Explainable Deep Neural Network for Design of Electric Motors
Explainable Deep Neural Network for Design of Electric Motors
复制标题
用于电动机设计的可解释深度神经网络
DOI：
10.1109/tmag.2021.3063141
复制
发表时间：
2021
影响因子：
2.1
通讯作者：
Igarashi Hajime
中科院分区：
文献类型：
--
作者：
Sasaki Hidenori;Hidaka Yuki;Igarashi Hajime
本研究提出一种新的两步优化方法，将可解释的神经网络的拓扑优化。训练深度神经网络（DNN）以从电机横截面的输入图像推断转矩性能。使用从DNN构造的梯度加权类激活映射（Grad-CAM）提取对平均扭矩具有显著影响的敏感区域。然后，仅在对平均转矩影响很小的激励区域中执行关于转矩涟漪的优化。所提出的方法被证明是增加了14%的内部永磁（IPM）电机的平均转矩，并减少了79%的转矩涟漪相比，原来的模型。
This study presents a novel two-step optimization method that incorporates explainable neural networks into topology optimization. The deep neural network (DNN) is trained to infer the torque performance from the input image of the motor cross section. The sensitive region that has a significant influence on the average torque is extracted using gradient-weighted class activation mapping (Grad-CAM) constructed from the DNN. Then, the optimization with respect to the torque ripple is performed only in the incentive region with little influence on the average torque. The proposed method is shown to increase the average torque of an interior permanent magnet (IPM) motor by 14% and reduce the torque ripple by 79% compared with the original model.