Evaluation of the Effectiveness of AI-Based Predictive Maintenance for Machine Tool
The application of machine learning methods for predictive maintenance of metalworking equipment is examined. The objective is to improve failure prediction accuracy using synthetic data simulating the dynamic operation of machines. The methodology includes data preprocessing, model selection and optimization (XGBoost and Random Forest), as well as result interpretation using SHAP analysis. Model performance was evaluated using Accuracy, Precision, Recall, and F1-score metrics. Incorporating temporal dependencies significantly improved classification accuracy compared to traditional approaches. The proposed method can be integrated into IoT systems and digital twins to automate condition monitoring and reduce maintenance costs.
Сведения
- Журнал
- Trudy Universiteta
- Опубликовано
- 2026 · Т. 3, № 104, С. 359
- Язык
- Английский
- ISSN
- 1609-1825 · 2710-3382
- Издатель
- Karaganda Technical University named after Abylkas Saginov
- Лицензия
- tu.kstu.kz/edition_policy
- Аффилиации
- Akhmet Baitursynuly Kostanay Regional University
Kostanay Engineering and Economics University n.a. M. Dulatov