KIT | KIT-Bibliothek | Impressum | Datenschutz

Transfer Learning-Based Modular Neural Network for Multi-Objective Optimization of Interior Permanent Magnet Synchronous Motors

Chen, Nuo ORCID iD icon 1; Doppelbauer, Martin 1
1 Elektrotechnisches Institut (ETI), Karlsruher Institut für Technologie (KIT)

Abstract:

Finite element analysis is frequently used to optimize the characteristics of interior permanent magnet synchronous motors throughout the design phase. The existing toolchains enable the full automation of simulating and optimizing a reference motor by manipulating the input design parameters within the feasible design space. However, for each motor design, a complete simulation is required, implying a high computational burden and time cost. Moreover, once the input design parameters undergo variations, it becomes necessary to initiate the simulation process from the beginning. The previously obtained simulation results are not helpful for the new task. In this paper, a new method using modular neural networks based on transfer learning (TL) under dimensionally varying input space conditions is presented. By transferring certain parts of the pre-trained neural networks (NNs) of the old task to the new task's NN, the previously learned parameters can be applied as the initial weight for the new network. Finally, the optimization process is completed by combining this approach with multi-objective optimization. The results show that the learning of the new NN is promoted with the help of TL. ... mehr

Zugehörige Institution(en) am KIT Elektrotechnisches Institut (ETI)
Publikationstyp Proceedingsbeitrag
Publikationsjahr 2024
Sprache Englisch
Identifikator ISBN: 979-8-3503-7061-4
KITopen-ID: 1000174539
Erschienen in International Conference on Electrical Machines ICEM 2024, Torino, Italy, 01-04 September 2024
Veranstaltung 26th International Conference on Electrical Machines (ICEM 2024), Turin, Italien, 01.09.2024 – 04.09.2024
Verlag Institute of Electrical and Electronics Engineers (IEEE)
Schlagwörter permanent magnet motor, finite element analysis, modular neural network, transfer learning, multi-objective optimization
Nachgewiesen in Scopus
Dimensions

Preprint §
DOI: 10.5445/IR/1000174539
Veröffentlicht am 21.10.2024
Seitenaufrufe: 44
seit 27.09.2024
Downloads: 11
seit 22.10.2024
Cover der Publikation
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page