Abstract
New design concepts for high-performance components are part of the current research. Because of various material properties and chemical composition, the cutting characteristics and chip formation mechanisms change during the machining process. Thus, it can be mandatory to identify the material and adapt the process parameters during machining. As a result, the workpiece quality is optimized while increasing the tool life. Therefore, this paper investigates a new approach to determine the machined material in-process by machine-learning. A cylindrical turning process is performed for friction welded EN-AW6082/20MnCr5 and C22/41Cr4 shafts. Acceleration and process force signals as well as control signals are measured and monitoring features are generated. These features are ranked and selected based on the information value by the joint mutual information method. Afterwards, four machine-learning models are trained to identify the machined material based on the signal features. The monitoring quality is evaluated during various cylindrical turning processes and the most appropriate machine-learning algorithm is determined. Thus, a new methodology for in-process material identification in CNC turning machines based on signal analysis and machine-learning algorithm is proposed.
Similar content being viewed by others
References
Altman, N. S. (1992). An introduction to kernel and nearest-neighbor nonparametric regression. The American Statistician, 46(3), 175–185.
Battiti, R. (1994). Using mutual information for selecting features in supervised neural netlearning. IEEE Transactionson Neural Networks, 5, 537–550.
Barnett, V., & Lewis, T. (2014). Outliers in statistical data (3rd ed.). New York: Wiley-Blackwell.
Behrens B. A., Bouguecha A., Frischkorn C., Huskic A., Stakhieva A., & Duran D. (2016). Tailored forming technology for three dimensional components: Approaches to heating and forming. In 5th international conference on thermomechanical processing, Italy.
Bennasar, M., Hicks, Y., & Setchi, R. (2015). Feature selection using joint mutual information maximization. Expert Systems with Applications, 42(22), 8520–8532.
Blohm, T., Mildebrath, M., Stonis, M., Langner, J., Hassel, T., & Behrens, B. A. (2017). Investigation of the coating thickness of plasma-transferred arc deposition welded and cross wedge rolled hybrid parts. Production Engineering Research and Development, 11, 255–263.
Boehnke, D. (2007). Qualitätsorientierte Zerspanung von Parallelverbunden im kontinuierlichen Schnitt. Dissertation, Leibniz Universität Hannover.
Brown, G., Pocock, A., Zhao, M. J., & Luján, M. (2012). Conditional likelihood maximisation: A unifying framework for information theoretic feature selection. Journal of Machine Learning Research, 13, 27–66.
Cho, S., Asfour, S., Onar, A., & Kaundinya, N. (2005). Tool breakage detection using support vector machine learning in a milling process. International Journal of Machine Tools and Manufacture, 45, 241–249.
Cortes, C., & Vapnik, V. N. (1995). Support vector networks. Machine Learning, 20, 273–297.
Denkena, B., Bergmann, B., & Witt, M. (2017). Automatic process parameter adaption for hybrid workpieces during cylindrical operations. The International Journal of Advanced Manufacturing Technology. https://doi.org/10.1007/s00170-017-1196-y.
Estévez, P. A., Tesmer, M., Perez, A., & Zurada, J. M. (2009). Normalized mutual information feature selection. IEEE Transactionson Neural Networks, 20, 189–201.
Hsueh, Y. W., & Yang, C. Y. (2009). Tool breakage diagnosis in face milling by support vector machine. Journal of Material Processing Technology, 209, 145–152.
Kannatey-Asibu, E., Yum, J., & Kim, T. H. (2017). Monitoring tool wear using classifier fusion. Mechanical Systems and Signal Processing, 85, 651–661.
Kwok, N., & Choi, C. (2002). Input feature selection for classification problems. IEEE Transactionson Neural Networks, 13, 143–159.
Lamraoui, M., Barakat, M., Thomas, M., & Badaoui, M. E. (2013). Chatter detection in milling machines by neural network classification and feature selection. Journal of Vibration and Control, 21, 1251–1266.
Meyer, P. E., & Bontempi, G. (2006). On the use of variable complementarity for feature selection in cancer classification. Proceedings of Applications of Evolutionary Computation, 3907, 91–102.
Mitchell, T. M. (1997). Machine learning. New York: McGraw-Hill.
Ozsváth P., Szmejkál A., Takács J., Eidenhammer M., & Obermair F. (2006). Development of face milling process for Mg-hybrid (Mg-Al, Mg-sintered steel) materials. In Proceedings of the 7th international conference on magnesium alloys and their applications (pp. 894–900). Wiley-VCH Verlag.
Peng, H., Long, F., & Ding, C. (2005). Feature selection based on mutual information: Criteria of max-dependency, max-relevance and min-redundancy. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27, 1226–1238.
Stojanovic, V., & Filipovic, V. (2014). Adaptive input design for identification of output error model with constrained output. Circuits, Systems, and Signal Processing, 33(1), 97–113.
Stojanovic, V., & Nedic, N. (2016). Identification of time-varying OE models in presence of non-Gaussian noise: Application to pneumatic servo drives. International Journal of Robust and Nonlinear Control, 26(18), 3974–3995.
Stojanovic, V., Nedic, N., Prsic, D., & Dubonjic, L. (2016). Optimal experiment design for identification of ARX models with constrained output in non-Gaussian noise. Applied Mathematical Modelling, 40(13–14), 6676–6689.
Sun, H. B., Zhang, X. Z., & Wang, J. Y. (2016). Online machining chatter forecast based on improved local mean decomposition. The International Journal of Advanced Manufacturing Technology, 84, 1045–1056.
Yang H., & Moody J. (1999). Feature selection based on joint mutual information. In Proceedings of international ICSC symposium on advances in intelligent data analysis, pp. 22–25.
Yao, Z., Mei, D., & Chen, Z. (2010). On-line chatter detection and detection based on wavelet and support vector machine. Journal of Materials Processing Technology, 210, 713–719.
Zhu, J., Ge, Z., & Song, Z. (2017). Non-Gaussian industrial process monitoring with probabilistic independent component analysis. IEEE Transactions on Automation Science and Engineering, 14(2), 1309–1319.
Acknowledgements
The results presented in this paper were obtained within the Collaborative Research Centre 1153 “Process chain to produce hybrid high performance components by Tailored Forming” in the subproject B5. The authors would like to thank the German Research Foundation (DFG) for the financial and organisational support of this project.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Denkena, B., Bergmann, B. & Witt, M. Material identification based on machine-learning algorithms for hybrid workpieces during cylindrical operations. J Intell Manuf 30, 2449–2456 (2019). https://doi.org/10.1007/s10845-018-1404-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10845-018-1404-0