scholarly journals A Neural Network Classifier with Multi-Valued Neurons for Analog Circuit Fault Diagnosis

Electronics ◽  
2021 ◽  
Vol 10 (3) ◽  
pp. 349
Author(s):  
Igor Aizenberg ◽  
Riccardo Belardi ◽  
Marco Bindi ◽  
Francesco Grasso ◽  
Stefano Manetti ◽  
...  
Keyword(s):  
Analog Circuits ◽  
Analog Circuit ◽  
Machine Learning Techniques ◽  
Rigorous Approach ◽  
Testability Analysis ◽  
Learning Techniques ◽  
Fabrication Tolerances ◽  
Circuit Fault Diagnosis ◽  
Faulty Component ◽  
Ambiguity Groups

In this paper, we present a new method designed to recognize single parametric faults in analog circuits. The technique follows a rigorous approach constituted by three sequential steps: calculating the testability and extracting the ambiguity groups of the circuit under test (CUT); localizing the failure and putting it in the correct fault class (FC) via multi-frequency measurements or simulations; and (optional) estimating the value of the faulty component. The fabrication tolerances of the healthy components are taken into account in every step of the procedure. The work combines machine learning techniques, used for classification and approximation, with testability analysis procedures for analog circuits.

scholarly journals Test Point Selection Method for Analog Circuit Fault Diagnosis Based on Similarity Coefficient

2018 ◽  
Vol 2018 ◽  
pp. 1-11 ◽  
Author(s):  
Qingfeng Ma ◽  
Yuzhu He ◽  
Fuqiang Zhou ◽  
Ping Song
Keyword(s):  
Analog Circuit ◽  
Selection Method ◽  
Test Point ◽  
Similarity Coefficient ◽  
Fault Isolation ◽  
Point Selection ◽  
Testability Analysis ◽  
Test Point Selection ◽  
Point Set ◽  
Circuit Fault Diagnosis

The demand for testability analysis has increased with the integration densities and complexity of circuits. As an important part of testability analysis, the test point selection method needs to be researched in depth. A new similarity coefficient criterion is proposed to determine the fault isolation degree because output responses of a circuit with component tolerance are approximately subject to the normal distribution. Then, a new test point selection method is proposed based on the fault-pair similarity coefficient criterion information table. Simulation experiments are used to validate the accuracy of the proposed method in terms of the optimum test point set and fault isolation degree. The results show that the proposed method improves the performance of test point selection by comparing with the other reported methods.

scholarly journals An Analog Circuit Fault Diagnosis Method Based on Circle Model and Extreme Learning Machine

2020 ◽  
Vol 10 (7) ◽  
pp. 2386
Author(s):  
Sumin Guo ◽  
Bo Wu ◽  
Jingyu Zhou ◽  
Hongyu Li ◽  
Chunjian Su ◽  
...  
Keyword(s):  
Fault Diagnosis ◽  
Extreme Learning Machine ◽  
Analog Circuits ◽  
Analog Circuit ◽  
Classification Performance ◽  
Fault Classification ◽  
Diagnosis Method ◽  
Circuit Fault Diagnosis ◽  
Learning Machine ◽  
Circle Model

The fault diagnosis of analog circuits faces problems, such as inefficient feature extraction and fault identification. To solve the problems, this paper combines the circle model and the extreme learning machine (ELM) into a fault diagnosis method for the linear analog circuit. Firstly, a circle model for the voltage features of fault elements was established in the complex domain, according to the relationship between the circuit response, element position and circuit topology. To eliminate the impacts of tolerances and signal aliasing, the 3D feature was introduced to make the indistinguishable features in fuzzy groups distinguishable. Fault feature separability is very important to improve the fault diagnosis accuracy. In addition, an effective classier can improve the precision and the time taken. With less computational complexity and a simpler process, the ELM algorithm has a fast speed and a good classification performance. The effectiveness of the proposed method is verified by simulation. The simulation results show the ELM-based algorithm classifier with the circle model can enhance precision and reduce time taken by about 80% in comparison with other methods for analog circuit fault diagnosis. To sum up, this proposed method offers a fault diagnosis method that reduces the complexity in generating fault features, improves the isolation probability of faults, speeds up fault classification, and simplifies fault testing.

scholarly journals Fault Diagnosis of Analog Circuits Based on CFNN

2012 ◽  
Vol 6-7 ◽  
pp. 1045-1050
Author(s):  
Mei Rong Liu ◽  
Yi Gang He ◽  
Xiang Xin Li
Keyword(s):  
Fault Diagnosis ◽  
Analog Circuits ◽  
Analog Circuit ◽  
Local Optimum ◽  
Chaotic Mapping ◽  
Movement Characteristic ◽  
Fuzzy Neural ◽  
Global Movement ◽  
Diagnosis Method ◽  
Circuit Fault Diagnosis

An analog circuits fault diagnosis method based on chaotic fuzzy neural network (CFNN) is presented. The method uses the advantage of the global movement characteristic inherent in chaos to overcome the shortcomings that BPNN is usually trapped to a local optimum and it has a low speed of convergence weights. The chaotic mapping was added into BPNN algorithm, and the initial value of the network was selected. The algorithm can effectively and reliably be used in analog circuit fault diagnosis by comparing the two methods and analyzing the results of the example.

Analog Circuit Intelligent Fault Diagnosis Based on PCA and OAOSVM

2012 ◽  
Vol 468-471 ◽  
pp. 802-806 ◽  
Author(s):  
Ke Guo ◽  
Yi Zhu ◽  
Ye San
Keyword(s):  
Principal Component Analysis ◽  
Fault Diagnosis ◽  
Analog Circuits ◽  
Analog Circuit ◽  
Principal Component ◽  
Electronic Systems ◽  
Analysis Technique ◽  
Fault Features ◽  
Major Fault ◽  
Circuit Fault Diagnosis

Fault diagnosis of analog circuits is essential for guaranteeing the reliability and maintainability of electronic systems. Analog circuit fault diagnosis can be regarded as a pattern recognition issue and addressed by one-against-one SVM. In order to obtain a good SVM-based fault classifier, the principal component analysis technique is adopted to capture the major fault features. The extracted fault features are then used as the inputs of SVM to solve fault diagnosis problem. The effectiveness of the proposed method is verified by the experimental results.

The Study of Test Stimulus Optimization of Analog Circuit Based on AS-PSO Hybrid Algorithm

2013 ◽  
Vol 303-306 ◽  
pp. 582-587
Author(s):  
Hai Jun Lin ◽  
Qi Gao Wang ◽  
Ting Yu Sun ◽  
Ming Chao Dai ◽  
Xu Hui Zhang
Keyword(s):  
Analog Circuits ◽  
Hybrid Algorithm ◽  
Euclidean Distance ◽  
Analog Circuit ◽  
Fitness Function ◽  
Volterra Kernel ◽  
Novel Approach ◽  
Swarm Algorithms ◽  
Faults Diagnosis ◽  
Circuit Fault Diagnosis

This paper proposes a novel approach to diagnosis the faults in analog circuits based on Volterra kernel and ant colony-particle swarm algorithms. In the analog circuit fault diagnosis, we use the Volterra kernel as the feature vector which makes the characteristic vector lumped Euclidean distance in serials of fault states under the same excitation signals as the fitness function. And the optimized the parameters are used to stimulate the multi- frequency sinusoidal signal. The AS-PSO hybrid algorithm is performed to find the best excitation signal parameters. Experimental results show that the proposed approach can achieve good faults diagnosis results.

scholarly journals Analog Circuit Fault Diagnosis Using a Novel Variant of aConvolutional Neural Network

Algorithms ◽  
2021 ◽  
Vol 15 (1) ◽  
pp. 17
Author(s):  
Liang Han ◽  
Feng Liu ◽  
Kaifeng Chen
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Convolutional Neural Network ◽  
Analog Circuits ◽  
Analog Circuit ◽  
Electronic Systems ◽  
Average Difference ◽  
Multi Scale ◽  
Novel Variant ◽  
Circuit Fault Diagnosis

Analog circuits play an important role in modern electronic systems. Aiming to accurately diagnose the faults of analog circuits, this paper proposes a novel variant of a convolutional neural network, namely, a multi-scale convolutional neural network with a selective kernel (MSCNN-SK). In MSCNN-SK, a multi-scale average difference layer is developed to compute multi-scale average difference sequences, and then these sequences are taken as the input of the model, which enables it to mine potential fault characteristics. In addition, a dynamic convolution kernel selection mechanism is introduced to adaptively adjust the receptive field, so that the feature extraction ability of MSCNN-SK is enhanced. Based on two well-known fault diagnosis circuits, comparison experiments are conducted, and experimental results show that our proposed method achieves higher performance.

Methods of Handling the Aliasing and Tolerance Problem for a New Unified Fault Modeling Technique in Analog-Circuit Fault Diagnosis

2014 ◽  
Vol 981 ◽  
pp. 11-16 ◽  
Author(s):  
Yuan Gao ◽  
Cheng Lin Yang ◽  
Shu Lin Tian
Keyword(s):  
Fault Diagnosis ◽  
Analog Circuits ◽  
Analog Circuit ◽  
Fault Modeling ◽  
Modeling Method ◽  
Soft Fault ◽  
The Difference ◽  
Circuit Fault Diagnosis ◽  
Nonlinear Analog Circuits ◽  
Nonlinear Analog

Soft fault diagnosis and tolerance are two challenging problems in analog circuit fault diagnosis. This paper proposes approaches to solve these two problems. First, a complex field modeling method and its theoretical proof are presented. This fault modeling method is applicable to both hard (open or short) and soft (parametric) faults. It is also applicable to either linear or nonlinear analog circuits. Then, the parameter tolerance is taken into consideration. A frequency selection method is proposed to maximize the difference between the faults fault signature. Hence, the aliasing problem arise from tolerance can be mitigated. The effectiveness of the proposed approaches is verified by simulated results.

Analog Circuit Fault Diagnosis Method Based on Characteristic Layer Fusion and Improved Potential Energy Function Classification

2013 ◽  
Vol 765-767 ◽  
pp. 2314-2318
Author(s):  
Xin Ying Li ◽  
Li Jie Sun ◽  
Li Zhang ◽  
Da Bo Zhang
Keyword(s):  
Fault Diagnosis ◽  
Potential Energy ◽  
Analog Circuits ◽  
Energy Function ◽  
Analog Circuit ◽  
Potential Energy Function ◽  
Fusion Method ◽  
Classification Problems ◽  
Reduction Effect ◽  
Circuit Fault Diagnosis

To circuit system with a transition state from normal to fault, this paper presents "sub-health" concept to describe it, and the experiments add sub-health diagnosis type. To problem of diagnosis difficulty caused by data overlapping due to tolerance existing in analog circuits, characteristic layer fusion method is selected for feature extraction, and put forward the distance evaluation factor for feature selection. Then potential energy function classification is adopted to diagnose faults, and principle of binary tree is combined with potential energy function classification to solve multiple classification problems. The experiments adopt BP neural network to compare and verify that the method proposed is effective. The results fully illustrate that characteristic layer fusion method can extract fault features effectively, distance evaluation factor has achieved a good dimension reduction effect, and improved potential energy function classification realizes soft fault diagnosis accurately.

Analog Circuit Fault Diagnosis Using LDA and OAOSVM Approach

2012 ◽  
Vol 490-495 ◽  
pp. 1130-1134 ◽  
Author(s):  
Ke Guo ◽  
Yi Zhu ◽  
Ye San
Keyword(s):  
Fault Diagnosis ◽  
Discriminant Analysis ◽  
Linear Discriminant Analysis ◽  
Analog Circuits ◽  
Analog Circuit ◽  
Linear Discriminant ◽  
Analysis Technique ◽  
Fault Features ◽  
Major Fault ◽  
Circuit Fault Diagnosis

Fault diagnosis of analog circuits is essential for guaranteeing the reliability and maintainability of electronic systems. Analog circuit fault diagnosis can be regarded as a pattern recognition issue and addressed by Multi-class SVM. A novel diagnosis technique based on linear discriminant analysis and one-against-one SVM is proposed in the paper. In order to obtain a good SVM-based fault classifier, the linear discriminant analysis technique is adopted to capture the major fault features. The extracted fault features are then used as the inputs of one-against-one SVMs to solve fault diagnosis issue. The effectiveness of the proposed approach is demonstrated by the experimental results.

Sign in / Sign up

Export Citation Format

Share Document