ID: 438
/ PB-M2: 1
Topics: Optimization and Design, AI and Machine Learning TechnologiesKeywords: Convolutional Neural Network, Deep Learning, Interior Permanent Magnet motor, Topology Optimization
Prediction of Interior Permanent Magnet Motor Characteristics Using CNN with Vector Input of Magnetic Flux Density Distribution
Kazuhisa Iwata1, Hidenori Sasaki1, Hajime Igarashi2, Daisuke Nakagawa3, Tomoya Ueda3
1Hosei University, Japan; 2Hokkaido University, Japan; 3Nidec Research and Development Center, Japan
ID: 396
/ PB-M2: 2
Topics: Numerical Techniques, AI and Machine Learning TechnologiesKeywords: Finite Element Analysis, Eddy Currents, Graph Neural Networks, Approximation Error
Discretization Error Approximation for FEM-Based Eddy Current Models using Neural Networks
Moritz von Tresckow, Herbert De Gersem, Dimitrios Loukrezis
TU Darmstadt, Germany
ID: 356
/ PB-M2: 3
Topics: AI and Machine Learning TechnologiesKeywords: Neural Networks, Direct and Inverse Electromagnetic problems
Physics-Informed Neural Networks for the Resolution of Analysis Problems in Electromagnetics
Sami Barmada1, Paolo Di Barba2, Alessandro Formisano3, Maria Evelina Mognaschi2, Mauro Tucci1
1Universita' di Pisa; 2Universita' di Pavia; 3Universita' della Campania Luigi Vanvitelli, Italy
ID: 381
/ PB-M2: 4
Topics: AI and Machine Learning TechnologiesKeywords: Finite element method, neural network, partial difference equation, physics-informed neural network
A Fast Physics-informed Neural Network Based on Extreme Learning Machine for Solving Magnetostatic Problems
Takahiro Sato1, Hidenori Sasaki2, Yuki Sato3
1Muroran Institute of Technology, Japan; 2Faculty of Science and Engineering, Hosei University, Japan; 3Department of Electrical Engineering and Electronics, Aoyama Gakuin University, Japan
ID: 285
/ PB-M2: 5
Topics: Mathematical Modelling and Formulations, Numerical Techniques, Electromagnetic Sensors, Sensing and Metrology, AI and Machine Learning TechnologiesKeywords: Boundary conditions; Capacitor; inverse problems; deep learning; numerical analysis
Boundary-Decoder network for inverse prediction of capacitor electrostatic analysis
Kart L Lim, RAHUL DUTTA, MIHAI ROTARU
Institute of Microelectronics, Singapore
ID: 211
/ PB-M2: 6
Topics: Optimization and Design, AI and Machine Learning TechnologiesKeywords: Genetic algorithms, Convolutional neural networks, Permanent magnet machines, Finite element methods
1DCNN as an Approximation Model for Torque Optimization of Spoke Type Electrical Machines
Marcelo D. Silva, Sandra Eriksson
Department of Electrical Engineering, Uppsala University, Sweden
ID: 544
/ PB-M2: 7
Topics: AI and Machine Learning TechnologiesKeywords: Deep Learning, Partial Differential Equation, Computational electromagnetics, Magnetic materials
Static Magnetic Field Simulation using Deep Learning-based Method
Katsuhiko Yamaguchi, Masaharu Matsumoto, Kenji Suzuki
Fukushima university, Japan
ID: 430
/ PB-M2: 8
Topics: Static and Quasi-Static Fields, AI and Machine Learning TechnologiesKeywords: deep learning, wireless power transmission, optimization
A deep learning approach to the optimization of the transferred power in dynamic WPT systems
Manuele Bertoluzzo1, Paolo Di Barba2, Michele Forzan1, Maria Evelina Mognaschi2, Elisabetta Sieni3
1University of Padova, Italy; 2University of Pavia, Italy; 3University of Insubria, Varese, Italy
ID: 512
/ PB-M2: 9
Topics: AI and Machine Learning TechnologiesKeywords: Convolutional neural network, reluctance motors, feature extraction, design optimization
Feature Extraction and Visualization Using Convolutional Neural Networks for Design Optimization of Synchronous Reluctance Motors
Marie Katsurai, Yasuhito Takahashi
Doshisha University, Japan
|
