Credit: DLR (CC BY-NC-ND 3.0).
Within the scope of this project, an open infrastructure for machine learning is being developed. It enables automatic creation of artificial intelligence (AI) models based on existing process data for manufacturing application and model exchange across company boundaries. For this purpose, the project partner WOGRA AG (https://wogra.com/) is developing the open source platform "Open Space for Machine Learning" (Os4ML). The goal of this platform is to enable non-experts to solve everyday problems with AI. It automates all steps on the way to the finished AI model with the help of an intuitive user interface.
The platform development is supported and verified by DLR with experience and expertise regarding its applicability in a manufacturing environment. For demonstration purposes, categorized data of the thermoplastic tape laying process will be provided. The data will be then selected, classified and annotated for the purpose of machine learning. Subsequently, the AI results will be checked for plausibility by scientific means and statistically analyzed.
The thermoplastic tape laying use case is of particular interest to the aerospace industry. This manufacturing process offers significant weight savings (thinner aircraft skin due to better toughness of the material) in combination with significantly simplified part manufacturing (no autoclave or oven due to in-situ consolidation) and final assembly (drill-free assembly, weldable material). Currently, there are no inspection systems available that automatically detect all mandatory critical defects as well as common anomalies.
The project page provides detailed information and the opportunity to request a free demo: www.os4ml.com
This open source project can be found freely available on Github: https://github.com/WOGRA-AG/Os4ML
Supported by: