An intelligent fault diagnosis system for process plant using a functional HAZOP and DBN integrated methodology

被引:36
作者
Hu, Jinqiu [1 ]
Zhang, Laibin [1 ]
Cai, Zhansheng [1 ,2 ]
Wang, Yu [1 ]
机构
[1] China Univ Petr, Coll Mech & Transportat Engn, Beijing 102249, Peoples R China
[2] CNOOC Zhong Jie Petrochem Co Ltd, Cang Zhou 061101, Peoples R China
基金
中国国家自然科学基金; 北京市自然科学基金;
关键词
Multilevel flow modeling (MFM); Functional HAZOP; Dynamic Bayesian network; Intelligent fault diagnosis system; SIGNED DIRECTED GRAPH; ROOT CAUSE ANALYSIS; PROPAGATION ANALYSIS; QUANTITATIVE MODEL; NETWORKS; SAFETY; MANAGEMENT; FRAMEWORK; SUPPORT;
D O I
10.1016/j.engappai.2015.06.010
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Integration of a functional HAZOP approach with dynamic Bayesian network (DBN) reasoning is presented in this contribution. The presented methodology can unveil early deviations in the fault causal chain on line. A functional HAZOP study is carried out firstly where a functional plant model (i.e., MFM) assists in a goal oriented decomposition of the plant purpose into the means of achieving the purpose. DBN model is then developed based on the functional HAZOP results to provide a probability-based knowledge representation which is appropriate for the modeling of causal processes with uncertainty. An intelligent fault diagnosis system (IFDS) is proposed based on the whole integrated framework, and investigated in a case study of process plants at a petrochemical corporation. The study shows that the IFDS provides a very efficient paradigm for facilitating HAZOP studies and for enabling reasoning to reveal potential causes and/or consequences far away from the site of the deviation online. (C) 2015 Elsevier Ltd. All rights reserved.
引用
收藏
页码:119 / 135
页数:17
相关论文
共 32 条
[1]   Using Bayesian networks for root cause analysis in statistical process control [J].
Alaeddini, Adel ;
Dogan, Ibrahim .
EXPERT SYSTEMS WITH APPLICATIONS, 2011, 38 (09) :11230-11243
[2]   A new self-diagnosing approach based on petri nets and correlation graphs for fault management in wireless sensor networks [J].
Babaie, Shahram ;
Khosrohosseini, Afsaneh ;
Khadem-Zadeh, Ahmad .
JOURNAL OF SYSTEMS ARCHITECTURE, 2013, 59 (08) :582-600
[3]   A critique of the Hazard and Operability (HAZOP) study [J].
Baybutt, Paul .
JOURNAL OF LOSS PREVENTION IN THE PROCESS INDUSTRIES, 2015, 33 :52-58
[4]   Fault diagnosis with automata generated languages [J].
Chang, Chuei-Tin ;
Chen, Chung Yang .
COMPUTERS & CHEMICAL ENGINEERING, 2011, 35 (02) :329-341
[5]   A BAYESIAN METHOD FOR THE INDUCTION OF PROBABILISTIC NETWORKS FROM DATA [J].
COOPER, GF ;
HERSKOVITS, E .
MACHINE LEARNING, 1992, 9 (04) :309-347
[6]   Improved qualitative fault propagation analysis [J].
Gabbar, Hossam A. .
JOURNAL OF LOSS PREVENTION IN THE PROCESS INDUSTRIES, 2007, 20 (03) :260-270
[7]   Simulation-based fault propagation analysis-Application on hydrogen production plant [J].
Gabbar, Hossam A. ;
Hussain, Sajid ;
Hosseini, Amir Hossein .
PROCESS SAFETY AND ENVIRONMENTAL PROTECTION, 2014, 92 (06) :723-731
[8]   Safety study of an LNG regasification plant using an FMECA and HAZOP integrated methodology [J].
Giardina, M. ;
Morale, M. .
JOURNAL OF LOSS PREVENTION IN THE PROCESS INDUSTRIES, 2015, 35 :35-45
[9]   Root cause analysis in multivariate statistical process monitoring: Integrating reconstruction-based multivariate contribution analysis with fuzzy-signed directed graphs [J].
He, Bo ;
Chen, Tao ;
Yang, Xianhui .
COMPUTERS & CHEMICAL ENGINEERING, 2014, 64 :167-177
[10]  
Hu J, 2015, PROCESS SAF ENV PROT