Function-Orientated Adaptive Assembly of Micro Gears Based on Machine Learning

The complexity of products is increasing and key functions can often only be realized by using micro components. The requirements of high-precision components often reach technological manufacturing limits. This is of particular importance for micro components with complex geometries, such as micro gears, where manufacturing deviations are relatively large compared to the component size and therefore have a large influence on the functional characteristics of the assembled product. In this paper, an approach is presented to predict and optimize the functional characteristics of assembled micro gear pairs in terms of Noise, Vibration and Harshness (NVH), based on optical in-line measurements of the entire topography of the gears. The overall quality is optimized by individually selecting the gears to be assembled with regard to minimising predefined NVH parameters. For implementation, a large number of possible combinations must be predicted. It is proposed to develop a meta-model with machine learning (ML) methods, which enables the near-real-time prediction of the NVH parameters of micro gear pairs, based on the optical in-line measurements.