Title :
Machine learning algorithms for fault diagnosis in analog circuits
Author :
Rajan, Vivek ; Jie Yang ; Chakrabarty, Sumangal ; Pattipati, Krishna
Author_Institution :
Dept. of Electr. & Syst. Eng., Connecticut Univ., Storrs, CT, USA
Abstract :
In this paper, we investigate and systematically evaluate two machine learning algorithms for analog fault detection and isolation: (1) restricted Coloumb energy (RCE) neural network, and (2) learning vector quantization (LVQ). The RCE and LVQ models excel at recognition and classification types of problems. In order to evaluate the efficacy of the two learning algorithms, we have developed a software tool, termed Virtual Test-Bench (VTB), which generates diagnostic information for analog circuits represented by SPICE descriptions. The RCE and LVQ models render themselves more naturally to online monitoring, where measurement data from various sensors is continuously available. The effectiveness of RCE and LVQ is demonstrated on illustrative example circuits
Keywords :
analogue circuits; circuit analysis computing; circuit testing; fault location; learning (artificial intelligence); neural nets; pattern classification; vector quantisation; LVQ; RCE neural network; SPICE descriptions; VQ; VTB; Virtual Test-Bench; analog circuits; analog fault detection; analog fault isolation; classification; fault diagnosis; learning vector quantization; machine learning algorithms; online monitoring; recognition; restricted Coloumb energy neural network; software tool; Analog circuits; Circuit testing; Electrical fault detection; Fault diagnosis; Machine learning; Machine learning algorithms; Neural networks; Software algorithms; Software tools; Vector quantization;
Conference_Titel :
Systems, Man, and Cybernetics, 1998. 1998 IEEE International Conference on
Conference_Location :
San Diego, CA
Print_ISBN :
0-7803-4778-1
DOI :
10.1109/ICSMC.1998.728169
