Topology Optimization Accelerated by Deep Learning

• Published in: IEEE transactions on magnetics Vol. 55; no. 6; pp. 1 - 5
• Main Authors: Sasaki, Hidenori, Igarashi, Hajime
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.06.2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Approximate computing; Artificial neural networks; Computational efficiency; convolutional neural network (CNN); Deep learning; deep learning (DL); Finite element analysis; Finite element method; interior permanent magnet (IPM) motor; Iron; Magnetism; Network topology; Optimization; Permanent magnets; Topology; Topology optimization; Torque
• ISSN: 0018-9464; 1941-0069
• DOI: 10.1109/TMAG.2019.2901906

The computational cost of topology optimization based on the stochastic algorithm is shown to be greatly reduced by deep learning. In the learning phase, the cross-sectional image of an interior permanent magnet motor, represented in RGB, is used to train a convolutional neural network (CNN) to infer the torque properties. In the optimization phase, all the individuals are approximately evaluated by the trained CNN, while finite element analysis for accurate evaluation is performed only for a limited number of individuals. It is numerically shown that the computational cost for the topology optimization can be reduced without the loss of optimization quality.