A multiple heterogeneous kernel RVM approach for analog circuit fault prognostic

This paper presents a multiple heterogeneous kernel relevance vector machine (MHKRVM) approach for analog circuit fault prognostic. Compared to other kernel learning methods, multiple kernel learning method produces the optimal kernel function because many effective kernels’ combination always generates better generalization performance. By using the multiple heterogeneous kernel learning method, the proposed MHKRVM method’s kernel function holds its diversification. Meanwhile, the sparse weights of consisted basic kernels in the MHKRVM are helpful in prediction accuracy, and they are yielded through particle swarm optimization algorithm. Six fault prognostic cases are conducted to demonstrate the whole prognostic procedure, and prove that the presented MHKRVM can predict the trend of falling circuit elements’ health degree trajectories closely and estimate the remaining useful performance of failing circuit elements accurately.

[1]  Shih-Wei Lin,et al.  Particle swarm optimization for parameter determination and feature selection of support vector machines , 2008, Expert Syst. Appl..

[2]  Bin Gu,et al.  Incremental Support Vector Learning for Ordinal Regression , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[3]  Mohammed A. Alam,et al.  Prognostics of Failures in Embedded Planar Capacitors using Model-Based and Data-Driven Approaches , 2011 .

[4]  Sankalita Saha,et al.  Metrics for Offline Evaluation of Prognostic Performance , 2021, International Journal of Prognostics and Health Management.

[5]  Yigang He,et al.  A Novel Approach for Analog Circuit Fault Prognostics Based on Improved RVM , 2014, J. Electron. Test..

[6]  M. Pecht,et al.  Prognostics of ceramic capacitor temperature‐humidity‐bias reliability using Mahalanobis distance analysis , 2007 .

[7]  Russell C. Eberhart,et al.  A new optimizer using particle swarm theory , 1995, MHS'95. Proceedings of the Sixth International Symposium on Micro Machine and Human Science.

[8]  C. L. Philip Chen,et al.  Intelligent Prognostics for Battery Health Monitoring Using the Mean Entropy and Relevance Vector Machine , 2014, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[9]  Xingming Sun,et al.  Structural Minimax Probability Machine , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[10]  Maya R. Gupta,et al.  Learning kernels from indefinite similarities , 2009, ICML '09.

[11]  Zenglin Xu,et al.  Efficient Sparse Generalized Multiple Kernel Learning , 2011, IEEE Transactions on Neural Networks.

[12]  John McPhee,et al.  A survey of mathematics-based equivalent-circuit and electrochemical battery models for hybrid and electric vehicle simulation , 2014 .

[13]  Sheng Xiang,et al.  Prognostics of Lithium-Ion Batteries Based on Wavelet Denoising and DE-RVM , 2015, Comput. Intell. Neurosci..

[14]  Farzan Aminian,et al.  A Modular Fault-Diagnostic System for Analog Electronic Circuits Using Neural Networks With Wavelet Transform as a Preprocessor , 2007, IEEE Transactions on Instrumentation and Measurement.

[15]  Lianggui Feng,et al.  A novel neural-network approach of analog fault diagnosis based on kernel discriminant analysis and particle swarm optimization , 2012, Appl. Soft Comput..

[16]  Fan Yang,et al.  Support vector machine with genetic algorithm for machinery fault diagnosis of high voltage circuit breaker , 2011 .

[17]  Lianggui Feng,et al.  A novel linear ridgelet network approach for analog fault diagnosis using wavelet-based fractal analysis and kernel PCA as preprocessors , 2012 .

[18]  X. C. Guo,et al.  A novel LS-SVMs hyper-parameter selection based on particle swarm optimization , 2008, Neurocomputing.

[19]  Wei He,et al.  A Novel Approach for Diagnosis of Analog Circuit Fault by Using GMKL-SVM and PSO , 2016, J. Electron. Test..

[20]  Bing Long,et al.  Diagnostics and Prognostics Method for Analog Electronic Circuits , 2013, IEEE Transactions on Industrial Electronics.

[21]  Hui Luo,et al.  A SVDD approach of fuzzy classification for analog circuit fault diagnosis with FWT as preprocessor , 2011, Expert Syst. Appl..

[22]  Yichuang Sun,et al.  A New Neural-Network-Based Fault Diagnosis Approach for Analog Circuits by Using Kurtosis and Entropy as a Preprocessor , 2010, IEEE Transactions on Instrumentation and Measurement.

[23]  Ivor W. Tsang,et al.  Efficient hyperkernel learning using second-order cone programming , 2004, IEEE Transactions on Neural Networks.

[24]  Cheng Gao,et al.  Particle swarm optimization based RVM classifier for non-linear circuit fault diagnosis , 2012 .

[25]  Qiang Miao,et al.  Prognostics of lithium-ion batteries based on relevance vectors and a conditional three-parameter capacity degradation model , 2013 .

[26]  Franklin Bien,et al.  An adaptive technique to improve wireless power transfer for consumer electronics , 2012, 2012 IEEE International Conference on Consumer Electronics (ICCE).

[27]  Bo-Suk Yang,et al.  Application of relevance vector machine and logistic regression for machine degradation assessment , 2010 .

[28]  Min Li,et al.  Prognostics of Analog Filters Based on Particle Filters Using Frequency Features , 2013, J. Electron. Test..

[29]  Konstantinos Blekas,et al.  Under Consideration for Publication in Knowledge and Information Systems Sparse Regression Mixture Modeling with the Multi-kernel Relevance Vector Machine , 2022 .

[30]  Wei He,et al.  A Novel Approach To Diagnosis Of Analog Circuit Incipient Faults Based On KECA And OAO LSSVM , 2015 .

[31]  Yiqiang Chen,et al.  Building Sparse Multiple-Kernel SVM Classifiers , 2009, IEEE Transactions on Neural Networks.

[32]  N. Narendran,et al.  An Accelerated Test Method for Predicting the Useful Life of an LED Driver , 2011, IEEE Transactions on Power Electronics.

[33]  Jie-Sheng Wang,et al.  Feed-Forward Neural Network Soft-Sensor Modeling of Flotation Process Based on Particle Swarm Optimization and Gravitational Search Algorithm , 2015, Comput. Intell. Neurosci..

[34]  George Eastman House,et al.  Sparse Bayesian Learning and the Relevance Vector Machine , 2001 .

[35]  Jian Zhang,et al.  Energy-efficient data-gathering rendezvous algorithms with mobile sinks for wireless sensor networks , 2017, Int. J. Sens. Networks.

[36]  Zongguo Wen,et al.  Quantitative assessment of industrial symbiosis for the promotion of circular economy: a case study of the printed circuit boards industry in China's Suzhou New District , 2015 .

[37]  Bin Gu,et al.  A Robust Regularization Path Algorithm for $\nu $ -Support Vector Classification , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[38]  Mehryar Mohri,et al.  L2 Regularization for Learning Kernels , 2009, UAI.

[39]  Jieping Ye,et al.  Learning the Optimal Neighborhood Kernel for Classification , 2009, IJCAI.

[40]  Yue Shi,et al.  A modified particle swarm optimizer , 1998, 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98TH8360).

[41]  Wenfa Zhan,et al.  A new scheme of test data compression based on equal-run-length coding (ERLC) , 2012, Integr..