摘要
随着智能化技术应用的普及,对电缆火灾预警的准确性和抗干扰能力提出了更高的要求。文中提出了一种基于人工智能与多传感器信息融合的电缆火灾预警算法,通过融合多传感器特征层的数据信息,基于BP神经网络的特征层融合实现电缆火灾预警。搜索最佳特征融合系数;使用多传感器分别采集电缆周围的温度、烟雾、CO的数据信息;在特征层数据融合的基础上,判断电缆火灾情况。利用600组电缆火灾试验数据分析讨论了文中所提火灾预警算法的准确性与抗干扰能力,结果表明,文中所提方法的准确率超过90%,具有良好的工程应用价值。
With the popularization of intelligent technology,higher requirements are put forward for the accuracy and anti-interference ability of cable fire warning.In this paper,a cable fire early warning algorithm based on artificial intelligence and multi-sensor information fusion is proposed.By fusing the data information of multi-sensor feature layer,the feature layer fusion based on BP neural network realizes cable fire early warning.The best feature fusion coefficient is searched;The temperature,smoke and CO data around the cable are collected by multi-sensor. The cable fire situation is judged based on the feature layer data fusion. Based on 600 sets of cable fire test data,the accuracy and anti-interference ability of the proposed fire warning algorithm are discussed.The results show that the accuracy of the proposed method is more than 90%,which has good engineering application value.
作者
张付东
赵子源
孙锐
田怀源
ZHANG Fudong;ZHAO Ziyuan;SUN Rui;TIAN Huaiyuan(Dezhou Power Supply Company,State Grid Shandong Electric Power Company,Dezhou 253000,China)
出处
《电子设计工程》
2022年第6期86-90,共5页
Electronic Design Engineering
基金
国家电网公司2020年科技项目(2020A-040)。