Optimal-Parameter Determination by Inverse Model Based on MANFIS: The Case of Injection Molding for PBGA

This paper presents a novel method of integrating both optimization and inversely modeling methods to determine the optimal input-parameter for a multi-input multi-output (MIMO) system to realize the desired output-performance. First, the Taguchi method is employed to minimize experimental numbers and to collect experimental data representing the quality performances of a MIMO system. Next, the MANFIS is used to train the inverse model based on the data from the Taguchi experimental method. The adaptive neuro-fuzzy inference system (ANFIS) has been widely used for modeling different kinds of nonlinear systems. In this study, the method is further extended to MIMO-ANFIS (MANFIS) architecture to train the inverse model. The well-trained model has the ability of uniquely determining the inverse relationship for each input-output set. A case study involving statistical characterization and multiple criteria optimization on injection molding for plastic ball grid array (PBGA) is successfully presented to demonstrate the effectiveness of the proposed method.

[1]  M. Hung,et al.  Study of rapid cure BGA mold compound on warpage with shadow moire , 1999, 1999 Proceedings. 49th Electronic Components and Technology Conference (Cat. No.99CH36299).

[2]  P. Brochet,et al.  Optimization with experimental design: an approach using Taguchi's methodology and finite element simulations , 2001 .

[3]  E. Mizutani,et al.  Neuro-Fuzzy and Soft Computing-A Computational Approach to Learning and Machine Intelligence [Book Review] , 1997, IEEE Transactions on Automatic Control.

[4]  A. A. Arkadan,et al.  ANN inverse mapping technique applied to electromagnetic design , 2001 .

[5]  Kevin Alam,et al.  A robust optimization of injection molding runner balancing , 2005, Comput. Chem. Eng..

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

[7]  S-J Huang,et al.  Fuzzy logic controller for a retrofitted closed-loop injection moulding machine , 2000 .

[8]  Tung-Kuan Liu,et al.  Tuning the structure and parameters of a neural network by using hybrid Taguchi-genetic algorithm , 2006, IEEE Trans. Neural Networks.

[9]  H. Vincent Poor,et al.  Detection of Stochastic Processes , 1998, IEEE Trans. Inf. Theory.

[10]  John H. Lau,et al.  Electronics Manufacturing: with Lead-Free, Halogen-Free, and Conductive-Adhesive Materials , 2002 .

[11]  Kuang-Ting Hsiao,et al.  Branch and bound search to optimize injection gate locations in liquid composite molding processes , 2002 .

[12]  John K. L. Ho,et al.  Minimizing manufacturing costs for thin injection molded plastic components , 2005 .

[13]  Henry C. W. Lau,et al.  Design and implementation of a process optimizer: a case study on monitoring molding operations , 2005, Expert Syst. J. Knowl. Eng..

[14]  Babur Ozcelik,et al.  Comparison of the warpage optimization in the plastic injection molding using ANOVA, neural network model and genetic algorithm , 2006 .

[15]  Cheng Ping Chiu,et al.  The Correlation Between the Residual Stresses of ABS Terpolymers and Injection Molding Conditions , 1987 .

[16]  Douglas E. Smith,et al.  Design sensitivity analysis and optimization for polymer sheet extrusion and mold filling processes , 2003 .

[17]  Harpreet Singh,et al.  Generating optimal adaptive fuzzy-neural models of dynamical systems with applications to control , 1998, IEEE Trans. Syst. Man Cybern. Part C.

[18]  C. Fung,et al.  Multi-response optimization in friction properties of PBT composites using Taguchi method and principle component analysis , 2005 .

[19]  Victor Solo,et al.  Limits to estimation to stochastic ill-conditioned inverse problems , 2000, IEEE Trans. Inf. Theory.

[20]  Bongtae Han,et al.  Development of real time/variable sensitivity warpage measurement technique and its application to plastic ball grid array package , 1999 .

[21]  Chin-Ping Fung.  Multi-response Optimization of Impact Performances in Fiber-reinforced Poly(butylene terephthalate) , 2006 .

[22]  Lin Tingyu,et al.  Optimizing warpage analysis for an optical housing , 2005 .

[23]  Shih-Jung Liu,et al.  The manufacturing of thermoplastic composite parts by water-assisted injection-molding technology , 2004 .

[24]  Massimo Panella,et al.  An input-output clustering approach to the synthesis of ANFIS networks , 2005, IEEE Transactions on Fuzzy Systems.

[25]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[26]  Ying Cai,et al.  Multiuser detection using the Taguchi method for DS-CDMA systems , 2005, IEEE Transactions on Wireless Communications.

[27]  Hasan Kurtaran,et al.  Efficient warpage optimization of thin shell plastic parts using response surface methodology and genetic algorithm , 2006 .

[28]  Elie Sanchez,et al.  Resolution of Composite Fuzzy Relation Equations , 1976, Inf. Control..

[29]  Ying Cai,et al.  Taguchi method for solving the economic dispatch problem with nonsmooth cost functions , 2005 .

[30]  Bernard Sanschagrin,et al.  Process control of injection molding , 1983 .

[31]  Sylvie Galichet,et al.  Nonlinear internal model control: application of inverse model based fuzzy control , 2003, IEEE Trans. Fuzzy Syst..

[32]  L. N. Harris,et al.  Taguchi techniques for quality engineering, Philip J. Ross, Mcgraw-hill book company, 1988 , 1989 .

[33]  Donald L. Snyder,et al.  Random point processes , 1975 .

[34]  Qi-Jun Zhang,et al.  Neural Network Inverse Modeling and Applications to Microwave Filter Design , 2008, IEEE Transactions on Microwave Theory and Techniques.

[35]  Cheng-Hung Huang,et al.  The Study on the Optimization of Injection Molding Process Parameters with Gray Relational Analysis , 2003 .