Important results from the project
The goal of the project was to develop and implement AI for image analysis in the metal industry. The biggest challenge was not the development of algorithms but the structuring of data collection, classification and implementation, as well as the integration of domain knowledge to train the AI correctly. We therefore developed a programme and a methodology that makes it easy for materials experts to collect and classify data themselves, and in turn train and improve the models continuously.
Expected long term effects
The project has developed a method and an AI-driven analysis program for microstructure analysis. It can be used to both train and apply AI, giving materials experts with unique domain knowledge the opportunity to easily train their own AI models. The hope is that this tool will be an easy entry point to the use of AI in industry. The program is used in aim to analyze image data while saving the analysis results and continuously improving the algorithm.
Approach and implementation
The project was run in collaboration with metal research institutes, university colleges and universities to implement AI for microstructure analysis. The focus was primarily on AI development, but also on collaboration and education via digital meetings and workshops. It became clear that AI experts could not deliver ready-made solutions to material experts. We continuously worked on sharing domain knowledge to find solutions together.
The project description has been provided by the project members themselves and the text has not been looked at by our editors.
