A Novel Contribution Graph Based Likert Scale Method and Its Application to Real-Time Alarm Evaluation
In the complex process industry,alarm management plays a very important role in industrial safety production.In a traditional alarm system,alarm flooding occurs frequently due to a large number of single-variable threshold alarms,which seriously affects the operators judgment on the order of alarm processing.For timely processing of alarms,the division of alarm priority is very important.In order to solve this problem,a novel method using Principal Component Analysis(PCA)contribution graph based Likert scale is proposed for online division of the priority of alarm variables.Different from the traditional Likert scale method,the method proposed in this paper can analyze the influence degree of each variable on the stability of the system and prioritize the alarm variables in real time.In addition,key alarm information among redundant alarms can be exactly extracted.The effectiveness of the method is verified by the Tennessee Eastman Process(TEP).
Industrial safety Alarm management Alarm priority Likert scale Contribution plot analysis
Qun-Xiong Zhu Rui Ding Yan-Lin He Yuan Xu
College of Information Science and Technology,Beijing University of Chemical Technology,Beijing 100029,China;Engineering Research Centre of Intelligent PSE,Ministry of Education of China,Beijing 100029,China
国际会议
江苏镇江
英文
448-455
2019-09-20（万方平台首次上网日期，不代表论文的发表时间）