An improved Kriging surrogate model method with high robustness for electrical machine optimization

Hengliang Zhang; Guangchen Wang; Junli Zhang; Yuan Gao; Wei Hua; Yuchen Wang

doi:10.1109/TIA.2024.3413042

An improved Kriging surrogate model method with high robustness for electrical machine optimization

Hengliang Zhang, Guangchen Wang, Junli Zhang, Yuan Gao, Wei Hua, Yuchen Wang

Department of Electronic & Electrical Engineering

Research output: Contribution to journal › Article › peer-review

2 Citations (SciVal)

38 Downloads (Pure)

Abstract

This article presents a highly robust optimization method for electrical machines, taking the uncertain tolerances of machine manufacturing into account. Different from the traditional multi-objective optimization methods based on Kriging surrogate model, two genetic algorithm (GA) models with disparate sampling principles are used here to release heavy computational burden and to improve prediction accuracy. One is adding the final optimization result of GA as the samples into the initial surrogate model, while the other one is adding the samples from the optimization process for the initial surrogate model. A 12-slot 14-pole interior permanent magnet synchronous machine (IPMSM) is used for the case study, and two GA models are compared. Furthermore, the proposed robust optimization method is compared with a deterministic optimization method to demonstrate its superiority, and its effectiveness is verified by prototype tests.

Original language	English
Pages (from-to)	6799-6810
Number of pages	12
Journal	IEEE Transactions on Industry Applications
Volume	60
Issue number	5
Early online date	12 Jun 2024
DOIs	https://doi.org/10.1109/TIA.2024.3413042
Publication status	Published - 30 Sept 2024

Funding

This work was supported in part by the National Natural Science Foundation of China under Grant 52207039, in part by the Natural Science Foundation of Jiangsu Province under Grant BK20220843, and in part byYoung Elite Scientists Sponsorship Program byCASTunderGrant 2023QNRC001. Paper 2023-EMC-1292.R2, presented at the 2022 IEEE Transportation Electrification Conference and Expo, Asia-Pacific, Haining, China, Oct. 28 31, and approved for publication in the IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS by the Electric Machines Committee of the IEEE Industry Applications Society [DOI: 10.1109/ITECAsia-Pacific56316.2022.9942076].

Funders	Funder number
National Natural Science Foundation of China	52207039
Natural Science Foundation of Jiangsu Province	BK20220843, 2023QNRC001, 2023-EMC-1292

Keywords

Genetic algorithm (GA)
kriging surrogate model
multi-objective optimization
permanent magnet synchronous machine
robustness

ASJC Scopus subject areas

Control and Systems Engineering
Industrial and Manufacturing Engineering
Electrical and Electronic Engineering

Access to Document

10.1109/TIA.2024.3413042

Cite this

@article{1ac2af5ab21342c8ad54246ade621c6a,

title = "An improved Kriging surrogate model method with high robustness for electrical machine optimization",

abstract = "This article presents a highly robust optimization method for electrical machines, taking the uncertain tolerances of machine manufacturing into account. Different from the traditional multi-objective optimization methods based on Kriging surrogate model, two genetic algorithm (GA) models with disparate sampling principles are used here to release heavy computational burden and to improve prediction accuracy. One is adding the final optimization result of GA as the samples into the initial surrogate model, while the other one is adding the samples from the optimization process for the initial surrogate model. A 12-slot 14-pole interior permanent magnet synchronous machine (IPMSM) is used for the case study, and two GA models are compared. Furthermore, the proposed robust optimization method is compared with a deterministic optimization method to demonstrate its superiority, and its effectiveness is verified by prototype tests.",

keywords = "Genetic algorithm (GA), kriging surrogate model, multi-objective optimization, permanent magnet synchronous machine, robustness",

author = "Hengliang Zhang and Guangchen Wang and Junli Zhang and Yuan Gao and Wei Hua and Yuchen Wang",

year = "2024",

month = sep,

day = "30",

doi = "10.1109/TIA.2024.3413042",

language = "English",

volume = "60",

pages = "6799--6810",

journal = "IEEE Transactions on Industry Applications",

issn = "0093-9994",

publisher = "IEEE",

number = "5",

}

TY - JOUR

T1 - An improved Kriging surrogate model method with high robustness for electrical machine optimization

AU - Zhang, Hengliang

AU - Wang, Guangchen

AU - Zhang, Junli

AU - Gao, Yuan

AU - Hua, Wei

AU - Wang, Yuchen

PY - 2024/9/30

Y1 - 2024/9/30

N2 - This article presents a highly robust optimization method for electrical machines, taking the uncertain tolerances of machine manufacturing into account. Different from the traditional multi-objective optimization methods based on Kriging surrogate model, two genetic algorithm (GA) models with disparate sampling principles are used here to release heavy computational burden and to improve prediction accuracy. One is adding the final optimization result of GA as the samples into the initial surrogate model, while the other one is adding the samples from the optimization process for the initial surrogate model. A 12-slot 14-pole interior permanent magnet synchronous machine (IPMSM) is used for the case study, and two GA models are compared. Furthermore, the proposed robust optimization method is compared with a deterministic optimization method to demonstrate its superiority, and its effectiveness is verified by prototype tests.

AB - This article presents a highly robust optimization method for electrical machines, taking the uncertain tolerances of machine manufacturing into account. Different from the traditional multi-objective optimization methods based on Kriging surrogate model, two genetic algorithm (GA) models with disparate sampling principles are used here to release heavy computational burden and to improve prediction accuracy. One is adding the final optimization result of GA as the samples into the initial surrogate model, while the other one is adding the samples from the optimization process for the initial surrogate model. A 12-slot 14-pole interior permanent magnet synchronous machine (IPMSM) is used for the case study, and two GA models are compared. Furthermore, the proposed robust optimization method is compared with a deterministic optimization method to demonstrate its superiority, and its effectiveness is verified by prototype tests.

KW - Genetic algorithm (GA)

KW - kriging surrogate model

KW - multi-objective optimization

KW - permanent magnet synchronous machine

KW - robustness

UR - http://www.scopus.com/inward/record.url?scp=85196101059&partnerID=8YFLogxK

U2 - 10.1109/TIA.2024.3413042

DO - 10.1109/TIA.2024.3413042

M3 - Article

AN - SCOPUS:85196101059

SN - 0093-9994

VL - 60

SP - 6799

EP - 6810

JO - IEEE Transactions on Industry Applications

JF - IEEE Transactions on Industry Applications

IS - 5

ER -

An improved Kriging surrogate model method with high robustness for electrical machine optimization

Abstract

Funding

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this