Cloud-based control for downstream defect reduction in the production of electric motors

Classical computing is shifted gradually into the cloud, offering completely new possibilities in information usage, computing power and application of learning algorithms. In this paper, a cloud-based architecture of control systems is investigated showing the benefit for multi-stage production systems. All sequential manufacturing and assembly processes are connected via a cloud-based architecture, which allows using information from a previous production step in one of the subsequent steps for downstream deviation compensation. This strategy is applied to the rotor production of electric motors in the automotive industry, as the current production shows high defect rates due to the lack of adequate sensor signals and optimization algorithms. The magnetization process of permanent magnets is executed in saturation, so that the generation of deviations cannot be avoided by process control or process optimization. Instead, the variance in the magnetization signal must be compensated in a downstream process, here the rotor assembly stage. Project results show how such a cloud-based architecture can increase the product quality while decreasing the amount of scrap parts in a real industrial scenario, consequently saving valuable resources like energy and raw materials. Reduction of deviations is crucial for this emerging industrial sector as electric motor production for vehicles is moving towards mass production.