Based on WCA-KELM and MOSOA: optimization of injection molding quality for plastic alloy products

Authors:

Abstract
For PC/ABS plastic alloy injection-molded products, warping and volumetric shrinkage are two prevalent quality defects attributed to the injection molding process. To mitigate these defects to the greatest extent, this study introduces an optimized injection molding process parameter scheme based on the water cycle algorithm enhanced kernel extreme learning machine (WCA-KELM), the multi-objective seagull optimization algorithm (MOSOA), and grey relational evaluation. Firstly, all experimental data were derived from orthogonal experimental designs conducted via Moldflow software, focusing on seven factors, such as melt temperature, mold temperature, packing pressure, and packing time. Warpage and volume shrinkage results were obtained in each set of experiments. Secondly, the predictive accuracy of the unoptimized kernel extreme learning machine (KELM) model was compared against that of the WCA-KELM model within this optimization framework, demonstrating that the WCA-KELM model predicts defect values with enhanced precision. Finally, the MOSOA was utilized to identify the pareto optimal frontier, from which the optimal solution was pinpointed through grey relational evaluation. According to the results, the warpage and volume shrinkage are 0.9388 mm and 8.538 %, respectively, which are effectively reduced by 41.73 % and 18.37 % compared with before optimization, indicating the efficacy and reliability of the proposed optimization methodology.
Funding Information
  • Innovation Program of Jiangsu Normal University (2024XKT0632)
  • National Natural Science Foundation of China (52075231)
  • Innovation Program of Jiangsu Normal University (2024XKT0632)
  • National Natural Science Foundation of China (52075231)

This publication has 18 references indexed in Scilit: