스마트 제조에서 스핀들 전력 데이터를 활용한 기계 학습 기반 공구 수명 예측
Machine Learning-Based Tool Life Prediction Using Spindle Power Data in Smart Manufacturing
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
This study develops a machine learning-based tool life prediction model using spindle power data collected from real manufactur- ing environments. The primary objective is to monitor tool wear and predict optimal replacement times, thereby enhancing manu- facturing efficiency and product quality in smart factory settings. Accurate tool life prediction is critical for reducing downtime, minimizing costs, and maintaining consistent product standards. Six machine learning models, including Random Forest, Decision Tree, Support Vector Regressor, Linear Regression, XGBoost, and LightGBM, were evaluated for their predictive performance. Among these, the Random Forest Regressor demonstrated the highest accuracy with R2 value of 0.92, making it the most suitable for tool wear prediction. Linear Regression also provided detailed insights into the relationship between tool usage and spindle power, offering a practical alternative for precise predictions in scenarios with consistent data patterns. The results highlight the potential for real-time monitoring and predictive maintenance, significantly reducing downtime, optimizing tool usage, and improving operational efficiency. Challenges such as data variability, real-world noise, and model generalizability across diverse processes remain areas for future exploration. This work contributes to advancing smart manufacturing by integrating data-driven approaches into operational workflows and enabling sustainable, cost-effective production environments.
Abstract
This study develops a machine learning-based tool life prediction model using spindle power data collected from real manufactur- ing environments. The primary objective is to monitor tool wear and predict optimal replacement times, thereby enhancing manu- facturing efficiency and product quality in smart factory settings. Accurate tool life prediction is critical for reducing downtime, minimizing costs, and maintaining consistent product standards. Six machine learning models, including Random Forest, Decision Tree, Support Vector Regressor, Linear Regression, XGBoost, and LightGBM, were evaluated for their predictive performance. Among these, the Random Forest Regressor demonstrated the highest accuracy with R2 value of 0.92, making it the most suitable for tool wear prediction. Linear Regression also provided detailed insights into the relationship between tool usage and spindle power, offering a practical alternative for precise predictions in scenarios with consistent data patterns. The results highlight the potential for real-time monitoring and predictive maintenance, significantly reducing downtime, optimizing tool usage, and improving operational efficiency. Challenges such as data variability, real-world noise, and model generalizability across diverse processes remain areas for future exploration. This work contributes to advancing smart manufacturing by integrating data-driven approaches into operational workflows and enabling sustainable, cost-effective production environments.
참고문헌 (10)
- Choi, H., "Development of a Tool Condition Diagnosis and Life Prediction System Using Machine Learning and Probabilistic Analysis Methods for Mechanical Machining Processes", Master, pp.2018
- Choi, S., "The Diagnosis of Tool Fault and the Decision of Tool Life Using Recurrent Neural Network", Master, pp.2020
- Choi, S.J., "Tool Wear Prediction and Product Surface Roughness Prediction by Asymmetric Support Vector Regression", Doctor, pp.2021
- Heo, K., "Research on Tool Wear Diagnosis System Based on Power Analysis of Spindle Motor During Processing", Master, pp.2018
- Kim, H. K., "Wear Diagnostic System for End Mill Based on Machine Learning", Journal of the Korean Society of Manufacturing Technology Engineers, 31(1), pp.37~40 (2022)
- Kim, M. R., "Tool Wear Prediction Based on Machine Learning Using Sensor Signal in End Milling of Ti-6Al-4V", Proceedings of the Korean Society of Manufacturing Process Engineers Autumn Conference, pp.158~ (2022)
- Lee, K., "A Study on the Prediction of CNC Tool Wear Using Machine Learning Technique", Journal of the Korea Convergence Society, 10(11), pp.15~21 (2019)
- Lee, Y. J., "Eco-Friendly Machining Strategy via Residual Tool Life Prediction", Proceedings of the Korean Society of Manufacturing Technology Engineers Academic Conference, pp.223~ (2021)
- Oh, D. B., "Monitoring System for Prediction of Tool Wear and Failure Using ART2", Proceedings of the Korean Society of Manufacturing Technology Engineers Academic Conference, pp.201~206 (2008)
- Yook, J. H., "Anomaly Detection of Machining Process based on Power Load Analysis", Journal of Korean Society of Industrial and Systems Engineering, 46(4), pp.173~180 (2023)