eCite Digital Repository

Causality analysis for root cause diagnosis in Fluid Catalytic Cracking unit

Citation

Gharahbagheri, H and Imtiaz, S and Khan, FI and Ahmed, S, Causality analysis for root cause diagnosis in Fluid Catalytic Cracking unit, Proceedings of the 9th IFAC Symposium on Fault Detection, Supervision and Safety for Technical Processes, SAFEPROCESS 2015, 2-4 September 2015, Paris, France, pp. 838-843. ISSN 2405-8963 (2015) [Refereed Conference Paper]

Copyright Statement

Copyright 2015 IFAC

DOI: doi:10.1016/j.ifacol.2015.09.631

Abstract

PCA based monitoring have good fault detection capability, however it can only point to few variables that have contribution in occurrence of fault and it cannot recognize the main root. Since there is cause and effect relationship between different variables in a process, accordingly a network based on transfer entropy methods was constructed for each case to show causal effect between different variables and to see propagation path of fault. It was shown that PCA in combination with causality analysis based on network construction is a powerful tool for diagnosing the root cause of a fault in the process. In this paper the proposed methodology was applied to Fluid Catalytic Cracking unit as a case study.

Item Details

Item Type:Refereed Conference Paper
Keywords:causality analysis, fluid catalytic cracking, principal component analysis, transfer entropy, catalytic cracking, cracks, data handling, fault detection, principal component analysis, causality analysis, cause-and-effect relationships, network-based
Research Division:Engineering
Research Group:Interdisciplinary Engineering
Research Field:Risk Engineering (excl. Earthquake Engineering)
Objective Division:Expanding Knowledge
Objective Group:Expanding Knowledge
Objective Field:Expanding Knowledge in Engineering
Author:Khan, FI (Professor Faisal Khan)
ID Code:120538
Year Published:2015
Deposited By:NC Maritime Engineering and Hydrodynamics
Deposited On:2017-08-28
Last Modified:2018-04-05
Downloads:0

Repository Staff Only: item control page