A Back Propagation Neural Network with Double Learning Rate for PID Controller in Phase-Shifted Full-Bridge Soft-switching Power Supply

被引：11

作者：

Cheng, Yan-Ming ^{[1
]}

Liu, Cheng ^{[1
]}

Wu, Jing ^{[1
]}

Liu, He-Miao ^{[1
]}

Lee, Il-Kyoo ^{[2
]}

Niu, Jing ^{[3
]}

Cho, Ju-Phil ^{[4
]}

Koo, Kyung-Wan ^{[5
]}

Lee, Min-Woo ^{[6
]}

Woo, Deok-Gun ^{[6
]}

机构：

[1] Beihua Univ, Coll Elect & Informat Engn, Jilin, Jilin, Peoples R China

[2] Kongju Natl Univ, Div Elect Elect & Control Engn, Kong Ju, South Korea

[3] Jilin Chem Fiber Grp Co Ltd, Jilin, Jilin, Peoples R China

[4] Kunsan Natl Univ, Dept Integrated IT & Commun Engn, Kunsan, South Korea

[5] Hoseo Univ, Dept ICT Automot Engn, Dangjin, South Korea

[6] Seoul Natl Univ Sci & Technol, IT Convergence Technol Res Lab, Seoul, South Korea

来源：

JOURNAL OF ELECTRICAL ENGINEERING & TECHNOLOGY | 2020年 / 15卷 / 06期

关键词：

Phase-shifting full-bridge; Soft-switching; BP neural network; Double learning rate; PID; DC-DC CONVERTER; DESIGN;

D O I：

10.1007/s42835-020-00523-5

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

This paper mainly focuses on the control strategy for phase-shifting full-bridge soft switching electrolytic silver power supply based on Zero Voltage Switching (ZVS) soft switching technology. Taking into consideration the low performance of traditional PID control for phase-shifting full-bridge soft-switching, this paper introduce a PID improved by Back Propagation (BP) neural network with one single learning rate which is used to calculate weights from the input layer to the hidden layer and weights from the hidden layer to the output layer. After testing, it is found that setting independent learning rate for calculation of weights from the input layer to the hidden layer and weights from the hidden layer to the output layer which will not have an adverse effect on the design of the controller. Instead, the learning rate can be set according to the respective characteristics of the weights between the two layers, which is called double learning rate BP neural network PID. The simulation results indicate that compared with the single learning rate BP neural network PID control, the double learning rate BP neural network control has higher response speed, less over-shoot, short time to enter the steady state and strong immunity.

引用

页码：2811 / 2822

页数：12