Advancements in synthetic data extraction for industrial injection molding

TL;DR

This paper explores integrating synthetic data generated through simulation into machine learning models for injection molding, aiming to enhance robustness and reduce costs in industrial data collection.

Contribution

It demonstrates a method to incorporate synthetic data into LSTM training for injection molding, optimizing data balance for improved model performance.

Findings

Synthetic data improves model robustness across scenarios

Optimal synthetic-to-real data ratio enhances accuracy

Method reduces need for extensive real data collection

Abstract

Machine learning has significant potential for optimizing various industrial processes. However, data acquisition remains a major challenge as it is both time-consuming and costly. Synthetic data offers a promising solution to augment insufficient data sets and improve the robustness of machine learning models. In this paper, we investigate the feasibility of incorporating synthetic data into the training process of the injection molding process using an existing Long Short-Term Memory architecture. Our approach is to generate synthetic data by simulating production cycles and incorporating them into the training data set. Through iterative experimentation with different proportions of synthetic data, we attempt to find an optimal balance that maximizes the benefits of synthetic data while preserving the authenticity and relevance of real data. Our results suggest that the inclusion of synthetic data improves the model's ability to handle different scenarios, with potential practical industrial applications to reduce manual labor, machine use, and material waste. This approach provides a valuable alternative for situations where extensive data collection and maintenance has been impractical or costly and thus could contribute to more efficient manufacturing processes in the future.