CNC 가공 공정 불량 예측 및 변수 영향력 분석
Defect Prediction and Variable Impact Analysis in CNC Machining Process
0
조회
0
다운로드
3
인용
0
참고문헌
키워드
초록
Purpose: The improvement of yield and quality in product manufacturing is crucial from the perspective of process management. Controlling key variables within the process is essential for enhancing the quality of the produced items. In this study, we aim to identify key variables influencing product defects and facilitate quality enhancement in CNC machining process using SHAP(SHapley Additive exPlanations) Methods: Firstly, we conduct model training using boosting algorithm-based models such as AdaBoost, GBM, XGBoost, LightGBM, and CatBoost. The CNC machining process data is divided into training data and test data at a ratio 9:1 for model training and test experiments. Subsequently, we select a model with excellent Accuracy and F1-score performance and apply SHAP to extract variables influencing defects in the CNC machining process. Results: By comparing the performances of different models, the selected CatBoost model demonstrated an Accuracy of 97% and an F1-score of 95%. Using Shapley Value, we extract key variables that positively of negatively impact the dependent variable(good/defective product). We identify variables with relatively low importance, suggesting variables that should be prioritized for management. Conclusion: The extraction of key variables using SHAP provides explanatory power distinct from traditional machine learning techniques. This study holds significance in identifying key variables that should be prioritized for management in CNC machining process. It is expected to contribute to enhancing the production quality of the CNC machining process.
Abstract
Purpose: The improvement of yield and quality in product manufacturing is crucial from the perspective of process management. Controlling key variables within the process is essential for enhancing the quality of the produced items. In this study, we aim to identify key variables influencing product defects and facilitate quality enhancement in CNC machining process using SHAP(SHapley Additive exPlanations) Methods: Firstly, we conduct model training using boosting algorithm-based models such as AdaBoost, GBM, XGBoost, LightGBM, and CatBoost. The CNC machining process data is divided into training data and test data at a ratio 9:1 for model training and test experiments. Subsequently, we select a model with excellent Accuracy and F1-score performance and apply SHAP to extract variables influencing defects in the CNC machining process. Results: By comparing the performances of different models, the selected CatBoost model demonstrated an Accuracy of 97% and an F1-score of 95%. Using Shapley Value, we extract key variables that positively of negatively impact the dependent variable(good/defective product). We identify variables with relatively low importance, suggesting variables that should be prioritized for management. Conclusion: The extraction of key variables using SHAP provides explanatory power distinct from traditional machine learning techniques. This study holds significance in identifying key variables that should be prioritized for management in CNC machining process. It is expected to contribute to enhancing the production quality of the CNC machining process.
참고문헌 (26)
- Ahn, Yoonae, "A Study on XAI-based Clinical Decision Support System", The Journal of the Korea Contents Association, 21(12), pp.13~22 (2021)
- Arrieta, A., B., "Explainable Artificial Intelligence(XAI) : Concepts, taxonomies, opportunities and challenges toward responsible AI", Information Fusion, 58, pp.82~115 (2020)
- Chen, Y., "Xgboost: A scalable tree boosting system", Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, 2016, pp.785~794 (2016)
- Freund, Y., "A short introduction to boosting", Journal of Japanese Society for Artificial Intelligence, 14(5), pp.771~780 (1999)
- Friedman, J. H, "Greedy function approximation : a gradient boosting machine", The Annals of Statistics, 29(5), pp.1189~1232 (2001)
- Han, Junga, "Exploring Predictors Affecting Creative Thinking in High School Students Using Random Forest and SHAP", Korean Journal of Educational Research, 61(4), pp.101~131 (2023)
- Han, Yonghee, "Prediction Model of CNC Processing Defects using Machine Learning", Journal of the Korea Convergence Society, 13(2), pp.249~255 (2022)
- Hong, Jisoo, "Injection Process Yield Improvement Methodology Based on eXplainable Artificial Intelligence(XAI)Algotihm", Journal of Korean Society for Quality Management, 51(1), pp.55~65 (2023)
- Ju, Hyejin, "A Case Study of CNC Machining Process Improvement and Quality Prediction Model Development Using Design of Experiments and Machine Learning", Journal of the Korean Institute of Industrial Engineers, 49(4), pp.354~368 (2023)
- "CNC Machine AI Dataset" (2020)[URL]
- Kang, Seonghyeon, "Multivariate Monitoring of the Metal Frame Process in Mobile Device Manufacturing", Journal of the Korean Insititute of Industrial Engineers, 42(6), pp.395~403 (2016)
- Ke, G., "Lightgbm: A highly efficient gradient boosting decision tree", Advances in Neural Information Processing Systems, 30(2017) (2017)
- Kim, Hyunju, "A Study on the Prediction of Fuel Consumption of Bulk Ship Main Engine Using Explainable Artificial Intelligence", Journal of Navigation and Port Research, 47(4), pp.182~190 (2023)
- Kim, Iljung, "Discovering Essential AI-based Manufacturing Policy Issues for Competitive Reinforcement of Small and Medium Manufacturing Enterprises", Journal of Korean Society for Quality Management, 50(4), pp.647~664 (2022)
- Kim, Kanghee, "A Study on the Build of a QbD Six Sigma System to Promote Quality Improvement(QbD)Based on Drug Design", Journal of Korean Society for Quality Management, 50(3), pp.373~386 (2022)
- Kim, Namki, "Predict the Quality of CNC Processes and Analyze the Causes of Defects", Proceedings of Korean Institute of Industrial Engineers Spring Joint Conference, 2022 (2022)
- Lee, Hyunggeun, "Identifying Process Capability Index for Electricity Distribution System through Thermal Image Analysis", Journal of Korean Society for Quality Management, 49(3), pp.327~340 (2021)
- Lee, Juyeon, "Technologies for Collecting, Processing, Analyzing, and Utilizing Data for Intelligent Die-casting Processes", Journal of the Korean Society of Manufacturing Technology Engineers, 29(6), pp.441~448 (2020)
- Lee, Kangbae, "A Study on the Predicition of CNC Tool Wear Using Machine Learning Technique", Journal of the Korea Convergence Society, 10(11), pp.15~21 (2019)
- Lee, Seunghoon, "A Pre-processing Using TadGAN-based Time-series Anomaly Detection", Journal of Korean Society for Quality Management, 50(3), pp.459~471 (2022)
- Lee, Youngchoon, "A Study on Design Method using CNC in Wooden Products", Journal of the Korea Furniture Society, 28(4), pp.371~379 (2017)
- Na, Kwangtek, "A Securities Company’s Customer Churn Prediction Model and Causal Inference with SHAP Value", The Korea Journal of BigData, 5(2), pp.215~229 (2020)
- Nahm, Euiseok, "A Study on Modeling of Activated Sludge Process in Wastewater Treatment System Utilizing XAI(eXplainable AI)", the Transactions of the Korean Instititue of Electrical Engineers, 72(2), pp.263~269 (2023)
- Oh, Hyungrok, "Occupational accident prediction modeling and analysis using SHAP", Journal of Digital Contents Society, 22(7), pp.1115~1123 (2021)
- Prokhorenkova, L., "CatBoost: unbiased boosting with categorical features", Advances in Neural Information Processing Systems, 31(2018) (2018)
- Seo, Jibeom, "Exploration of Factors on Pre-service Science Teacher’s Major Satisfaction and Academic Satisfaction using Machine Learning and Explainable AI SHAP", Journal of Science Education, 47(1), pp.37~51 (2023)