Manufacturing Technology Today

Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Learning Machining Stability Diagrams From Data Using Neural Networks


Affiliations
1 Indian Institute of Technology Kanpur, Kanpur, India
     

   Subscribe/Renew Journal


Machining instabilities are detrimental. model predicted stability charts help identify cutting parameters for stability. Since models disregard speed-varying cutting force characteristics and dynamics, charts fail to guide stable cutting in industrial praxis. This study shows how supervised neural networks can learn stability charts from data. The learning capacity of this machine learning model depends on the size of the training dataset, its train-test split, the learning rate, the activation function, the number of hidden layers, and the number of neurons in each layer. This is the first study to examine how hyperparameters influence learning machining stability diagrams. Learnings from a linear stability dataset are transferrable to nonlinear datasets, demonstrating the prediction model is physics-agnostic. Predictions accuracies of up to 97.2% were obtained. Since the data used to train the model includes all the vagaries and uncertainties of the cutting process, the results can inform self-optimizing and autonomous machining systems.


Keywords

Machining, Stability, Chatter, Machine Learning, Neural Network, Hyperparameters
User
Subscription Login to verify subscription
Notifications
Font Size

  • Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I., Harp, A., Irving, G., Isard, M., Jozefowicz, R., Jia, Y., Kaiser, L., Kudlur, M., ... Zheng, X. (2015). TensorFlow: Large-scale machine learning on heterogeneous systems. Software available from tensorflow.org.

  • Aggogeri, F., Pellegrini, N., & Tagliani, F. L. (2021). Recent Advances on Machine Learning Applications in Machining Processes. Applied Sciences, 11(18), 8764. https://doi.org/10.3390/ app11188764

  • Altintas, Y., Stepan, G., Budak, E., Schmitz, T., & Kilic, Z. M. (2020). Chatter stability of machining operations. ASME. Journal of Manufacturing Science and Engineering, 142(11), 110801. https://doi.org/10.1115/1.4047391

  • Bergman, B., & Reimer, S. (2021). Online adaption of milling parameters for a stable and productive process. CIRP Annals – Manufacturing Technology, 70, 341-344.

  • Chen, G., Li, Y., Liu, X., & Yang, B. (2021). Physics- informed Bayesian inference for milling stability analysis. International Journal of Machine Tools and Manufacture, 167, 103767.

  • Cherukuri, H., Bernabeu, E. P., Selles, M., & Schmitz, T. (2019). Machining chatter prediction using a data learning model. Journal of Manufacturing and Materials Processing, 3(2), 45.

  • Cornelius, A., Karandikar, J., Gomez, M., & Schmitz, T. (2021). A Bayesian framework for milling stability prediction and reverse parameter identification. Procedia Manufacturing, 53, 760-772. https://doiorg /10.1016/j.promfg.2021. 06.073

  • Denkena, B., Bergmann, B., & Reimer, S. (2020). Analysis of different machine learning algorithms to learn stability lobe diagram. Procedia CIRP, 88, 282-287.

  • Friedrich, J., Hinze, C., Renner, A., & Verl, A. W. (2017). Estimation of stability lobe diagrams in milling with continuous learning algorithms. Robotics and Computer-Integrated Manufacturing, 43, 124-134.

  • Friedrich, J., Torzewski, J., & Verl, A. W. (2018). Online learning of stability lobe diagrams in milling. Procedia CIRP, 67, 278-283.

  • Gurney, K. (1997). An introduction to neural networks (1st ed.). CRC press.

  • Karandikar, J., Honeycutt, A., Schmitz, T., & Smith, S. (2020). Stability boundary and optimal operating parameter identification in milling using Bayesian learning. Journal of Manufacturing Processes, 56, 1252-1262.

  • Kvinevskiy, I., Bedi, S., & Mann, S. (2020). Detecting machine chatter using audio data and machine learning. The International Journal of Advanced Manufacturing Technology, 108, 3707-3716. https://doi.org/10.1007/s00170-020-05571-9

  • Liu, P. L., Du, Z. C., Li, H. M. et al. (2021). Thermal error modeling based on BiLSTM deep learning for CNC machine tool. Advances in Manufacturing, 9, 235-249. https://doi.org/10.1007/s40436- 020-00342-x

  • Liu, Y., & Altintas, Y. (2021). Transmissibility Enhanced Inverse Chatter Stability Solution. ASME Journal of Manufacturing Science and Engineering, 144(1), 011002. https://doi. org/10.1115/1.4051286

  • Mohring, H. C., Wiederkehr, P., Erkorkmaz, K., & Kakinuma, Y. (2020). Self-optimizing machining systems. CIRP Annals, 69(2), 740-763. https:// doi.org/10.1016/j.cirp.2020.05.007

  • Munoa, J., Beudaert, X., Dombovari, Z., Altintas, Y., Budak, E., Brecher, C., & Stepan, G. (2016). Chatter suppression techniques in metal cutting. CIRP Annals, 65(2), 785-808. https://doi. org/10.1016/j.cirp.2016.06.004

  • Postel, M., Bugdayci, B., & Wegener, K. (2020a). Ensemble transfer learning for refining stability predictions in milling using experimental stability states. The International Journal of Advanced Manufacturing Technology, 107, 4123-4139.

  • Postel, M., Bugdayci, B., Kuster, F., & Wegener, K. (2020b). Neural network supported inverse parameter identification for stability predictions in milling. CIRP Journal of Manufacturing Science and Technology, 29(A), 71-87. https://doi. org/10.1016/j.cirpj.2020.02.004

  • Rahimi, M. H., Huynh, H. N., & Altintas, Y. (2021). On-line chatter detection in milling with hybrid machine learning and physics- based model. CIRP Journal of Manufacturing Science and Technology, 35, 25-40. https://doi. org/10.1016/j.cirpj.2021.05.006

  • Reddy, T. N., Shanmugaraj, V., Vinod, P., & Krishna, S. G. (2020). Real-time thermal error compensation strategy for precision machine tools. Materials Today: Proceedings, 22(4), 2386-2396. https:// doi.org/10.1016/j.matpr.2020.03.363

  • Saadallah, A. Finkeldey, F., Morik, K., & Wiederkehr, P. (2018). Stability prediction in milling processes using a simulation-based Machine Learning approach. Procedia CIRP, 72, 1493-1498.

  • Sahu, G. N., Jain, P., Wahi, P., & Law, M. (2021a). Emulating bistabilities in turning to devise gain tuning strategies to actively damp them using a hardware-in-the-loop simulator. CIRP Journal of Manufacturing Science and Technology, 32, 120-131.

  • Sahu, G. N., Jain, P., Law, M., & Wahi, P. (2021b). Emulating chatter with process damping in turning using a hardware-in-the-loop simulator. Proceedings of the 8th Int. and 29th National All India Manufacturing Technology, Design and Research Conference AIMTDR 2021.

  • Sahu, G. N., & Law, M. (2022). Hardware-in-the- loop simulator for emulation and active control of chatter. HardwareX, 11, e00273.

  • Sahu, G. N., Vashisht, S., Wahi, P., & Law, M. (2020). Validation of a hardware-in-the-loop simulator for investigating and actively damping regenerative chatter in orthogonal cutting. CIRP Journal of Manufacturing Science and Technology, 29(A), 115-129.

  • Shanavas, N. A. (2022). Learning machining stability diagrams from data using neural networks. Retrieved from osf.io/wds5g

  • Shi, F., Cao, H., Wang, Y., & Feng, B. (2020). Chatter detection in high-speed milling processes based on ON-LSTM and PBT. The International Journal of Advanced Manufacturing Technology, 111, 3361-3378. https://doi.org/10.1007/s00170- 020-06292-9

  • Shi, F., Cao, H., Zhang, X., & Chen, X. (2020). A Reinforced k-Nearest Neighbors Method With Application to Chatter Identification in High- Speed Milling. IEEE Transactions on Industrial Electronics. PP. 1-1. 10.1109/TIE.2019.2962465.

  • Tarng, Y. S., & Chen, M.C. (1994). An intelligent sensor for detection of milling chatter. Journal of Intelligent Manufacturing, 5, 193-200. https:// doi.org/10.1007/BF00123923

  • Unver, H. O., & Sener, B. (2021). A novel transfer learning framework for chatter detection using convolutional neural networks. Journal of Intelligent Manufacturing. https://doi. org/10.1007/s10845-021-01839-3

  • Vaishnav, S., Agarwal, A., & Desai, K. A. (2020). Machine learning-based instantaneous cutting force model for end milling operation. Journal of Intelligent Manufacturing, 31, 1353-1366. https://doi.org/10.1007/s10845-019-01514-8

  • Wang, Y., Zhang, M., Tang, X., Peng, F., & Yan, R. (2021). A kMap optimized VMD-SVM model for milling chatter detection with an industrial robot. Journal of Intelligent Manufacturing. https://doi.org/10.1007/s10845-021-01736-9

  • Yesilli, M. C., Khasawneh, F. A., & Otto, A. (2020). On transfer learning for chatter detection in turning using wavelet packet transform and ensemble empirical mode decomposition. CIRP Journal of Manufacturing Science and Technology, 28, 118-135. https://doi.org/10.1016/j. cirpj.2019.11.003


Abstract Views: 244

PDF Views: 0




  • Learning Machining Stability Diagrams From Data Using Neural Networks

Abstract Views: 244  |  PDF Views: 0

Authors

Namras Amakkattil Shanavas
Indian Institute of Technology Kanpur, Kanpur, India
Mohit Law
Indian Institute of Technology Kanpur, Kanpur, India
Manjesh K. Singh
Indian Institute of Technology Kanpur, Kanpur, India

Abstract


Machining instabilities are detrimental. model predicted stability charts help identify cutting parameters for stability. Since models disregard speed-varying cutting force characteristics and dynamics, charts fail to guide stable cutting in industrial praxis. This study shows how supervised neural networks can learn stability charts from data. The learning capacity of this machine learning model depends on the size of the training dataset, its train-test split, the learning rate, the activation function, the number of hidden layers, and the number of neurons in each layer. This is the first study to examine how hyperparameters influence learning machining stability diagrams. Learnings from a linear stability dataset are transferrable to nonlinear datasets, demonstrating the prediction model is physics-agnostic. Predictions accuracies of up to 97.2% were obtained. Since the data used to train the model includes all the vagaries and uncertainties of the cutting process, the results can inform self-optimizing and autonomous machining systems.


Keywords


Machining, Stability, Chatter, Machine Learning, Neural Network, Hyperparameters

References