Surrogate Models for Design and Optimization of Inverter-Fed Synchronous Motor Drives

Ibrahim, Issah; Silva, Rodrigo C. P.; Mohammadi, Mohammad Hossain; Ghorbanian, Vahid; Lowther, D.A.

doi:10.1109/tmag.2021.3070486

Cited by 7 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where the parameters are defined similar to (9). Based on the given equations, 625 (5 � 125) surrogate model have been evaluated for each waveform.…”

Section: Development Of Surrogate Models Based On Waveform Datasetsmentioning

confidence: 99%

“…The background of surrogate modelling techniques for engineering designs can be found in [7]. These models can be established based on TS-FEM data and represent a simplified connection between inputs (design dimensions or circuit parameters) and outputs (such as average torque, torque ripple, losses and efficiency) of the optimization problem with significantly faster computation speed [8][9][10][11][12][13][14][15][16].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Electrical machines surrogate‐based design optimization based on novel waveform targeting strategy with improvement of the computational efficiency

Roomi

Vahedi

Nobahari

2022

IET Electric Power Appl

View full text Add to dashboard Cite

Electrical machine design optimization is an expensive procedure as it contains numerous variables and multiple objectives. Therefore, it might require hundreds of timeconsuming finite element analyses (FEA). Surrogate models are one of the superior alternatives that can overcome the computational burden of FEA. However, in optimization problems with sensitive input-output relationships, surrogate models can lack accuracy or suffer from unreasonable initial FE-computational cost. To tackle this problem, this work presents a novel strategy called Waveform-Targeted Surrogate Modeling (WTSM) that improves the computational efficiency of surrogate-based design optimization of electrical machines by modifying the model construction process. In this paper, an Interior Permanent Magnet Machine (IPMSM) is studied to evaluate the proposed strategy's performance compared to the conventional Black Box Modeling (BBM) method. A two-step assessment procedure consisting of multiple scenarios has been developed to analyse the reliability of the WTSM concerning different training-validation datasets. Meanwhile, the Kriging model and Latin-Hypercube-Sampling (LHS) method are employed for surrogate model construction purposes. From the discussion and the results, it can be found that the proposed WTSM strategy can significantly increase the accuracy of the surrogate modelling procedure while the required computational cost can be reduced.This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

“…where the parameters are defined similar to (9). Based on the given equations, 625 (5 � 125) surrogate model have been evaluated for each waveform.…”

Section: Development Of Surrogate Models Based On Waveform Datasetsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Electrical machines surrogate‐based design optimization based on novel waveform targeting strategy with improvement of the computational efficiency

Roomi

Vahedi

Nobahari

2022

IET Electric Power Appl

View full text Add to dashboard Cite

show abstract

“…Soft magnetic materials for inductors, transformers, and electrical machines have often been overlooked, but they have been considered important in worldwide energy conversions. In general, when driving a motor, excitation with a PWM inverter is used to provide an arbitrary frequency or voltage [16][17][18][19][20][21][22][23][24][25].…”

Section: Introductionmentioning

confidence: 99%

Effect of Laminated Core Body Size on Motor Magnetic Properties

Yun

2023

Magnetism

View full text Add to dashboard Cite

The magnetic characteristics of electromagnetic steel sheets used for motors are evaluated under ideal sinusoidal excitation. However, in actual equipment driving, excitation by pulse-width modulation (PWM) waves is the mainstream method. Therefore, it is necessary to clarify how the magnetic properties used in motors are changed by sinusoidal excitation and inverter excitation. To clarify the magnetic properties of the laminated core by inverter excitation, samples with different core sizes were prepared and the effects on the magnetic properties were then investigated. The magnetic properties were measured by changing only the input voltage VDC while maintaining the carrier frequency and modulation factor constant. As the results, the iron loss values of the small, medium, and large samples with inverter excitation were 6.05, 9.58, and 11.62 W/kg, respectively. The iron losses of the small, medium, and large toroidal cores with inverter excitation increased by 124.9, 256.1, and 332.0%, respectively, compared with the iron loss of each toroidal core with sinusoidal excitation. The larger the body, the higher the required voltage and iron loss. It can be inferred that a larger amount of energy was required to excite a larger toroidal core. This was because the change in magnetic flux density per unit time of the large toroidal core was greater than that of other cores. This indicates that the large toroidal core generated larger eddy currents than other cores. Therefore, it is possible to say that large toroidal cores generate greater eddy current losses than other cores.

show abstract

“…Only a few published articles can be found in the literature on the application of ANNs for modelling the transient behaviour of IM with FE to the best knowledge of the authors. These articles are mostly focused on condition monitoring [3], optimization [4], [5], and in the improvements of different analytical equation based control strategies [6].…”

Section: Introductionmentioning

confidence: 99%

Transient Modeling of Induction Machine Using Artificial Neural Network Surrogate Models

2022

View full text Add to dashboard Cite

A transient model of an induction machine is developed in this work using an artificial neural network surrogate model. The model is suitable to be used for direct-on-line induction machines. Finite element based model of induction machine is used to generate the training, validation, and testing datasets. Different inputs and model configurations are investigated to find an optimal solution in developing the transient model. The proposed transient model is suitable to be used in digital twin services, since it can estimate the current and torque accurately in real time based on only voltage and measured shaft speed.

show abstract

Surrogate Models for Design and Optimization of Inverter-Fed Synchronous Motor Drives

Cited by 7 publications

References 9 publications

Electrical machines surrogate‐based design optimization based on novel waveform targeting strategy with improvement of the computational efficiency

Electrical machines surrogate‐based design optimization based on novel waveform targeting strategy with improvement of the computational efficiency

Effect of Laminated Core Body Size on Motor Magnetic Properties

Transient Modeling of Induction Machine Using Artificial Neural Network Surrogate Models

Contact Info

Product

Resources

About