SurfConInspect

Resource-efficiency and competitiveness are main aims of the European Green Deal transformation. In this global restructuring process yield improvement and reduction of waste aimed by a zero-defect production are low-cost opportunities for European steel manufacturers to realize a more sustainable production. Enabling zero-defect manufacturing for flat steel production requires an early detection of surface defects and a fast and adequate control action once a defect appears. Therefore, the SurfConInspect (SCI) project follows a holistic approach incorporating new concepts as well for the measuring of surface defects as for the support of adequate control actions. To optimize surface inspection results the applicability of two new detector types is foreseen. A 3D detector and a spectral band specific detector will be applied for a more reliable detection of surface defects. Furthermore, it will be evaluated if methods for unsupervised ASIS domain adaptation and/or synthetic ASIS data generation completed by an Open-data concept can help to realize a more reliable classification by increasing the amount of high-quality training data. For the support of adequate control actions, a modular SCI framework will be implemented able to provide in-coil control actions as well for the operator as directly for the process control systems. To support the operator the applicability of Augmented Reality (AR) devices for the online visualization of quality information directly on the moving coil will be investigated. The useability of the system will be demonstrated at tin-plate and automotive production where the demands on surface quality are highest realizing the following four industrial use cases: UC1: Automated cutting control for heavy defects at the pickling line (tin-plate) UC2: Optimized speed at the pickling line based on the scale affection (tin-plate) UC3+4: Online grading at the finishing lines based on various surface defect types (tin-plate + automotive)