Data-driven modelling in the era of Industry 4.0: A case study of friction modelling in sheet metal forming simulations
By Christian, August 8, 2018
Reading Time: < 1minute
With growing demands on quality of produced parts, concepts like zero-defect manufacturing are gaining increasing importance. As one of the means to achieve this, industries strive to attain the ability to control product/process parameters through connected manufacturing technologies and model-based control systems that utilize process/machine data for predicting optimum system conditions without human intervention. Present work demonstrates an automated approach to process in-line measured data of tribology conditions and incorporate it within sheet metal forming (SMF) simulations to enhance the prediction accuracy while reducing overall modelling effort. The automated procedure is realized using a client-server model with an in-house developed application as the server and numerical computing platform/commercial CAD software as clients. Firstly, the server launches the computing platform for processing measured data from the production line. Based on this analysis, the client then executes CAD software for modifying the blank model thereby enabling assignment of localized friction conditions. Finally, the modified blank geometry and accompanied friction values is incorporated into SMF simulations. The presented procedure reduces time required for setting up SMF simulations as well as improves the prediction accuracy. In addition to outlining suggestions for future work, paper concludes by discussing the importance of the presented procedure and its significance in the context of Industry 4.0.
Sheet Metal Forming, Friction Modelling, Automation, Zero Defect Manufacturing, Industry 4.0, Digitization, Data Analytics, Production Engineering
Tatipala, S., Wall, J., Johansson, C., & Sigvant, M. (2018). Data-driven modelling in the era of Industry 4.0 : A case study of friction modelling in sheet metal forming simulations. In Journal of Physics : Conference Series 1063 (2018) 012135 (Vol. 1063). https://doi.org/10.1088/1742-6596/1063/1/012135