A forewarning method of nitrogen-block in air-separation units based on clustering and fuzzy evaluation

被引：0
|
作者：
Lu Y.-S. [1 ,2 ]
Zou T. [1 ,2 ]
Jia Y. [1 ,2 ]
Zhang X. [1 ,2 ]
Ma X.-L. [1 ,2 ]
机构：
[1] Shenyang Institute of Automation Chinese Academy of Sciences, Shenyang
[2] Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang
来源：
Gao Xiao Hua Xue Gong Cheng Xue Bao/Journal of Chemical Engineering of Chinese Universities | 2019年 / 33卷 / 03期
关键词：
Air separation unit; Clustering; Fuzzy evaluation; Nitrogen-block; Variable condition;
D O I：
10.3969/j.issn.1003-9015.2019.03.022
中图分类号：
学科分类号：
摘要：
Nitrogen-block often happens in air separation units when working condition changes. A nitrogen-block fault forewarning method based on clustering and fuzzy comprehensive evaluation was proposed in this paper. The clustering method was first used to divide the conditions of air separation unit into several typical working conditions, and then the fuzzy evaluation models for each working condition were established. For online forewarning applications, the current condition was identified through clustering methods and the corresponding fuzzy evaluation model was then used to identify whether nitrogen-block occurs and evaluate its severity in order to forewarn of nitrogen-block fault. The verification results using nitrogen-block historical data of an air separation enterprise demonstrate that the proposed nitrogen-block forewarning method is better than traditional manual method and Principle Component Analysis, and the forewarning time can meet the practical requirement. © 2019, Editorial Board of "Journal of Chemical Engineering of Chinese Universities". All right reserved.
引用
收藏
页码：672 / 679
页数：7
相关论文
共 20 条
  • [1] Ji P., Air separation unit load change control and diagnose, (2008)
  • [2] Yu Z.C., Variable operation and its influence on the working condition of argon production system, Proceedings of the 11th CSM Steel Congress, pp. 1-3, (2017)
  • [3] Zhang H.Y., Tian X.M., A fault identification method based on asynchronous PCA, Journal of Chemical Engineering of Chinese Universities, 30, 3, pp. 680-685, (2016)
  • [4] Chu F., Wu Q., Dai W., Latent variable techniques based operating performance assessment for the dense medium coal preparation process, Proceedings of the 35th Chinese Control Conference, pp. 9821-9826, (2016)
  • [5] Chu F., Dai W., Shen J., Et al., Online complex nonlinear industrial process operating optimality assessment using modified robust total kernel partial M-regression, Chinese Journal of Chemical Engineering, 26, 4, pp. 775-785, (2018)
  • [6] Guo J.Y., Wang X., Li Y., Fault detection in chemical processes using weighted differential principal component analysis, Journal of Chemical Engineering of Chinese Universities, 32, 1, pp. 183-192, (2018)
  • [7] Li C.K., Zhao D.F., Wang C.L., Et al., Study on a knowledge automation method for fault diagnosis of chemical processes, Journal of Chemical Engineering of Chinese Universities, 32, 2, pp. 393-400, (2018)
  • [8] Wang J.Y., Shao Z.J., Ji P., Et al., On-line diagnosis of abnormal conditions of separation process by dynamic PCA, Computers and Applied Chemistry, 27, 1, pp. 1-5, (2010)
  • [9] Lu N.Y., Wang L., Jiang B., A fault prognosis method based on time-delayed SDG and ICA for multi-mode industrial processes, Control Engineering of China, 18, 4, (2011)
  • [10] Wang L., Lu N.Y., Hou Q., Et al., Diagnosis evaluation of nitrogen-block fault in raw argon column of air separation unit, Control and Instruments in Chemical Industry, 38, 2, pp. 162-166, (2010)
12