← Back to Publications List

Enhancing Predictive Maintenance in Smart Textile Manufacturing Using Machine Learning Models

Students & Supervisors

Student Authors
Md. Ibtihazzaman
Bachelor of Science in Computer Science & Engineering, FST
Zuhaer Al Sadat
Bachelor of Science in Computer Science & Engineering, FST
Sadman Sakib
Bachelor of Science in Computer Science & Engineering, FST
Saiful Islam Oni
Bachelor of Science in Computer Science & Engineering, FST
Supervisors
Mahfuza Khatun
Associate Professor, Faculty, FST

Abstract

In smart textile manufacturing, predictive mainte nance is one of the innovations being implemented to reduce unplanned equipment downtime and enhance overall productiv ity. This research proposes a machine learning-driven solution based on the AI4I 2020 predictive maintenance dataset for equipment condition classification and failure prognosis. After feature extraction and preprocessing, two models Random Forest and XGBoost were developed and assessed. The Random Forest model scored 98.23% accuracy with AUC 0.97 while XGBoost also presented competitive results of 97.30% accuracy and a matching AUC score. Interpretability in model decisions through SHAP was performed to highlight the driving factors and best explainable predictions. The results highlight the opportunity that exists to employ machine learning techniques to improve maintenance in the textile sector, revealing the possibilities of shifting from manual to fully automated factory systems through intelligent data-driven machine learning algorithms.

Keywords

Predictive Maintenance Machine Learning XG Boost Random Forest Equipment Failure Prediction Smart Manufacturing AI4I 2020 Dataset.

Publication Details

  • Type of Publication:
  • Conference Name: IEEE 2nd INTERNATIONAL CONFERENCE ON COMPUTING, APPLICATIONS AND SYSTEMS (COMPAS 2025)
  • Date of Conference: 23/10/2025 - 23/10/2025
  • Venue: Islamic University, Kushtia, Bangladesh.
View on Publisher