An artificial neural network approach for tool path generation in incremental sheet metal free-forming
- 576 Downloads
This research considers a specific incremental sheet metal free-forming process, which allows for individualized component manufacturing. However, for a reasonable application in practice, an automation of the manual process is mandatory. Unfortunately, up to now, no general tool path generation strategies are available when free-forming processes are to be utilized. On this account, for the investigated driving process, a holistic concept for deriving tool paths for the production of sheet metal parts directly from a digital component model is presented adopting an artificial neural network architecture. Consequently, for the very first time an automated part production is possible in incremental sheet metal free-forming applications. For this, a suitable network input and output structure is designed. Balanced sample data sets are generated for appropriate training. An associated network topology is determined and undergoes a training and testing phase. The influence of different training algorithms, network configurations, as well as training sets have been studied in relation to a feedforward network structure with backpropagation. Finally, the proposed computer integrated manufacturing system is subject to validation and verification by automated sheet part production, which is followed by concluding remarks on the capabilities and limits of the concept.
KeywordsSheet metal processing Computer integrated manufacturing Flexible manufacturing systems Neural networks Learning systems
- Arainz-Gonzlez, A., Fernndez-Valdivielso, A., Bustillo, A., & de Lacalle, L. (2016). Using artificial neural networks for the prediction of dimensional error on inclined surfaces manufactured by ball-end milling. International Journal of Advaced Manufacturing Technology, 83, 847–859.CrossRefGoogle Scholar
- Botsch, M., Pauly, M., Kobbelt, L., Alliez, P., Lévy, B., Bischoff, S., & Rössl, C. (2008). Geometric modeling based on polygonal meshes. Eurographics Course NotesGoogle Scholar
- Carreira-Perpinn, M. (1997). A review of dimension reduction techniques. Technical Report CS-96-06, Department of Computer Science, University of SheffieldGoogle Scholar
- Cohen-Steiner, D., & Morvan, JM. (2003). Restricted delaunay triangulations and normal cycle. In Proceedings of the 19th Annual Symposium on Computational Geometry, (pp. 312–321).Google Scholar
- de Carmo, M. (1976). Differential geometry of curves and surfaces. Englewood Cliffs: Prentice-Hall.Google Scholar
- Fahlman, S. (1988). An empirical study of learning speed in backpropagation. Technical Report CMU-CS-88-162, Carnegie-Mellon University, PittsburghGoogle Scholar
- Floaster, M., & Hormann, K. (2005). Surface parameterization: A tutorial and Survey. Berlin: Springer.Google Scholar
- Griffin, J. (2015). The prediction of profile deviations from multi process machining of complex geometrical features using combined evolutionary and neural network algorithms with embedded simulation. Journal of Intelligent Manufacturing. doi: 10.1007/s10845-015-1165-y.
- Guyon, I., & Elisseeff, A. (2003). An introduction to variable and feature selection. Journal of Machine Learning Research, 3, 1157–1182.Google Scholar
- Hagan, M., Demuth, H., & Beale, M. (1996). Neural network design. Boston: PWS Publishing.Google Scholar
- Hecht-Nielsen, R. (1990). Neurocomputing. Boston: Addison-Wesley.Google Scholar
- Hinton, G., Srivastava, N., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2012). Improving neural networks by preventing co-adaptation of feature detectors. arXiv:1207.0580.
- Hormann, K., Lévy, B., & Sheffer, A. (2007). Mesh parametrization: Theory and practice. Siggraph Course NotesGoogle Scholar
- Lee, Y., Oh, S., & Kim, M. (1991). The effect of initial weights on premature saturation in backpropagation learning. In Proceedings of the International Joint Conference on Neural Networks, (pp. 765–770).Google Scholar
- Masters, T. (1993). Practical neural network recipes in C++. San Diego: Academic Press.Google Scholar
- Nguyen, D., & Widrow, B. (1990). Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights. In Proceedings of the International Joint Conference on Neural Networks, (pp. 21–26).Google Scholar
- Oberhofer, W., & Zimmerer, T. (1996). Wie Künstliche Neuronale Netze lernen: Ein Blick in die Black Box der Backpropagation Netzwerke. Regensburger Diskussionsbeiträge 287Google Scholar
- Pohlak, M., Majak, J., & Küttner, R. (2007). Manufacturability and limitations in incremental sheet forming. Proceedings of the Estonian Academy of Sciences and Engineering, 13, 129–139.Google Scholar
- Riedmiller, M., & Braun, H. (1993). A direct adaptive method for faster backpropagation learning: The rprop algorithm. In Proceedings of the IEEE International Conference on Neural Networks, (pp. 586–591).Google Scholar
- Sola, J., & Sevilla, J. (1997). Importance of input data normalization for the application of neural networks to complex industrial problems. IEEE Transactions on Nuclear Science, 44, 1464–1468.Google Scholar
- Sorzano, C., Vargas, J., & Pascual-Montano, A. (2014). A survey of dimensionality reduction techniques. arXiv:1403.2877.
- Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: A simple way to prevent neural networks from overftting. Journal of Machine Learning Research, 15, 1929–1958.Google Scholar
- Taubin, G. (1995). Estimating the tensor of curvature of a surface from a polyhedral approximation. In Proceedings of the 5th International Conference on Computer Vision, (pp. 902–907).Google Scholar
- van der Maaten, L., & Postma, E. (2009). Dimensionality reduction: A comparative review. Technical Report TiCC TR 2009005, Tilburg centre for Creatice Computing, Tilburg UniversityGoogle Scholar
- Volk, W., Opritescu, D., Gritzmann, P., & Schmiedl, F. (2013). Automatisiertes Kopiertreiben Analyse und Katalogisierung von Bauteilen und Fertigungsstrategien. Hanover: European Research Association for Sheet Metal Working.Google Scholar
- Wintgen, P. (1982). Normal cycle and integral curvature for polyhedra in riemmannian manifolds. In G. Soos & J. Szenthe (Eds.), Differential geometry (pp. 805–816). Amsterdam: North-Holland.Google Scholar