太阳能光伏发电系统中蓄电池SOC预测模型及监控方法研究  

Battery SOC Forecasting Model and its Monitoring Method in the Solar PV System

作　　者：赵巍巍[1,2] 王洪诚[2] 戴安全[1] 王焕佳 傅磊[2] 

机构地区：[1]四川建筑职业技术学院,四川德阳618000 [2]西南石油大学,成都610500 [3]中石油西南油气田分公司,成都610000

出　　处：《电测与仪表》2014年第16期41-45,共5页Electrical Measurement & Instrumentation

基　　金：西南石油大学学科建设专项基金(2013-2015)

摘　　要：建立了一种基于反向传播(BP)神经网络算法的阀控密封式铅酸蓄电池(VRLA)的剩余容量(SOC)预测模型,利用MATLAB仿真对三层BP网络模型的性能进行了校验,采用由TMS320F28335为核心组成的硬件控制电路对VRLA蓄电池组进行了实时数据采集,依据预测出的SOC值和控制电路,实现对蓄电池组的放电工作状态的智能监测与控制,保证了系统的经济、高效、安全可靠运行。监测控制系统具有蓄电池SOC预测,端电压、充放电电流等参数实时监控,数据传输及状态显示等功能,具有较高的实际应用价值。A state of charge （SOC） forecasting established in this paper, which was based on the model of the Valve-Regulated Lead Acid （VRLA） battery was Back-Propagation neural network algorithm. MATLAB simulations were used to check the performance of the threelayer BP network model.. The hardware control circuit with TMS320F28335 as MCU was utilized to gather real-time data, and based on the predicted SOC value and the control circuit,intelligent monitoring and control of the SOC of the VRLA battery was realized so as to ensurethe economic, efficient, safe and reliable operation of the system. The monitoring system was provided with SOC prediction, realtime monitoring of the charge and discharge current parameters, data transmission, status display, and other functions, which contained high application values.

关 键 词：剩余容量 阀控密封式铅酸蓄电池组 BP神经网络预测 实时监控 DSP 

分 类 号：TM91[电气工程—电力电子与电力传动]