Research Article
Application of Artificial Neural Networks for Quality Classification in Electromobility Manufacturing Processes
@ARTICLE{10.4108/dtip.13005, author={Paula Czarnik and Katarzyna Antosz and Jose Mendes Machado}, title={Application of Artificial Neural Networks for Quality Classification in Electromobility Manufacturing Processes}, journal={EAI Endorsed Transactions on Digital Transformation of Industrial Processes}, volume={2}, number={1}, publisher={EAI}, journal_a={DTIP}, year={2026}, month={5}, keywords={quality control, artificial neural networks, machine learning, predictive quality, electromobility, manufacturing process, product classification, data-driven quality management}, doi={10.4108/dtip.13005} }- Paula Czarnik
Katarzyna Antosz
Jose Mendes Machado
Year: 2026
Application of Artificial Neural Networks for Quality Classification in Electromobility Manufacturing Processes
DTIP
EAI
DOI: 10.4108/dtip.13005
Abstract
INTRODUCTION: Modern manufacturing requires proactive, data-driven quality control methods that support process stability, reduce non-conformities and improve product reliability. OBJECTIVES: The objective of this paper is to evaluate the applicability of selected artificial neural network models for quality classification in an electromobility-related manufacturing process. METHODS: The study used empirical production data, SIPOC process analysis and five neural network models evaluated with accuracy, error rate, validation cost, operational indicators, confusion matrices and ROC/AUC analysis. RESULTS: The analysed models achieved validation accuracy above 95%, with the Narrow Neural Network obtaining the best overall result of 97.0% accuracy, 3.0% error rate and the lowest validation cost. CONCLUSION: The results confirm that artificial neural networks can effectively support quality classification and proactive quality management in electromobility manufacturing processes.
Copyright © 2026 P. Czarnik et al., licensed to EAI. This is an open access article distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.
