Analog circuit fault diagnosis method based on wavelet packet analysis and Hopfield network

Abstract

The invention provides an analog circuit fault diagnosis method based on wavelet packet analysis and the Hopfield network. The method includes data obtaining, feature extraction and fault classification, wherein data obtaining includes performing data sampling for output response of an analog circuit respectively through simulation program with integrated circuit emphasis (SPICE) simulation and a data collection plate connected at a practical circuit terminal so as to obtain an ideal output response data set and an actually-measured output response data set; feature extraction includes performing wavelet packet decomposition with ideal circuit output response and actually-measured output response respectively serving as a training data set and a test data set, and leading energy values obtained by decomposed wavelet coefficient through energy calculating to form feature vectors of corresponding faults; and fault classification includes leading the feature vectors of all samples to be subjected to Hopfield coding and then submitting the coded feature vectors to the Hopfield network to achieve accurate and fast fault classification. The analog circuit fault diagnosis method is good in fault feature pretreatment effect aiming at hard faults with weak amplitude response and soft faults with large amplitude response, and the newly defined energy function and the newly defined coding rule are remarkable in influence on fault diagnosis accuracy of the analog circuit.

Description

technical field [0001] The invention relates to an analog circuit fault diagnosis method, in particular to an analog circuit fault diagnosis method based on wavelet packet analysis and Hopfield network. Background technique [0002] In the signal input and output between the system and the outside world, the analog circuit plays a key role. Taking the control system as an example, no matter whether its controller is replaced by digital technology or not, the system needs to obtain input signals from external sensors and generate actual output through actuators. The transmission, filtering, amplification, and conversion of analog signals are the basic functions necessary for many complex systems. Therefore, the reliability of analog circuits is one of the important factors affecting the reliability of many complex industrial systems, and the fault diagnosis of analog circuits has always been a research focus in the field of electronics industry. [0003] In fact, due to the...

AI Technical Summary

Problems solved by technology

Literature discloses related technologies, for example: Catelani M, Fort A. Soft fault detection and isolation in analog circuits: some results and a comparison between a fuzzy approach and radial basis function networks. IEEE Trans. Instrum. Meas., 2002, 51 (2 ):196-202.; Spina R, Upadhyaya S. Linear circuit fault diagnosis using neuromorphic analyzer. IEEE Trans. Circuits Syst. II, 1997,44(3):188-196.; Maidon Y, Jervis B W, Fouillat, Lesage P S.Using artificial neural networks or lagrange interpolation to characterize the faults in an analog circuit:an experimental study.IEEE Trans.Instrum.Meas.,1999,48(5):932-938.; Negnevitsky M,Pavlovsky V.Neural networks approach to online identification of multiple failures of protection systems. IEEE Trans. Power Delivery, 2005, 20(2): 588-594. They all directly use the circuit output response without any processing as the input of the neural network, and the diagnostic accuracy is relatively high. Low, complex network structure, long training time; another example: Mehran A, Farzan A.A modular fault-diagnostic system for analog electronic circuits using neural networks with wavelet transform as a preprocessor.IEEE Trans.Instrum.Meas.,2007,5(5 ): 1546-1554, divide the analog circuit into different modules according to the types of faults, each module corresponds to a neural network, and each The output response of the module is subjected to principal component analysis as the input of the neural network, which improves the accuracy of fault diagnosis, but increases the network overhead; another example: Aminian M, Aminian F. Neural network based analog circuit fault diagnosis using wavelet transform as preprocessor .IEEE Trans.CircuitsSyst.II, Analog Digit.Signal Process., 2000,47(2):151-156. Submit the low-frequency wavelet coefficients of the circuit response after the principal component analysis to the neural network as the fault feature, although improving the diagnosis accuracy, but the complexity of the network has not been substantially improved; in addition, "A multi-wavelet neural network algorithm for fault diagnosis of analog circuits". Wang Junfeng, Zhang Weiqiang, Song Guoxiang. Journal of Electrotechnical Society, 2006, 21(1): 33-36. The complexity of the neural network is reduced by calculating the energy value of the wavelet coefficient and using it as a candidate fault feature, but the energy value is small and the feature distinction is not obvious

Images