XAI(eXplainable Artificial Intelligence) 알고리즘 기반 사출 공정 수율 개선 방법론
Injection Process Yield Improvement Methodology Based on eXplainable Artificial Intelligence (XAI) Algorithm
0
조회
0
다운로드
4
인용
0
참고문헌
키워드
초록
Purpose: The purpose of this study is to propose an optimization process to improve product yield in the process using process data. Recently, research for low-cost and high-efficiency production in the manufacturing process using machine learning or deep learning has continued. Therefore, this study derives major variables that affect product defects in the manufacturing process using eXplainable Artificial Intelligence(XAI) method. After that, the optimal range of the variables is presented to propose a methodology for improving product yield. Methods: This study is conducted using the injection molding machine AI dataset released on the Korea AI Manufacturing Platform(KAMP) organized by KAIST. Using the XAI-based SHAP method, major variables affecting product defects are extracted from each process data. XGBoost and LightGBM were used as learning algorithms, 5-6 variables are extracted as the main process variables for the injection process. Subsequently, the optimal control range of each process variable is presented using the ICE method. Finally, the product yield improvement methodology of this study is proposed through a validation process using Test Data. Results: The results of this study are as follows. In the injection process data, it was confirmed that XGBoost had an improvement defect rate of 0.21% and LightGBM had an improvement defect rate of 0.29%, which were improved by 0.79%p and 0.71%p, respectively, compared to the existing defect rate of 1.00%. Conclusion: This study is a case study. A research methodology was proposed in the injection process, and it was confirmed that the product yield was improved through verification.
Abstract
Purpose: The purpose of this study is to propose an optimization process to improve product yield in the process using process data. Recently, research for low-cost and high-efficiency production in the manufacturing process using machine learning or deep learning has continued. Therefore, this study derives major variables that affect product defects in the manufacturing process using eXplainable Artificial Intelligence(XAI) method. After that, the optimal range of the variables is presented to propose a methodology for improving product yield. Methods: This study is conducted using the injection molding machine AI dataset released on the Korea AI Manufacturing Platform(KAMP) organized by KAIST. Using the XAI-based SHAP method, major variables affecting product defects are extracted from each process data. XGBoost and LightGBM were used as learning algorithms, 5-6 variables are extracted as the main process variables for the injection process. Subsequently, the optimal control range of each process variable is presented using the ICE method. Finally, the product yield improvement methodology of this study is proposed through a validation process using Test Data. Results: The results of this study are as follows. In the injection process data, it was confirmed that XGBoost had an improvement defect rate of 0.21% and LightGBM had an improvement defect rate of 0.29%, which were improved by 0.79%p and 0.71%p, respectively, compared to the existing defect rate of 1.00%. Conclusion: This study is a case study. A research methodology was proposed in the injection process, and it was confirmed that the product yield was improved through verification.
참고문헌 (19)
- 안윤애, "XAI 기반의 임상의사결정시스템에 관한 연구", 한국콘텐츠학회 논문지, 21(12), pp.13~22 (2021), 한국콘텐츠학회[DOI]
- Arrieta, A. B., "Explainable Artificial Intelligence(XAI) : Concepts, taxono-mies, opportunities and challenges toward responsible AI", Information Fusion, 58, pp.82~115 (2020)
- Chen. T., "XGBoost : A Scalable Tree Boosting System", KDD 2016: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data MiningAugust 2016, pp.785~794 (2016)
- 정재엽, "플라스틱 DVD-Tray의 박막 사출성형을 위한 최적화 설계 Simulation에 관한 연구", 한국산학기술학회논문지, 9(6), pp.1726~1732 (2008), 한국산학기술학회
- Goldstein, A., "Peeking inside the black box : Visualizing statistical learning with plots of individual conditional expectation", Journal of Computational and Graphical Statistics, 24(1), pp.44~65 (2015)
- 황순환, "CAE와 Decision-tree를 이용한 사출성형 공정개선에 관한 연구", 한국산학기술학회논문지, 22(4), pp.580~586 (2021), 한국산학기술학회[DOI]
- Ke, G., "Lightgbm : A highly efficient gradient boosting decision tree", Advances in neural information processing systems, pp.30~ (2017)
- Kim, G., "Direct Search-Based Robust Design of Warpage in Injection Molded Parts", J Korean Soc Qual Manag, 29(3), pp.87~ (2001)
- "Injection Molding Machine AI Dataset, KAIST (UNIST, EPM Solutions)" (2020)[URL]
- 이형근, "열화상 이미지 분석을 통한 배전 설비 공정능력지수 감지 시스템 개발", 품질경영학회지, 49(3), pp.327~340 (2021), 한국품질경영학회[DOI]
- 이승훈, "TadGAN 기반 시계열 이상 탐지를 활용한 전처리 프로세스 연구", 품질경영학회지, 50(3), pp.459~471 (2022), 한국품질경영학회[DOI]
- 이강혁, "불균형 데이터 분류를 위한 Expectation-maximization 알고리즘과 경계 관측치를 이용한 SMOTE", 대한산업공학회지, 47(3), pp.232~241 (2021), 대한산업공학회
- Lundberg, S, "A unified approach to interpreting model predictions", Advances in neural in-formation processing systems, pp.30~ (2017)
- Mohammed. R., "Machine Learning with Oversampling and Undersampling Techniques: Overview Study and Experimental Results", International Conference on Information and Communication Systems (2020)
- 오형록, "SHAP을 활용한 산업재해 예측 모델링 및 분석", 디지털콘텐츠학회논문지, 22(7), pp.1115~1123 (2021), 한국디지털콘텐츠학회[DOI]
- Thiriez, A., "An environmental analysis of injection molding", Proceedings of the 2006IEEE International Symposium on Electronics and the Environment, pp.195~200 (2006)
- Wu, H., "Interpretable machine learning for covid-19: An empirical study on severity prediction task", IEEE Transactions on Artificial Intelligence (2021)
- 양동철, "인공신경망을 활용한 최적 사출성형조건 예측에 관한 연구", 소성∙가공, 29(4), pp.218~228 (2020), 한국소성∙가공학회
- Zhao, P., "A nondestructive online method for monitoring the injection molding process by collecting and analyzing machine running data", The International Journal of Advanced Manufacturing Technology, 72(5), pp.765~777 (2014)