Comparison of Two Machine Learning Models for Predicting Volumetric Errors From On-The-Fly R-Test Type Device Data and Virtual End Point Constraints

• Autorzy: Zeng Min , Mayer J. R. R. , Feng Miao , Bitar-Nehme Elie , Duong Xuan Truong

Identyfikatory

DOI

10.36897/jme/203805

• Języki publikacji: EN

Abstrakty

EN

On-the-fly virtual end-point constraints consists in moving all five axes of the machine tool while nominally maintaining the coincidence of a sensing head centre point with a master ball centre attached to the workpiece table. The sensing head detects the deviations from the nominal coincidence as a 3D volumetric error vector. More than one ball can be so measured, and a fixed length ball bar is also measured for detecting isotropic scaling effects. Initial processing of data using the SAMBA (scale and master ball artefact) method eliminates setup errors and provides estimates of inter- and intra-axis errors as well as volumetric error vectors. Two ML models are trained and compared, Neural Network (NN) and eXtreme Gradient Boosting (XGBoost), to find the most suitable model and the required amount of training data to predict volumetric errors of a five-axis machine tool with wCBXfZY(S)t topology based on axis commands. The results show that NN marginally outperforms XGBoost and a kinematic model with ratios of prediction error over volumetric error norms of 0.12, 0.13 and 0.14, respectively.

Słowa kluczowe

EN

machine learning; five-axis machine tool; volumetric errors; R-test

• Wydawca: Wydawnictwo Wrocławskiej Rady FSNT NOT
• Czasopismo: Journal of Machine Engineering
• Rocznik: 2025
• Tom: Vol. 25, No. 2
• Strony: 13--27
• Opis fizyczny: Bibliogr. 16 poz., rys., tab.

Twórcy

autor

Zeng Min

• Department of Mechanical Engineering, Polytechnique Montréal, Canada

autor

Mayer J. R. R.

• Department of Mechanical Engineering, Polytechnique Montréal, Canada

autor

Feng Miao

• Department of Computer Science and Operations Research, Université de Montréal, Canada

autor

Bitar-Nehme Elie

• Department of Mechanical Engineering, Polytechnique Montréal, Canada

autor

Duong Xuan Truong

• Department of Mechanical Engineering, Dawson College, Canada

Bibliografia

• [1] NGUYEN V.-H., LE T.-T., 2022, Developing Geometric Error Compensation Software for Five-Axis CNC Machine Tool on NC Program Based on Artificial Neural Network, Advances in Asian Mechanism and Machine Science, Conference paper, 113, 541–548.
• [2] NGUYEN V.-H., LE T.-T., TRUONG H.-S, DUONG H.T., LE M.V., 2023, Predicting Volumetric Error Compensation for Five-Axis Machine Tool Using Machine Learning, International Journal of Computer Integrated Manufacturing, 36, 1191–1218.
• [3] LI Q., WANG W., ZHANG J., SHEN R., LI H., JIANG Z., 2019, Measurement Method for Volumetric Error of Five-Axis Machine Tool Considering Measurement Point Distribution and Adaptive Identification Process, International Journal of Machine Tools and Manufacture, 147, 103465.
• [4] WAN A., SONG L., XU J., LIU S., CHEN K., 2018, Calibration and Compensation of Machine Tool Volumetric Error Using a Laser Tracker, International Journal of Machine Tools and Manufacture, 124, 126–133.
• [5] GUO Q., XU R., MAO C., XU H., YANG J., 2014, Application of Information Fusion to Volumetric Error Modeling of CNC Machine Tools, The International Journal of Advanced Manufacturing Technology, 78, 439–447.
• [6] VU NGOC H., MAYER J.R.R., BITAR-NEHME E., 2022, Deep Learning LSTM for Predicting Thermally Induced Geometric Errors Using Rotary Axes Powers as Input Parameters, CIRP Journal of Manufacturing Science and Technology, 37, 70–80.
• [7] NGOC H.V., MAYER J.R.R., BITAR-NEHME E., 2023, Deep Learning to Directly Predict Compensation Values of Thermally Induced Volumetric Errors, Machines, 11, 496.
• [8] LIU J., MA C., WANG S., 2020, Data-Driven Thermally-Induced Error Compensation Method of High-Speed and Precision Five-Axis Machine Tools, Mechanical Systems and Signal Processing, 138, 106538.
• [9] BITAR-NEHME E., MAYER J.R.R., 2016, Thermal Volumetric Effects Under Axes Cycling Using an Invar R-Test Device and Reference Length, International Journal of Machine Tools and Manufacture, 105, 14–22.
• [10] ZARGARBASHI S.H.H., MAYER J.R.R., 2009, Single Setup Estimation of a Five-Axis Machine Tool Eight Link Errors by Programmed End Point Constraint and on the Fly Measurement with Capball Sensor, International Journal of Machine Tools and Manufacture, 49, 759–766.
• [11] BRINGMANN B., KNAPP W., 2006, Model-Based Chase-The-Ball Calibration of A 5-Axes Machining Center, CIRP Annals, 55, 531–534.
• [12] MAYER J.R.R., 2012, Five-Axis Machine Tool Calibration by Probing a Scale Enriched Reconfigurable Uncalibrated Master Balls Artefact, CIRP Annals, 61, 515–518.
• [13] YU T., ZHU H., 2020, Hyper-Parameter Optimization: a Review of Algorithms and Applications, arXiv preprint arXiv:2003.05689.
• [14] BURKOV A., 2019, The Hundred-Page Machine Learning Book, Andriy Burkov Quebec City, QC, Canada, Vol. 1.
• [15] KAVZOGLU T., TEKE A., 2022, Advanced Hyperparameter Optimization for Improved Spatial Prediction of Shallow Landslides Using Extreme Gradient Boosting (Xgboost), Bulletin of Engineering Geology and the Environment, 81.
• [16] CHICCO D., WARRENS M.J., JURMAN G., 2021, The Coefficient of Determination R-Squared is More Informative than SMAPE, MAE, MAPE, MSE and RMSE in Regression Analysis Evaluation, PeerJ. Comput. Sci., 7, e623.