 |
MetaMaintain A meta-learning approach to select appropriate prognostic methods for the predictive maintenance of digital manufacturing systems In the project, a meta-learning system was developed to automatically select suitable prognostic methods for preventive condition-based maintenance in manufacturing systems. The evaluation was carried out via prognostic performance and logistic key figures, which describe the effects of the derived maintenance measures on the performance of the manufacturing system. For this purpose, the meta-learning system was coupled with a manufacturing system, which was represented in the project by a discrete-event simulation model. Integrated production and maintenance planning based on the predictions was performed using priority rules constructed by a simulation-based optimization. This project was carried out in cooperation with Professor Dr.-Ing. Enzo Morosini Frazzon (UFSC, Brazil) and Professor Dr.-Ing. Carlos Eduardo Pereira (UFRGS, Brazil). Financial support was provided by the German Research Foundation (DFG) and by the Brazilian Coordination Center for the Improvement of Higher Education Personnel (CAPES). Contact persons: H. Engbers   (Project manager)S. Leohold Funded by: DFG Duration: 01.01.2020 - 31.03.2022 See project's publications List all projects |
