基于神经网络和模糊控制的光伏发电MPPT研究  

Research on Photovoltaic Power Generation MPPT Based on Neural Network and Fuzzy Control

作　　者：焦科名 徐凯[2] JIAO Ke-ming;XU Kai(School of Physics and Telecommunication Engineering,South China Normal University,Guangzhou Guangdong 510006,China;School of Information Science and Engineering,Chongqing Jiaotong University,Chongqing 400074,China)

机构地区：[1]华南师范大学物理与电信工程学院,广东广州510006 [2]重庆交通大学信息科学与工程学院,重庆400074

出　　处：《计算机仿真》2020年第5期71-76,共6页Computer Simulation

摘　　要：光伏电池的输出功率随着外部环境条件和负载的变化而变化,为了提高光伏发电的效率和系统稳定性,鉴于其最大功率点主要受光照强度和温度影响,提出一种新的智能型最大功率点跟踪方法,首先根据输入的光照强度和温度,使用径向基神经网络对最大功率点电压进行预测并输出参考电压,然后将光伏电池输出电压与该参考电压的偏差及其变化率作为模糊控制器的输入,用以实现对占空比的调整。最后分别在标准情况、光照强度变化条件和温度变化等各条件下,使该方法与通用模糊控制法、电导增量法进行了仿真比较。实验结果表明,上述方法能够迅速跟踪光伏电池的最大功率点,动态性能和稳态性能良好。The output power of photovoltaic cells varies with the change of external environment and load. In order to improve the efficiency and stability of photovoltaic power generation, a novel and intelligent maximum power point tracking(MPPT) method is proposed in this paper, considering the maximum power point affected mainly by solar insolation and temperature. First, the maximum power point voltage was predicted and outputted by radial basis function(RBF) neural network according to solar insolation and temperature. Then, the duty cycle was adjusted with fuzzy control method that the deviation between the output voltage of photovoltaic cells and reference voltage and its change rate are taken as the input of the fuzzy controller. Finally, the method was compared with the common fuzzy control method and the incremental conductance algorithm under the standard condition, the condition of irradiation change and temperature change condition, respectively. The experimental results show that the proposed method can quickly track the maximum power point of photovoltaic cell, and has good dynamic and steady-state performance.

关 键 词：最大功率点跟踪 径向基神经网络 模糊控制 光照强度 温度 

分 类 号：TP615[自动化与计算机技术—控制理论与控制工程]