Bayesian Network Based Approach for Diagnosis of Modified Sequencing Batch Reactor

doi:10.1007/s12204-019-2047-9

Abstract

Abstract: Wastewater treatment is a complicated dynamic process affected by microbial, chemical and physical factors. Faults are inevitable during the operation of modified sequencing batch reactors (MSBRs) because of the uncertainty of various factors. Abnormal MSBR results require fault diagnosis to determine the cause of failure and implement appropriate measures to adjust system operations. Bayesian network (BN) is a powerful knowledge representation tool that deals explicitly with uncertainty. A BN-based approach to diagnosing wastewater treatment systems based on MSBR is developed in this study. The network is constructed using the knowledge derived from literature and elicited from experts, and it is parametrized using independent data from a pilot test. A one-year pilot study is conducted to verify the diagnostic analysis. The proposed model is reasonable, and the diagnosis results are accurate. This approach can be applied with minimal modifications to other types of wastewater treatment plants.

Key words: diagnostic analysis | modified sequencing batch reactor (MSBR)| Bayesian network (BN)| inference| probability distribution

摘要： Wastewater treatment is a complicated dynamic process affected by microbial, chemical and physical factors. Faults are inevitable during the operation of modified sequencing batch reactors (MSBRs) because of the uncertainty of various factors. Abnormal MSBR results require fault diagnosis to determine the cause of failure and implement appropriate measures to adjust system operations. Bayesian network (BN) is a powerful knowledge representation tool that deals explicitly with uncertainty. A BN-based approach to diagnosing wastewater treatment systems based on MSBR is developed in this study. The network is constructed using the knowledge derived from literature and elicited from experts, and it is parametrized using independent data from a pilot test. A one-year pilot study is conducted to verify the diagnostic analysis. The proposed model is reasonable, and the diagnosis results are accurate. This approach can be applied with minimal modifications to other types of wastewater treatment plants.

关键词: diagnostic analysis | modified sequencing batch reactor (MSBR)| Bayesian network (BN)| inference| probability distribution

CLC Number:

X 703.1

LI Dan (李丹), WANG Hongdong (王鸿东), LIANG Xiaofeng *(梁晓锋). Bayesian Network Based Approach for Diagnosis of Modified Sequencing Batch Reactor[J]. Journal of Shanghai Jiao Tong University (Science), 2019, 24(4): 417-429.

References 21

[1]	YANG H Z. Mechanism and technology process experiment to MSBR process for nitrogen and phosphorus removals of municipal wastewater [D]. Shanghai,China: School of Environmental Science and Engineering,Tongji University, 2001 (in Chinese).
[2]	LI D, YANG H Z, LIANG X F. Prediction analysis of a wastewater treatment system using a Bayesian network[J]. Environmental Modelling & Software, 2013,40: 140-150.
[3]	HE Q P, QIN S J, WANG J. A new fault diagnosis method using fault directions in Fisher discriminant analysis [J]. AIChE Journal, 2005, 51(2): 555-571.
[4]	BAGGIANI F, MARSILI-LIBELLI S. Real-time fault detection and isolation in biological wastewater treatment plants [J]. Water Science & Technology,2009, 60(11): 2949-2961.
[5]	GARCIA-ALVAREZ D, FUENTE M J, VEGA P, et al. Fault detection and diagnosis using multivariate statistical techniques in a wastewater treatment plant[J]. IFAC Proceedings Volumes, 2009, 42(11): 952-957.
[6]	HAN H G, LI Y, QIAO J F. A fuzzy neural network approach for online fault detection in waste water treatment process [J]. Computers & Electrical Engineering,2014, 40(7): 2216-2226.
[7]	SANCHEZ-FERN′ANDEZ A, FUENTE M J, SAINZPALMERO G I. Fault detection in wastewater treatment plants using distributed PCA methods [C]//2015IEEE 20th Conference on Emerging Technologies &Factory Automation (ETFA). Luxembourg: IEEE,2015: 1-7.
[8]	VARIS O. Belief networks for modelling and assessment of environmental change [J]. Environmetrics,2010, 6(5): 439-444.
[9]	NASH D, WATERS D, BULDU A, et al. Using a conceptual Bayesian network to investigate environmental management of vegetable production in the Lake Taihu region of China [J]. Environmental Modelling &Software, 2013, 46: 170-181.
[10]	NASH D, HANNAH M. Using Monte-Carlo simulations and Bayesian networks to quantify and demonstrate the impact of fertiliser best management practices[J]. Environmental Modelling & Software, 2011,26: 1079-1088.
[11]	ZHAO Y, WEN J, WANG S W. Diagnostic Bayesian networks for diagnosing air handling units faults. Part II: Faults in coils and sensors [J]. Applied Thermal Engineering,2015, 90: 145-157.
[12]	SUCH′ANEK P, MARECKI F, BUCKI R. Selflearning Bayesian networks in diagnosis [J]. Procedia Computer Science, 2014, 35: 1426-1435.
[13]	SAHELY B S G E, BAGLEY D M. Diagnosing upsets in anaerobic wastewater treatment using Bayesian belief networks [J]. Journal of Environmental Engineering,2001, 127(4): 302-310.
[14]	FRANCO C, HEPBURN L A, SMITH D J, et al. A Bayesian belief network to assess rate of changes in coral reef ecosystems [J]. Environmental Modelling &Software, 2016, 80: 132-142.
[15]	LANDUYT D, BROEKX S, D’HONDT R, et al. A review of Bayesian belief networks in ecosystem service modelling [J]. Environmental Modelling & Software,2013, 46: 1-11.
[16]	MOLINA J L, BROMLEY J, GARC′IA-AR′OSTEGUI J L, et al. Integrated water resources management of overexploited hydrogeological systems using objectoriented Bayesian networks [J]. Environmental Modelling & Software, 2010, 25(4): 383-397.
[17]	FORIO M A E, LANDUYT D, BENNETSEN E, et al.Bayesian belief network models to analyse and predict ecological water quality in rivers [J]. Ecological Modelling,2015, 312: 222-238.
[18]	AGUILERA P A, FERN′ANDEZ A, FERN′ANDEZ R, et al. Bayesian networks in environmental modelling[J]. Environmental Modelling & Software, 2011,26(12): 1376-1388.
[19]	CHEN S H, POLLINO C A. Good practice in Bayesian network modelling [J]. Environmental Modelling &Software, 2012, 37: 134-145.
[20]	MYLLYM′AKI P, SILANDER T, TIRRI H, et al.B-course: A web service for Bayesian data analysis[C]//International Conference on Tools with Artificial Intelligence. Dallas, TX, USA: IEEE, 2001: 247-256.
[21]	PRADHAN M, HENRION M, PROVAN G, et al. The sensitivity of belief networks to imprecise probabilities:An experimental investigation [J]. Artificial Intelligence,1996, 85(1/2): 363-397.