Combining neural networks and genetic algorithms for optimising the parameter design of the inter-metal dielectric process

An inter-metal dielectric (IMD) is deposited between metal layers to provide isolation capability to a device and separate the different metal layers that are unnecessary in the conduction of electricity. Owing to the complicated input/response relationships of the IMD process, the void problem results in electric leakage and causes wafer scraping. In the current study, we combined neural networks, genetic algorithms (GAs) and the desirability function in order to optimise the parameter settings of the IMD process. Initially, a backpropagation (BP) neural network was developed to map the complex non-linear relationship between the process parameters and the corresponding responses. Moreover, the desirability function and GAs were employed to obtain the optimum operating parameters in respect to each response. The implementation of the proposed approach was carried out in a semiconductor manufacturing company in Taiwan, and the results illustrate the practicability of the proposed approach.

[1]  Zhang Lin,et al.  Global optimization of absorption chiller system by genetic algorithm and neural network , 2002 .

[2]  Charles E. Heckler,et al.  Applied Multivariate Statistical Analysis , 2005, Technometrics.

[3]  Vicente Hernández,et al.  Combining Neural Networks and Genetic Algorithms to Predict and Reduce Diesel Engine Emissions , 2007, IEEE Transactions on Evolutionary Computation.

[4]  M. Quirk,et al.  Semiconductor manufacturing technology , 2000 .

[5]  Bo K. Wong,et al.  A bibliography of neural network business applications research: 1994-1998 , 2000, Comput. Oper. Res..

[6]  Cliff T. Ragsdale,et al.  Combining a neural network with a genetic algorithm for process parameter optimization , 2000 .

[7]  Chih-Ming Hsu,et al.  Multi-objective machine-component grouping in cellular manufacturing: a genetic algorithm , 1998 .

[8]  Maghsud Solimanpur,et al.  Optimisation of cutting parameters using a multi-objective genetic algorithm , 2009 .

[9]  Tarunraj Singh,et al.  Machining condition optimization by genetic algorithms and simulated annealing , 1997, Comput. Oper. Res..

[10]  Jie Zhang,et al.  Fuzzy neural network based yield prediction model for semiconductor manufacturing system , 2010 .

[11]  Seung-Soo Han,et al.  Using neural network process models to perform PECVD silicon dioxide recipe synthesis via genetic algorithms , 1997 .

[12]  Charles L. Karr,et al.  Industrial Applications of Genetic Algorithms , 1998 .

[13]  Ching-Kong Chao,et al.  Applying ANN/GA algorithm to optimize the high fill-factor microlens array fabrication using UV proximity printing process , 2005 .

[14]  Nirupam Chakraborti,et al.  Optimizing Surface Profiles during Hot Rolling: A Genetic Algorithms based Multi-objective Analysis , 2005, Practical Approaches to Multi-Objective Optimization.

[15]  P. Snow,et al.  Introduction to artificial neural networks for physicians: Taking the lid off the black box , 2001, The Prostate.

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

[17]  Guoqiang Peter Zhang,et al.  Neural networks for classification: a survey , 2000, IEEE Trans. Syst. Man Cybern. Part C.

[18]  Sam Kwong,et al.  Genetic Algorithms : Concepts and Designs , 1998 .

[19]  Douglas C. Montgomery,et al.  Response Surface Methodology: Process and Product Optimization Using Designed Experiments , 1995 .

[20]  Rintu Banerjee,et al.  Optimization of culture parameters for extracellular protease production from a newly isolated Pseudomonas sp. using response surface and artificial neural network models , 2004 .

[21]  Kurt Hornik,et al.  Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks , 1990, Neural Networks.

[22]  Chao-Ton Su,et al.  Application of Six Sigma Methodology to Optimize the Performance of the Inter-Metal Dielectric Process , 2009, IEEE Transactions on Semiconductor Manufacturing.

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

[24]  G. Derringer,et al.  Simultaneous Optimization of Several Response Variables , 1980 .

[25]  Tung-Hsu Hou,et al.  An integrated multi-objective immune algorithm for optimizing the wire bonding process of integrated circuits , 2008, J. Intell. Manuf..

[26]  Chih-Hsuan Wang,et al.  Automatic identification of spatial defect patterns for semiconductor manufacturing , 2006 .

[27]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[28]  Pei-Chann Chang,et al.  A fuzzy neural network for the flow time estimation in a semiconductor manufacturing factory , 2008 .

[29]  P. Kabisatpathy,et al.  Artificial neural-network model-based observers , 2005, IEEE Circuits and Devices Magazine.

[30]  C. C. Tsao,et al.  Comparison between response surface methodology and radial basis function network for core-center drill in drilling composite materials , 2008 .

[31]  Nirupam Chakraborti,et al.  Optimizing surface profiles during hot rolling: A genetic algorithms based multi-objective optimization , 2006 .