Explainable Deep Neural Network for Design of Electric Motors

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.

[1]  Abhishek Das,et al.  Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[2]  Hajime Igarashi,et al.  Topology Optimization of Synchronous Reluctance Motor Using Normalized Gaussian Network , 2015, IEEE Transactions on Magnetics.

[3]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[4]  Hajime Igarashi,et al.  Topology Optimization Accelerated by Deep Learning , 2019, IEEE Transactions on Magnetics.

[5]  Hajime Igarashi,et al.  Topology Optimization Using Basis Functions for Improvement of Rotating Machine Performances , 2018, IEEE Transactions on Magnetics.

[6]  H. Igarashi,et al.  Multi-Objective Topology Optimization of Rotating Machines Using Deep Learning , 2019, IEEE Transactions on Magnetics.

[7]  Franco Turini,et al.  A Survey of Methods for Explaining Black Box Models , 2018, ACM Comput. Surv..

[8]  Chang Seop Koh,et al.  Pole-Shape Optimization of a Switched-Reluctance Motor for Torque Ripple Reduction , 2007, IEEE Transactions on Magnetics.

[10]  K. Yamazaki,et al.  Reduction of inverter carrier harmonic losses in interior permanent magnet synchronous motors by optimizing rotor and stator shapes , 2017, 2017 IEEE Energy Conversion Congress and Exposition (ECCE).

[11]  Hajime Igarashi,et al.  Multimaterial Topology Optimization of Electric Machines Based on Normalized Gaussian Network , 2015, IEEE Transactions on Magnetics.