New research approach

The high-wage state of the Federal Republic of Germany and the state of Baden-Württemberg owe much of their prosperity to the ability of their medium-sized industry to bring innovative products to the world market quickly and repeatedly. It is crucial to permanently maintain a scientific and technological lead over international competitors and potential imitators.

The methodology to be developed in the Karlsruher Forschungsfabrik® is aimed at systematically developing and expanding such advances in new, challenging manufacturing processes. The starting point is the increasingly frequent observation that engineers and production planners no longer specify new manufacturing processes in full as they have done in the past. Rather, it has to be possible to produce high-quality new products while the manufacturing processes are still under development. ‘Immature processes’ are manufacturing processes that are not yet fully understood and controlled, either because they are new, because they use new materials or because it is not clear which process parameters are actually responsible for product quality. At the Karlsruhe research factory, the partners are investigating which screws in the process need to be 'turned' in order to ensure that the quality of the products is and remains consistently high. Based on machine learning methods as well as measurement and control technology, the machines and plants will ultimately adjust their process parameters themselves if the quality of the products deteriorates gradually or if the environmental conditions change (high humidity, lower temperatures, etc.). Therefore the market can be served with new products much earlier, because immature processes can be industrialized faster. With the considerably shorter time-to-market, the target markets for new products can be conquered even before the manufacturing processes have been optimized in terms of manufacturing costs.

But how can one resolve the apparent contradiction between immature processes and a production based on them and at the same time bring the process to maturity? On one hand, the answer lies, in the generic basic idea of first massively instrumenting the immature process with sensors, measurement technology and intervention options. The evaluation of the data obtained in this way, e.g. by using current methods of machine learning and their comprehensible visualization for the expert, makes it possible to explore the process, understand it more quickly and improve it in a targeted manner. At the same time, the initial over-instrumentation creates the prerequisites for being able to impose a desired target behaviour on the immature sub-processes within certain limits in terms of control technology. This makes the sub-processes controllable, even if it initially requires more effort. On the other hand, the answer lies in the interdisciplinary cooperation of two strong institutes of the Fraunhofer-Gesellschaft in Karlsruhe and the production engineering expertise of the wbk at Karlsruhe Institute of Technology (KIT). The three partners combine the relevant competences in materials, production, and process engineering as well as in automation, sensor, and information technology.

Current work of the partners