Risk analysis of atmospheric and vacuum distillation unit using Bayesian networks

Junyan Zhang; Baoping Cai; Yiliu Liu; Min Xie

doi:10.1109/ICRMS.2016.8050046

Risk analysis of atmospheric and vacuum distillation unit using Bayesian networks

Junyan Zhang^*
, Baoping Cai
, Yiliu Liu
, Min Xie

^*Corresponding author for this work

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

2 Citations (Scopus)

Abstract

The accidents occurred in chemical plants often regard as low frequency and high consequence. It is necessary to raise the risk analysis for the petrochemical system to help people to find the weakest process in the whole system thus people can strength the process to improve the safety. In this paper, a methodology by using Bayesian Networks (BNs) to give a model for a chemical plant has been raised. According to the harm extend, the methodology classifies the events into three layers, cause, incident, and accident. Then the application of the methodology is illustrated by analyzing an atmospheric and vacuum distillation unit. The model identifies the most possible cause when an accident happened. After that, mutual information and variety of beliefs are calculated in order to find the most sensitive event of an accident. The study gives suggestions to people of identification the most relevant and weakest point in the plant.

Original language	English
Title of host publication	Integrating Big Data, Improving Reliability & Serving Personalization
Subtitle of host publication	The Proceedings of 2016 11th International Conference on Reliability, Maintainability and Safety (ICRMS)
Editors	Wenhua Chen
Publisher	IEEE
ISBN (Print)	9781509027149
DOIs	https://doi.org/10.1109/ICRMS.2016.8050046
Publication status	Published - 25 Sept 2017
Event	2016 11th International Conference on Reliability, Maintainability and Safety (ICRMS) - Zhjiang Sci-Tech University, Hangzhou, China Duration: 26 Oct 2016 → 28 Oct 2016 https://www.aconf.org/conf_80918.html

Conference

Conference	2016 11th International Conference on Reliability, Maintainability and Safety (ICRMS)
Abbreviated title	ICRMS 2016
Place	China
City	Hangzhou
Period	26/10/16 → 28/10/16
Internet address	https://www.aconf.org/conf_80918.html

Research Keywords

Bayesian Networks
Chemical plant
Risk analysis
Three-layer hierarchical model

Access Output

10.1109/ICRMS.2016.8050046

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Zhang, J., Cai, B., Liu, Y., & Xie, M. (2017). Risk analysis of atmospheric and vacuum distillation unit using Bayesian networks. In W. Chen (Ed.), Integrating Big Data, Improving Reliability & Serving Personalization: The Proceedings of 2016 11th International Conference on Reliability, Maintainability and Safety (ICRMS) Article 8050046 IEEE. https://doi.org/10.1109/ICRMS.2016.8050046

@inproceedings{817d50c0d5c64c29af1b6f44a2df10b5,

title = "Risk analysis of atmospheric and vacuum distillation unit using Bayesian networks",

abstract = "The accidents occurred in chemical plants often regard as low frequency and high consequence. It is necessary to raise the risk analysis for the petrochemical system to help people to find the weakest process in the whole system thus people can strength the process to improve the safety. In this paper, a methodology by using Bayesian Networks (BNs) to give a model for a chemical plant has been raised. According to the harm extend, the methodology classifies the events into three layers, cause, incident, and accident. Then the application of the methodology is illustrated by analyzing an atmospheric and vacuum distillation unit. The model identifies the most possible cause when an accident happened. After that, mutual information and variety of beliefs are calculated in order to find the most sensitive event of an accident. The study gives suggestions to people of identification the most relevant and weakest point in the plant.",

keywords = "Bayesian Networks, Chemical plant, Risk analysis, Three-layer hierarchical model",

author = "Junyan Zhang and Baoping Cai and Yiliu Liu and Min Xie",

year = "2017",

month = sep,

day = "25",

doi = "10.1109/ICRMS.2016.8050046",

language = "English",

isbn = "9781509027149",

editor = "Wenhua Chen",

booktitle = "Integrating Big Data, Improving Reliability \& Serving Personalization",

publisher = "IEEE",

address = "United States",

note = "2016 11th International Conference on Reliability, Maintainability and Safety (ICRMS), ICRMS 2016 ; Conference date: 26-10-2016 Through 28-10-2016",

url = "https://www.aconf.org/conf\_80918.html",

}

Zhang, J, Cai, B, Liu, Y & Xie, M 2017, Risk analysis of atmospheric and vacuum distillation unit using Bayesian networks. in W Chen (ed.), Integrating Big Data, Improving Reliability & Serving Personalization: The Proceedings of 2016 11th International Conference on Reliability, Maintainability and Safety (ICRMS)., 8050046, IEEE, 2016 11th International Conference on Reliability, Maintainability and Safety (ICRMS), Hangzhou, China, 26/10/16. https://doi.org/10.1109/ICRMS.2016.8050046

Risk analysis of atmospheric and vacuum distillation unit using Bayesian networks. / Zhang, Junyan; Cai, Baoping; Liu, Yiliu et al.
Integrating Big Data, Improving Reliability & Serving Personalization: The Proceedings of 2016 11th International Conference on Reliability, Maintainability and Safety (ICRMS). ed. / Wenhua Chen. IEEE, 2017. 8050046.

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Risk analysis of atmospheric and vacuum distillation unit using Bayesian networks

AU - Zhang, Junyan

AU - Cai, Baoping

AU - Liu, Yiliu

AU - Xie, Min

PY - 2017/9/25

Y1 - 2017/9/25

N2 - The accidents occurred in chemical plants often regard as low frequency and high consequence. It is necessary to raise the risk analysis for the petrochemical system to help people to find the weakest process in the whole system thus people can strength the process to improve the safety. In this paper, a methodology by using Bayesian Networks (BNs) to give a model for a chemical plant has been raised. According to the harm extend, the methodology classifies the events into three layers, cause, incident, and accident. Then the application of the methodology is illustrated by analyzing an atmospheric and vacuum distillation unit. The model identifies the most possible cause when an accident happened. After that, mutual information and variety of beliefs are calculated in order to find the most sensitive event of an accident. The study gives suggestions to people of identification the most relevant and weakest point in the plant.

AB - The accidents occurred in chemical plants often regard as low frequency and high consequence. It is necessary to raise the risk analysis for the petrochemical system to help people to find the weakest process in the whole system thus people can strength the process to improve the safety. In this paper, a methodology by using Bayesian Networks (BNs) to give a model for a chemical plant has been raised. According to the harm extend, the methodology classifies the events into three layers, cause, incident, and accident. Then the application of the methodology is illustrated by analyzing an atmospheric and vacuum distillation unit. The model identifies the most possible cause when an accident happened. After that, mutual information and variety of beliefs are calculated in order to find the most sensitive event of an accident. The study gives suggestions to people of identification the most relevant and weakest point in the plant.

KW - Bayesian Networks

KW - Chemical plant

KW - Risk analysis

KW - Three-layer hierarchical model

UR - https://www.scopus.com/pages/publications/85032796245

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85032796245&origin=recordpage

U2 - 10.1109/ICRMS.2016.8050046

DO - 10.1109/ICRMS.2016.8050046

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9781509027149

BT - Integrating Big Data, Improving Reliability & Serving Personalization

A2 - Chen, Wenhua

PB - IEEE

T2 - 2016 11th International Conference on Reliability, Maintainability and Safety (ICRMS)

Y2 - 26 October 2016 through 28 October 2016

ER -

Risk analysis of atmospheric and vacuum distillation unit using Bayesian networks

Abstract

Conference

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this