Tandem Neural Networks for Electric Machine Inverse Design

    •  Xu, Y., Wang, B., Sakamoto, Y., Yamamoto, T., Nishimura, Y., Koike-Akino, T., Wang, Y., "Tandem Neural Networks for Electric Machine Inverse Design", IEEE International Electric Machines and Drives Conference (IEMDC), May 2023.
      BibTeX TR2023-040 PDF
      • @inproceedings{Xu2023may2,
      • author = {Xu, Yihao and Wang, Bingnan and Sakamoto, Yusuke and Yamamoto, Tatsuya and Nishimura, Yuki and Koike-Akino, Toshiaki and Wang, Ye},
      • title = {Tandem Neural Networks for Electric Machine Inverse Design},
      • booktitle = {IEEE International Electric Machines and Drives Conference (IEMDC)},
      • year = 2023,
      • month = may,
      • url = {}
      • }
  • MERL Contacts:
  • Research Areas:

    Applied Physics, Electric Systems, Machine Learning, Multi-Physical Modeling


In electric motor design tasks, multiple design goals often need to be placed on a single motor, and multi-objective optimization plays a significant role. Trade-offs and Pareto front searching are needed, as these design goals or responses cannot be optimized concurrently due to their interdependent nature. However, tuning the motor parameters in the iterative optimization process is typically ineffective and heavily dependent on the expertise of the engineers due to the large number of time- consuming finite-element simulations required to evaluate each motor design candidate. In this paper, we propose an inverse design approach for electric machines based on a tandem neural network, which can effectively provide desired motor design candidates for various design targets without iteration. The one- to-many mapping problem can be avoided by the tandem neural network, which constructs loss functions based on the responses of the generated motor designs. The proposed intelligent design strategy is generally applicable for the design tasks of different types of electric motors.


  • Related News & Events