AI-based sensor layout for predicting thermal deformations of CFRP machine tools

Using data-based approaches, accurate predictions of thermal deformations, which can significantly affect the quality of manufactured components, can be enabled. However, a sufficient amount of data with maximised information content is necessary for efficient training. In this paper, an approach for optimising sensor configurations for predicting thermal deformations is presented. From initially 300 temperature sensors, the number of required sensors was significantly reduced while maintaining predictive accuracy. Furthermore, a pattern for sensor placement was identified, providing the potential for an efficient sensor layout that enables cost-effective data acquisition and improved monitoring of machining and wear progression of machine tool components.