一种基于神经网络优化预测模型的SiC MOSFET阻断电压确定方法
A Method of Determining Blocking Voltage of SiC MOSFET Based on the Neural Network Predict Model
- 机车电传动 2021年第5期 页码：150-155
- 作者机构：
1.西南交通大学 电气工程学院，四川 成都 611756
- 作者简介：
刘东（1988—），男，博士，主要从事电力电子与电力传动的研究；E-mail: 1164523854@qq.com
- 基金信息：
DOI：10.13890/j.issn.1000-128x.2021.05.024
中图分类号：
扫 描 看 全 文
沈俊, 刘东, 唐茂森, 等. 一种基于神经网络优化预测模型的SiC MOSFET阻断电压确定方法[J]. 机车电传动, 2021,(5):150-155.
Jun SHEN, Dong LIU, Maosen TANG, et al. A Method of Determining Blocking Voltage of SiC MOSFET Based on the Neural Network Predict Model[J]. Electric Drive for Locomotives, 2021,(5):150-155.
沈俊, 刘东, 唐茂森, 等. 一种基于神经网络优化预测模型的SiC MOSFET阻断电压确定方法[J]. 机车电传动, 2021,(5):150-155. DOI： 10.13890/j.issn.1000-128x.2021.05.024.
Jun SHEN, Dong LIU, Maosen TANG, et al. A Method of Determining Blocking Voltage of SiC MOSFET Based on the Neural Network Predict Model[J]. Electric Drive for Locomotives, 2021,(5):150-155. DOI： 10.13890/j.issn.1000-128x.2021.05.024.
摘要
功率器件设计者常需要通过器件仿真进行器件的设计与优化，但由于仿真结果的未知性，设计者需要逐步调整相关参数，使仿真结果不断逼近目标值，这需要耗费大量的时间，而目前又没有有效的解决办法。为解决这个问题，提出了一种基于神经网络的优化预测模型，以确定SiC MOSFET的阻断电压。将测试温度、第一场限环间距、环间距变化步长、场限环个数和漂移区浓度作为自变量，代入器件仿真软件中进行仿真，从而得到VDMOSFET阻断电压（作为因变量），将其分别代入BP神经网络和RBF神经网络中进行预测，并对二者的预测误差进行对比。结果表明，使用LM算法的BP神经网络预测模型能够很好地预测VDMOSFET的正向阻断电压，可为设计者节约大量时间。
Abstract
Power device designers often need to design and optimize devices by device simulation, however, due to the simulation results are unknown before the simulation, designers need to gradually adjust the relevant parameters to make the simulation results constantly approach the target value, which costs much time. There is no effective solution to this problem. In order to solve the problem, an optimal prediction model based on neural network was proposed to determine the blocking voltage of SiC MOSFET. The test temperature, the first field limiting ring spacing, the ring spacing change step, the number of field limiting rings and the drift zone concentration were regarded as independent variable, and brought into the device simulation software for simulation. The blocking voltage of VDMOSFET was obtained as the dependent variable, which was brought into BP neural network and RBF neural network for prediction respectively, and the prediction errors of the two were compared. The results show that the BP neural network prediction model by using LM algorithm can well predict the forward blocking voltage of VDMOSFET,and save a lot of time for designers.
关键词
阻断电压SiC MOSFET场限环神经网络预测模型仿真
Keywords
blocking voltageSiC MOSFETfield limiting ringneural networkprediction modelsimulation
references
ROTHMUND Daniel, BORTIS Dominik, KOLAR Johann W. Highly compact isolated gate driver with ultrafast overcurrent protection for 10 kV SiC MOSFETs[J]. CPSS Transactions on Power Electronics and Applications, 2018, 3(4): 278-291. DOI: 10.24295/CPSSTPEA.2018.00028http://doi.org/10.24295/CPSSTPEA.2018.00028.
潘晓伟, 冯全源, 陈晓培. 单区JTE加场板终端结构的优化设计[J]. 电子元件与材料, 2016, 35(11): 38-41.
PAN Xiaowei, FENG Quanyuan, CHEN Xiaopei. Optimization design of single-zone JTE termination with field plate[J]. Electronic Components & Materials, 2016, 35(11): 38-41.
HIRAO Takashi, ONOSE Hidekatsu, YASUI Kan, et al. Edge termination with enhanced field-limiting rings insensitive to surface charge for high-voltage SiC power devices[J]. IEEE Transactions on Electron Devices, 2020, 67(7): 2850-2853.
于静, 金秀章. 基于RBF神经网络的PFC-PID主汽温串级预测控制[J]. 华北电力大学学报(自然科学版), 2020, 47(6): 91-98.
YU Jing, JIN Xiuzhang. PFC-PID main steam temperature cascade predictive control based on RBF neural network[J]. Journal of North China Electric Power University(Natural Science Edition), 2020, 47(6): 91-98.
苏学能, 刘天琪, 曹鸿谦, 等. 基于Hadoop架构的多重分布式BP神经网络的短期负荷预测方法[J]. 中国电机工程学报, 2017, 37(17): 4966-4973.
SU Xueneng, LIU Tianqi, CAO Hongqian, et al. A multiple distributed BP neural networks approach for short-term load forecasting based on Hadoop framework[J]. Proceedings of the CSEE, 2017, 37(17): 4966-4973.
SEZGIN-UGRANLI H G, ÖZÇELEP Y. A new approach for VDMOSFETS gate oxide degradation based on capacitance and subthreshold current measurements under constant electrical stress[J]. IEEE Transactions on Electron Devices, 2018, 65(4): 1650-1652. DOI: 10.1109/TED.2018.2808162http://doi.org/10.1109/TED.2018.2808162.
孔晓李. 高压功率器件结终端技术分析与新结构研究[D]. 成都: 电子科技大学, 2016.
KONG Xiaoli. Research on the technology and new structure of terminal in the high voltage power devices[D]. Chengdu: University of Electronic Science and Technology of China, 2016.
谭犇. 超高压4H-SiC MOSFET器件设计及关键工艺研究[D]. 成都: 电子科技大学, 2019.
TAN Ben. Design and process research of ultra-high voltage 4H-SiC MOSFET[D]. Chengdu: University of Electronic Science and Technology of China, 2019.
盛况, 任娜, 徐弘毅. 碳化硅功率器件技术综述与展望[J]. 中国电机工程学报, 2020, 40(6): 1741-1752.
SHENG Kuang, REN Na, XU Hongyi. A recent review on silicon carbide power devices technologies[J]. Proceedings of the CSEE, 2020, 40(6): 1741-1752.
李龙, 魏靖, 黎灿兵, 等. 基于人工神经网络的负荷模型预测[J]. 电工技术学报, 2015, 30(8): 225-230.
LI Long, WEI Jing, LI Canbin, et al. Prediction of load model based on artificial neural network[J]. Transactions of China Electrotechnical Society, 2015, 30(8): 225-230.
WANG Shaoshuai, ZHU Huangqiu, WU Mengyao, et al. Active disturbance rejection decoupling control for three-degree-of-freedom six-pole active magnetic bearing based on BP neural network[J]. IEEE Transactions on Applied Superconductivity, 2020, 30(4). DOI: 10.1109/TASC.2020.2990794http://doi.org/10.1109/TASC.2020.2990794.
LU Qidong, YANG Rui, ZHONG Maiying, et al. An improved fault diagnosis method of rotating machinery using sensitive features and RLS-BP neural network[J]. IEEE Transactions on Instrumentation and Measurement, 2020, 69(4): 1585-1593. DOI: 10.1109/TIM.2019.2913057http://doi.org/10.1109/TIM.2019.2913057.
童新安. 基于灰色系统与神经网络的组合预测方法及应用研究[D]. 西安: 西安电子科技大学, 2012.
TONG Xin’an. Application and research on combined forecasting model based on grey system and neural network theory[D]. Xi’an: Xidian University, 2012.
0
浏览量
16
下载量
0
CSCD
1
CNKI被引量
- 网络PDF下载
- Meta-XML下载
- BibTeX下载
- Endnote下载
- RefMan 下载
- NoteExpress下载
- NoteFirst下载
关联资源
相关文章
相关作者
相关机构
- 技术支持由北京北大方正电子有限公司提供 湘ICP备20010475号-1
京公网安备11010802024621 - 本系统建议在Chrome、 IE9+ 以上版本浏览器阅读本站内容，360浏览器请切换至极速模式
- Cookies帮助我们提供服务并提供个性化体验。使用本网站，即表示您同意我们使用Cookies