A combined clustering and neural network approach for analog multiple hard fault classification

被引:20
作者
El-Gamal, MA [1 ]
Abu El-Yazeed, MF
机构
[1] United Arab Emirates Univ, Dept Math & Comp Sci, Al Ain, U Arab Emirates
[2] United Arab Emirates Univ, Dept Phys, Al Ain, U Arab Emirates
来源
JOURNAL OF ELECTRONIC TESTING-THEORY AND APPLICATIONS | 1999年 / 14卷 / 03期
关键词
analog circuits; feature selection; multiple hard faults; fault clustering; fault classification; learning vector quantization neural networks;
D O I
10.1023/A:1008353901973
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
A new neural network-based fault classification strategy for hard multiple faults in analog circuits is proposed. The magnitude of the harmonics of the Fourier components of the circuit response at different test nodes due to a sinusoidal input signal are first measured or simulated. A selection criterion for determining the best components that describe the circuit behaviour under fault-free (nominal) and fault situations is presented. An algorithm that estimates the overlap between different faults in the measurement space is also introduced. The learning vector quantization neural network is then effectively trained to classify circuit faults. Performance measures reveal very high classification accuracy in both training and testing stages. Two different examples, which demonstrate the proposed strategy, are described.
引用
收藏
页码:207 / 217
页数:11
相关论文
共 23 条
[1]  
APSTEIN B, 1993, IEEE T COMPUT AID D, V12, P102
[2]   FAULT-DIAGNOSIS OF ANALOG CIRCUITS [J].
BANDLER, JW ;
SALAMA, AE .
PROCEEDINGS OF THE IEEE, 1985, 73 (08) :1279-1325
[3]   AN INTEGRATED NEURAL-NETWORK EXPERT-SYSTEM APPROACH FOR FAULT-DIAGNOSIS [J].
BECRAFT, WR ;
LEE, PL .
COMPUTERS & CHEMICAL ENGINEERING, 1993, 17 (10) :1001-1014
[4]  
DAGUE P, 1991, P 12 INT JOINT C ART, P1109
[5]  
ELGAMAL MA, 1990, THESIS OHIO U ATHENS
[6]  
ELGAMAL MA, 1998, P INT ICSC S ENG INT, V2, P227
[7]  
ELGAMAL MA, 1995, P IEEE INT S CIRCUIT, V3, P2019
[8]  
ELGAMAL MA, 1997, P IEEE INT C NEUR NE, V3, P1580
[9]   QUALITATIVE DYNAMIC DIAGNOSIS OF CIRCUITS [J].
FANNI, A ;
DIANA, P ;
GIUA, A ;
PEREZZANI, M .
AI EDAM-ARTIFICIAL INTELLIGENCE FOR ENGINEERING DESIGN ANALYSIS AND MANUFACTURING, 1993, 7 (01) :53-64
[10]  
FANNI A, 1996, NEURAL NETWORKS THEO, P745