A fault diagnosis method for complex processes based on Regflow graph and data mining

Journal of Beijing University of Chemical Technology ›› 2013, Vol. 40 ›› Issue (5) : 104-109.

PDF(1161 KB)
Welcome to Journal of Beijing University of Chemical Technology, Today is February 22, 2025
Email Alert  RSS
PDF(1161 KB)
Journal of Beijing University of Chemical Technology ›› 2013, Vol. 40 ›› Issue (5) : 104-109.
机电工程和信息科学

A fault diagnosis method for complex processes based on Regflow graph and data mining

Author information +
History +

Abstract

Fault diagnosis in a crude oil distillation process has been studied using Regflow graphs(RFG) combined with data mining. First the RFG model of the process was constructed. Then qualitative simulations were completed, which showed the propagation path of each fault and the effects of the faults on each observed variable. The simulation results can be used to establish a fault diagnosis model by incorporating data mining methods. The simple structure of this fault diagnosis model makes the diagnosis fast and direct, which can partly solve the combinatorial explosion problem in the realtime fault diagnosis of complex processes.

Cite this article

Download Citations
A fault diagnosis method for complex processes based on Regflow graph and data mining[J]. Journal of Beijing University of Chemical Technology, 2013, 40(5): 104-109

References

[1]Venkatasubramanian V, Rengaswamy R, Yin K, et al. A review of process fault detection and diagnosis Part I: Quantitative modelbased methods[J]. Computers and Chemical Engineering, 2003, 27(3): 293-311. 
[2]Maurya M R, Rengaswamy R, Venkatasubramanian V. Application of signed digraphsbased analysis for fault diagnosis of chemical process flowsheets[J]. Engineering Applications of Artificial Intelligence, 2004, 17(5): 501-518. 
[3]Khan F I, Abbasi S A. Analytical simulation and PROFAT II: a new methodology and a computer automated tool for fault tree analysis in chemical process industries[J]. Journal of Hazardous Materials, 2000, 75(1): 1-27. 
[4]Prasad P R, Davis J F, Jirapinyo Y, et al. Structuring diagnostic knowledge for largescale process systems[J]. Computers and Chemical Engineering, 1998, 22(12): 1897-1905. 
[5]Say A C C, Akin H L. Sound and complete qualitative simulation is impossible[J]. Artificial Intelligence, 2003, 149(2): 251-266. 
[6]王文辉, 周东华. 基于定性和半定性方法的故障检测与诊断技术[J]. 控制理论与应用, 2002, 19(5):653-659.
Wang W H, Zhou D H. Survey on qualitative/semiqualitative based fault detection and diagnostics techniques[J]. Control Theory and Applications, 2002, 19(5): 653-659. (in Chinese)
[7]李秀喜, 吉世明. 基于半定量SDG模型的化工过程故障诊断[J]. 清华大学学报: 自然科学版, 2012, 52(8): 1112-1115.
Li X X, Ji S M. Chemical process fault diagnosis using semiquantitative SDG model[J]. Journal of Tsinghua University: Science and Technology, 2012, 52(8): 1112-1115. (in Chinese)
[8]张卫华, 李传坤, 吴重光, 等. 基于SDG的化工过程多故障诊断[J]. 系统仿真学报, 2009, 21(21): 6972-6977.
Zhang W H, Li C K, Wu C G, et al. SDGbased multiple fault diagnosis of chemical process[J]. Journal of System Simulation, 2009, 21(21): 6972-6977. (in Chinese)
[9]郑娆, 王奎升, 王耘. 实体语法系统框架下的化工过程调控流图模型[J]. 计算机工程与应用, 2010, 46(13): 245-248. 
Zheng R, Wang K S, Wang Y. Regulating flow graph model of chemical processes in framework of entity grammar systems[J]. Computer Engineering and Applications, 2010, 46(13): 245-248. (in Chinese)
[10]郑娆. 复杂化工过程的调控流图建模方法及故障诊断技术研究 [D]. 北京: 北京化工大学, 2010. 
Zheng R. Studies on Regflow modeling and fault diagnosis method of complex chemical processes[D]. Beijing: Beijing University of Chemical Technology, 2010. (in Chinese)
[11]Witten I H, Frank E. 数据挖掘实用机器学习技术[M]. 董琳, 邱泉, 于晓峰, 等, 译. 北京: 机械工业出版社, 2006. 
Witten I H, Frank E. Data mining practical machine learning tools and techniques[M]. Dong L, Qiu Q, Yu X F, et al, trans. Beijing: China Machine Press, 2006. (in Chinese)
[12]吴重光, 沈承林, 侯贵海. 石油化工仿真培训系统的研制[J]. 系统仿真学报, 1993, 5(1): 31-39. 
Wu C G, Shen C L, Hou G H. The development of training simulation systems for petrochemical process[J]. Journal of System Simulation, 1993, 5(1): 31-39. (in Chinese)
PDF(1161 KB)

1616

Accesses

0

Citation

Detail

Sections
Recommended

/