TY - GEN

T1 - Prediction of Processing Optical Elements Results Using Machine Learning

AU - Гадасина, Людмила Викторовна

AU - Высоцкий, Роман Валерьевич

AU - Ловля, Николай

PY - 2023/9/10

Y1 - 2023/9/10

N2 - Improving the quality of processing optical elements in a shorter production cycle is an actual problem. The complexity of the task increases with the production of complex rare products. On the one hand, it is necessary to produce high-quality products, on the other hand, to optimize the processing process, minimizing its cycle. The paper proposes machine learning models that predict, based on historical data, the results of polishing optical elements of experimental-design production. Classification and regression models are constructed. The best results for the classification were obtained using the Xgboost and LightGBM algorithms, for the regression using the CatBoost algorithm. The achieved quality levels of models on test datasets allowed us to identify the influence of machine settings on the result of polishing using SHAP method. The obtained results were agreed with the production technologists of the Research Institute of Optical and Electronic Instrumentation.

AB - Improving the quality of processing optical elements in a shorter production cycle is an actual problem. The complexity of the task increases with the production of complex rare products. On the one hand, it is necessary to produce high-quality products, on the other hand, to optimize the processing process, minimizing its cycle. The paper proposes machine learning models that predict, based on historical data, the results of polishing optical elements of experimental-design production. Classification and regression models are constructed. The best results for the classification were obtained using the Xgboost and LightGBM algorithms, for the regression using the CatBoost algorithm. The achieved quality levels of models on test datasets allowed us to identify the influence of machine settings on the result of polishing using SHAP method. The obtained results were agreed with the production technologists of the Research Institute of Optical and Electronic Instrumentation.

KW - experimental-design production

KW - machine learning

KW - optical elements

KW - polishing

KW - variables importance

UR - https://www.mendeley.com/catalogue/7822eff5-420a-32b6-bcee-57df50a43432/

U2 - 10.1109/rusautocon58002.2023.10272862

DO - 10.1109/rusautocon58002.2023.10272862

M3 - Conference contribution

SN - 9798350345551

SP - 758

EP - 762

BT - Proceedings - 2023 International Russian Automation Conference, RusAutoCon 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - International Russian Automation Conference (RusAutoCon) 2023

Y2 - 10 September 2023 through 16 September 2023

ER -