Multiple fault diagnosis of analog circuit using quantum hopfield neural network

Abstract

This paper address the multiple fault problem of analog circuit using quantum Hopfield neural network. The proposed quantum neural model, from the evolution of quantum states, gives a new interpretation of the associative memory mechanism in term of probability. The fault features are obtained by the wavelet packet analysis and energy calculation. The quantized ideal features of single fault and the actual features of multiple fault are regarded as quantum ground states and quantum excited states in the quantum space, respectively. Any excited state (multiple fault) in this space can be described as a superposition state of each quantum ground state with different probability amplitudes. The occurrence of this probability amplitude can be obtained by comparing the measurement matrix of the quantum-keyinput mode with the measurement matrix of the quantum memory prototype. The numerical experiments offer a good explanation of the appearing probability of multiple faults.

Review of Machine Learning Approaches In Fault Diagnosis applied to IoT Systems

“…-Unsupervised learning: the input data does not contain information about the desired output; the learning is carried out with rules that change the parameters of the network according to the input data. The associative memory learning algorithm for Hopfield Nets is an example [18].…”

Effectiveness of Selected Neural Network Structures Based on Axial Flux Analysis in Stator and Rotor Winding Incipient Fault Detection of Inverter-fed Induction Motors

“…In addition to the MLP network belonging to the feedforward structure category and SOM belonging to self-organizing networks, the use of recursive Hopfield network (RHN) has been presented. This network, usually associated with its special feature, namely associative memory, is mainly used in pattern recognition [39]. However, the authors of the paper [40] presented the possibility of using RHN in the errors' detection of servo-positioning systems.…”

“…For the most part of diagnostic applications of RHN, it can be found in the detection of electrical and electronic circuit faults. For example, in [39] the authors showed the possibility of detecting electronic system failures by using Wavelet Packet Transform (WPD) and the RHN. Therefore, in the present article, the possibility of using RHN to detect IM electrical failures has been tested (according to the authors' knowledge-for the first time in the literature).…”

Wavelet-Based Feature Extraction in Fault Diagnosis for Biquad High-Pass Filter Circuit

“…A well-trained diagnosis approach was based not only on an appropriate classification algorithm, but also on the large amount of training data that should cover every fault class as well as effective feature extracting process that is used to select the fault features. In the past decades, some effective classifiers based on genetic algorithms [8,9], artificial neural network [3,[10][11][12][13][14][15], wavelet theory [9,11,13], fuzzy theory [3,16], artificial immune system [17][18][19], support vector machine [9], particle filtering [20], and clonal selection algorithm [21] were widely reported, but there were just few researches about how to extract the fault feature from responses of circuits. In fact, it is a critical procedure and primary task for general-purpose PR-based diagnosis algorithms to find some effective methods and circuit-dependent fault feature extraction and construction approaches to reduce the dimension of input data and minimize its training and processing time.…”

“…The defect of retaining only one part of coefficients may lead to the loss of valid information, thus with high probability of ambiguity cases and low diagnosis ability. Although many researchers [11,13,15,21,28,29] used both low frequency approximation and detail coefficient from wavelet decomposition to construct the optimal feature factors, different processes were employed without convincing reasons. For instance, Li et al [15,29] selected Haar as mother wavelet and calculated the fault feature from the coefficients associated with level 3 Haar wavelet packet analysis.…”