摘要
随着储能电站的增多,锂电池储能舱的火灾事故频繁发生,严重威胁了电力系统的稳定运行和人员的生命安全,为解决人工灭火危险性,设计了一种应用于储能站的灭火机器人。针对储能站的环境,对机器人的本体结构与灭火作业机构进行了设计,保证机器人能够在储能站顺利进行灭火作业。探究了锂电池火灾的特点与热失控的规律,分析了液氮的灭火机理,发现使用液氮作为灭火剂对锂电池火灾有着很好的抑制作用。由于机器人可携带的液氮容量有限,为此设计了一种基于长短期记忆网络(LSTM)的灭火策略,以保证液氮的利用率最大化。首先液氮全速输出将明火扑灭,然后利用热电耦合模型估计电池的内部温度与荷电状态,将电池的状态数据与舱内可燃气体体积输入预测模型,对电池的内部温度与舱内可燃气体体积进行预测,最后将输出数据带入控制公式得到液氮注入流量与排气泵流量。通过控制气泵的流量,抑制锂电池热失控蔓延,防止发生复燃和爆炸。对该灭火策略进行了仿真实验,结果表明,该灭火策略能够在10 s内将明火扑灭,并有效抑制电池热失控蔓延,控制舱内可燃气体浓度在爆炸极限以外。该灭火机器人与灭火策略对储能站锂电池火灾的抑制作用效果显著。
With the increase of energy storage stations,fire accidents in lithium battery storage compartments also occur frequently,which seriously threatens the stable operation of the power system and the life safety of personnel,in order to solve the danger of manual fire extinguishing.A fire extinguishing robot applied to the energy storage station is designed,and the robot’s body structure and fire extinguishing operation mechanism are designed for the environment of the energy storage station to ensure that the robot can carry out fire extinguishing operation in the energy storage station smoothly.The characteristics of lithium battery fires and the law of thermal runaway are investigated,and the mechanism of liquid nitrogen fire extinguishing is analyzed,and it is found that the use of liquid nitrogen as fire extinguishing agent has a very good suppression effect on lithium battery fires.Since the robot can carry limited capacity of liquid nitrogen,a fire extinguishing strategy based on long-short term memory network(LSTM)is designed for this purpose to ensure the maximum utilization of liquid nitrogen.Firstly,the liquid nitrogen is output at full speed to extinguish the open fire,then the internal temperature and SOC of the battery are estimated by using the thermoelectric coupling model,the state data of the battery and the volume of combustible gas in the chamber are input into the prediction model to predict the internal temperature of the battery and the volume of combustible gas in the chamber,and finally the output data are brought into the control equation to obtain the liquid nitrogen injection flow rate and the exhaust pump flow rate.By controlling the flow rate of the gas pump,the thermal runaway propagation of the lithium battery is suppressed to prevent re-ignition and explosion.Simulation experiments are conducted to verify that the fire extinguishing strategy can extinguish the open fire within 10 seconds and effectively inhibit the thermal runaway spread of the battery and control the concentration of combustible gas in the chamber beyond the explosion limit.Conclusions The fire extinguishing robot and fire extinguishing strategy are effective in suppressing lithium battery fires in energy storage stations.
作者
甘剑冰
樊绍胜
GAN Jianbing;FAN Shaosheng(School of Electrical and Information Engineering,Changsha University of Science and Technology,Changsha 410114,China)
出处
《电力学报》
2023年第3期198-208,共11页
Journal of Electric Power
基金
国家自然科学基金项目(62271087)。
关键词
储能电站
锂电池储能舱
灭火策略
灭火机器人
热失控预测
LSTM
液氮
pumped storage plant
lithium battery energy storage compartment
fire fighting strategy
fire fighting robot
thermal runaway prediction
LSTM
liquid nitrogen