Statistical learning-driven parameter tuning in injection molding using modified simplex method

The optimization of product parameters, including length and standard deviation, is a persistent challenge, despite the fact that injection molding is a critical manufacturing technique. Nonlinear interactions and quality inconsistencies are frequently encountered by existing methods. The Statistica...

Full description

Saved in:
Bibliographic Details
Main Authors: Pongchanun Luangpaiboon, Walailak Atthirawong, Anucha Hirunwat, Pasura Aungkulanon
Format: Article
Language:English
Published: Elsevier 2025-09-01
Series:Results in Engineering
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2590123025027574
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The optimization of product parameters, including length and standard deviation, is a persistent challenge, despite the fact that injection molding is a critical manufacturing technique. Nonlinear interactions and quality inconsistencies are frequently encountered by existing methods. The Statistical Learning-Driven Modified Simplex Method (SLMSM) is a novel hybrid optimization framework that is introduced to resolve this gap. The SLMSM fine-tunes injection molding process (IMP) parameters for improved production consistency by combining the Modified Simplex Method (MSM) with regression-based statistical learning (SL). The Taguchi design of experiments and desirability function analysis were employed to establish a baseline. Subsequently, SLMSM was implemented to iteratively optimize process parameters, with an emphasis on the average product length and its variability. The results suggest that SLMSM effectively accomplishes target specifications while minimizing standard deviation. SLMSM addresses nonlinear, noisy objective functions with enhanced precision and fewer experimental trials by utilizing adaptive sampling and predictive modeling. Significant enhancements in length uniformity, reduced process variation, and alignment with client specifications were observed. Practical implications for manufacturing, such as enhanced product quality, cost savings, and reduced waste, are suggested by these results. Additionally, SLMSM exhibits adaptability to changing production environments, rendering it appropriate for a wider range of industrial applications. This research provides a data-driven framework for optimizing IMPs, thereby improving both operational efficiency and product reliability. The integration of real-time monitoring systems, the extension to other manufacturing domains, and the incorporation of advanced machine learning techniques for predictive quality control should be the focus of future research.
ISSN:2590-1230