Genetic programming-based analog circuit fault test optimal sequential search method

Abstract

The invention discloses a genetic programming-based analog circuit fault test optimal sequential search method. A plurality of fault diagnosis trees are firstly randomly generated according to a test dependency matrix of a modular circuit, a genetic programming method is adopted to carry out selection, crossover and mutation on the fault diagnosis trees, a reciprocal of the test cost corresponding to the fault diagnosis tree serves as the individual fitness of the fault diagnosis tree, a fault rally point and a sub tree are exchanged only during the crossover process according to features of the fault diagnosis tree, a testing point is only selected for mutation during the mutation process, a sub tree under the testing point and the rally point is generated again, the fault diagnosis tree with the minimal test cost is selected from the current plurality of fault diagnosis trees after multiple times of iteration to serve as the final fault diagnosis tree. Through accurate search, a testing point sequence isolating the maximal fault points at the minimal test cost can be obtained, and guidance is provided for modular circuit fault test.

Description

technical field [0001] The invention belongs to the technical field of analog circuit fault testing, and more specifically relates to an optimal sequential search method for analog circuit fault testing based on genetic programming. Background technique [0002] The problem of optimal sequential testing is a key issue in design and analysis methods for testability of analog circuits. The optimal sequential testing problem in its simplest form can be defined as a quadruple (S,p,T,c). S={s 0 ,s 1 ,s 2 ,...,s m} represents all possible failure sets, where s 0 Indicates no fault state, s j Indicates any possible failure and m indicates the number of failure situations. P=[p(s 0 ),p(s 1 ),…,p(s m )] T is the prior probability set of possible occurrences of the above fault set elements, p(s 0 ) represents the probability that no fault occurs. In theory, the prior probability sum should be 1, that is In some cases, the probability sum obtained by the direct strategy ...

AI Technical Summary

Problems solved by technology

However, in practical applications, due to the large number of measurement points, how to quickly and accurately search for the optimal sequential test is a big problem

Images