Method for diagnosing faults of analog circuit of multi-fractional order information fusion

Abstract

The invention discloses a method for diagnosing faults of an analog circuit of multi-fractional order information fusion, belonging to the field of network fault test and diagnosis of the analog circuit. The method comprises the following steps of: A inputting N types of effective sinusoidal excitation signals with different frequencies in series at the input end of a circuit to be tested to obtain an initial dataset; B randomly dividing a sample set into k feature space subsets by adopting a random subspace method; C mapping the feature space subsets into k diverse fractional-order time-frequency spaces by using fractional-order Fourier transform; and D obtaining a final diagnosis result by utilizing the weight of a failure class and fusing the diagnosis results of k basic classifying models, and dynamically updating the weight of the failure class after completing the diagnosis on each batch of test data. The invention improves the difference degree of the feature space subsets, increases complementarity among basic classifiers, combines with the gradual change characteristics of device faults and effectively improves the precision of a diagnosing system.

Description

technical field [0001] The invention relates to an analog circuit fault diagnosis method, in particular to an analog circuit fault diagnosis method with multi-fractional information fusion. Background technique [0002] Analog circuits are an indispensable and important part of electronic circuits. With the rapid development of large-scale analog integrated circuits, especially analog-digital hybrid circuits, the complexity and density of analog circuits continue to increase. Once a fault occurs somewhere, it cannot be obtained in time. If it is diagnosed and restored, it will cause shutdown at least, and cause casualties and huge economic losses at worst. For applications with high reliability requirements, the reliability of equipment is particularly important. Therefore, vigorously developing and applying technologies such as autonomous analog circuit fault diagnosis and fault prediction has become an important content in modern industrial production and national defense...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide an analog circuit fault diagnosis method that can solve the problems of poor diagnostic model generalization ability and ignoring fault gradient in existing analog circuit fault diagnosis methods

Images