基于化工生产过程历史数据的报警优化方法研究  

Study on alarm optimization method based on historical data of chemical production process

作　　者：王春利[1] 张桂鑫[2] 韩华伟[1] 于晓灵 高新江[1] 

机构地区：[1]中国石油化工股份有限公司青岛安全工程研究院,山东青岛266071 [2]青岛科技大学化工学院,山东青岛266042 [3]兰州石化公司合成橡胶厂,甘肃兰州730060

出　　处：《中国安全生产科学技术》2016年第11期182-187,共6页Journal of Safety Science and Technology

摘　　要：为了有效降低报警装置漏报率和误报率,基于化工生产的过程历史数据,探讨了报警优化的两种方法。以误报率和漏报率为优化指标,建立报警阈值目标函数,从最小化目标函数的角度出发,采用数值优化的方法进行报警阈值的优化设计。基于报警时长的变异系数,应用自适应报警延时方法来降低报警数量。实例研究表明,应用基于化工生产过程历史数据的方法,可有效减少无效报警数量,降低误报率和漏报率,提高报警质量,对于提高石化生产过程的安全性具有积极意义。In order to effectively reduce the missing alarm rate and false alarm rate of alarm device,two methods of alarm optimization were studied based on the historical data of chemical production process. Taking the missing alarm rate and false alarm rate as optimization indexes,an objective function of alarm threshold was established. The optimization design of alarm threshold was conducted by the method of numerical optimization from the view of minimized objective function. The number of alarm was reduced using the method of adaptive alarm delay base on the variation coefficient of alarm duration. The case study showed that the method based on the historical data of chemical production process is of great significance for improving the safety of petrochemical production process,which can effectively reduce the number of invalid alarm,the missing alarm rate and false alarm rate,and improve the quality of alarming.

关 键 词：报警阈值 漏报率 误报率 概率密度函数 

分 类 号：X937[环境科学与工程—安全科学]