透過您的圖書館登入
IP:3.137.178.133
  • 期刊

A Process Parameters Determination Model by Integrating Artificial Neural Network and Ant Colony Optimization

整合神經網路與螞蟻群聚最佳化的製程參數決策模式設計

摘要


本研究主要提出一製程參數最佳化的方法。其方法以螞蟻群聚最佳化與資料挖掘為主;此外以類神經網路來做為製程模擬的技術。然而類神經網路整個建模的過程為黑箱作業,使得需靠著能見度(visibility)進行找解的螞蟻群聚最佳化,在發展演算法時會遇到瓶頸。因此,本研究目的在於以類神經網路為模擬工具下的螞蟻群聚最佳化演算架構,主要藉由資料挖掘中的決策樹來萃取出類神經網路的輸入與輸出關係,以此克服黑箱作業,藉此找出製程參數的最佳組合。最後以半導體化學機械研磨製程來進行測試。

並列摘要


In this paper, a methodology which integrates data mining (DM) and ant colony optimization (ACO) is proposed for process parameters determination of the chemical mechanical polishing (CMP) processes in semiconductor manufacturing. In the proposed method, an Artificial Neural Network (ANN) is first studied to realize the training process between inputs and outputs of network. However, due to the invisibility in the solution procedures of ANN, the decision tree approach of Data Mining is adopted to analyze and provide the necessary information for ACO. The simulation results demonstrated the proposed method provides an efficient tool for parameters selection for the initial CMP process.

參考文獻


Yeh. J. Y.,B. H. Huang(2003).Genetic algorithm based semiconductor manufacturing process controller for chemical mechanical planarization.Journal of the Chinese Institute of Industrial Engineers.20(6),625-635.
Bauer. A.,B. Bullnheinner,R. F. Hartl,C. Strauss(1999).An Ant Colony Optimization approach for the single machine total tardiness problem.Proceedings of the 1999 Congress on Evolutionary Computation.1445-1450.
Bode, C. A.,B. S. Ko,T. F. Edgar.(2004).Run-to-run control and performance monitoring of overlay in semiconductor manufacturing.Control Engineering Practice.12(7),893-900.
Carvalho. D. R.,A. A. Freitas.(2004).A hybrid decision tree/genetic algorithm method for data mining.Information Science.163(1),13-35.
Del Castillo. E.,J. Y. Yeh.(1998).An adaptive run-to-run optimizing controller for linear and nonlinear semiconductor processes.IEEE Transactions on Semiconductor Manufacturing.11(2),285-295.

延伸閱讀