Federated Learning for Enablement of Digital Twin

Creation, maintenance, and update of digital twins are costly time-consuming mechanisms. The required effort can be optimized with the use LiDAR technologies, which support process collecting data related to spatial information such as location, geometry, position. Sharing in multi-stakeholder environments is hindered due competition, confidentiality, security requirements. Multi-stakeholder favor decentralized creation mechanisms reduced exchange. Such facilitated by Federated Learning, where learning performed at owner’s location. Two case studies presented this paper, used extract from industrial equipment a part twin.