Development of Dual Response Approach using Artificial Intelligence for Robust Parameter Design

Tritiya A. R. Arungpadang, Benny L. Maluegha, Lily S. Patras

Abstract


Prediction process of parameters in robust design is very important. If the prediction results is fairly precise then the quality improvement process will economize time and reduce cost. Dual response approach based on response surface methodology has widely investigated. Separately estimating mean and variance responses, dual response approach may take advantages of optimization modeling for finding optimum setting of input factors. A sufficient number of experimentations are required to improve the precision of estimations. This research recommended an alternative dual response approach without performing experiments. A hybrid neural network-genetic algorithm has been applied to model relationships between responses and input factors. Mean and variance responses conform to output nodes while input factors are used for input nodes. Using empirical process data, process parameter can be predicted without performing real experimentations. A genetic algorithm has been applied to obtain the input factors optimum setting. An example has been studied to demonstrate the procedures and applicability of the proposed approach.

Full Text:

PDF

References


Kovach J and Cho B R 2008 Constrained robust design experiments and optimization with the consideration of uncontrollable factors The International Journal of Advanced Manufacturing Technology 38 pp 7-18

Taguchi G 1987 Systems of experimental design: engineering methods to optimize quality and minimize cost (White Plains, New York: UNIPBUK/Krans International)

Vining G G and Myers R H 1990 Combining Taguchi & response surface philosophies: A dual response approach J Qual Technol 22 pp 38-45

Arungpadang T A R and Kim Y J 2012 Robust Parameter Design Based on Back Propagation Neural Network The Korean OR/MS Society 29 pp 81-9

Arungpadang T A R and Kim Y J 2012 Design Optimization for Capability Enhancement based on a Dual Response Approach ICIC International 7

Arungpadang T A R and Kim Y J 2014 Studi Pendekatan Respon Ganda dengan Kecerdasan Buatan untuk Robust Parameter Design Prosiding Seminar Nasional Fakultas Teknik Unsrat Tahun 2014 (Manado: Universitas Sam Ratulangi)

Arungpadang T A R, Neyland J and Patras L 2016 Prediction of Electricity Demand by Using Smoothing Method and Artificial Intelligence (Case Study: SulutGo System) The 2nd International Multidisciplinary Conference’s Proceeding (Jakarta: Universitas Muhammadiyah Jakarta)

Zhou X Z, Ma Y, Tu Y and Feng Y 2013 Ensemble of Surrogates for Dual Response Surface Modeling in Robust Parameter Design Quality and Reability Engineering International 29 pp 173-97

Subramaniam N, Yajnik A and Murthy R 2004 Artificial neural network as an alternative to multiple regression analysis in optimizing formulation parameters of cytarabine liposomes AAPS PharmSciTech 5

Rumelhart D E, Hinton G E and Williams R J 1986 Parallel Distributted Processing: Exploration in the Microstructure of Cognition Vol. 1 (Cambridge: MIT)

Liao T W and Chen L J 1994 A neural networks approach for grinding processes: Modelling and optimization International Journal of Machine Tools and Manufacture 34 pp 919-37

Koksoy O and Yalcinoz T 2015 A Hopfield neural network approach to the dual response problem Quality & Reliability Engineering Int 21 pp 595-603

Adeli H 2001 Neural networks in civil engineering: 1989-2000 Computer-Aided Civil and Infrastructure Engineering 16 pp 126-42

Su C T and Hsieh K L 1998 Applying Neural Network Approach to Achieve Robust Design for Dynamic Quality Characteristics International Journal of Quality and Reliability Management 15 pp 509-19

Ma H Y and Su C T 2010 Applying Hierarchical Genetic Algorithm based Neural Network and Multiple Objective Evolutionary Algorithmn to Optimize Parameter Design with Dynamic Characteristic Journal of Quality 17 pp 311-25

Chang H H 2008 A Data Mining Approach to Dynamic Multiple Responses in Taguchi Experimental Design Expert Systems with Applications 35 pp 1095-103

Chang H H and Chen Y K 2011 NeuroGenetic Approach to Optimize Parameter Design of Dynamic Multiresponse Experiments Applied Soft Computing 11 pp 436-42

Sexton R S, Dorsey R E and Sikander N A 2014 Simultaneous optimization of neural network function and architecture algorithm Decision Support Systems 36 pp 283-96

Ozcelik B and Erzurumlu T 2006 Comparison of the warpage optimization in plastic injection molding using ANOVA, neural network model and genetic algorithm J Mater Process Technol 171 pp 437-45

Yin F, Mao H, Hua L, Guo W and Shu M 2011 Back propagation neural network modeling for warpage prediction and optimization of plastic products during injection molding Materials & Design 32 pp 1844-50


Refbacks

  • There are currently no refbacks.