基于ISMA-BP神经网络的光伏发电储能双向DC-DC变换器控制  

Control of Bidirectional DC-DC Converter for Photovoltaic Energy Storage based on ISMA-BP Neural Network

作　　者：党娟 王伟超 Dang Juan;Wang Weichao(Yulin Vocational and Technical College,Yulin 719000,China;Chongqing University of Technology,Chongqing 400054,China)

机构地区：[1]榆林职业技术学院,陕西榆林719000 [2]重庆理工大学,重庆400054

出　　处：《现代科学仪器》2024年第4期214-218,共5页Modern Scientific Instruments

基　　金：陕西省榆林市科学技术局课题项目(编号:CXY-2020-016-01)。

摘　　要：通过对光伏发电储能双向DC-DC变换器抗干扰问题进行研究,提出一种基于ISMA-BP神经网络的光伏发电储能双向DC-DC变换器控制方法。首先,建立双向DC-DC变换器双闭环模型,采用模糊神经网络优化后的PID控制器对电压外环进行控制。其次,设计多子种群多进化策略黏菌优化算法(Slime Mould Algorithm,SMA),以提高算法全局寻优精度。采用改进的SMA(improved SMA,ISMA)初始化BP神经网络参数,以提升BP神经网络控制稳定性。最后,利用ISMA-BP神经网络实时动态调整PID控制器参数,实现变换器输出电压稳定控制。仿真结果表明,所提双向DC-DC变换器控制方法稳定性较好、抗干扰能力较强。the anti-interference issues of bidirectional DC-DC converters for photovoltaic energy storage is researched,and a control method for bidirectional DC-DC converters for photovoltaic energy storage based on ISMA-BP neural network is proposed.The dual closed-loop model for the bidirectional DC-DC converter is established,and the fuzzy neural network optimized PID controller to control the voltage outer loop is used.Secondly,the multi subpopulation and multi evolutionary strategy slime mould algorithm(SMA)is designed to improve the global optimization accuracy.The improved SMA(ISMA)is used to initialize the parameters of the BP neural network,in order to enhance the stability of the BP neural network control.Finally,the ISMA-BP neural network is used to dynamically adjust the parameters of the PID controller in real-time,achieving stable control of the output voltage of the converter.The simulation results show that the proposed bidirectional DC-DC converter control method has good rate stability and strong anti-interference ability.

关 键 词：光伏发电 储能 双向DC-DC变换器 黏菌优化算法 BP神经网络 PID控制 

分 类 号：TM46[电气工程—电器]