“…Each model was applied on the generated FE database and trained 50 times with random resampling of the available data set from which 20% were reserved for testing the efficacy of the models, although not all samples for used. A portion of the training data set was also used for the hyperparameter tuning similar to the tuning process in Hanic et al (2021). This experimental methodology was used to assess not only the quality but also the robustness of the surrogate models with respect to different training and test sets.…”
Section: Surrogate Modeling Of Coupled Multiphysics Finite Element Si...mentioning
confidence: 99%
“…Also, the authors in Liao et al (2021) applied a neural network to optimize the performance of electric motors, where the control drive circuit, particularly the inverter module, was the major highlight of their work. Again, neural network models were used in Hanic et al (2021) to predict iron losses and the power output of synchronous machines.…”
Purpose
Evaluating the multiphysics performance of an electric motor can be a computationally intensive process, especially where several complex subsystems of the motor are coupled together. For example, evaluating acoustic noise requires the coupling of the electromagnetic, structural and acoustic models of the electric motor. Where skewed poles are considered in the design, the problem becomes a purely three-dimensional (3D) multiphysics problem, which could increase the computational burden astronomically. This study, therefore, aims to introduce surrogate models in the design process to reduce the computational cost associated with solving such 3D-coupled multiphysics problems.
Design/methodology/approach
The procedure involves using the finite element (FE) method to generate a database of several skewed rotor pole surface-mounted permanent magnet synchronous motors and their corresponding electromagnetic, structural and acoustic performances. Then, a surrogate model is fitted to the data to generate mapping functions that could be used in place of the time-consuming FE simulations.
Findings
It was established that the surrogate models showed promising results in predicting the multiphysics performance of skewed pole surface-mounted permanent magnet motors. As such, such models could be used to handle the skewing aspects, which has always been a major design challenge due to the scarcity of simulation tools with stepwise skewing capability.
Originality/value
The main contribution involves the use of surrogate models to replace FE simulations during the design cycle of skewed pole surface-mounted permanent magnet motors without compromising the integrity of the electromagnetic, structural, and acoustic results of the motor.
“…Each model was applied on the generated FE database and trained 50 times with random resampling of the available data set from which 20% were reserved for testing the efficacy of the models, although not all samples for used. A portion of the training data set was also used for the hyperparameter tuning similar to the tuning process in Hanic et al (2021). This experimental methodology was used to assess not only the quality but also the robustness of the surrogate models with respect to different training and test sets.…”
Section: Surrogate Modeling Of Coupled Multiphysics Finite Element Si...mentioning
confidence: 99%
“…Also, the authors in Liao et al (2021) applied a neural network to optimize the performance of electric motors, where the control drive circuit, particularly the inverter module, was the major highlight of their work. Again, neural network models were used in Hanic et al (2021) to predict iron losses and the power output of synchronous machines.…”
Purpose
Evaluating the multiphysics performance of an electric motor can be a computationally intensive process, especially where several complex subsystems of the motor are coupled together. For example, evaluating acoustic noise requires the coupling of the electromagnetic, structural and acoustic models of the electric motor. Where skewed poles are considered in the design, the problem becomes a purely three-dimensional (3D) multiphysics problem, which could increase the computational burden astronomically. This study, therefore, aims to introduce surrogate models in the design process to reduce the computational cost associated with solving such 3D-coupled multiphysics problems.
Design/methodology/approach
The procedure involves using the finite element (FE) method to generate a database of several skewed rotor pole surface-mounted permanent magnet synchronous motors and their corresponding electromagnetic, structural and acoustic performances. Then, a surrogate model is fitted to the data to generate mapping functions that could be used in place of the time-consuming FE simulations.
Findings
It was established that the surrogate models showed promising results in predicting the multiphysics performance of skewed pole surface-mounted permanent magnet motors. As such, such models could be used to handle the skewing aspects, which has always been a major design challenge due to the scarcity of simulation tools with stepwise skewing capability.
Originality/value
The main contribution involves the use of surrogate models to replace FE simulations during the design cycle of skewed pole surface-mounted permanent magnet motors without compromising the integrity of the electromagnetic, structural, and acoustic results of the motor.
“…Application of metamodels in electrical engineering is wide. As an example, it is used for the evaluation of electromagnetic performances [6] or the sizing of an electric machine for automotive application in [7] and [4]. This paper proposes an approach based on metamodeling and analytical modelling to evaluate electric powertrain losses on a drive cycle.…”
Components selection and mutualizing for different segments are needed to improve electric vehicle powertrains and limit costs. This paper proposes a first accelerated approach to model and design the electric vehicle powertrain. The optimization scope includes relevant electric powertrain components such as the inverter, the electrical machine, and the reducer. This methodology applies metamodeling techniques for estimating losses in the machine and analytical models for calculating the inverter and the reducer power losses. The driving cycle is considered through the k-means method to reduce the number of operating points considered. The multi-objective optimization is applied to a case study for the WLTC drive cycle and multiple component combinations to investigate modularity.
“…Several authors are interested in using these modeling methods for the design of electrical machines. The application of metamodels for the optimal design of electric machines is wide, for example, neural networks are used to represent the torque waveforms as a function of current amplitude and frequency [5], for the evaluation of electromagnetic performances [6], or as in [7] for the sizing of an induction machine for an automotive application. Although the formulation of the metamodel is complex [8], its use is straightforward and gives the system designer the possibility to exploit a trade-off between accuracy and computation time [9].…”
HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.