Researching an adaptive system for tool wear monitoring based on artificial intelligence

• Applicant: Professor Dr.-Ing. Thomas Bergs
• Subject Area: Metal-Cutting and Abrasive Manufacturing Engineering
• Term: since 2023
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 509813741

In this project it is to be investigated how a self-learning system for the identification of the tool wear condition and for the prediction of the tool wear progress for machining with defined cutting edge can be developed. The research question arises, which absolute accuracy or which increase in accuracy can be achieved with such a system in the course of adaptive learning. The system can be understood as the interaction between the human user, different sensors simultaneously in use within a data acquisition and automation solution as well as different algorithms of machine learning for data processing. The diversity of the sensors can refer to their physical measuring principle, the target variable to be acquired or other characteristics. Finally, the processing of data from several, different sensor sources will be carried out with algorithms of supervised machine learning. The main objective of the project is to combine these algorithms on several levels so that the result of the previous level is used as a reference for the following one. This way, a system capable of learning is created, which allows a more precise identification of the tool wear condition and wear progress with increasing data base.

• DFG Programme: Research Grants