Loading [MathJax]/extensions/tex2jax.js

Data-Driven Prediction of Casting Defects in Magnesium High-Pressure Die Casting Using Machine Learning

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Autorschaft

  • Slava Pachandrin
  • Norbert Hoffmann
  • Klaus Dilger
  • Markus Rokicki
  • Claudia Niederée
  • Lukas Stürenburg
  • Hendrik Noske
  • Berend Denkena

Externe Organisationen

  • Technische Universität Braunschweig
  • Hochschule Emden/Leer
Plum Print visual indicator of research metrics
  • Captures
    • Readers: 1
  • Mentions
    • News Mentions: 1
see details

Details

OriginalspracheEnglisch
Aufsatznummer101822
Seitenumfang20
FachzeitschriftInternational Journal of Metalcasting
Frühes Online-Datum1 Apr. 2025
PublikationsstatusElektronisch veröffentlicht (E-Pub) - 1 Apr. 2025

Abstract

In this study, different machine learning algorithms were analysed to predict casting defects in a cold chamber magnesium high-pressure die casting process. Based on component-related process and quality data from 7982 casting cycles, models were trained using Support Vector Machine, Random Forest and AutoML algorithms from Auto-Sklearn. The aim was to predict the presence of defect classes ("cold flow", "shrinkage cavity", "blister", "soldering point", "scrap"). Random Forest models achieved the best prediction quality overall, especially for the defect class "soldering points", which is the least frequent detected defect. An analysis of training data amounts showed that the prediction quality only improves slightly beyond 1000 training cycles, except for the "soldering point" defect class, which showed further improvements with more training data. Furthermore, the scope of data in terms of measurement sources affected the prediction quality significantly. Random Forest prediction models that were trained exclusively with casting machine data generally provide a solid basis for predicting casting defects. The highest increase in prediction performance was achieved by adding die sensor data. Overall, the prediction quality of all models was always above the statistically expected values (Balanced Accuracy of 50%), and soldering points in particular were predicted with a Balanced Accuracy of more than 80%. It was found that block temperature sensors in the shot sleeve and force measurements (for measuring the cavity pressure via the ejector pin) had comparatively high correlations with all defect classes and were weighted highly by the Random Forest models for decision-making.

ASJC Scopus Sachgebiete

Zitieren

Data-Driven Prediction of Casting Defects in Magnesium High-Pressure Die Casting Using Machine Learning. / Pachandrin, Slava; Hoffmann, Norbert; Dilger, Klaus et al.
in: International Journal of Metalcasting, 01.04.2025.

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Pachandrin, S, Hoffmann, N, Dilger, K, Rokicki, M, Niederée, C, Stürenburg, L, Noske, H, Denkena, B, Kallisch, J & Wunck, C 2025, 'Data-Driven Prediction of Casting Defects in Magnesium High-Pressure Die Casting Using Machine Learning', International Journal of Metalcasting. https://doi.org/10.1007/s40962-025-01592-w
Pachandrin, S., Hoffmann, N., Dilger, K., Rokicki, M., Niederée, C., Stürenburg, L., Noske, H., Denkena, B., Kallisch, J., & Wunck, C. (2025). Data-Driven Prediction of Casting Defects in Magnesium High-Pressure Die Casting Using Machine Learning. International Journal of Metalcasting, Artikel 101822. Vorabveröffentlichung online. https://doi.org/10.1007/s40962-025-01592-w
Pachandrin S, Hoffmann N, Dilger K, Rokicki M, Niederée C, Stürenburg L et al. Data-Driven Prediction of Casting Defects in Magnesium High-Pressure Die Casting Using Machine Learning. International Journal of Metalcasting. 2025 Apr 1;101822. Epub 2025 Apr 1. doi: 10.1007/s40962-025-01592-w
Download
@article{8fc8d60cc5f54373801add0b45183d0e,
title = "Data-Driven Prediction of Casting Defects in Magnesium High-Pressure Die Casting Using Machine Learning",
abstract = "In this study, different machine learning algorithms were analysed to predict casting defects in a cold chamber magnesium high-pressure die casting process. Based on component-related process and quality data from 7982 casting cycles, models were trained using Support Vector Machine, Random Forest and AutoML algorithms from Auto-Sklearn. The aim was to predict the presence of defect classes ({"}cold flow{"}, {"}shrinkage cavity{"}, {"}blister{"}, {"}soldering point{"}, {"}scrap{"}). Random Forest models achieved the best prediction quality overall, especially for the defect class {"}soldering points{"}, which is the least frequent detected defect. An analysis of training data amounts showed that the prediction quality only improves slightly beyond 1000 training cycles, except for the {"}soldering point{"} defect class, which showed further improvements with more training data. Furthermore, the scope of data in terms of measurement sources affected the prediction quality significantly. Random Forest prediction models that were trained exclusively with casting machine data generally provide a solid basis for predicting casting defects. The highest increase in prediction performance was achieved by adding die sensor data. Overall, the prediction quality of all models was always above the statistically expected values (Balanced Accuracy of 50%), and soldering points in particular were predicted with a Balanced Accuracy of more than 80%. It was found that block temperature sensors in the shot sleeve and force measurements (for measuring the cavity pressure via the ejector pin) had comparatively high correlations with all defect classes and were weighted highly by the Random Forest models for decision-making.",
keywords = "artificial intelligence, high-pressure die casting, industry 4.0, machine learning, quality prediction, random forest",
author = "Slava Pachandrin and Norbert Hoffmann and Klaus Dilger and Markus Rokicki and Claudia Nieder{\'e}e and Lukas St{\"u}renburg and Hendrik Noske and Berend Denkena and Jonas Kallisch and Christoph Wunck",
note = "Publisher Copyright: {\textcopyright} The Author(s) 2025.",
year = "2025",
month = apr,
day = "1",
doi = "10.1007/s40962-025-01592-w",
language = "English",
journal = "International Journal of Metalcasting",
issn = "1939-5981",
publisher = "American Foundry Society",

}

Download

TY - JOUR

T1 - Data-Driven Prediction of Casting Defects in Magnesium High-Pressure Die Casting Using Machine Learning

AU - Pachandrin, Slava

AU - Hoffmann, Norbert

AU - Dilger, Klaus

AU - Rokicki, Markus

AU - Niederée, Claudia

AU - Stürenburg, Lukas

AU - Noske, Hendrik

AU - Denkena, Berend

AU - Kallisch, Jonas

AU - Wunck, Christoph

N1 - Publisher Copyright: © The Author(s) 2025.

PY - 2025/4/1

Y1 - 2025/4/1

N2 - In this study, different machine learning algorithms were analysed to predict casting defects in a cold chamber magnesium high-pressure die casting process. Based on component-related process and quality data from 7982 casting cycles, models were trained using Support Vector Machine, Random Forest and AutoML algorithms from Auto-Sklearn. The aim was to predict the presence of defect classes ("cold flow", "shrinkage cavity", "blister", "soldering point", "scrap"). Random Forest models achieved the best prediction quality overall, especially for the defect class "soldering points", which is the least frequent detected defect. An analysis of training data amounts showed that the prediction quality only improves slightly beyond 1000 training cycles, except for the "soldering point" defect class, which showed further improvements with more training data. Furthermore, the scope of data in terms of measurement sources affected the prediction quality significantly. Random Forest prediction models that were trained exclusively with casting machine data generally provide a solid basis for predicting casting defects. The highest increase in prediction performance was achieved by adding die sensor data. Overall, the prediction quality of all models was always above the statistically expected values (Balanced Accuracy of 50%), and soldering points in particular were predicted with a Balanced Accuracy of more than 80%. It was found that block temperature sensors in the shot sleeve and force measurements (for measuring the cavity pressure via the ejector pin) had comparatively high correlations with all defect classes and were weighted highly by the Random Forest models for decision-making.

AB - In this study, different machine learning algorithms were analysed to predict casting defects in a cold chamber magnesium high-pressure die casting process. Based on component-related process and quality data from 7982 casting cycles, models were trained using Support Vector Machine, Random Forest and AutoML algorithms from Auto-Sklearn. The aim was to predict the presence of defect classes ("cold flow", "shrinkage cavity", "blister", "soldering point", "scrap"). Random Forest models achieved the best prediction quality overall, especially for the defect class "soldering points", which is the least frequent detected defect. An analysis of training data amounts showed that the prediction quality only improves slightly beyond 1000 training cycles, except for the "soldering point" defect class, which showed further improvements with more training data. Furthermore, the scope of data in terms of measurement sources affected the prediction quality significantly. Random Forest prediction models that were trained exclusively with casting machine data generally provide a solid basis for predicting casting defects. The highest increase in prediction performance was achieved by adding die sensor data. Overall, the prediction quality of all models was always above the statistically expected values (Balanced Accuracy of 50%), and soldering points in particular were predicted with a Balanced Accuracy of more than 80%. It was found that block temperature sensors in the shot sleeve and force measurements (for measuring the cavity pressure via the ejector pin) had comparatively high correlations with all defect classes and were weighted highly by the Random Forest models for decision-making.

KW - artificial intelligence

KW - high-pressure die casting

KW - industry 4.0

KW - machine learning

KW - quality prediction

KW - random forest

UR - http://www.scopus.com/inward/record.url?scp=105001936064&partnerID=8YFLogxK

U2 - 10.1007/s40962-025-01592-w

DO - 10.1007/s40962-025-01592-w

M3 - Article

AN - SCOPUS:105001936064

JO - International Journal of Metalcasting

JF - International Journal of Metalcasting

SN - 1939-5981

M1 - 101822

ER -