

Abstract

The invention provides an analog circuit fault diagnosis method based on an artificial immunity diagnosis network, which comprises the following steps of extracting a characteristic value of a circuitresponse signal in a training sample to form a training antigen set; performing data clustering with a director on the training antigen of each fault type to obtain a memory antibody set; acquiring aresponse signal of an actual circuit to be diagnosed, and extracting a characteristic value of the response signal to form a new antigen; activating a memory antibody in the artificial immunity diagnosis network by using the new antigen, and judging the specific fault type of the circuit to be diagnosed according to the total affinity of the new antigen and various fault type memory antibodies. According to the method, the fault type information of the circuit can be memorized after network training is completed, the fault recognition function is achieved, and the method has the advantages that influences of circuit tolerance can be effectively handled, and an analysis model does not need to be established.

Description

technical field [0001] The invention relates to the technical field of fault diagnosis, in particular to an analog circuit fault diagnosis method based on an artificial immune diagnosis network. Background technique [0002] With the rapid development of science and technology, the complexity of industrial equipment is getting higher and higher, and the research on fault diagnosis of equipment is of great significance, which is directly related to the safety of equipment and personnel. In the field of electronic equipment, although digital circuits are increasingly widely used, the characteristics of signals in the objective world determine that analog circuits are still essential. In complex environments, the probability of failure of analog circuits is much greater than that of digital circuits. However, due to the variety of fault phenomena, the ubiquity of tolerance, the difficulty of establishing an analytical model, and the influence of nonlinear factors, the fault di...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to aim at the defects of the prior art, provide a kind of analog circuit fault diagnosis method based on the artificial immune diagnosis network, make the fault type information of the circuit memorize after the network training is completed, have the fault identification ability, and effectively handle the fault of the tolerance impact, to enable fault diagnosis without building an analytical model of the circuit to be diagnosed

Images