Multi-objective optimization based on hyperparameter random forest regression for linear motor design

Cheng, Wu; Zhao, Qiankai; Li, Mingye; Liu, Jingna; Li, Mingwei; Zhao, Xingqiao

doi:10.1007/s13042-022-01573-z

Cited by 9 publications

(5 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To mitigate the temperature rise of the motor, perforations were made on the stator and stator yoke, precisely targeting the center of the double-H movers where the flux and magnetic density distributions were comparatively lower [ [6]]. Figure 2 shows the flux and magnetic density distribution of the DLFSPM motor under no load before and after drilling the stator.…”

Section: Electromagnetic Field Model Of Dlfspmmentioning

confidence: 99%

“…The response surface method was also employed to analyze the EM characteristics of the water-cooled motor. A sensorless temperature estimation method is proposed in a study [6] where the thermal network model of an induction motor is created. The losses are incorporated into an equivalent thermal network model to estimate the temperature of the induction motor.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A long secondary linear traction motor analysis based on electromagnetic-thermal-fluid coupling

Shi,

Wen,

Wang

et al. 2024

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

The temperature analysis of the motor is critical for its functioning and durability as it has a significant impact on enhancing its efficiency. The purpose of this paper is to design a rational water cooling system for the Double-sided Linear Flux Switching Permanent Magnet motor (DLFSPM), thereby reducing the adverse effects of temperature rise. This paper conducts electromagnetic fluid and thermal analyses of DLFSPM. It also designs a rational cooling structure to reduce the temperature rise while running thereby contributing to its operation reliability. The electromagnetic-thermal-fluid coupling model provides a feasible solution for reducing the temperature increase of the DLFSPM motor under rated operating conditions, thereby enhancing its overall performance.

show abstract

Section: Electromagnetic Field Model Of Dlfspmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A long secondary linear traction motor analysis based on electromagnetic-thermal-fluid coupling

Shi,

Wen,

Wang

et al. 2024

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…In [7], significant parameters of the motor are optimized using multi-objective GA considering the multiplicity of effects on the single-sided linear induction motors (SLIMs), which substantially reduces the normal force of the motor. In [8], introducing Bayesian Optimization (BO) and Hyper Band (HB) into the random forest regression algorithm (RF) to improve the prediction accuracy of the model as well as combining it with the second-generation non-dominated sorting genetic algorithm (NSGA-II) for multi-objective optimization improves the output performance of flux-switching linear motors.…”

Section: Introductionmentioning

confidence: 99%

Co-optimization of Long Secondary Double-sided Linear Flux Switching Permanent Magnet Motors

Wen,

Cui,

et al. 2024

PIER C

View full text Add to dashboard Cite

This study aims to achieve the co-optimization of thrust force and thrust fluctuation using a long secondary double-sided linear flux switching permanent magnet motor (LSDLFSPM). Firstly, the motor model is constructed and derived using a theoretical approach. Subsequently, the motor parameters are subjected to sensitivity analysis using the Taguchi method to identify the significant influencing factors. Based on the screening results, the Response Surface Method (RSM) is employed to construct the test space and derive regression equations for thrust force and thrust fluctuation. The Multi-Objective Grasshopper Optimization Algorithm (MOGOA) is then utilized to iteratively optimize the regression equation for optimal parameter sizes. Finally, the optimized results are validated through finite element analysis (FEA) and compared with the original motor performance to demonstrate the effectiveness of the optimization approach proposed in this paper.

show abstract

“…Optimization efforts for interior permanent magnet synchronous motors within hub motors, utilizing a Kriging model based on Latin hypercube sampling, have achieved a broader speed range and reduced cogging torque [17]. The optimization of average thrust and thrust ripple for double-layered flux-switching permanent magnet motors was successfully realized through a hybrid approach, integrating random forest optimization of hyperparameters with non-dominated sorting genetic algorithm-II (NSGA-II) [18]. The utilization of a proxy model based on DNN has facilitated the optimization of rotor torque and mechanical stress for motors [19].…”

Section: Introductionmentioning

confidence: 99%

A Data-Driven Motor Optimization Method Based on Support Vector Regression—Multi-Objective, Multivariate, and with a Limited Sample Size

Li,

Hou

et al. 2024

Electronics

View full text Add to dashboard Cite

The increasing demand for sustainable development and energy efficiency underscores the importance of optimizing motors in driving the upgrade of energy structures. This paper studies a data-driven approach for the multi-objective optimization of motors designed for scenarios involving multiple variables, objectives, and limited sample sizes and validates its efficacy. Initially, sensitivity analysis is employed to identify potentially influential variables, thus selecting key design parameters. Subsequently, Latin hypercube sampling (LHS) is utilized to select experimental points, ensuring the coverage of the modeled test points across the experimental space to enhance fitting accuracy. Finally, the support vector regression (SVR) algorithm is employed to fit the objective function, in conjunction with multi-objective particle swarm optimization (MOPSO) for solution derivation. The presented method is used to optimize the efficiency, average output torque, and induced electromotive force harmonic distortion rate of a permanent magnet synchronous motor (PMSM). The results show an improvement of approximately 6.80% in average output torque and a significant decrease of about 59.5% in the induced electromotive force harmonic distortion rate, with minimal impact on efficiency. This study offers a pathway for enhancing motor performance, holding practical significance.

show abstract

Multi-objective optimization based on hyperparameter random forest regression for linear motor design

Cited by 9 publications

References 43 publications

A long secondary linear traction motor analysis based on electromagnetic-thermal-fluid coupling

A long secondary linear traction motor analysis based on electromagnetic-thermal-fluid coupling

Co-optimization of Long Secondary Double-sided Linear Flux Switching Permanent Magnet Motors

A Data-Driven Motor Optimization Method Based on Support Vector Regression—Multi-Objective, Multivariate, and with a Limited Sample Size

Contact Info

Product

Resources

About