PDF(Pubmed)
Abstract：
In this paper, we propose a data classification and analysis method to estimate fire risk using facility data of thermal power plants. To estimate fire risk based on facility data, we divided facilities into three states-Steady, Transient, and Anomaly-categorized by their purposes and operational conditions. This method is designed to satisfy three requirements of fire protection systems for thermal power plants. For example, areas with fire risk must be identified, and fire risks should be classified and integrated into existing systems. We classified thermal power plants into turbine, boiler, and indoor coal shed zones. Each zone was subdivided into small pieces of equipment. The turbine, generator, oil-related equipment, hydrogen (H2), and boiler feed pump (BFP) were selected for the turbine zone, while the pulverizer and ignition oil were chosen for the boiler zone. We selected fire-related tags from Supervisory Control and Data Acquisition (SCADA) data and acquired sample data during a specific period for two thermal power plants based on inspection of fire and explosion scenarios in thermal power plants over many years. We focused on crucial fire cases such as pool fires, 3D fires, and jet fires and organized three fire hazard levels for each zone. Experimental analysis was conducted with these data set by the proposed method for 500 MW and 100 MW thermal power plants. The data classification and analysis methods presented in this paper can provide indirect experience for data analysts who do not have domain knowledge about power plant fires and can also offer good inspiration for data analysts who need to understand power plant facilities.
摘要：
在本文中,我们提出了一种数据分类和分析方法，利用火力发电厂的设施数据来估计火灾风险。根据设施数据估计火灾风险，我们将设施分为三个状态-稳定，瞬变,和异常-按其目的和操作条件分类。该方法旨在满足火电厂消防系统的三个要求。例如,必须识别有火灾危险的区域，火灾风险应分类并整合到现有系统中。我们把火力发电厂分为汽轮机,锅炉,和室内煤棚区。每个区域被细分为小设备。涡轮机,发电机,石油相关设备,氢气(H2),和锅炉给水泵（BFP）被选择用于涡轮区，而锅炉区选择了粉碎机和点火油。我们根据多年来对火电厂火灾和爆炸情况的检查，从监控和数据采集（SCADA）数据中选择了与火灾相关的标签，并在特定时期为两个火电厂获取了样本数据。我们专注于关键的火灾案例，如泳池火灾，3D火灾,和喷射火灾，并为每个区域组织了三个火灾危险级别。通过所提出的方法对500MW和100MW火电厂进行了实验分析。本文提出的数据分类和分析方法可以为没有电厂火灾领域知识的数据分析师提供间接经验，也可以为需要了解电厂设施的数据分析师提供很好的启示。
