Multi-objective optimization for multi-stage sequential plastic injection molding with plating process using RSM and PCA-based weighted-GRA

Abstract

The multi-stage sequential process with multi-objective is a complex problem to address as the decision made at a particular stage influences the subsequent stage and vice versa. In this article, the effects of input variables of plastic injection, mold, and different plating stages were investigated on different output responses, namely weldline, warpage, length, and various metal plating thicknesses. This paper investigates a real-time industrial data of manufacturing an automotive exterior part made of ABS material. A D-optimal experimental layout with 55 experiments was generated for eight input factors each at three levels. Nine different output responses in each experiment were normalized into a weighted grey relational grade using grey relational analysis coupled with principal component analysis. The solutions obtained by the analysis of variance on weighted grey relational grade, and by the desirability analysis of D-optimal were compared and validated. The confirmation experiments recorded an average improvement in cumulative process outputs as 40.56% by grey relational analysis and 38.50% by desirability analysis.

Static Robust Design Optimization Using the Stochastic Frontier Method: A Case Study of Pulsed EPD Process on TiO2 Films

“…Viswanathan et al [41] combined the S/N ratio approach and the grey relational analysis with a principal component analysis based on the response surface methodology to optimize the optimal parameter-setting process. Sreedharan et al [42] combined a weighted grey relational analysis with a principal component analysis as well as the desirability analysis in response surface methodology to obtain the best combination set that optimizes the process with a multi-objective response. Kumar and Mondal [43] applied the technique for order of preference by similarity to ideal solution (TOPSIS) and grey relational analysis to investigate the capability of optimizing the output performance characteristics of a process.…”

Optimization of Polymer Processing: A Review (Part II-Molding Technologies)

“…The experimental data was fitted to a multiple response surface (data analysis). Sreedharan et al [43] also applied data analysis to the experimental results based on grey relational and principal component analyses, to generate a response surface and optimize the operating conditions in order to nine objectives that were aggregated in a single function using a weighted sum. Kumar et al [44] conducted experiments according to the Taguchi L27 Orthogonal Array and analyzed and optimized the response data using the Grey Relational Analysis (an evaluation technique able to solve complex problems for which only incomplete information exists) and a multivariate analysis.…”

Optimization of Polymer Processing: A Review (Part II- Molding Technologies)

“…The experimental data was fitted to a multiple response surface (data analysis). Sreedharan et al [43] also applied data analysis to the experimental results based on grey relational and principal component analyses, to generate a response surface and optimize the operating conditions in order to nine objectives that were aggregated in a single function using a weighted sum. Kumar et al [44] conducted experiments according to the Taguchi L27 Orthogonal Array, and analyzed and optimized the response data using the Grey Relational Analysis (an evaluation technique able to solve complex problems for which only incomplete information exists) and a multivariate analysis.…”