EPE Association: EPE 2022 - LS4e: Neural Network / Machine Learning

EPE 2022 - LS4e: Neural Network / Machine Learning
You are here: EPE Documents > 01 - EPE & EPE ECCE Conference Proceedings > EPE 2022 ECCE Europe - Conference > EPE 2022 - Topic 10: > EPE 2022 - LS4e: Neural Network / Machine Learning

   [return to parent folder]

   Characterization of Online Junction Temperature of the SiC power MOSFET by Combination of Four TSEPs using Neural Network
By Kanuj SHARMA [View]
[Download]

Abstract: This paper presents an approach to combine multiple temperature-sensitive electrical parameters to improve the accuracy and precision of the junction temperature estimation of power transistors using the example of a silicon-carbide power MOSFET. Switching delays and the threshold voltage of the power transistor during turn-on and -off of a silicon-carbide power transistor are used as temperature-sensitive electrical parameters for the online junction temperature measurements. In order to improve the accuracy, a shallow fully-connected neural network is used as the means to combine the four measurements in one switching cycle of the transistor. The maximum measurement error of the junction temperature of the power transistor is reduced approximately 10 fold from 8.98 K to 0.92 K.

   Deep Neural Network for Magnetic Core Loss Estimation using the MagNet Experimental Database
By Xaiobing SHEN [View]
[Download]

Abstract: Magnetic components play a critical role in power electronics systems and their evolution towards higher power density and efficiency. Nevertheless, accurately modelling magnetic core losses is not a trivial task, requiring extensive measurements. In the context of the general advances of Machine Learning technologies in power electronics applications, this paper presents a Deep Neural Network (DNN) approach to core loss estimations. Various internal parameters of the DNN are tested and compared, to identify the optimal DNN structure for the core loss estimation, including the number of hidden layers, number of neurons, data transformation, and different activation functions. The training data-set comprises the MagNet database for N87 toroid magnetic cores, based on an experimental data acquisition system capable of automatically measuring various magnetic cores under arbitrary excitation signals. The results of the DNN models indicate that a DNN with suitable parameters can robustly and accurately model the core losses. The attainable accuracy is well within the required range for magnetic core losses. The optimal structure proposed in this paper consists of 10 hidden layers with sigmoid activation functions, 10 neurons in each layer, integrating a log-transformation and data normalization. The model is validated with extensive experimental tests similar to the MagNet measurement system. Furthermore, tests at higher switching frequencies up to 1MHz indicate that the model can predict losses for parameters outside the range of its training data. With the achieved performance, the DNN can benefit various power electronics engineering challenges such as loss estimation for inductor design.

   Knowledge Based Grey Box Modeling of Inaccessible Circuits for System EMC-Simulation in Time Domain
By Jan-Philipp ROCHE [View]
[Download]

Abstract: Time domain simulations are important to efficiently optimize function and EMC of electrical circuits in one setup together. Knowledge based grey box modeling is a promising approach for modeling inaccessible circuits which enables simulations of whole electrical systems. Grey box modeling combines the advantages of white and black box modeling. This work examines and evaluates the application possibilities in the field of EMC considerations. Furthermore, perspectives for future work are given.

EPE 2022 - LS4e: Neural Network / Machine Learning
You are here: EPE Documents > 01 - EPE & EPE ECCE Conference Proceedings > EPE 2022 ECCE Europe - Conference > EPE 2022 - Topic 10: > EPE 2022 - LS4e: Neural Network / Machine Learning
	[return to parent folder]

	Characterization of Online Junction Temperature of the SiC power MOSFET by Combination of Four TSEPs using Neural Network By Kanuj SHARMA	[View] [Download]
Abstract: This paper presents an approach to combine multiple temperature-sensitive electrical parameters to improve the accuracy and precision of the junction temperature estimation of power transistors using the example of a silicon-carbide power MOSFET. Switching delays and the threshold voltage of the power transistor during turn-on and -off of a silicon-carbide power transistor are used as temperature-sensitive electrical parameters for the online junction temperature measurements. In order to improve the accuracy, a shallow fully-connected neural network is used as the means to combine the four measurements in one switching cycle of the transistor. The maximum measurement error of the junction temperature of the power transistor is reduced approximately 10 fold from 8.98 K to 0.92 K.

	Deep Neural Network for Magnetic Core Loss Estimation using the MagNet Experimental Database By Xaiobing SHEN	[View] [Download]
Abstract: Magnetic components play a critical role in power electronics systems and their evolution towards higher power density and efficiency. Nevertheless, accurately modelling magnetic core losses is not a trivial task, requiring extensive measurements. In the context of the general advances of Machine Learning technologies in power electronics applications, this paper presents a Deep Neural Network (DNN) approach to core loss estimations. Various internal parameters of the DNN are tested and compared, to identify the optimal DNN structure for the core loss estimation, including the number of hidden layers, number of neurons, data transformation, and different activation functions. The training data-set comprises the MagNet database for N87 toroid magnetic cores, based on an experimental data acquisition system capable of automatically measuring various magnetic cores under arbitrary excitation signals. The results of the DNN models indicate that a DNN with suitable parameters can robustly and accurately model the core losses. The attainable accuracy is well within the required range for magnetic core losses. The optimal structure proposed in this paper consists of 10 hidden layers with sigmoid activation functions, 10 neurons in each layer, integrating a log-transformation and data normalization. The model is validated with extensive experimental tests similar to the MagNet measurement system. Furthermore, tests at higher switching frequencies up to 1MHz indicate that the model can predict losses for parameters outside the range of its training data. With the achieved performance, the DNN can benefit various power electronics engineering challenges such as loss estimation for inductor design.

	Knowledge Based Grey Box Modeling of Inaccessible Circuits for System EMC-Simulation in Time Domain By Jan-Philipp ROCHE	[View] [Download]
Abstract: Time domain simulations are important to efficiently optimize function and EMC of electrical circuits in one setup together. Knowledge based grey box modeling is a promising approach for modeling inaccessible circuits which enables simulations of whole electrical systems. Grey box modeling combines the advantages of white and black box modeling. This work examines and evaluates the application possibilities in the field of EMC considerations. Furthermore, perspectives for future work are given.