Optimizing Manufacturing Processes With AI: A Signal-Based CNC Machining Case Study In The Automotive Industry
DOI:
https://doi.org/10.29284/yw7ga383Keywords:
Artificial intelligence, CNC machining, automotive manufacturing, process optimization, vibration signal analysis.Abstract
Signal-based monitoring of CNC processes is critical in optimizing automotive manufacturing since the existence of abnormalities in machining states may lead to negative consequences on the manufacturing process. This paper attempts to solve the issue of identifying abnormal CNC machining states from the raw vibration/acceleration data and converting the performance of the identification into manufacturing process-optimization metrics. An end-to-end signal-based pipeline was created for abnormal machining-state detection by utilizing the Bosch CNC Machining dataset, consisting of 1702 HDF5 machining-run files taken from three CNC machines and fifteen operations. Files within each operation were viewed as one machining run with labels of either normal or abnormal based on good or bad folders. Feature vectors were obtained from HDF5 files in numeric signals form and then transformed to both time and frequency domains. Eight models were tested; those include Logistic Regression, Support Vector Machine, Random Forest, Extra Trees, Gradient Boosting, XGBoost, LightGBM, and CatBoost. The Support Vector Machine delivered optimal balanced performance with a result of 0.9971 accuracy, 0.9807 macro F1 score, 0.9661 ROC-AUC, one missed abnormal case, and zero false positives.
References
[1] C. Li, P. Zheng, Y. Yin, B. Wang, and L. Wang, “Deep reinforcement learning in smart manufacturing: A review and prospects,” CIRP Journal of Manufacturing Science and Technology, vol. 40, pp. 75–101, 2023, doi: 10.1016/j.cirpj.2022.11.003.
[2] Z. Liu, Q. Liu, W. Xu, L. Wang, and Z. Zhou, “Robot learning towards smart robotic manufacturing: A review,” Robotics and Computer-Integrated Manufacturing, vol. 77, Art. no. 102360, 2022, doi: 10.1016/j.rcim.2022.102360.
[3] S. Wang, J. Zhang, P. Wang, J. Law, R. Calinescu, and L. Mihaylova, “A deep learning-enhanced Digital Twin framework for improving safety and reliability in human–robot collaborative manufacturing,” Robotics and Computer-Integrated Manufacturing, vol. 85, Art. no. 102608, 2024, doi: 10.1016/j.rcim.2023.102608.
[4] O. Surucu, S. A. Gadsden, and J. Yawney, “Condition monitoring using machine learning: A review of theory, applications, and recent advances,” Expert Systems with Applications, vol. 221, Art. no. 119738, 2023, doi: 10.1016/j.eswa.2023.119738.
[5] Y. Liang, C. Dai, J. Wang, G. Zhang, S. To, and Z. Zhao, “Typical applications and perspectives of machine learning for advanced precision machining: A comprehensive review,” Expert Systems with Applications, vol. 283, Art. no. 127770, 2025, doi: 10.1016/j.eswa.2025.127770.
[6] M. Soori, B. Arezoo, and R. Dastres, “Machine learning and artificial intelligence in CNC machine tools: A review,” Sustainable Manufacturing and Service Economics, vol. 2, Art. no. 100009, 2023, doi: 10.1016/j.smse.2023.100009.
[7] O. Serradilla, E. Zugasti, J. Rodriguez, and U. Zurutuza, “Deep learning models for predictive maintenance: A survey, comparison, challenges and prospects,” Applied Intelligence, vol. 52, pp. 10934–10964, 2022, doi: 10.1007/s10489-021-03004-y.
[8] J. Zipfel, F. Verworner, M. Fischer, U. Wieland, M. Kraus, and P. Zschech, “Anomaly detection for industrial quality assurance: A comparative evaluation of unsupervised deep learning models,” Computers & Industrial Engineering, vol. 177, Art. no. 109045, 2023, doi: 10.1016/j.cie.2023.109045.
[9] Y. Zhang, H. Zhu, D. Tang, T. Zhou, and Y. Gui, “Dynamic job shop scheduling based on deep reinforcement learning for multi-agent manufacturing systems,” Robotics and Computer-Integrated Manufacturing, vol. 78, Art. no. 102412, 2022, doi: 10.1016/j.rcim.2022.102412.
[10] P. Bakhshandeh, Y. Mohammadi, Y. Altintas, and F. Bleicher, “Digital twin assisted intelligent machining process monitoring and control,” CIRP Journal of Manufacturing Science and Technology, vol. 49, pp. 180–190, 2024, doi: 10.1016/j.cirpj.2024.01.005.
[11] A. Hussain, T. A. M. Janjua, A. N. Malik, A. Najib, and S. A. Khan, “Health monitoring of CNC machining processes using machine learning and wavelet packet transform,” Mechanical Systems and Signal Processing, vol. 212, Art. no. 111326, 2024, doi: 10.1016/j.ymssp.2024.111326.
[12] G. Li, Y. Bao, H. Wang, Z. Dong, X. Guo, and R. Kang, “An online monitoring methodology for grinding state identification based on real-time signal of CNC grinding machine,” Mechanical Systems and Signal Processing, vol. 200, Art. no. 110540, 2023, doi: 10.1016/j.ymssp.2023.110540.
[13] L. Bai, J. Zhang, E. Budak, Y. Tang, and W. Zhao, “Vibration energy-based indicators for multi-target condition monitoring in milling operations,” Journal of Manufacturing Systems, vol. 77, pp. 284–300, 2024, doi: 10.1016/j.jmsy.2024.09.015.
[14] Z. Liu, Z.-Q. Lang, Y. Gui, Y.-P. Zhu, and H. Laalej, “Digital twin-based anomaly detection for real-time tool condition monitoring in machining,” Journal of Manufacturing Systems, vol. 75, pp. 163–173, 2024, doi: 10.1016/j.jmsy.2024.06.003.
[15] J. Wang, Y. Li, R. Zhao, and R. X. Gao, “Physics guided neural network for machining tool wear prediction,” Journal of Manufacturing Systems, vol. 57, pp. 298–310, 2020, doi: 10.1016/j.jmsy.2020.09.005.
[16] S. Schwendemann, Z. Amjad, and A. Sikora, “A survey of machine-learning techniques for condition monitoring and predictive maintenance of bearings in grinding machines,” Computers in Industry, vol. 125, Art. no. 103380, 2021, doi: 10.1016/j.compind.2020.103380.
[17] D. Y. Pimenov, M. K. Gupta, L. R. R. da Silva, M. Kiran, N. Khanna, and G. M. Krolczyk, “Application of measurement systems in tool condition monitoring of milling: A review of measurement science approach,” Measurement, vol. 199, Art. no. 111503, 2022, doi: 10.1016/j.measurement.2022.111503.
[18] W. Li, H. Fu, Z. Han, X. Zhang, and H. Jin, “Intelligent tool wear prediction based on Informer encoder and stacked bidirectional gated recurrent unit,” Robotics and Computer-Integrated Manufacturing, vol. 77, Art. no. 102368, 2022, doi: 10.1016/j.rcim.2022.102368.
[19] L. Bai, H. Liu, J. Zhang, and W. Zhao, “Real-time tool breakage monitoring based on dimensionless indicators under time-varying cutting conditions,” Robotics and Computer-Integrated Manufacturing, vol. 81, Art. no. 102502, 2023, doi: 10.1016/j.rcim.2022.102502.
[20] L. Bai, J. Zhang, J. Yan, L. N. López de Lacalle, and J. Muñoa, “Cutting model integrated digital twin-based process monitoring in small-batch machining,” The International Journal of Advanced Manufacturing Technology, vol. 133, pp. 1881–1895, 2024, doi: 10.1007/s00170-024-13884-2.
[21] M. Feil, “Bosch CNC Machining Dataset,” UCI Machine Learning Repository, 2022. [Online]. https://archive.ics.uci.edu/dataset/752/bosch+cnc+machining+dataset doi: 10.1016/j.procir.2022.04.022.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
