Design-LIME: An Interpretable Visualization Method for Electric Motor Design Based on Deep Learning

A novel visualization method for interpreting the resultant design from topology optimization (TO) is proposed. We employ a pre-trained deep learning (DL) model to predict the degree of influence of transitions from air to magnetic materials, and build an interpretable linear model to display the visualization result. The proposed method, Design-LIME, is applied for visualizing the impact of effective regions on the torque characteristics of interior permanent magnet synchronous motors (IPMSMs). Compared to conventional visualization methods based on explainable artificial intelligence (XAI), Design-LIME presents accurate and simple visualization results. Furthermore, a novel multistep TO method is proposed. The proposed TO utilizes Design-LIME to efficiently address the electromagnetic and mechanical characteristics of IPMSMs by extracting the effective region of the IPMSM characteristics. The proposed TO method improves search performance by 18.7% when compared with the conventional single-step optimization method. The proposed method enables more efficient motor designs with improved electromagnetic and mechanical performance. The proposed method contributes to the streamlining of the design process not only for motors but also for various electrical devices.