GA Optimized Binary Tree SVM for Analog Circuit Fault Diagnosis

2012 ◽  
Vol 235 ◽  
pp. 423-427 ◽  
Author(s):  
Bao Yu Dong ◽  
Guang Ren

This paper presents a novel method of analog circuit fault diagnosis based on genetic algorithm (GA) optimized binary tree support vector machine (SVM). The real-valued coding genetic algorithm is used to optimize the binary tree structure. In optimization algorithm, we use roulette wheel selection operator, partially mapped crossover operator, inversion mutation operator. In simulation experiment, we use Monte-carlo analysis for 40kHz Sallen-Key bandpass filter and get transient response of ten faults. Then we extract feature vector by db3 wavelet packet transform and principal component analysis (PCA), and diagnose circuit faults by different SVM methods. Experiment results show the proposed method has the better classification accuracy than one-against-one (o-a-o), one-against-rest (o-a-r), Directed Acyclic Graph SVM (DAGSVM) and binary tree SVM (BT-SVM). It is suitable for practical use.

2012 ◽  
Vol 591-593 ◽  
pp. 1414-1417 ◽  
Author(s):  
Bao Yu Dong ◽  
Guang Ren

This paper presents a novel method of analog circuit fault diagnosis using AdaBoost with SVM-based component classifiers. We use binary-SVMs of o-a-r SVM as weak classifiers and design appropriate structure of SVM ensemble. Tent map is used to adjust parameters of SVM component classifiers for maintaining the diversity of weak classifiers. In simulation experiment, we use Monte-carlo analysis for 40kHz Sallen-Key bandpass filter and get transient response of thirteen faults. We extract feature vector by db3 wavelet packet transform and principal component analysis (PCA), and diagnose circuit faults by different methods. Simulation results show that the proposed method has the higher classification accuracy compared with other SVM methods. The generalization performance of ensemble method is good. It is suitable for practical use


2014 ◽  
Vol 1055 ◽  
pp. 99-102
Author(s):  
Jun Shi ◽  
Tong Shu

Analog circuit fault diagnosis is essentially a multiple state pattern classification problems. The traditional support vector machine classifier is for binary classification problems. In more than three kinds of commonly used class promotion model. This paper adopted the decision directed acyclic graph of multi-value classification algorithm. Multi-fault SVM classifier model is established. And the kernel function selection and nuclear parameter determination method were studied. Based on this model, support vector machine is used for analog circuit fault diagnosis given the basic idea and implementation steps. In analog circuit fault feature extraction technology, the effective sample point voltage amplitude response signal as well as the fault characteristic samples are extracted by wavelet packet decomposition of the energy spectrum method to extract the signal fault characteristics as the fault samples, formed based on effective sampling points. The SVM classifier is based on wavelet packet decomposition and the SVM classifier two methods of analog circuit fault diagnosis.


Author(s):  
Jianfeng Jiang

Objective: In order to diagnose the analog circuit fault correctly, an analog circuit fault diagnosis approach on basis of wavelet-based fractal analysis and multiple kernel support vector machine (MKSVM) is presented in the paper. Methods: Time responses of the circuit under different faults are measured, and then wavelet-based fractal analysis is used to process the collected time responses for the purpose of generating features for the signals. Kernel principal component analysis (KPCA) is applied to reduce the features’ dimensionality. Afterwards, features are divided into training data and testing data. MKSVM with its multiple parameters optimized by chaos particle swarm optimization (CPSO) algorithm is utilized to construct an analog circuit fault diagnosis model based on the testing data. Results: The proposed analog diagnosis approach is revealed by a four opamp biquad high-pass filter fault diagnosis simulation. Conclusion: The approach outperforms other commonly used methods in the comparisons.


Electronics ◽  
2021 ◽  
Vol 10 (12) ◽  
pp. 1496
Author(s):  
Hao Liang ◽  
Yiman Zhu ◽  
Dongyang Zhang ◽  
Le Chang ◽  
Yuming Lu ◽  
...  

In analog circuit, the component parameters have tolerances and the fault component parameters present a wide distribution, which brings obstacle to classification diagnosis. To tackle this problem, this article proposes a soft fault diagnosis method combining the improved barnacles mating optimizer(BMO) algorithm with the support vector machine (SVM) classifier, which can achieve the minimum redundancy and maximum relevance for feature dimension reduction with fuzzy mutual information. To be concrete, first, the improved barnacles mating optimizer algorithm is used to optimize the parameters for learning and classification. We adopt six test functions that are on three data sets from the University of California, Irvine (UCI) machine learning repository to test the performance of SVM classifier with five different optimization algorithms. The results show that the SVM classifier combined with the improved barnacles mating optimizer algorithm is characterized with high accuracy in classification. Second, fuzzy mutual information, enhanced minimum redundancy, and maximum relevance principle are applied to reduce the dimension of the feature vector. Finally, a circuit experiment is carried out to verify that the proposed method can achieve fault classification effectively when the fault parameters are both fixed and distributed. The accuracy of the proposed fault diagnosis method is 92.9% when the fault parameters are distributed, which is 1.8% higher than other classifiers on average. When the fault parameters are fixed, the accuracy rate is 99.07%, which is 0.7% higher than other classifiers on average.


2014 ◽  
Vol 981 ◽  
pp. 3-10 ◽  
Author(s):  
Yuan Gao ◽  
Cheng Lin Yang ◽  
Shu Lin Tian

Soft fault diagnosis and tolerance are two challenging problems in linear analog circuit fault diagnosis. To solve these problems, a phasor analysis based fault modeling method and its theoretical proof are presented at first. Second, to form fault feature data base, the differential voltage phasor ratio (DVPR) is decomposed into real and imaginary parts. Optimal feature selection method and testability analysis method are used to determine the optimal fault feature data base. Statistical experiments prove that the proposed fault modeling method can improve the fault diagnosis robustness. Then, Multi-class support vector machine (SVM) classifiers are used for fault diagnosis. The effectiveness of the proposed approaches is verified by both simulated and experimental results.


2018 ◽  
Vol 173 ◽  
pp. 03090
Author(s):  
WANG Ying-chen ◽  
DUAN Xiu-sheng

Aiming at the problem that the traditional intelligent fault diagnosis method is overly dependent on feature extraction and the lack of generalization ability, deep belief network is proposed for the fault diagnosis of the analog circuit; Then, by analyzing the deficiency of deep belief network application, a Gaussian deep belief network based on adaptive learning rate is proposed. The automatic adjustment learning step is adopted to further improve fault diagnosis efficiency and diagnosis accuracy; Finally, particle swarm support vector machine to extract the fault characteristics to identify. The simulation results of circuit fault diagnosis show that the algorithm has faster convergence speed and higher fault diagnosis accuracy.


2014 ◽  
Vol 540 ◽  
pp. 456-459
Author(s):  
Hu Cheng Zhao ◽  
Hao Lin Cui ◽  
Zhi Bin Chen

To obtain the improvement of analog circuit fault diagnosis, a RBF diagnosis model based on an Adaptive Genetic Algorithm (AGA) is proposed. First an adaptive mechanism about crossover and mutation probability is introduced into the traditional genetic algorithm, and then AGA algorithm is used to optimize the network parameters such as center, width and connection weight. The experiment simulation indicates that the proposed model has exact diagnosis characteristic.


Sign in / Sign up

Export Citation Format

Share Document