Surrogate Thermal Model for Power Electronic Modules using Artificial Neural Network

Abstract

Virtual prototyping of power electronic modules aims to allow rapid evaluation of potential designs without building and testing physical prototypes. Among the interests in thermal models of the virtual modules, process of compact thermal models needs effective methodology to fast generate small models describing the thermal performance of a potential design. This study chooses the Generalized Minimized Residual (GMRES) Algorithm to process thermal models due to its efficiency. Based on that, a machine learning aided surrogate model is proposed for the prediction of thermal performance since existing approaches take much time to determine the thermal response to a particular input power. This surrogate model is created by training a dedicated artificial neural network (ANN) on simulation data, after that this model can quickly map the module temperature and the power input in time domain. In the training process, crossvalidation method is introduced to determine which neuron structure should be selected for the practical data generated by thermal equations. The test group is noted in cross-validation to give the prediction performance of structure candidates. To verify the proposed method, the resulting data of trained surrogate models are compared with the accurate simulation data after the ANN based cross-validation.

A Model-Data-Hybrid-Driven Diagnosis Method for Open-Switch Faults in Power Converters

“…are multiplied with given weights and then the bias is added. After that, the result is further processed through an activation function to give the neuron's output [20] . Namely,…”

Filter Design and Optimization of Electromechanical Actuation Systems Using Search and Surrogate Algorithms for More-Electric Aircraft Applications

“…The neuron number in hidden layers can be set an ANN algorithm developer. Therefore, neuron number selection for different ANN structures is flexible and this has been a persistent and hot topic in multi-discipline studies [31]- [33]. Bayesian network, SVM and other ML methods can also be trained and used in similar ways thus they should be categorised as surrogate algorithms.…”

“…In addition, 'KernelScale' is set as 'auto', 'Standardize' is 'ture' and 'outlierFraction' is zero [20], [46]. It takes 102.95 secs to train this SVM model in Matlab on a standard computer and around 8 mins to do the further cross-validation [33] and validation loss calculation. The training performance is quantified by the class loss which can be obtained using crossvalidation [33].…”

“…It takes 102.95 secs to train this SVM model in Matlab on a standard computer and around 8 mins to do the further cross-validation [33] and validation loss calculation. The training performance is quantified by the class loss which can be obtained using crossvalidation [33]. In this study, the class loss result is 7.53%.…”

Machine Learning Based Correction Model in PMSM Power Loss Estimation for More-Electric Aircraft Applications

“…This paper proposes a ML based correction model to give the correction factors ( ) for motor loss estimation. This model is implemented by establishing a forward Artificial Neural Network (ANN) which is a common and powerful learning method in ML, deep learning and artificial intelligence areas [11][12][13][14]. ANN is based on a nonparametric regression model which is a technique for supervised learning.…”