Cheap-expensive multi-objective Bayesian optimization for permanent magnet synchronous motor design
- Author
- Nasrulloh Ratu Bagus Satrio Loka, Mohamed Ibrahim (UGent) , Ivo Couckuyt (UGent) , Inneke Van Nieuwenhuyse and Tom Dhaene (UGent)
- Organization
- Project
- Abstract
- Bayesian optimization (BO) is a popular optimization technique for expensive-to-evaluate black-box functions. We propose a cheap-expensive multi-objective BO strategy for optimizing a permanent magnet synchronous motor (PMSM). The design of an electric motor is a complex, time-consuming process that contains various heterogeneous objectives and constraints; in particular, we have a mix of cheap and expensive objective and constraint functions. The expensive objectives and constraints are usually quantified by a time-consuming finite element method, while the cheap ones are available as closed-form equations. We propose a BO policy that can accommodate cheap-expensive objectives and constraints, using a hypervolume-based acquisition function that combines expensive function approximation from a surrogate with direct cheap evaluations. The proposed method is benchmarked on multiple test functions with promising results, reaching competitive solutions much faster than traditional BO methods. To address the aforementioned design challenges for PMSM, we apply our proposed method, which aims to maximize motor efficiency while minimizing torque ripple and active mass, and considers six other performance indicators as constraints.
- Keywords
- IMPROVEMENT, ALGORITHM, Bayesian optimization, Multi-objectives optimization, Constrained optimization, Permanent magnet synchronous motor, Constrained, optimization
Downloads
-
(...).pdf
- full text (Published version)
- |
- UGent only
- |
- |
- 2.67 MB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-01HEJ2S6QB5KAT95TKNMZMHWGC
- MLA
- Satrio Loka, Nasrulloh Ratu Bagus, et al. “Cheap-Expensive Multi-Objective Bayesian Optimization for Permanent Magnet Synchronous Motor Design.” ENGINEERING WITH COMPUTERS, vol. 40, no. 4, 2024, pp. 2143–59, doi:10.1007/s00366-023-01900-0.
- APA
- Satrio Loka, N. R. B., Ibrahim, M., Couckuyt, I., Van Nieuwenhuyse, I., & Dhaene, T. (2024). Cheap-expensive multi-objective Bayesian optimization for permanent magnet synchronous motor design. ENGINEERING WITH COMPUTERS, 40(4), 2143–2159. https://doi.org/10.1007/s00366-023-01900-0
- Chicago author-date
- Satrio Loka, Nasrulloh Ratu Bagus, Mohamed Ibrahim, Ivo Couckuyt, Inneke Van Nieuwenhuyse, and Tom Dhaene. 2024. “Cheap-Expensive Multi-Objective Bayesian Optimization for Permanent Magnet Synchronous Motor Design.” ENGINEERING WITH COMPUTERS 40 (4): 2143–59. https://doi.org/10.1007/s00366-023-01900-0.
- Chicago author-date (all authors)
- Satrio Loka, Nasrulloh Ratu Bagus, Mohamed Ibrahim, Ivo Couckuyt, Inneke Van Nieuwenhuyse, and Tom Dhaene. 2024. “Cheap-Expensive Multi-Objective Bayesian Optimization for Permanent Magnet Synchronous Motor Design.” ENGINEERING WITH COMPUTERS 40 (4): 2143–2159. doi:10.1007/s00366-023-01900-0.
- Vancouver
- 1.Satrio Loka NRB, Ibrahim M, Couckuyt I, Van Nieuwenhuyse I, Dhaene T. Cheap-expensive multi-objective Bayesian optimization for permanent magnet synchronous motor design. ENGINEERING WITH COMPUTERS. 2024;40(4):2143–59.
- IEEE
- [1]N. R. B. Satrio Loka, M. Ibrahim, I. Couckuyt, I. Van Nieuwenhuyse, and T. Dhaene, “Cheap-expensive multi-objective Bayesian optimization for permanent magnet synchronous motor design,” ENGINEERING WITH COMPUTERS, vol. 40, no. 4, pp. 2143–2159, 2024.
@article{01HEJ2S6QB5KAT95TKNMZMHWGC,
abstract = {{Bayesian optimization (BO) is a popular optimization technique for expensive-to-evaluate black-box functions. We propose a cheap-expensive multi-objective BO strategy for optimizing a permanent magnet synchronous motor (PMSM). The design of an electric motor is a complex, time-consuming process that contains various heterogeneous objectives and constraints; in particular, we have a mix of cheap and expensive objective and constraint functions. The expensive objectives and constraints are usually quantified by a time-consuming finite element method, while the cheap ones are available as closed-form equations. We propose a BO policy that can accommodate cheap-expensive objectives and constraints, using a hypervolume-based acquisition function that combines expensive function approximation from a surrogate with direct cheap evaluations. The proposed method is benchmarked on multiple test functions with promising results, reaching competitive solutions much faster than traditional BO methods. To address the aforementioned design challenges for PMSM, we apply our proposed method, which aims to maximize motor efficiency while minimizing torque ripple and active mass, and considers six other performance indicators as constraints.}},
author = {{Satrio Loka, Nasrulloh Ratu Bagus and Ibrahim, Mohamed and Couckuyt, Ivo and Van Nieuwenhuyse, Inneke and Dhaene, Tom}},
issn = {{0177-0667}},
journal = {{ENGINEERING WITH COMPUTERS}},
keywords = {{IMPROVEMENT,ALGORITHM,Bayesian optimization,Multi-objectives optimization,Constrained optimization,Permanent magnet synchronous motor,Constrained,optimization}},
language = {{eng}},
number = {{4}},
pages = {{2143--2159}},
title = {{Cheap-expensive multi-objective Bayesian optimization for permanent magnet synchronous motor design}},
url = {{http://doi.org/10.1007/s00366-023-01900-0}},
volume = {{40}},
year = {{2024}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: