Research On Intelligent Monitoring Of Silicon Battery In Substation Dc Power Supply

Batteries are an important part of the dc system,and as a backup power,they have been widely used in the fields of electric power,transportation and communication since the last century.Especially in the modern power system,dc system is more and more important role and status,substation of battery as relay protection device,signal,communication power supply,emergency lighting and other important load,its power supply reliability will directly affect the safe and stable operation of power system.In order to guarantee the normal operation of the transformer substation system,ensure the power supply reliability,real-time effective monitoring of substation battery state has important practical significance.Nowadays substation dc power supply monitor is only for the temperature of the whole battery pack,the terminal voltage monitoring,and not for specific monitoring of monomer battery state,so it is easy to cause damage of monomer battery,which affects the operation of dc power supply.In this paper,the principle and characteristics of the valve controlled silicon battery are studied,and the advantages of the lead-acid battery are studied.And then analyze the dc power supply way of charging,the Buck converter with closed-loop control to achieve control of the battery charging process,the final realization of single battery voltage,current,temperature real-time monitoring and prediction of the monomer battery are charged.This paper USES the prediction method of neural network to predict the charge status of the battery.Then,in more traditional LMBP neural network and improved LMBP neural network on the battery charged state prediction on the basis of the established based on improved LMBP neural network predictive model of battery charged state,modeling and simulation with MATLAB,and verified the validity of the model and the accuracy,finally,the design of the dc system monitoring PC and set up the experimental prototype,can monitor page monitor to the status of battery,and can predict charged state,problems of the voltage and the charged state of battery fault detection in a timely manner.