ANFIS Direct Inverse Control of Substrate in an Activated Sludge Wastewater Treatment System

Abstract:

Nonlinearity of the substrate dynamics is the main inconveniences in its control. Low substrate concentration significantly affects the growth of the microorganisms responsible for treating the wastewater and too high substrate concentration level may lead to drop in the growth rate. Therefore, the control of substrate concentration is highly essential for effective and optimal operation of wastewater treatment plants. However, the control using conventional techniques is quite cumbersome and often impossible. This paper presents adaptive neuro fuzzy inference system (ANFIS) direct inverse control of substrate in an activated sludge system. The performances of the proposed controller are illustrated by tracking the substrate set-points. The simulation results demonstrate that the proposed controller can effectively and accurately control the substrate concentration level. The proposed inverse controller may serve as a valuable control strategy for the wastewater treatment plant.

• Periodical: Applied Mechanics and Materials (Volume 554)
• Pages: 246-250
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.554.246
• Online since: June 2014
• Authors: Muhammad Gaya Sani, Norhaliza Abdul Wahab*, Yahya M. Sam, Sharatul Izah Samsudin, Irma Wani Jamaludin
• Keywords: Controller, Fuzzy Inference System, Inverse Learning, Wastewater

References

[1] R. Aguilar-López, Regulation of an activate sludge wastwater plant via robust active control design, Int. J. Environ. Res., 7(2012)61–68.

[2] M. Cristea and S. Agachi, Nonlinear model predictive control of the wastewater treatment plant, Comput. Aided Chem. Eng., (2006) 1365–1370.

DOI: 10.1016/s1570-7946(06)80237-3

[3] F. Nejjari, B. Dahhou, A. Benhammou, and G. Roux, Nonlinear multivariable adaptive control of an activated sludge wastewater, Int. J. Adapt. Control Signal Process., 365(1998) 347–365.

DOI: 10.1002/(sici)1099-1115(199908)13:5<347::aid-acs543>3.0.co;2-8

[4] A. Chirosca, G. Dumitra, M. Barbu, and S. Caraman, Fuzzy Control of a Wastewater Treatment Process, in: J. Wadata et al. (Eds. ), Intelligent Decision Technologies, SIST 10, Springer-Verlag Berlin Heidelberg, 2011, pp.155-163.

DOI: 10.1007/978-3-642-22194-1_16

[5] D. Dochain, and P.A. Vanrolleghem, Dynamical Modelling and Estimation in Wastewater Treatment Processes. IWA Publishing, London, UK, (2001).

[6] J. Jang, ANFIS: Adaptive-network-based fuzzy inference system, IEEE Transactions on Syst. Man Cybern., 23(1993) 665–685.

DOI: 10.1109/21.256541

[7] M. A. Denai, F. Palis, and A. Zeghbib, ANFIS based modelling and control of non-linear systems: a tutorial, 2004 IEEE Int. Conf. Syst. Man Cybern., Oran, Algeria. IEEE: 3433–3438.

DOI: 10.1109/icsmc.2004.1400873

[8] B. Widrow and E. Walach, Adaptive Inverse Control: A Signal Processing Approach, Reissue Edition. John Wiley & Sons, Inc., New Jersey, (2008).