Search

Special issue of journal of manufacturing systems on new trends in manufacturing systems research

Special issue of journal of manufacturing processes on new trends in manufacturing processes research

Special Issue of Journal of Manufacturing Systems on Advancing Manufacturing Systems Research at NAMRC 46

Experimental data can provide a rich source of information and opportunities for the improvement of production processes. This paper provides a conceptual description of a data-driven model and discusses its possible implementation strategies. Two data driven methods are applied to air bending, a conventional sheet metal forming process. Self-improving data-driven prediction based on an available experimental database is implemented for two calculation approaches: the gray box and the black box. A significant improvement in terms of springback prediction has been achieved with only a limited set of training data: with 100 training samples the relative error decreases from 6.75%, as given by a state-of-the-art analytical model, to 1.6%. Additionally, a material model-free approach is studied. In this model, no predefined material model is used and all necessary material related parameters are calculated based on experimental data. With only 10 training samples and using Kriging interpolation, this approach resulted in a relative error of 5%. Such results demonstrate that data-driven calculation methods allow for significant improvements in prediction accuracy with limited number of test samples. In the case of air bending, this allows the use of a data-driven response purely based on experimental data instead of on a material law that is typically expensive to obtain. ispartof: pages:177-184 ispartof: Procedia Manufacturing vol:29 pages:177-184 ispartof: 18th International Conference on Sheet Metal, SHEMET 2019 location:Leuven, Belgium date:15 Apr - 17 Apr 2019 status: published

Laser cutting of metal sheets is a well-established industrial process, however, major process changes are constantly being introduced by newer technologies, e.g. new laser technologies, higher power sources, polarization and beam shaping control units, and gas flow optimizations. The multi-physical nature of the laser cutting process makes detailed simulations complex and demanding in terms of computational and implementation efforts. The gap between accurate modeling and industrial requirements makes an experimental approach often more economically realistic. Nevertheless, efficient assessment models that utilize a trade-off between model complexity and accuracy of the response to be assessed are attractive. Such models can be used for further technological development by efficiently supporting engineers in designing and selecting optical systems. This paper revisits model assumptions of an in-house developed laser cutting model as it is validated for larger thicknesses. This model assesses polarization and beam shaping effects on the cutting performance of thin sheets. In this work, dedicated cutting experiments to assess the maximum cutting speed of stainless steel 304L of 2, 6, and 10 mm thickness for a wide range of focal point positions are conducted and compared to the model prediction. The results show that R 2 of this comparison decreases from 0.99 for 2 mm thickness, to 0.58 for 10 mm. It can be concluded that the trend prediction accuracy degrades for thicker plates. Analysis of the experiments and simulation data for 10 mm plates reveals two possible phenomena that become more important with thickness: multiple reflections and instability of the melt flow dynamics. ispartof: pages:383-389 ispartof: Procedia Manufacturing vol:29 pages:383-389 ispartof: 18th International Conference on Sheet Metal, SHEMET 2019 location:Leuven, Belgium date:15 Apr - 17 Apr 2019 status: published