摘要
针对电动汽车动力锂电池火灾早期预警问题,提出基于多传感器数据融合的电动汽车动力锂电池火灾探测系统。首先,研究电动汽车动力锂电池火灾发生过程,筛选火灾初期发生明显变化的物理参数及固体、气体发生物;然后,采用D-S证据理论对多传感器数据进行融合分析,降低使用单一传感器时的误报率,实现电动汽车动力锂电池火灾的准确判断;最后,根据多传感器数据的相关性对数据融合算法进行优化,提高系统判断速度,降低硬件成本。
Aiming at the early warning problem of electric vehicle power lithium battery fire,an electric vehicle power lithium battery fire detection system based on multi-sensor data fusion is proposed.Firstly,the fire process of electric vehicle power lithium battery is studied to screen the physical parameters and solid and gas generators that change significantly in the early stage of the fire;Then,the D-S evidence theory is used to fuse and analyze the multi-sensor data,reduce the false alarm rate when using a single sensor,and realize the accurate judgment of lithium battery fire of electric vehicle;Finally,according to the correlation of multi-sensor data,the data fusion algorithm is optimized to improve the system judgment speed and reduce the hardware cost.
作者
劳中建
张洋
丘嘉乐
梁中棚
连柏尧
Lao Zhongjian;Zhang Yang;Qiu Jiale;Liang Zhongpeng;Lian Baiyao(Guangzhou Tongda Auto Electric Co.,Ltd.Guangzhou 510700,China)
出处
《自动化与信息工程》
2021年第4期16-19,共4页
Automation & Information Engineering