Integrating machine learning with machine parameters to predict plastic part quality in injection moulding

Tools

Al-Ahmad, Manaf and Yang, Song and Qin, Yi (2024) Integrating machine learning with machine parameters to predict plastic part quality in injection moulding. MATEC Web of Conferences, 401. 08011. ISSN 2261-236X (https://doi.org/10.1051/matecconf/202440108011)

[thumbnail of Al-Ahmad-etal-2024-Integrating-Machine-Learning-with-Machine-Parameters-to-Predict-Plastic-Part]
Preview
 Text. Filename: Al-Ahmad-etal-2024-Integrating-Machine-Learning-with-Machine-Parameters-to-Predict-Plastic-Part.pdf
Final Published Version
License: Creative Commons Attribution 4.0 logo
Download (1MB)| Preview

Abstract

The plastic injection moulding process is a critical manufacturing technique renowned for its high productivity, cost-effectiveness, and ability to produce intricate plastic components for various industries including medical and aerospace. The quality of the manufactured parts is influenced by several parameters, such as machine settings and mould characteristics, particularly thermal aspects. This paper specifically investigates the influence of primary machine parameters on part quality, excluding considerations of time, mould features, and cooling channel geometries. By focusing on the machine parameters and employing advanced machine learning methods, a comprehensive understanding is developed on how these factors can be utilised to predict the quality of the parts produced. The findings provide valuable insights into optimising the injection moulding process to enhance product quality and consistency.

ORCID iDs

Al-Ahmad, Manaf ORCID logoORCID: https://orcid.org/0000-0001-7510-9973, Yang, Song ORCID logoORCID: https://orcid.org/0000-0001-8920-9457 and Qin, Yi ORCID logoORCID: https://orcid.org/0000-0001-7103-4855;
CORE (COnnecting REpositories)