Accelerated Design and Characterization of Inductive Position Sensors through AI-Driven Design Support System

We propose an accelerated method to characterize linear and angular inductive position sensors (IPS) without any physical prototypes. The technique is based on an in-house developed electromagnetic simulation tool which shows three orders of magnitude improvement with respect to the most widely used commercial software. This simulation software is used for producing synthetic data for training a machine learning surrogate model based on a neural network. In this way, the characterization of a sensor takes just milliseconds. This opens the possibility for developing a Design Support System (DesSS), a software tool that guides the user in selecting optimal design parameters to ensure robust performance under both nominal conditions and misalignments. Consequently, development time and costs are drastically reduced, transforming IPS design from a complex engineering task into a simplified, accessible process.