Search

Your search keyword '"Sanada, Masayuki"' showing total 5 results
Start Over Author "Sanada, Masayuki" Journal ieee transactions on energy conversion
5 results on '"Sanada, Masayuki"'

2. Experimental Verification of Four-Layer SynRM With Asymmetric Rotor Structure in the Stacking Direction.

Author

Kobayashi, Marika, Morimoto, Shigeo, Sanada, Masayuki, Inoue, Yukinori, Tamamura, Shuhei, and Maetani, Tatsuo

Subjects
RELUCTANCE motors, SYNCHRONOUS electric motors, INDUCTION motors, PERMANENT magnet motors, FINITE element method, ROTORS
Abstract

Synchronous reluctance motors (SynRMs) with four layers of flux barriers are currently in practical use as high-efficiency motors for industrial applications. While SynRMs have higher efficiency than induction motors, they have a high torque ripple. In this study, an asymmetric rotor structure was designed to reduce the torque ripple of the four-layer SynRM, considering the mechanical strength. Two rotor structures with different flux barrier angles were combined in the stacking direction, and the ratio of the combination was optimized by finite element analysis. In addition, prototypes of the initial structure and proposed asymmetric structure were manufactured, and their torque and efficiency characteristics were measured. The experimental results show that the proposed asymmetric structure can reduce the torque ripple while maintaining the basic characteristics such as average torque and efficiency. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

3. Automatic Design System With Generative Adversarial Network and Convolutional Neural Network for Optimization Design of Interior Permanent Magnet Synchronous Motor

Author

Shimizu, Yuki, Morimoto, Shigeo, Sanada, Masayuki, and Inoue, Yukinori

Abstract

The optimal design of interior permanent magnet synchronous motors requires a long time because finite element analysis (FEA) is performed repeatedly. To solve this problem, many researchers have used artificial intelligence to construct a prediction model that can replace FEA. However, because the training data are generated by FEA, it takes a very long time to obtain a sufficient amount of data, making it impossible to train a large-scale prediction model. Here, we propose a method for generating a large amount of data from a small number of FEA results using machine learning. An automatic design system with a deep generative model and a convolutional neural network is then constructed. With its sufficient data, the proposed system can handle three topologies and three motor parameters in a wide range of current vector regions. The proposed system was applied to multi-objective optimization design, with the optimization completed in 13–15 seconds.

Published
2023
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results