Modeling Finite-Element Constraint to Run an Electrical Machine Design Optimization Using Machine Learning

Arnoux, Pierre-Hadrien; Caillard, Pierre; Gillon, F.

doi:10.1109/tmag.2014.2364031

Cited by 11 publications

(6 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This enables predictive maintenance, minimizes failures, and extends the machine's lifespan. • Performance Prediction and Optimization: Data mining techniques can be applied to historical performance data to identify patterns, correlations, and relationships between operating conditions, design parameters, and performance metrics [190]. This information can then be used to predict the performance of FSMs under different conditions and optimize their operation for maximum efficiency and desired output.…”

Section: ) Machine Learning and Data Mining Techniquesmentioning

confidence: 99%

Advancements in Flux Switching Machine Optimization: Applications and Future Prospects

Abunike,

Okoro,

Far

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Flux switching machines play a crucial role in emerging sectors such as renewable energy, electric vehicles, and the aerospace industry. Recent advancements have underscored their potential for achieving high torque density, effective heat management, and flux-weakening capabilities. This paper provides a comprehensive review of the design optimization of these machines, offering a unique contribution, as no previous attempts have delved into a detailed exploration of various optimization techniques specific to this technology. Special attention is given to state-of-the-art technologies related to multi-objective optimization and the performance analysis of the three variants: permanent magnet, wound-field, and hybrid excited. The review highlights and compares several optimization strategies from recent research, revealing research gaps in integrating advanced control algorithms, thermal, vibroacoustic, and structural models into the optimization design process of these machines. Furthermore, this review identifies essential trends in optimization development, offering valuable insights and future perspectives for these machines across diverse applications.

show abstract

Section: ) Machine Learning and Data Mining Techniquesmentioning

confidence: 99%

Advancements in Flux Switching Machine Optimization: Applications and Future Prospects

Abunike,

Okoro,

Far

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Overall, there is more research carried out on machine learning for improving the runtime of the optimization of electromagnetic devices, as was also shown in Table 2. Different machine learning algorithms, such as SVM, multi-layer perceptron (MLP), Knearest neighbor (KNN), and CNN have been investigated to optimize transformers, antennas, and motors (motors are the majority applications) [135][136][137][138][139][140][141][142][146][147][148][149][150]. It is noted that deep learning follows promising results when applied for topology optimization of electromagnetic devices, and this topic has attracted much attention recently [143][144][145].…”

Section: Machine Learning For Optimization Of Electromagnetic Devicesmentioning

confidence: 99%

Machine Learning for Design Optimization of Electromagnetic Devices: Recent Developments and Future Directions

Lei

Bramerdorfer

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

This paper reviews the recent developments of design optimization methods for electromagnetic devices, with a focus on machine learning methods. First, the recent advances in multi-objective, multidisciplinary, multilevel, topology, fuzzy, and robust design optimization of electromagnetic devices are overviewed. Second, a review is presented to the performance prediction and design optimization of electromagnetic devices based on the machine learning algorithms, including artificial neural network, support vector machine, extreme learning machine, random forest, and deep learning. Last, to meet modern requirements of high manufacturing/production quality and lifetime reliability, several promising topics, including the application of cloud services and digital twin, are discussed as future directions for design optimization of electromagnetic devices.

show abstract

“…On the other hand, with the development of the graphics processing unit hardware and algorithm efficiency, deep learning (DL) is poised to be a very powerful tool that can significantly increase our ability to conduct scientific research [5] and has demonstrated good potentials for the application in the field of computational electromagnetics [6]. DL has been successfully applied in the design and optimization of electrical devices such as motors [7], transformers [8, 9] and antennas [10], with satisfactory results. Among the many DL networks, in particular, the convolutional neural network (CNN), which is a type of network that automatically detects important features without any human supervision, has been widely used and some state‐of‐the‐art performances acheived.…”

Section: Introductionmentioning

confidence: 99%

Further investigation of convolutional neural networks applied in computational electromagnetism under physics‐informed consideration

Gong

Tang

2022

IET Electric Power Appl

View full text Add to dashboard Cite

Convolutional neural networks (CNN) have shown great potentials and have been proven to be an effective tool for some image‐based deep learning tasks in the field of computational electromagnetism (CEM). In this work, an energy‐based physics‐informed neural network (EPINN) is proposed for low‐frequency electromagnetic computation. Two different physics‐informed loss functions are designed. To help the network focus on the region of interest instead of computing the whole domain on average, the magnetic energy norm error loss function is proposed. Besides, the methodology of energy minimization is integrated into the CNN by introducing the magnetic energy error loss function. It is observed that the introduction of the physics‐informed loss functions improved the accuracy of the network with the same architecture and database. Meanwhile, these changes also cause the network to be more sensitive to some hyperparameters and makes the training process oscillate or even diverge. To address this issue, the sensitivity of the network hyperparameters for both physics‐informed loss functions are further investigated. Numerical experiments demonstrate that the proposed approaches have good accuracy and efficiency with fine‐tuned hyperparameters. Furthermore, the post‐test illustrates that the EPINN has excellent interpolation performance and can obtain good extrapolation results under certain restrictions.

show abstract

Modeling Finite-Element Constraint to Run an Electrical Machine Design Optimization Using Machine Learning

Cited by 11 publications

References 10 publications

Advancements in Flux Switching Machine Optimization: Applications and Future Prospects

Advancements in Flux Switching Machine Optimization: Applications and Future Prospects

Machine Learning for Design Optimization of Electromagnetic Devices: Recent Developments and Future Directions

Further investigation of convolutional neural networks applied in computational electromagnetism under physics‐informed consideration

Contact Info

Product

Resources

About