Dynamic alarmprediction for critical alarms using a probabilisticmodel

doi:10.1016/j.cjche.2016.04.017

›› 2016, Vol. 24 ›› Issue (7): 881-885.DOI: 10.1016/j.cjche.2016.04.017

• Process Systems Engineering and Process Safety • Previous Articles Next Articles

Dynamic alarmprediction for critical alarms using a probabilisticmodel

Jianfeng Zhu¹, Chunli Wang¹, Chuankun Li¹, Xinjiang Gao¹, Jinsong Zhao²

1 Sinopec Research Institute of Safety Engineering, Qingdao 266071, China;
2 State Key Laboratory of Chemical Engineering, Department of Chemical Engineering, Tsinghua University, Beijing 100084, China

Received:2015-06-26 Revised:2015-12-11 Online:2016-08-17 Published:2016-07-28
Supported by:
Supported by the National High Technology Research and Development Program of China (2013AA040701).

Dynamic alarmprediction for critical alarms using a probabilisticmodel

Jianfeng Zhu¹, Chunli Wang¹, Chuankun Li¹, Xinjiang Gao¹, Jinsong Zhao²

1 Sinopec Research Institute of Safety Engineering, Qingdao 266071, China;
2 State Key Laboratory of Chemical Engineering, Department of Chemical Engineering, Tsinghua University, Beijing 100084, China

通讯作者: Jianfeng Zhu
基金资助:
Supported by the National High Technology Research and Development Program of China (2013AA040701).

Abstract

Abstract: Alarm systems play important roles for the safe and efficient operation of modern industrial plants. Critical alarms are configured with a higher priority and are safety related among many other alarms. If critical alarms can be predicted in advance, the operator will have more time to prevent them from happening. In this paper, we present a dynamic alarm prediction algorithm, which is a probabilistic model that utilizes alarm data from distributed control system, to calculate the occurrence probability of critical alarms. It accounts for the local interdependences among the alarms using the n-gram model, which occur because of the nonlinear relationships between variables. Finally, the dynamic alarm prediction algorithm is applied to an industrial case study.

Key words: Dynamic alarm prediction, Alarm management, The n-gram model, Alarm sequence

摘要： Alarm systems play important roles for the safe and efficient operation of modern industrial plants. Critical alarms are configured with a higher priority and are safety related among many other alarms. If critical alarms can be predicted in advance, the operator will have more time to prevent them from happening. In this paper, we present a dynamic alarm prediction algorithm, which is a probabilistic model that utilizes alarm data from distributed control system, to calculate the occurrence probability of critical alarms. It accounts for the local interdependences among the alarms using the n-gram model, which occur because of the nonlinear relationships between variables. Finally, the dynamic alarm prediction algorithm is applied to an industrial case study.

关键词: Dynamic alarm prediction, Alarm management, The n-gram model, Alarm sequence

Jianfeng Zhu, Chunli Wang, Chuankun Li, Xinjiang Gao, Jinsong Zhao. Dynamic alarmprediction for critical alarms using a probabilisticmodel[J]. , 2016, 24(7): 881-885.

References

[1] EEMUA, Alarm systems:A guide to design,management and procurement, London:EEMUA Publication No. 191 Engineering Equipment and Materials Users' Association, second ed., 2007.
[2] ISA,Management of alarm systems for the process industries, Technical Reportansi/ISA-18.2-2009 International Society of Automation ISA, 67 AlexanderDrive, P.O. Box 12277, Research Triangle Park, North Carolina 27709, 2009.
[3] I. Izadi, S. Shah, D. Shook, T. Chen, An introduction to alarm analysis and design, Fault Detection, Supervision and Safety of Technical Processes, Barcelona, Spain 2009, pp. 645-650.
[4] N.A. Adnan, I. Izadi, T. Chen, On expected detection delays for alarm systems with deadbands and delay-timers, J. Process Control 21(9) (2011) 1318-1331.
[5] S.R. Kondaveeti, S. Shah, I. Izadi, Application of multivariate statistics for efficient alarm generation, Fault Detection, Supervision and Safety of Technical Processes 2009, pp. 657-662.
[6] F. Higuchi, I. Yamamoto, T. Takai, M. Noda, H. Nishitani, Use of event correlation analysis to reduce number of alarms, Comput. Aided Chem. Eng. 27(2009) 1521-1526.
[7] X. Liu, M. Noda, H. Nishitani, Evaluation of plant alarm systems by behavior simulation using a virtual subject, Comput. Chem. Eng. 34(2010) 374-386.
[8] Z. Yang, J.Wang, T. Chen, On correlation analysis of bivariate alarmsignals, Information and Automation (ICIA), 2012 International Conference on IEEE 2012, pp. 530-535.
[9] K. Ahmed, I. Izadi, T. Chen, D. Joe, T. Burton, Similarity analysis of industrial alarm flood data, Automation Science and Engineering, Trans. IEEE 10(2) (2013) 452-457.
[10] F. Yang, S.L. Shah, D. Xiao, T. Chen, Improved correlation analysis and visualization of industrial alarm data, ISA Trans. 51(4) (2012) 499-506.
[11] S.R. Kondaveeti, I. Izadi, S.L. Shah, T. Black, T. Chen, Graphical tools for routine assessment of industrial alarm systems, Comput. Chem. Eng. 46(2012) 39-47.
[12] J. Zhu, Y. Shu, J. Zhao, F. Yang, A dynamic alarm management strategy for chemical process transitions, J. Loss Prev. Process Ind. 30(2014) 207-218.
[13] F. Yang, L.S. Sirish, D. Xiao, Signed directed graph modeling of industrial processes and their validation by data-based methods, Control and Fault-Tolerant Systems (SysTol), 2010 Conference on IEEE 2010, pp. 387-392.
[14] R. Brooks, R. Thorpe, J. Wilson, A new method for defining and managing process alarms and for correcting process operation when an alarm occurs, J. Hazard. Mater. 115(1) (2004) 169-174.
[15] Y. Cheng, I. Izadi, T. Chen, Pattern matching of alarm flood sequences by a modified Smith-Waterman algorithm, Chem. Eng. Res. Des. 91(6) (2013) 1085-1094.
[16] E. Naghoosi, I. Izadi, T. Chen, Estimation of alarm chattering, J. Process Control 21(9) (2011) 1243-1249.
[17] H.U. Osmanbeyoglu, M.K. Ganapathiraju, N-gram analysis of 970 microbial organisms reveals presence of biological language models, BMC Bioinf. 12(1) (2011) 12.
[18] P.F. Brown, P.V. Desouza, R.L. Mercer, V.J.D. Pietra, J.C. Lai, Class-based n-gram models of natural language, Comput. Linguist. 18(4) (1992) 467-479.
[19] J. Wu, S. Khudanpur, Maximum Entropy Language Modeling with Non-local Dependencies(Ph.D Dissertation) The Johns Hopkins University, 2003.
[20] S.F. Chen, J. Goodman, An empirical study of smoothing techniques for language modeling, Comput. Speech Lang. 13(4) (1999) 359-393.

Dynamic alarmprediction for critical alarms using a probabilisticmodel

Dynamic alarmprediction for critical alarms using a probabilisticmodel

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 0

Recommended Articles

Metrics

Comments