微型电脑应用2025，Vol.41Issue(4)：309-312,4.
多方向阈值下的大型城市户内变电站消防风险分区预警算法
Fire Risk Zoning Early Warning Algorithm for Large Urban Indoor Substation under Multi-directional Threshold
李兴余 1沈春杨 1张烜梓 1陶雄武 1韦灿炫 2姜海港2
作者信息
- 1. 广东电网有限责任公司惠州供电局,广东,惠州 516000
- 2. 广东华成电力能源股份有限公司,广东,珠海 519000
- 折叠
摘要
Abstract
This paper proposes a fire risk zoning early warning algorithm for indoor substations in large cities under multi-direc-tional threshold to avoid false early warning and ensure safe operation of substations.After the salt and pepper noise contained in the substation monitoring image is removed by the median filtering algorithm,the foreground and background of the image are separated by the local threshold segmentation method based on the multi-directional gray fluctuation to obtain the suspected fire risk area of the substation,and the area change rate,shape similarity,R,G component area ratio,high and low frequency energy ratio characteristics of the suspected fire risk area are extracted to input the fire risk identification model based on the twin support vector machine.The artificial fish swarm algorithm is used to optimize the model parameters to realize the identifi-cation of high and low risk areas of substation fire protection,and the corresponding red or yellow warning information is sent to the intelligent fire protection cloud platform of the Internet of Things to realize the substation fire risk zoning early warning.The experimental results show that this method can eliminate the noise contained in the substation monitoring image.The fire risk suspected area of segmentation is complete and free from incorrect segmentation.The fire risk zoning early warning results can be obtained.关键词
多方向阈值/变电站/消防风险/分区预警/中值滤波/孪生支持向量机Key words
multi-directional threshold/substation/fire risk/zoning early warning/median filtering/twin support vector ma-chine分类
信息技术与安全科学引用本文复制引用
李兴余,沈春杨,张烜梓,陶雄武,韦灿炫,姜海港..多方向阈值下的大型城市户内变电站消防风险分区预警算法[J].微型电脑应用,2025,41(4):309-312,4.
