Scholarlink

<p>Temperature monitoring of permanent magnet synchronous motors which is an important driving component of electric vehicles, is closely related to the performance of permanent magnet synchronous motors. A deep neural network-based temperature prediction method for permanent magnet synchronous motors is proposed in this study. The core component temperature features of permanent magnet synchronous motors obtained from the test bench are selected using maximal information coefficient (MIC) method, and then the core component temperature is predicted using a nested deep neural network composed of one-dimensional convolutional neural networks (1D-CNN) and gated recurrent unit (GRU) neural networks. The effectiveness of the proposed prediction method is verified by experimental comparison with long short-term memory (LSTM), GRU, CNN-GRU(CGRU), and other models.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A new temperature prediction method for PMSM based on a nested depth neural network

  • 期刊论文

  • 发表日期：

    2025年3月15日

查看全文
  • Yuefeng Cen,
  • Hao Guo,
  • Xucheng Li,
  • Gang Cen,
  • Cheng Zhao,
  • Yongping Cai

摘要

Temperature monitoring of permanent magnet synchronous motors which is an important driving component of electric vehicles, is closely related to the performance of permanent magnet synchronous motors. A deep neural network-based temperature prediction method for permanent magnet synchronous motors is proposed in this study. The core component temperature features of permanent magnet synchronous motors obtained from the test bench are selected using maximal information coefficient (MIC) method, and then the core component temperature is predicted using a nested deep neural network composed of one-dimensional convolutional neural networks (1D-CNN) and gated recurrent unit (GRU) neural networks. The effectiveness of the proposed prediction method is verified by experimental comparison with long short-term memory (LSTM), GRU, CNN-GRU(CGRU), and other models.