Short-Term Scientific Mission

Multi-Objective Optimization and Knowledge-Driven Decision Making: Application to a Real Problem on Polymer Injection Molding

Main theme: Single- and Multiobjective Optimisation
Grantee: António Gaspar da Cunha, University of Minho, Guimarães, Portugal
Host: Sunith Bandaru, University of Skövde, Skövde, Sweden

Start date: 2025-09-15
End date: 2025-09-26
Awarded: 2025-01-29
Report approved: 2025-10-31

Description

This Short-Term Scientific Mission aims to optimize the plastics injection molding process using advanced computational tools such as Non-Linear Principal Component Analysis (NL-PCA), Artificial Neural Networks (ANN), and Multiobjective Evolutionary Algorithms (MOEAs). Planned activities include refining objective selection methods, developing robust optimization frameworks, and enhancing decision-making processes. The collaboration between the University of Minho and the University of Skövde seeks to advance the efficiency and sustainability of manufacturing processes, with broader implications for multiobjective optimization in various industries.

Achievements

During the STSM, the focus was on learning across recurring problems, where similarity can be assumed. Critical design decisions were refined by considering real-world(-like) applications like route planning and hyperparameter optimization. Baseline experiments that were defined and run demonstrated the ability to iteratively tailor an algorithm to improve its performance over multiple problem instances. Nevertheless, the uncertainty of the algorithm behavior and the strength of the learning signal remain open issues. Additionally, extending beyond recurring problems requires significant work on measuring their similarity. The STSM laid the groundwork for future collaborations by establishing stronger ties, sharing data, and planning upcoming publications to address these challenges.