Sequence Prediction for SiC MOSFET Active Gate Driving With a Recurrent Neural Network
This article develops a recurrent neural network (RNN) with an encoder–decoder structure to predict the driving sequence of SiC MOSFET active gate drivers (AGDs). With a set of switching targets as the input, the predictor generates an optimal active gate driving sequence to improve the s...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Open Journal of Industry Applications |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10171405/ |
| _version_ | 1797780785020796928 |
|---|---|
| author | Li Yang Yuxuan Liu Wensong Yu Iqbal Husain |
| author_facet | Li Yang Yuxuan Liu Wensong Yu Iqbal Husain |
| author_sort | Li Yang |
| collection | DOAJ |
| description | This article develops a recurrent neural network (RNN) with an encoder–decoder structure to predict the driving sequence of SiC MOSFET active gate drivers (AGDs). With a set of switching targets as the input, the predictor generates an optimal active gate driving sequence to improve the switching transient. The development is based on a hybrid platform across MATLAB, PyTorch, and LTspice. A high-fidelity switching model is implemented in MATLAB to obtain reliable training data. The sequence predictor is trained with PyTorch. The predicted sequence is verified on an example Buck circuit in LTspice. In contrast to the state-of-the-art approach, the proposed method avoids exhaustive search in a large solution space; the sequence length is dynamically predicted per the driving strength at each step. The AGD sequences generated by the predictor effectively and precisely improve the switching transients, making the proposed sequence predictor an integral and valuable component for active gate driving. |
| first_indexed | 2024-03-12T23:48:46Z |
| format | Article |
| id | doaj.art-cf9bfeaa1390429abe816230a22a0e27 |
| institution | Directory Open Access Journal |
| issn | 2644-1241 |
| language | English |
| last_indexed | 2024-03-12T23:48:46Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Industry Applications |
| spelling | doaj.art-cf9bfeaa1390429abe816230a22a0e272023-07-13T23:00:53ZengIEEEIEEE Open Journal of Industry Applications2644-12412023-01-01422723710.1109/OJIA.2023.329163710171405Sequence Prediction for SiC MOSFET Active Gate Driving With a Recurrent Neural NetworkLi Yang0https://orcid.org/0000-0002-7116-3419Yuxuan Liu1Wensong Yu2https://orcid.org/0000-0002-2459-4697Iqbal Husain3https://orcid.org/0000-0003-0089-4326FREEDM System Center, North Carolina State University, Raleigh, NC, USADepartment of Mechanical and Aerospace Engineering, North Carolina State University, Raleigh, NC, USAFREEDM System Center, North Carolina State University, Raleigh, NC, USAFREEDM System Center, North Carolina State University, Raleigh, NC, USAThis article develops a recurrent neural network (RNN) with an encoder–decoder structure to predict the driving sequence of SiC MOSFET active gate drivers (AGDs). With a set of switching targets as the input, the predictor generates an optimal active gate driving sequence to improve the switching transient. The development is based on a hybrid platform across MATLAB, PyTorch, and LTspice. A high-fidelity switching model is implemented in MATLAB to obtain reliable training data. The sequence predictor is trained with PyTorch. The predicted sequence is verified on an example Buck circuit in LTspice. In contrast to the state-of-the-art approach, the proposed method avoids exhaustive search in a large solution space; the sequence length is dynamically predicted per the driving strength at each step. The AGD sequences generated by the predictor effectively and precisely improve the switching transients, making the proposed sequence predictor an integral and valuable component for active gate driving.https://ieeexplore.ieee.org/document/10171405/Active gate driver (AGD)deep learningrecurrent neural network (RNN)sequence predictionSiC MOSFET |
| spellingShingle | Li Yang Yuxuan Liu Wensong Yu Iqbal Husain Sequence Prediction for SiC MOSFET Active Gate Driving With a Recurrent Neural Network IEEE Open Journal of Industry Applications Active gate driver (AGD) deep learning recurrent neural network (RNN) sequence prediction SiC MOSFET |
| title | Sequence Prediction for SiC MOSFET Active Gate Driving With a Recurrent Neural Network |
| title_full | Sequence Prediction for SiC MOSFET Active Gate Driving With a Recurrent Neural Network |
| title_fullStr | Sequence Prediction for SiC MOSFET Active Gate Driving With a Recurrent Neural Network |
| title_full_unstemmed | Sequence Prediction for SiC MOSFET Active Gate Driving With a Recurrent Neural Network |
| title_short | Sequence Prediction for SiC MOSFET Active Gate Driving With a Recurrent Neural Network |
| title_sort | sequence prediction for sic mosfet active gate driving with a recurrent neural network |
| topic | Active gate driver (AGD) deep learning recurrent neural network (RNN) sequence prediction SiC MOSFET |
| url | https://ieeexplore.ieee.org/document/10171405/ |
| work_keys_str_mv | AT liyang sequencepredictionforsicmosfetactivegatedrivingwitharecurrentneuralnetwork AT yuxuanliu sequencepredictionforsicmosfetactivegatedrivingwitharecurrentneuralnetwork AT wensongyu sequencepredictionforsicmosfetactivegatedrivingwitharecurrentneuralnetwork AT iqbalhusain sequencepredictionforsicmosfetactivegatedrivingwitharecurrentneuralnetwork |