Open Collections

Abstract

Thermoforming is a manufacturing process in which thermoplastic sheets are heated and shaped over a mould to produce desired geometries. Traditionally, given a mould shape, determining the optimal heaters configurations to achieve accurate temperature distributions has relied heavily on trial-and-error methods, resulting in inefficiencies in both time and resource usage. This thesis presents an interactive operator training application that integrates predictive neural networks with a series of feedback-providing tools in order to assist in determining an optimal heaters setting in thermoforming based on the expert-specified temperature distribution target. Users and learners can interactively sketch their desired thermal distribution on a virtual canvas, and the application computes and visualizes both the corresponding heater configuration and the resulting temperature profile in real-time. This system combines two neural network architectures: a Backward Convolutional Neural Network (CNN) that determines proper heater power settings based on the thermal targets (R² up to 0.9650) and a Forward Fully Connected Neural Network (FCNN) that predicts temperature distributions from power input configurations with high predictive accuracy (R² > 0.97). Both models were trained on synthetic datasets generated from a calibrated lab-scale simulation environment. These models are embedded within a user-friendly, Unity-based application that runs across multiple platforms, such as tablet or mobile, enabling continuous, interactive exploration of heat transfer behaviour in a digital twin environment. To evaluate the educational effectiveness of the developed application, we conducted a user study with participants from engineering and computer science backgrounds to evaluate the educational effectiveness of the developed application. The accuracy of task performance increased significantly when interacting with the predictive module (from 80.6% to 92.10%, p < 0.001, Cohen’s d = 1.27), indicating the application’s potential for conceptual learning and skill transfer. Furthermore, no differences in performance were found according to academic background, prior thermoforming skill, or immersive tool experience, indicating that the application ensures equitable learning for a variety of user groups. By equipping operators with intelligent tools that reduce reliance on costly physical prototyping and accelerate decision-making, this work contributes to the goals of Industry 5.0, promoting sustainable, human-centric manufacturing through emerging digital innovations.