Abstract
This paper presents parametric fault diagnosis in analog circuit using machine learning algorithm. Single and multiple parametric fault diagnosis based on Simulation before test approach are considered in this study. A benchmark State Variable Filter circuit has been used as an example circuit for experiment validations. Extreme learning machine based autoencoder (ELM-AE) is proposed in this paper for feature reduction and classification. The transfer function of the benchmark circuit is simulated by performing Monte-Carlo analysis, the features are obtained to form fault dictionary for single and double faults in such way that the dictionary contains unique values for faulty and fault free configuration of the circuit. The input test patterns from the fault dictionary which are required for testing are reduced to improve the classification by autoencoder. Autoencoder is used as pre-processor to learn and reduce the features before performing classification by the extreme learning machine (ELM) algorithm. The results obtained by the proposed algorithm is compared with the other ELM empirical models like extreme learning machine, kernel extreme learning machine and an evolutionary algorithm called self-adaptive evolutionary extreme learning machine to analyze the performance of the proposed algorithm. The experimental results show that the ELM-AE contributes the higher diagnosis accuracy than other ELM models referred in this paper.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Aminian M, Aminian F (2000) Neural-network based analog-circuit fault diagnosis using wavelet transform as pre-processor. IEEE Trans Circuits SystII Analog Digit Signal Process 47(2):151–156. https://doi.org/10.1109/82.823545
Aminian M, Aminian F (2007) 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. https://doi.org/10.1109/TIM.2007.904549
Aminian F, Aminian M, Collins HW (2002) Analog fault diagnosis of actual circuits using neural networks. IEEE Trans Instrum Meas 51(3):544–550. https://doi.org/10.1109/TIM.2002.1017726
Cao J, Lin Z, Huang GB (2012) Self-adaptive evolutionary extreme learning machine. Neural Process Lett 36(3):285–305. https://doi.org/10.1007/s11063-012-9236-y
Devarayanadurg G, Soma M (1995) Dynamic test signal design for analog IC. In Computer-Aided Design, ICCAD-95. Digest of Technical Papers, IEEE/ACM International Conference, 627–630. https://doi.org/10.1109/ICCAD.1995.480194
Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks”. Reports 313:504–507. https://doi.org/10.1126/science.1127647
Huang GB, Zhu QY, Siew CK (2006) Extreme learning machine: theory and applications. Neurocomputing 70:489–501. https://doi.org/10.1016/j.neucom.2005.12.126
Ji L, Hu X (2018) Analog circuit soft-fault diagnosis based on sensitivity analysis with minimum fault number rule. Analog Integr Circ Sig Process. https://doi.org/10.1007/s10470-018-1111.y
Jahangiri M, Razaghian F (2014) Fault detection in analogue circuits using hybrid evolutionary algorithm and neural network. Analog Integr Circuits Sig Process. https://doi.org/10.1007/s10470-014-0352-7
Kabisatpathy P, Barua A, Sinha S (2006) Fault diagnosis of analog integrated circuits. Springer, Dordrecht
Kalpana P, Gunavathi K (2009) Test generation based fault detection in analog VLSI circuits using neural network. ETRI J 31(2):209–214. https://doi.org/10.4218/etrij.09.0108.0383
Kumar A, Singh AP (2013) Fuzzy classifier for fault diagnosis in analog electronic circuits. ISA Trans 52(6):816–824. https://doi.org/10.1016/j.isatra.2013.06.006
Lekamalage L, Kasun C, Zhou H, Huang GB, Vong CM (2013) Representational learning with extreme learning machine for big data,1–4.
Long B, Xian W, Li M, Wang H (2014) Improved diagnostics for the incipient faults in analog circuits using LSSVM based on PSO algorithm with Mahalanobis distance. Neurocomputing 133:237–248. https://doi.org/10.1016/j.neucom.2013.11.012
Long T, Wang H, Long B (2011a) A classical parameter identification method and a modern test generation algorithm. Circuits Syst Signal Process 30(2):391–412. https://doi.org/10.1007/s00034-010-9228-y
Long T, Wang H, Long B (2011b) Test generation algorithm for analog systems based on support vector machine. SIViP 5(4):527–533. https://doi.org/10.1007/s11760-010-0168-6)
Ma Q, He Y, Zhou F (2016) A new decision tree approach of support vector machine for analog circuit fault diagnosis. Analog Integr Circ Sig Process. https://doi.org/10.1007/s10470-016-0775-4
Michal T, Stainslaw H (2019) A method for multiple soft fault diagnosis of linear analog circuits. Measurement. https://doi.org/10.1016/j.measurement.2018.09.001
Nagi N, Abraham JA (1992) Hierarchical fault modeling for analog and mixed-signal circuits. In VLSI Test Symposium,10th Anniversary. Design, Test and Application: ASICs and Systems-on-a-Chip Digest of Papers: 96–101. https://doi.org/10.1109/VTEST.1992.232731
Omar MS, Inoue K, Ahmed S, Lotfy S, Mohammed SS (2018) Autoencoder based features extraction for automatic classification of earthquakes and explosions. In: 17th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2018. https://doi.org/10.1109/ICIS.2018.8466464
Shanthi M, Bhuvaneswari MC (2016) Fault detection in state variable filter circuit using kernel extreme learning machine (KELM) algorithm. Informacije MIDEM 46(4)
Spina R, Upadhyaya S (1997) Linear circuit fault diagnosis using neuromorphic analyzers. IEEE Trans Circuits Syst II Analog Digit Sig Process 44(3):188–196. https://doi.org/10.1109/82.558453
Srdjan DD (2018) Analog circuit diagnosis based on the nullor concept and multiport description of/ the circuit. Analog Integr Circuits Sig Process. https://doi.org/10.1007/s10470-018-1123.7
Srimani S, Parai MK, Ghosh K, Rahaman H (2017) Parametric fault detection of analog circuits based on Bhattacharyya measure. Analog Integr Circ Sig Process. https://doi.org/10.1007/s10470-017-1052.x
Stopjakova V, Malosek P, Nag V (2006) Neural network based defect detection in analog and mixed IC using digital signal preprocessing. J Electr Eng 57(5):249–257
Tan Y, Sun Y, Yin X (2013) Analog fault diagnosis using S-transform preprocessor and a QNN classifier. Measurement 46(7):2174–2183. https://doi.org/10.1016/j.measurement.2013.03.002
Xiao Y, He Y (2010) A linear ridgelet network approach for fault diagnosis of analog circuit. Sci China Inf Sci 53(11):2251–2264. https://doi.org/10.1016/j.measurement.2011.11.018
Xiao Y, Feng L (2012) 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. https://doi.org/10.1016/j.measurement.2011.11.018)
Xiao Y, He Y (2011) A novel approach for analog fault diagnosis based on neural networks and improved kernel PCA. Neurocomputing 74(7):1102–1115. https://doi.org/10.1016/j.neucom.2010.12.003
Xie X, Li X, Bi D, Zhou Q, Xie S, Xie Y (2015) Analog circuits soft fault diagnosis using Renyi’s entropy. J Electron Test 31(2):217–224. https://doi.org/10.1007/s10836-015-5520-x
Yang C, Tian S, Long B, Chen F (2010) A novel test point selection for analog fault dictionary techniques. J Electron Test 26(5):523–534. https://doi.org/10.1007/s10836-010-5169-4
Yang C, Tian S, Long B (2009) Application of heuristic graph search to test-point selection for analog fault dictionary techniques. IEEE Trans Instrum Meas 58(7):2145–2158. https://doi.org/10.1109/TIM.2008.2006725
Yuan L, He Y, Huang J, Sun Y (2010) A new neural-network-based fault diagnosis approach for analog circuits by using kurtosis and entropy as a pre-processor. IEEE Trans Instr 59(3):586–595. https://doi.org/10.1109/TIM.2009.2025068
Yusheng C, Dawei Z, Yibin W, Gensheng P (2019) Multi-label learning with kernel extreme learning machine autoencoder. Knowl-Based Syst 4732:1–20. https://doi.org/10.1016/j.knosys.2019.04.002
Zahra EH, Amirhosein H, Seyed AG (2018) A fingerprint method for indoor localization using autoencoder based deep extreme learning machine. IEEE Sens Lett 2(1):1–4. https://doi.org/10.1109/LSENS.2017.2787651
Zhou J, Tain S, Yang C, Ren X (2014) Test generation algorithm for fault detection of analog circuits based on extreme learning machine. Comput Intell Neurosci Hindawi 2014:1–11. https://doi.org/10.1155/2014/740838
Author information
Authors and Affiliations
Corresponding author
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
Kalpana, V., Maheswar, R. & Nandakumar, E. Multiple parametric fault diagnosis using computational intelligence techniques in linear filter circuit. J Ambient Intell Human Comput 11, 5533–5545 (2020). https://doi.org/10.1007/s12652-020-01908-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12652-020-01908-0