Achieving lightweight construction through only material substitution does not realize the full potential of producing a lightweight material, hence, it is no longer sufficient. Weight-saving goals are best achieved through additional function integration. In order to implement this premise for mass production, a manufacturing process for joining and forming hybrid laminates using a new tool concept is presented. All materials used are widely producible and processable. The manufactured cover of an automotive center console serves to demonstrate a human interface device with impact detection and action execution. This is only possible through a machine learning system, which is implemented on a small—and thus space- and energy-saving—embedded system. The measurement results confirm the objective and show that localization was sufficiently accurate.

The problem of speaker separation is an established field in science and goes back to the cocktail party problem defined in 1953. For decades, methods have been improved and developed, but the computational complexity is rarely considered just as the possibility to use hardware acceleration mechanisms. For this reason, this paper addresses the research question: how speaker separation can be realized on embedded systems by exploiting parallelization and intelligent hardware/software partitioning. For this purpose, a concept is described which uses an FPGA for parallelization to separate a speech signal from an intended direction providing a constant throughput rate. The implementation results show the independence of FPGA resources except BRAM size, proving the scalability of the concept, just as the real-time capabilities.