Development of an AI-based inspection assistant for weld seam detection: Development of an assistance system for optical quality inspection.
Sentin provides AI-powered assistance systems as a prototype application for HUMAINE, making the collaboration between humans and AI-based systems for interpreting large volumes of image data (e.g. X-ray images of welds) more reliable and faster than is possible today with human-based inspection alone. A pre-trained AI model for detecting common weld imperfections is embedded in a motivating and reliable software system that enables humans to interpret bulk weld image data faster and more reliably. The hybrid human-AI system should be able to inspect more accurately (probability of detecting the corresponding defect images in the weld), faster (time per image interpretation) and more reliably (continuous inspection quality over an inspection period) than the purely human-based version. Studies by BAM (Federal Institute for Materials Testing) can be used as a benchmark here.
- User-centered interfaces for training AI solutions (INI)
- Procedure model for identification- and acceptance-promoting AI analysis and AI training (INI)
- Method set for the development of adaptive and context-sensitive assistance systems in AI work systems and the use of AI for their adaptation (LPS)
- Job Change Acceptance Toolbox for increasing the acceptance of AI-related change processes (WiPsy)
- Guidelines for designing internal communication with employees during the organizational development process, including satisfaction with the quantity and quality of communication forms and content (WiPsy)
- Criteria for creating workplaces that promote motivation, identity, and vigilance in human-AI teams (WiPsy)
- Job Perception Inventory (JOPI) to measure workplaces that support motivation, identity and vigilance (WiPsy)