Advanced Design Optimization Technique for Torque Profile Improvement in Six-Phase PMSM Using Supervised Machine Learning for Direct-Drive EV

Dhulipati, Himavarsha; Ghosh, Eshaan; Mukundan, Shruthi; Korta, Philip; Tjong, Jimi; Kar, Narayan C.

doi:10.1109/tec.2019.2933619

Cited by 51 publications

(36 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other studies as [16] use the so called computationally-efficient FEA (CE-FEA), which uses the pseudo rotating position to reproduce the time evolution of electromagnetic magnitudes using magneto-static analysis. Some other studies avoid using FEA by applying supervised machine learning [17] . Nevertheless, these methods are limited to the PMSM topology of study, while depending on an analytical model to perform the electromagnetic [18] or a thermal analysis [19].…”

Section: Introductionmentioning

confidence: 99%

Customized PMSM Design and Optimization Methodology For Water Pumping Applications

Candelo-Zuluaga

Riba

Espinosa

et al. 2022

IEEE Trans. Energy Convers.

View full text Add to dashboard Cite

The need to reduce water pumps size to achieve compact designs adapted to multiple working points opens new fields of study. PMSMs are the preferred choice due to outstanding torque-speed range capabilities. This paper presents a methodology to design and optimize PMSMs by defining the desired torque-speed-efficiency map, adapting its performance to the hydraulic characteristics of the water pump. Once the hydraulic efficiency is known, an initial PMSM reference torquespeed-efficiency map is defined according to the objective motor performance, including the distribution of power losses and the power rating of the selected application. The designer has full freedom to define the efficiency levels and distribution along the torque-speed map. The design optimization algorithm achieves the PMSM characteristics which adjust as much as possible to the defined performance. This methodology uses ultra-fast finite element analysis by applying magneto-static computations and a time-space conversion to compute the iron losses, reducing the computational requirements. The torque-speed-efficiency map is calculated by applying a direct-quadrature electrical model. The objective function uses a novel image comparison technique that allows comparing the similarity between the objective and optimized maps. The methodology is validated experimentally by designing and testing a PMSM adapted to a real WP application.

show abstract

Section: Introductionmentioning

confidence: 99%

Customized PMSM Design and Optimization Methodology For Water Pumping Applications

Candelo-Zuluaga

Riba

Espinosa

et al. 2022

IEEE Trans. Energy Convers.

View full text Add to dashboard Cite

show abstract

“…The PMSM's properties are always restricted by heat generation and dissipation, so elevated temperature distribution has a significant impact on in-wheel motor performance. To further improve the power density and torque density of motor, numerous methods are researched such as non-dominated sorting genetic algorithm ჟ for dual-structure permanent magnet machine [3] and supervised machine learning for sixphase PMSM [4].…”

Section: Introductionmentioning

confidence: 99%

Investigation of Axial Flux In-Wheel Motor Performances Based on Multiphysics Analysis

Dou

Zhang

et al. 2021

E3S Web Conf.

View full text Add to dashboard Cite

The axial flux with amorphous alloy stators has the virtues of high power density, high torque density, compact structure. But specific to the disadvantage of restricted space of in-wheel, the compact axial flux in-wheel motor was proposed in this paper. The in-wheel motor’s performance affects the dynamic and security of electric vehicles directly. And the electromagnetic loss has a significant impact on in-wheel motor performance. To demonstrate the influence of electromagnetic loss on the thermal behavior of the machine, thermal analyses employing magneto-thermal coupling simulations have been performed. Then the experimental prototype was manufactured and tested. The simulation of the output power model was verified by test value, proving that the magneto-thermal coupling simulation is feasible. Therefore, this design technique provides a reference for the in-wheel motor structure.

show abstract

“…A six-phase transverse flux tubular permanent magnet linear motor was designed with a faulttolerant control strategy in [25]. Authors in [26] optimized the torque profile of a six-phase PMSM for a direct-drive EV with supervised machine learning. In [27], multi-level inverter was optimally designed with two sets of three-phase windings for better fault-tolerant and reduced torque ripple of an induction motor.…”

Section: Introductionmentioning

confidence: 99%

Digital Collaborative Development of a High Reliable Auxiliary Electric Drive System for eTransportation: From Dual Three-Phase PMSM to Control Algorithm

Guang-ming

et al. 2020

IEEE Access

View full text Add to dashboard Cite

For electrified transportation (eTransportation) systems, multi-phase motors can provide higher performance and reliability than three-phase ones, but also bring more challenges in their optimal design and control. In this article, a set of high reliable electric drive system based on dual three-phase permanent magnet synchronous motor (DTP PMSM) is developed for auxiliary systems in eTransportation field. A digital collaborative develop process is proposed with the support of multiple software tools. Design, manufacture, and bench testing stages of the DTP PMSM, the two-level six-phase inverter, and the control algorithm are efficiently incorporated. A prototype of the multi-phase electric drive system is fabricated and tested. Comparison of the simulation analysis and experimental results confirms the effectiveness of the collaborative develop progress. Control algorithms based on dual d-q model and vector space decomposition model are both verified and compared via the bench test. Operation mode switching from six-phase mode to three-phase mode is also realized with the prototype system, verifying its capability in fault-tolerant and potential in efficiency optimizing. INDEX TERMS Dual three-phase motor, auxiliary electric drive system, transportation electrification, digital collaborative development, motor design and control.

show abstract

Advanced Design Optimization Technique for Torque Profile Improvement in Six-Phase PMSM Using Supervised Machine Learning for Direct-Drive EV

Cited by 51 publications

References 37 publications

Customized PMSM Design and Optimization Methodology For Water Pumping Applications

Customized PMSM Design and Optimization Methodology For Water Pumping Applications

Investigation of Axial Flux In-Wheel Motor Performances Based on Multiphysics Analysis

Digital Collaborative Development of a High Reliable Auxiliary Electric Drive System for eTransportation: From Dual Three-Phase PMSM to Control Algorithm

Contact Info

Product

Resources

About