Abstract
Correct diagnosing analog circuit fault is beneficial to the circuit’s health management, and its core challenge is extracting essential features from the circuit’s output signals. Wavelet transform is a classical features extraction method whose performance relies on its wavelet basis function deeply. However, there are no satisfying rules to discover an optimal wavelet basis function for wavelet transform. In this paper, an improved wavelet transform with optimal wavelet basis function selection strategy is proposed. In the strategy, the optimal wavelet basis function is selected based on calculating the distance score and mean score of its features, and the features extracted by the optimal wavelet basis function are considered as the best features of signals. Subsequently, the features are split into training data and testing data randomly and evenly. By using the training data, a multiple kernel extreme learning machine (MKELM) based diagnosing model is initialized, and the parameters of MKELM are yielded by using particle swarm optimization algorithm. Finally, the MKELM is used to identify the faults of testing data for the purpose of verifying its performance. Fault diagnosis experiments of three circuits are performed to show the proposed optimal wavelet basis function selection strategy and MKELM’s establishing process. Comparison experiments are performed to verify that the optimal wavelet basis function selection strategy is effective and MKELM is better than other classifiers in analog circuit fault diagnosis.
Similar content being viewed by others
Data Availability
Data in the work is available and collected in the laboratory of Anqing Normal University.
References
F. Aminian, M. Aminian, Fault diagnosis of analog circuits using Bayesian neural networks with wavelet transform as preprocessor. J. Electron. Test. 17(1), 29–36 (2001)
F. Aminian, M. Aminian, H.W. Collins, Analog fault diagnosis of actual circuits using neural networks. IEEE Trans. Instrum. Meas. 51(3), 544–550 (2002)
M. Aminian, F. Aminian, Neural-network based analog-circuit fault diagnosis using wavelet transform as preprocessor. IEEE Trans. Circuits. 47(2), 151–156 (2000)
M. Aminian, F. Aminian, A modular fault-diagnostic system for analog electronic circuits using neural networks with wavelet transform as a preprocessor. IEEE Trans. Instrum. Meas. 56(5), 1546–1554 (2007)
S. Arias-Guzman, O.A. Ruiz-Guzman, L.F. Garcia-Arias, M. Jaramillo-Gonzales, P.D. Cardona-Orozco, A.J. Ustariz-Farfan, E.A. Cano-Plata, A.F. Salazar-Jimenez, Analysis of voltage sag severity case study in an industrial circuit. IEEE Trans. Ind. Appl. 53(1), 15–21 (2017)
Y. Ding, W. Zhang, L. Yu, K. Lu, The accuracy and efficiency of GA and PSO optimization schemes on estimating reaction kinetic parameters of biomass pyrolysis. Energy 176, 582–588 (2019)
R. Djekidel, S.A. Bessedik, P. Spiteri, D. Mahi, Passive mitigation for magnetic coupling between HV power line and aerial pipeline using PSO algorithms optimization. Electr. Power Syst. Res. 165, 18–26 (2018)
S. Dong, J. Sheng, B. Tang, L. Zhong, X. Xu, L. Chen, Q. Hu, J. Luo, L. Zhao, R. Chen, Bearings in simulated space conditions running state detecton based on Tsallis entropy-KPCA and optimized fuzzy c-means model. Noise Control Eng. J. 65(2), 62–70 (2017)
E.M.N. Figueiredo, T.B. Ludermir, Investigating the use of alternative topologies on performance of the PSO-ELM. Neurocomputing 127, 4–12 (2014)
G.D. Goez, R.A. Velasquez, J.S. Botero, UAV route planning optimization using PSO implemented on microcontrollers. IEEE Lat. Am. Trans. 14(4), 1705–1710 (2016)
Y. Gu, J. Chanussot, X. Jia, J.A. Benediktsson, Multiple Kernel Learning for Hyperspectral Image classification: a review. IEEE Trans. Geosci. Remote 55(11), 6547–6565 (2017)
X. Hu, C.M. Martinez, Y. Yang, Charging, power management, and battery degradation mitigation in plug-in hybrid electric vehicles: a unified cost-optimal approach. Mech. Syst. Signal Process. 87, 4–16 (2017)
G.-B. Huang, Q.-Y. Zhu, C.-K. Siew, Extreme learning machine: theory and applications. Neurocomputing 70(1–3), 489–501 (2006)
J. Huang, X. Zhang, Z. Shuai, X. Zhang, P. Wang, L.H. Koh, J. Xiao, X. Tong, Robust circuit parameters design for the CLLC-type DC transformer in the hybrid AC–DC microgrid. IEEE Trans. Ind. Electron. 66(3), 1906–1918 (2019)
J.-H. Jeong, C.-W. Ha, J. Lim, J.-Y. Choi, Analysis and control of electromagnetic coupling effect of levitation and guidance systems for semi-high-speed maglev train considering current direction. IEEE Trans. Magn. 53(6), 1–4 (2017)
C. Jin, S.-W. Jin, L.-N. Qin, Attribute selection method based on a hybrid BPNN and PSO algorithms. Appl. Soft Comput. 12(8), 2147–2155 (2012)
J. Kennedy, R. Eberhart, Particle swarm optimization. In: Icnn95-international Conference on Neural Networks. IEEE, (2002)
Y. Lifen, H. Yigang, H. Jiaoying, S. Yichuang, A new neural-network-based fault diagnosis approach for analog circuits by using kurtosis and entropy as a preprocessor. IEEE Trans. Instrum. Meas. 59(3), 586–595 (2010)
Z. Liu, Z. Jia, C.-M. Vong, S. Bu, J. Han, X. Tang, Capturing high-discriminative fault features for electronics-rich analog system via deep learning. IEEE Trans. Ind. Inform. 13(3), 1213–1226 (2017)
X. Lu, H. Zhao, H. Lin, Q. Wu, Multifractal analysis for soft fault feature extraction of nonlinear analog circuits. Math. Probl. Eng. 2016, 1–7 (2016)
H. Luo, Y. Wang, J. Cui, A vague decision method for analog circuit fault diagnosis based on description sphere. Chin. J. Aeronaut. 24(6), 768–776 (2011)
Q. Ma, Y. He, F. Zhou, A new decision tree approach of support vector machine for analog circuit fault diagnosis. Analog Integr. Circuits Signal Process. 88(3), 455–463 (2016)
S. Ma, M. Chen, J. Wu, Y. Wang, B. Jia, Y. Jiang, High-voltage circuit breaker fault diagnosis using a hybrid feature transformation approach based on random forest and stacked autoencoder. IEEE Trans. Ind. Electron. 66(12), 9777–9788 (2019)
S. Ougiaroglou, K.I. Diamantaras, G. Evangelidis, Exploring the effect of data reduction on neural network and support vector machine classification. Neurocomputing 280, 101–110 (2018)
M. Pan, J. Jiang, Q. Kong, J. Shi, Q. Sheng, T. Zhou, Radar HRRP target recognition based on t-SNE segmentation and discriminant deep belief network. IEEE Geosci. Remote Sens. 14(9), 1609–1613 (2017)
D.H. Park, S. Shin, Y.K. Kim, Module packaging effects on MEMS airbag sensor performance for automobiles. Microelectron. Reliab. 79, 328–335 (2017)
M. Rico-Secades, E.L. Corominas, J. García, J. Ribas, A.J. Calleja, J.M. Alonso, J. Cardesín, Low cost electronic ballast for a 36-W fluorescent lamp based on a current-mode-controlled boost inverter for a 120-V DC bus power distribution. IEEE Trans. Power Electr. 21(4), 1099–1106 (2006)
D. Shi, J. Guo, L. Chen, C. Xia, Z. Yu, Y. Ai, C.M. Li, Y. Kang, Z. Wang, Differential microfluidic sensor on printed circuit board for biological cells analysis. Electrophoresis 36(16), 1854–1858 (2015)
S.M. Shokrolahi, A.T.N. Kazempour, A novel approach for fault detection of analog circuit by using improved EEMD. Analog Integr. Circuit Signal 98(3), 527–534 (2018)
K.R. Singh, S. Chaudhury, Efficient technique for rice grain classification using back-propagation neural network and wavelet decomposition. IET Comput. Vis. 10(8), 780–787 (2016)
R. Spina, S. Upadhyaya, Linear circuit fault diagnosis using neuromorphic analyzers. IEEE Trans. Circuits II 44(3), 188–196 (1997)
Y. Tan, Y. Sun, X. Yin, Analog fault diagnosis using S-transform preprocessor and a QNN classifier. Measurement 46(7), 2174–2183 (2013)
S. Tang, Z. Li, L. Chen, Fault detection in analog and mixed-signal circuits by using Hilbert-Huang transform and coherence analysis. Microelectron. J. 46(10), 893–899 (2015)
Q. Wang, Y. Gu, D. Tuia, Discriminative Multiple Kernel Learning for Hyperspectral Image Classification. IEEE Trans. Geosci. Remote Sens. 54(7), 3912–3927 (2016)
R. Wang, Y. Zhan, H. Zhou, Application of S transform in fault diagnosis of power electronics circuits. Sci. Iran. 19(3), 721–726 (2012)
Y. Xiao, L. Feng, A novel linear ridgelet network approach for analog fault diagnosis using wavelet-based fractal analysis and kernel PCA as preprocessors. Measurement 45(3), 297–310 (2012)
X. Xie, X. Li, D. Bi, Q. Zhou, S. Xie, Y. Xie, Analog circuits soft fault diagnosis using Rényi’s Entropy. J. Electron. Test. 31(2), 217–224 (2015)
Z. Xue, P. Du, H. Su, Harmonic analysis for hyperspectral image classification integrated With PSO optimized SVM. IEEE J-Stars 7(6), 2131–2146 (2014)
D. Yang, Z. Dong, L.H.I. Lim, L. Liu, Analyzing big time series data in solar engineering using features and PCA. Sol. Energy 153, 317–328 (2017)
W. Yu, Y. Sui, J. Wang, The faults diagnostic analysis for analog circuit based on FA-TM-ELM. J. Electron. Test. 32(4), 459–465 (2016)
C. Zhang, Y. He, S. Jiang, T. Wang, L. Yuan, B. Li, transformer fault diagnosis method based on self-powered RFID sensor Tag, DBN, and MKSVM. IEEE Sens. J. 19(18), 8202–8214 (2019)
C. Zhang, Y. He, L. Yuan, W. He, S. Xiang, Z. Li, A novel approach for diagnosis of analog circuit fault by using GMKL-SVM and PSO. J. Electron. Test. 32(5), 531–540 (2016)
C. Zhang, Y. He, L. Yuan, S. Xiang, Analog circuit incipient fault diagnosis method using DBN based features extraction. IEEE Access 6, 23053–23064 (2018)
J. Zhou, S. Tian, C. Yang, X. Ren, Test generation algorithm for fault detection of analog circuits based on extreme learning machine. Comput. Intell. Neurosci. 740838 (2014)
C. Zou, C. Manzie, D. Nesic, A framework for simplification of PDE-based lithium-ion battery models. IEEE Trans. Control Syst. Technol. 24(5), 1594–1609 (2016)
Acknowledgements
This work was supported by the National Natural Science Foundation of China (51607004, 51577046, 51777050), the State Key Program of National Natural Science Foundation of China (51637004), the national key research and development plan "important scientific instruments and equipment development" (2016YFF0102200), Equipment research project in advance (41402040301), the Natural Science Foundation of Hunan Province (2017JJ2080), the University Synergy Innovation Program of Anhui Province (GXXT-2019-002), Natural Science Research Project of Anhui Universities (KJ2020A0509), and Anhui Provincial Natural Science Foundation (2008085MF197).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Zhang, C., He, Y., Yang, T. et al. An Analog Circuit Fault Diagnosis Approach Based on Improved Wavelet Transform and MKELM. Circuits Syst Signal Process 41, 1255–1286 (2022). https://doi.org/10.1007/s00034-021-01842-2
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00034-021-01842-2