An investigation of a hybrid CBR method for failure mechanisms identification

Abstract The correct identification of the underlying mechanism of a failure is an important step in the entire failure analysis process. This study investigates the performance of a hybrid case-based reasoning method that integrates a multi-layer perceptron (MLP) neural network with case-based reasoning (CBR) for the automatic identification of failure mechanisms. The trained MLP neural network provides the basis to obtain attribute weights, whereas CBR serves as a classifier to identify the failure mechanism. Different parameters of the hybrid methods were varied to study their effect. The results indicate that better performance could be (but not always) achieved by the proposed hybrid method than that using conventional CBR or MLP neural networks alone.

[1]  C. R. Mount,et al.  A case-based reasoning system for identifying failure mechanisms , 2000 .

[2]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[3]  James H. Garrett,et al.  Engineering applications of neural networks , 1993, J. Intell. Manuf..

[4]  T.Warren Liao,et al.  An integrated database and expert system for failure mechanism identification: Part I—automated knowledge acquisition , 1999 .

[5]  Kenjiro Komai,et al.  Recognition of different fracture surface morphologies using computer image processing technique , 1993 .

[6]  T. Warren Liao,et al.  Automated Extraction of Welds from Digitized Radiographic Images Based on MLP Neural Networks , 1997, Appl. Artif. Intell..

[7]  Siu Cheung Hui,et al.  A Multimedia Information System For IC Failure Analysis , 1993, Comput. J..

[8]  T.Warren Liao,et al.  An integrated database and expert system for failure mechanism identification: Part II—the system and performance testing , 1999 .

[9]  Sang-Chan Park,et al.  A hybrid approach of neural network and memory-based learning to data mining , 2000, IEEE Trans. Neural Networks Learn. Syst..

[10]  T. Warren Liao,et al.  Flexural strength of creep feed ground ceramics: general pattern, ductile-brittle transition and mlp modeling , 1998 .

[11]  T. Warren Liao,et al.  Manufacturing Process Modeling and Optimization Based on Multi-Layer Perceptron Network , 1998 .

[12]  P. J Graham-Jones,et al.  Expert and knowledge-based systems in failure analysis , 1995 .

[13]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[14]  Zhiming Zhang,et al.  Similarity Measures for Retrieval in Case-Based Reasoning Systems , 1998, Appl. Artif. Intell..

[15]  W. F. Caley,et al.  New industrial mineral opportunities in southeastern Ontario , 1990 .

[16]  Bernard Widrow,et al.  Neural networks: applications in industry, business and science , 1994, CACM.

[17]  T. Warren Liao.  MLP neural network models of CMM measuring processes , 1996, J. Intell. Manuf..

[18]  Ken-ichi Funahashi,et al.  On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

[19]  Roy H. Propst,et al.  Efficient Computer-Aided Failure Analysis of Integrated Circuits using Scanning Electron Microscopy , 1985, IEEE Transactions on Reliability.

[20]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[21]  Janet L. Kolodner,et al.  Case-Based Reasoning , 1989, IJCAI 1989.

[22]  Farhi Marir,et al.  Case-based reasoning: A review , 1994, The Knowledge Engineering Review.

[23]  Kurt Hornik,et al.  Approximation capabilities of multilayer feedforward networks , 1991, Neural Networks.