Development of data-driven PHM solutions for robot hemming in automotive production lines

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Luca Actis Grosso Andrea De Martin Giovanni Jacazio Massimo Sorli

Abstract

Robotic roller hemming is currently one of the most used solution for joining metal sheets in automotive industry, especially for those production lines which need to favor flexibility with respect to raw productivity and is mostly employed to assemble car doors. Hemming is a fairly delicate process since it does not only suffice a technical requirement – to join two panels together – but also an aesthetical one, since the joint panels are an integral part of the vehicle design and as such an important selling point. An unpredicted rupture or an advanced degradation condition of the system would lead to a significant loss in the quality of the final product or to a sudden stoppage of the production line. The development of a PHM system for hemming devices would hence provide a significant advantage, especially if designed to work for both new and legacy equipment. In this paper, we provide the results of a preliminary analysis of a new PHM framework for robotic roller hemming studied to work without having access to PLC data; the employed data-driven methodology is detailed and applied to the case of increasing wear in the head finger roll. Results from different prognostics routines are hence presented and compared.

Abstract 20 | PDF Downloads 13

##plugins.themes.bootstrap3.article.details##

Keywords

Industrial robot, data driven, LSTM, particle filtering

References
Acuña, D.E., & Orchard, M. (2017) Particle-filtering based failure prognosis via sigma-points: application to Lithium-Ion battery State-of-Charge monitoring. Mechanical Systems and Signal Processing, vol. 85, pp.827-848.
Acuña, D.E., & Orchard, M. (2018) A theoretically rigorous approach to failure prognosis. Annual conference of the PHM society. September 24-27, Philadelphia, PA, USA.
Alzahrani, A.M., Liu, R., & Kolodziej, J.R. (2018) Acoustic assessment of an End Mill for Analysis of tool wear. Annual conference of the PHM society. September 24-27, Philadelphia, PA, USA.
Autin, S., Socheleau, J., Dellacasa, A., De Martin, A., Jacazio, G., & Vachtsevanos (2018) Feasibility study of a PHM system for electro-hydraulic servo-actuators for primary flight controls. Annual Conference of the PHM society. September 24-27, Philadelphia, PA, USA.
Arumpalam, S., Maskell, S., Gordon. S., & Clapp, N.J. (2002) A Tutorial on Particle Filters for On-line Nonlinear/ Non-Gaussian Bayesian Tracking. IEEE Trans. On Signal Processing, vol. 50, no. 2, pp.174-188.
Bevilacqua, M. and Braglia, M. (2007) The analytic hierarchy process applied to maintenance strategy selection. Reliability Engineering and System Safety, vol. 70, no. 1, pp. 71-83.
Courville, A., Goodfellow, I., & Bengio, Y. (2016). Deep Learning. The MIT Press.
De Martin, A., Jacazio, G., & Sorli, M. (2018). Enhanced Particle Filter framework for improved prognosis of electro-mechanical flight controls actuators. Proceedings of the 4th European conference of the PHM society. July 3-6, Utrecht, NL.
De Ruyte, A.S., Cardew-Hall, M.J., & Hodgson, P.D. (2002) Estimating quality costs in an automotive stamping plant through the use of simulation.
International Journal of Production Research, vol. 40, no. 15, pp.3855-3848.
Drossel, W.-G., Pfeifer, M., Findeisen, M., Rössinger, M., Eckert, A., & Barth, D. (2014) The influence of the robot's stiffness on roller hemming processes. ISR/Robotik 2014; 41st International Symposium on Robotics, Munich, Germany, 2014, pp. 1-8.
Esquivel, E., Carbone, G., Ceccarelli, M., & Jáuregui (2016) Requirements and constraints for a robotized roll hemming solution. Advances in Robot Design and Intelligent Control. RAAD 2016. Advances in Intelligent Systems and Computing, vol. 540. Springer, Cham.
FCA (2016) WCM in FCA. Retrieved from https://www.wcm.fcagroup.com/en-us/wcm_at_fca
Gers, F.A., Schmidhuber, J., & Cummins, F. (2000). Learning to forget: continual prediction with LSTM. IET Conference Proceedings of 9th International
Conference on Artificial Neural Networks: ICANN '99, p. 850-855, DOI: 10.1049/cp:19991218.
Hochreiter, S. & Schmidhuber, Jü. (1997). Long short-term memory. Neural computation, vol. 9, pp. 1735-1780.
Huang, W., Khorasgani, H., Gupta, C., Faraht, A., & Zheng, S. (2018) Remaining Useful Life Estimation of Systems with Abrupt Failures. Annual conference of the PHM society. September 24-27, Philadelphia, PA, USA.
Kullback, S., & Leibler, R.A (1951) On information and sufficiency. Ann. Math. Stat. vol. 22, pp. 79–86.
Le Maoût, N., Thuillier, S., & Manach, P.Y. (2010) Drawing, flanging and hemming of metallic thin sheets: a multi-step process. Material & Design, vol. 31, no. 6, pp. 2725-2736.
Li, Z., Wu, D. (2018) A Data-driven approach to material removal rate prediction in chemical mechanical polishing. Annual conference of the PHM society. September 24-27, Philadelphia, PA, USA.
Longo, N., Serpi, V., Jacazio, G., & Sorli, M. (2018) Model-based predictive maintenance tecniques applied to automotive industry. Proceedings of the 4th European conference of the PHM society. July 3-6, Utrecht, NL.
Montalbo, T., Roth, R., & Kirchain, R. (2008) Modelling Costs and Fuel Economy Benefits of Lightweighting Vehicle Closure Panels. SAE Technical Paper 2008-01-0370. 2008 World Congress. April 14-17, Detroit, MI, USA.
Orchard, M. (2007) A particle filtering-based framework for on-line fault diagnosis and failure prognosis, Doctoral dissertation. School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA.
Pascual, R., Meruane. V., & Rey, P.A. (2008) On the effect of downtime costs and budget constraint on preventive and replacement policies. Reliability and System Safety, vol. 93, pp. 144-151.
Roemer, M., Byington, C., Kacprszynksi, G., Vachtsevanos, G., & Goebel., K. (2011) Prognostics, in System Health Management with Aerospace Applications, Wiley, pp. 281-295.
Roy, R., Souchoroukov, P., & Shehab, E. (2011) Detailed cost estimating in the automotive industry: Data and information requirements. International Journal of Production Economics, vol. 133, pp. 694-707.
Thomas, D. (2018) Advanced maintenance in manufacturing: costs and benefits. Annual conference of the PHM society. September 24-27, Philadelphia, PA, USA.
Saboori, B., Saboori, B., Carlson, J.S., & Söderberg, R. (2009) Introducing fast robot roller hemming process in automotive industry. World Academy of Science, Engineering and Technology, vol. 34, pp. 503-506.
Saxena, A., Celaya, J., Balaban, E., Goebel, K., Saha, B., & Scwabacher, M. (2008) Metrics for evaluating performance of prognostic techniques. International Conference on Prognostics and Health Management, October 6-8, Denver, CO, USA.
Singh, K., Selvanathan, B, Zope, K., Nistala, & S.H., Runkana, V. (2018). Concurrent estimation of Remaining Useful Life for multiple faults in an Ion
Etch Mill: a data-driven approach. Annual conference of the PHM society. September 24-27, Philadelphia, PA, USA.
Tabikh, M. (2014) Downtime cost and reduction analysis; survey results. Master Thesis. Mälardalen University, Sweden.
Vachtsevanos, G., Lewis, F. L., Roemer, M., Hess, A., & Wu, B. (2006). Intelligent fault diagnosis and prognosis for engineering system. Hoboken, NJ: John Wiley & Sons, Inc
Vogl, G., Weiss, B., Helu, M. (2016) A review of diagnostic and prognostic capabilities and best practices for manufacturing. Journal of Intelligent Manufacturing.
Vu, H.C., Do, P., Jha, M.S., Theilliol, D., & Peysson, F. (2018) On the use of particle filters for prognostics in industrial applications. Proceedings of the 4th European conference of the PHM society. July 3-6, Utrecht, NL.
Section
Technical Papers