ID: 176
/ PC-M1: 1
Topics: Optimization and Design, AI and Machine Learning TechnologiesKeywords: Design optimization, Induction motors, Reinforcement learning
A Data-driven Automatic Design Method of Induction Motors Based on Tree Search and Reinforcement Learning Considering Multiple Objectives
Takahiro Sato, Kota Watanabe
Muroran Institute of Technology, Japan
ID: 233
/ PC-M1: 2
Topics: Optimization and Design, AI and Machine Learning TechnologiesKeywords: AC motors, permanet magnet motors, traction motors, design optimization, data-driven modeling
A data-driven approach to the design of traction electric motors
Francesco Moraglio, Paolo Ragazzo, Gaetano Dilevrano, Simone Ferrari, Gianmario Pellegrino, Maurizio Repetto
Politecnico di Torino, Italy
ID: 470
/ PC-M1: 3
Topics: AI and Machine Learning TechnologiesKeywords: Convolutional neural networks, data visualization, topology optimization, explainable artificial intelligence.
Visual Interpretation of Topology Optimization Results Based on Deep Learning
Hayaho Sato, Hajime Igarashi
Hokkaido University, Japan
ID: 292
/ PC-M1: 4
Topics: Mathematical Modelling and Formulations, AI and Machine Learning TechnologiesKeywords: neural networks, computational electromagnetics, method of moments
Towards Physics Informed Neural Network Generalised Polygonal Vector Basis Function Model
Marijana Krivic1,2, Jeannick Sercu1, Filip Demuynck1, Tom De Muer1, Thomas Zwick2
1Keysight Technologies, Belgium; 2Institute of Radio Frequency Engineering and Electronics, Karlsruhe Institute of Technology, Karlsruhe, Germany
ID: 166
/ PC-M1: 5
Topics: AI and Machine Learning TechnologiesKeywords: Analytical models, Fault detection, Induction motors, Machine learning
Classification of Electrical Faults in Induction Machines using Multiple Coupled Circuit Modeling and a Neural Network
Moritz Benninger1, Marcus Liebschner1, Christian Kreischer2
1University of Applied Sciences Aalen, Germany; 2Helmut-Schmidt-University, Germany
ID: 334
/ PC-M1: 6
Topics: AI and Machine Learning TechnologiesKeywords: Lightning Localization, Machine Learning, Transmission Lines.
Neural Network Based Procedure for Lightning Localization
Sami Barmada1, Mauro Tucci1, Massimo Brignone2, Martino Nicora2, Renato Procopio2
1Universita di Pisa, Italy; 2University of Genoa, Italy
ID: 128
/ PC-M1: 7
Topics: AI and Machine Learning TechnologiesKeywords: Neural network, alternative flux model, synchronous machines, hybrid-field motor, Bayesian approach
Alternative Flux Model Generation Method for Hybrid-Field Motors Based on Bayesian Approach and Neural Networks
ZHAO TIEYANG1, HIDAKA YUKI1, HIRUMA SHINGO2, KAIMORI HIROYUKI3, EGAWA MICHI4, MATSUSHITA YOSHIKO4
1Department of Electrical, Electronics and Information Engineering,Nagaoka University of Technology; 2Graduate School of Engineering,Kyoto University; 3Science Solutions International Laboratory, Inc.; 4MSC Software Corporation
ID: 144
/ PC-M1: 8
Topics: Multi-Physics and Coupled Problems, AI and Machine Learning TechnologiesKeywords: Electrostatic discharges, Numerical simulation, Plasma simulation, Neural networks, Deep learning.
Numerical Simulation of Streamer Discharge Using Physics-Informed Neural Networks
Changzhi Peng1, Ruth V. Sabariego2, Xuzhu Dong1, Jiangjun Ruan1
1School of Electrical Engineering and Automation, Wuhan University,47000 Wuhan, China; 2Dept. of Electrical Engineering (ESAT), KU Leuven, Campus EnergyVille, 3600 Genk, Belgium
|