Study on Efficiency Map Prediction of Synchronous Motors Using Tandem Variational Autoencoder-Based Surrogate Model
Open Access
- 16 February 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Industry Applications
- Vol. 7, 338-350
Abstract
To reduce the computational cost of finite element analysis for rapid optimal motor design, surrogate modeling techniques have been widely studied. While conventional surrogate models mainly predict scalar performance metrics, propulsion motors must be evaluated over a wide operating range, requiring the prediction of high-dimensional outputs such as efficiency maps. Owing to the large dimensional gap between design variables and efficiency maps, conventional neural networks often suffer from limited accuracy and unstable convergence. This paper proposes a Tandem Variational Autoencoder (TD-VAE) that directly predicts high-dimensional efficiency maps from motor design variables. The model employs a tandem architecture in which a variational autoencoder compresses and reconstructs efficiency maps, while an auxiliary autoencoder reconstructs the design variables to enforce latent consistency. This structure enables stable training and allows previously collected simulation data to be used without modification. The TD-VAE is further extended to predict physically interpretable loss components, including copper and iron losses. The model performance is evaluated using mean absolute percentage error (MAPE) and the coefficient of determination (R²), and predictive uncertainty is analyzed through pixel-wise confidence and prediction intervals. When applied to an interior permanent magnet synchronous motor, the proposed TD-VAE achieves a maximum MAPE of 0.18% compared with finite element analysis, demonstrating accurate prediction, stable convergence, and significantly reduced design iteration time.Keywords
Funding Information
- National Research Foundation of Korea
- Korea government (RS-2023-00304959)
This publication has 22 references indexed in Scilit:
- A CVAE-based generative model for generalized
B
1
inhomogeneity corrected chemical exchange saturation transfer MRI at 5 TNeuroImage, 2025
- Design of IPMSM Considering Shaft Voltage and AC Copper Loss for EV Propulsion with Wide Operating RangeJournal of Electrical Engineering & Technology, 2025
- An efficient surrogate model for damage forecasting of composite laminates based on deep learningComposite Structures, 2023
- Generative AIBusiness & Information Systems Engineering, 2023
- Improved Copula-based conformal prediction for uncertainty quantification of multi-output regressionJournal of Process Control, 2023
- A deep generative model based on CNN-CVAE for wind turbine condition monitoringMeasurement Science and Technology, 2022
- Study of Residual Networks for Image Recognition2021
- Surrogate Modeling of Electrical Machine Torque Using Artificial Neural NetworksIEEE Access, 2020
- Accurate torque‐sensorless control approach for interior permanent‐magnet synchronous machine based on cascaded sliding mode observerThe Journal of Engineering, 2017
- Bayes’ Theorem1990