Complex analog circuit fault identification and estimation method and system

Abstract

The invention discloses a complex analog circuit fault identification and estimation method and system, and belongs to the field of power electronic circuit fault prediction, and the method comprisesthe steps: building a degradation simulation model of a to-be-diagnosed analog circuit, and carrying out parameter aging simulation experiment of different devices; extracting a series of time domainfeatures of the output signal by using a time sequence transformation method, and establishing health indices of the devices based on the angular similarity; whether the circuit is degraded and a degradation starting point are identified in combination with a time sliding window and a convolutional neural network; reusing a part of hidden layers in the previous identification network and the long-short-term memory cycle network to perform health state estimation on an analog circuit in degradation; and evaluating prediction accuracy. The health state of the analog circuit can be effectively estimated while the fault state starting point of the analog circuit is accurately recognized, and the invention has the advantages of being high in operation efficiency and accurate in recognition.

Description

technical field [0001] The invention belongs to the field of power electronic circuit fault prediction, and more specifically relates to a complex analog circuit fault identification and estimation method and system. Background technique [0002] With the development of the ubiquitous power Internet of Things, the degree of integration of automobiles, aircraft, and power systems is becoming higher and higher, and the interaction between internal components of the system is becoming more and more complex. These have brought challenges to the clean and stable operation of power equipment. Therefore, the degradation of analog circuits needs to be concerned. [0003] Degradation may occur in all stages of analog circuit operation, and timely measures can be taken for the identification of early circuit degradation to avoid further economic and property losses. At the same time, the original equipment can be preserved to the greatest extent to ensure the normal operation of exp...

AI Technical Summary

Problems solved by technology

Although the hybrid forecasting method can take into account the advantages of the two types of methods, due to its dependence on the model-based forecasting method, the internal computational complexity is still high, the cost of comprehensive modeling is high, and the parameter dependence is strong.

Images