Digital transformation in the production
Predictive Maintenance Strategy - Predictive Maintenance
Huge data streams (for example, machine data, process data, etc.) from diverse, heterogeneous data sources must be linked and analyzed in order to provide a meaningful decision-making basis and recommendations for human action. The SCCH presents its methods for the realization of Predictive Analytics and Predictive Maintenance. By using data mining and machine learning methods, error prognosis models are created to find an "early warning point", thus enabling foresighted maintenance strategies. The key is the combination of expert knowledge and data-based error prognosis models. The application spectrum for these methods ranges from the process industry and production, through the energy management up to the production and maintenance of machinery and equipment.
The optimum man-machine interaction during welding
Welding tasks which are not automated often make particularly high demands on their execution. Not only because of the geometry and position of the weld to be produced, but often also because of the necessary working steps and execution accuracy. In the small series this means a lot of information which is necessary for every welding process. Even for welding professionals, this is a big challenge which takes a lot of time and is also fault-prone. For this reason, a joint project with an industry partner was used to explore new opportunities for interaction. For this purpose, the "Human Centered Software Engineering" (HCSE) approach has been applied to ensure that the results can be used in practice and support the user decisively at work. In the initial investigations of the work process, a first decision was quickly made. Due to the special conditions of welding and the limited possibility of interacting with the hands shortly before or during welding, the information presentation and interaction with Augmented Reality (AR) was used to show additional information in the work environment.
The concrete solution is divided into two areas: information on the work order and the configuration of the current source (welding device). The availability of the corresponding data is required for the information on the current work order. This information includes, for example, the preparation (sheet metal, sheet metal spacing, welding gap geometry) as well as the welding process itself (welding layers, welding material, necessary setting of the current source, welding direction, speed and cooling phase). This information is displayed and visually linked to the workpieces. Errors are minimized. At the power source, all parameters can be set via the AR glasses. The gear to the device is no longer necessary.