Sensor-fault tolerance in a wastewater treatment plant by means of ANFIS-based soft sensor and control reconfiguration
- 127 Downloads
This work presents a sensor-fault-tolerant design applied to a decentralized dissolved oxygen control in an activated sludge process subject to sensor faults such as bias and slow drifts. The core idea is to use a data-driven soft sensor based on adaptive neuro-fuzzy inference system to act as a backup of the joint sensor and controller block, and to exploit the data/analytical correlations existing in the system. After fault detection and isolation, a control reconfiguration technique takes action in order to surmount/counteract the effect of the fault until the faulty sensor is repaired. The approach presented here was applied to the Benchmark Simulation Model n.1 and was able to demonstrate the improvements on the control system dependability.
KeywordsSensor-fault-tolerant control Data-driven soft sensor ANFIS Activated sludge process Decentralized dissolved oxygen control
The authors would like to thank Eng. Paulo Resende that is with Luságua, Serviços Ambientais S.A. for his insight about the wastewater treatment process. This work was supported by the Fundação para a Ciência e a Tecnologia (FCT), and ISA—Intelligent Sensing Anywhere, under Bolsa de Doutoramento em Empresa Fellowship SFRH/BDE/33295/2008.
Compliance with ethical standards
Conflict of interest
We declare that no conflict of interest exits in the submission of this manuscript, and the manuscript is approved by all authors for publication.
- 1.Alex J, Benedetti L, Copp J, Gernaey KV, Jeppsson U, Nopens I, Pons MN, Rieger L, Rosen C, Steyer JP, Vanrolleghem P, Winkler S (2008) Benchmark simulation model no. 1 (bsm1). Technical Report LTH-IEA-7229. Department of Industrial Electrical Engineering and Automation, Lund University, LundGoogle Scholar
- 4.Bolles S (2006) Modeling wastewater aeration systems to discover energy savings opportunities. Process Energy Services LLCGoogle Scholar
- 5.Chiu S (1994) A cluster extension method with extension to fuzzy model identification. In: Proceedings of the third IEEE conference on fuzzy systems, 1994 IEEE World congress on computational intelligence, vol 2, pp 1240–1245. doi: 10.1109/FUZZY.1994.343644
- 6.Copp JB (2002) The COST simulation benchmark: description and simulator manual. Directions in development (Washington): Environment, Directorate-General for ResearchGoogle Scholar
- 10.Gonzalez GD (1999) Soft-sensors for processing plants. In: Proceedings of the second international conference on intelligent processing and manufacturing of materials (IPMM 99), vol 1, pp 59–69. doi: 10.1109/IPMM.1999.792454
- 11.Hamdan H (2003) An exploration of the adaptive neuro-fuzzy inference system (ANFIS) for modelling survival, Ph.D. thesis. The University of NottinghamGoogle Scholar
- 12.Henze M, Grady C Jr, Gujer W, Marais GvR, Matsuo T (2000) Activated sludge model no. 1. In: Henze M, Gujer W, Mino T, van Loosdrecht M (eds) Activated sludge models ASM1, ASM2, ASM2d and ASM3. IWA Publishing, London, pp 1–37Google Scholar
- 22.Niemann H (2010) A model-based approach for fault-tolerant control. In: 2010 conference on control and fault-tolerant systems (SysTol), pp 481–492. doi: 10.1109/SYSTOL.2010.5675947
- 29.Yager RR, Filev DP (1994) Generation of fuzzy rules by mountain clustering. J Intell Fuzzy Syst 2(3):209–219Google Scholar