Using neural networks and immune algorithms to find the optimal parameters for an IC wire bonding process

The wire bonding process is the key process in an IC chip-package. It is an urgent problem for IC chip-package industry to improve the wire bonding process capability. In this study, an integration of artificial neural networks (ANN) with artificial immune systems (AIS) is proposed to optimize parameters for an IC wire bonding process. The algorithm of AIS with memory cell and suppressor cell mechanisms is developed. The back-propagation ANN is used to establish the nonlinear multivariate relationships between the wire boning parameters and responses. Then a Taguchi method is applied to identify the critical parameters of AIS. Finally, the AIS algorithm is applied to find the optimal parameters by using the output of ANN as the affinity measure. A comparison between the result of the proposed AIS and that of a genetic algorithm (GA) is conducted in this study. The comparison shows that the searching quality of the proposed AIS is more effective than the GA in finding the optimal wire bonding process parameters.

[1]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[2]  Hiok Chai Quek,et al.  GA-TSKfnn: Parameters tuning of fuzzy neural network using genetic algorithms , 2005, Expert Syst. Appl..

[3]  Dipankar Dasgupta,et al.  Parallel Search for Multi-Modal FunctionOptimization with Diversity and Learningof Immune Algorithm , 1999 .

[4]  Koji Yamada,et al.  Immune algorithm for n-TSP , 1998, SMC'98 Conference Proceedings. 1998 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.98CH36218).

[5]  Chao-Ton Su,et al.  Optimal design for a ball grid array wire bonding process using a neuro-genetic approach , 2002 .

[6]  Leo Chau-Kuang Liau,et al.  Process optimization of gold stud bump manufacturing using artificial neural networks , 2005, Expert Syst. Appl..

[7]  Mitsuo Gen,et al.  Genetic algorithms and engineering design , 1997 .

[8]  Alireza Khotanzad,et al.  Adaptive fuzzy process control of integrated circuit wire bonding , 1999 .

[9]  Song-Yop Hahn,et al.  A study on comparison of optimization performances between immune algorithm and other heuristic algorithms , 1998 .

[10]  Ta-Cheng Chen,et al.  Immune algorithms-based approach for redundant reliability problems with multiple component choices , 2005, Comput. Ind..

[11]  Hong Xie,et al.  Process optimization using a fuzzy logic response surface method , 1994 .

[12]  Shang Hwa Hsu,et al.  An integrated approach to achieving optimal design of computer games , 2006, Expert Syst. Appl..

[13]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[14]  Jonathan Timmis,et al.  Artificial Immune Systems: A New Computational Intelligence Approach , 2003 .

[15]  Jonathan Timmis,et al.  Artificial immune systems - a new computational intelligence paradigm , 2002 .

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

[17]  Yu-Lung Lo,et al.  Integrated Taguchi method and neural network analysis of physical profiling in the wirebonding process , 2002 .

[18]  Li Pheng Khoo,et al.  Solving the assembly configuration problem for modular products using an immune algorithm approach , 2003 .

[19]  D. Dasgupta.  Artificial Immune Systems and Their Applications , 1998, Springer Berlin Heidelberg.

[20]  Jau-Liang Chen,et al.  A new approach in free air ball formation process parameters analysis , 2000 .