Equivalent Motor Radiation of an Electric Vehicle Based on Neural Network Approach

The feedforward neural network method is utilized in this paper for predicting the desired electromagnetic radiation properties of the motor of an electric vehicle. The neural network is first fully trained by simulation data and its predicted field values are then compared with those obtained through "traditional" FEKO simulations. The comparison has demonstrated a similar level of accuracy for both approaches, but the simulation time and cost can be dramatically reduced by employing the neural network method.

[1]  Prediction of IC Equivalent Magnetic Dipoles Using Deep Convolutional Neural Network , 2018, 2018 IEEE Electrical Design of Advanced Packaging and Systems Symposium (EDAPS).

[2]  Om P. Malik,et al.  An orthogonal test approach based control parameter optimization and its application to a hydro-turbine governor , 1997 .

[3]  Fabio Viola,et al.  Evaluation of Radiated EMI in 42-V Vehicle Electrical Systems by FDTD Simulation , 2007, IEEE Transactions on Vehicular Technology.

[4]  Skewed stator synchronous motor modeling by a 2D electromagnetic simulation software , 1991 .

[5]  N. Takorabet,et al.  Optimization of instantaneous torque shape of PM motors using artificial neural networks based on FE results , 2006, IEEE Transactions on Magnetics.

[6]  X. Ferrieres,et al.  Application of a hybrid finite difference/finite volume method to solve an automotive EMC problem , 2004, IEEE Transactions on Electromagnetic Compatibility.

[7]  Zhonghong Wang,et al.  Artificial neural networks controlled fast valving in a power generation plant , 1997, IEEE Trans. Neural Networks.

[8]  Shaoqiu Xiao,et al.  Design of Pattern Reconfigurable Antennas Based on a Two—Element Dipole Array Model , 2013, IEEE Transactions on Antennas and Propagation.

[9]  C. Ullrich,et al.  Validation of Hybrid MoM Scheme With Included Equivalent Glass Antenna Model for Handling Automotive EMC Problems , 2010, IEEE Transactions on Electromagnetic Compatibility.

[10]  G. Capizzi,et al.  A Neural Network tool for the prediction of electromagnetic field in urban environment , 2006, 2006 12th Biennial IEEE Conference on Electromagnetic Field Computation.