Using Neural Networks and Immune Algorithms to Find the OptimalParameters for an IC Wire Bonding Process

摘要

The wire bonding is the key process in an IC chip-package. It is an urgent problem for IC chip-package industry tornimprove the wire bonding process capability. In this study, an application of artificial neural networks (ANN) andrnartificial immune systems (AIS) is proposed to optimize parameters for the wire bonding process in order to achievernhighly level performance and quality. In this research, the algorithm of AIS with memory cell and suppressor cellrnmechanisms is developed. A back propagation ANN is used to establish the nonlinear multivariate relationshipsrnbetween the wire boning parameters and responses. Then a Taguchi method is applied to identify the criticalrnparameters of the AIS. Finally, the AIS is applied to find the most desired parameter settings by using the output ofrnANN as the affinity measure. A comparison between the proposed AIS and a genetic algorithm is conducted in thisrnstudy. The comparison shows that the searching quality of the proposed AIS is more effective than the GA in findingrnthe optimal wire bonding process parameters.