Artificial Neural Network as a Virtual Sensor of Nitrate Nitrogen (V) Concentration in an Activated Sludge Reactor
More details
Hide details
The Silesian University of Technology, Gliwice, Poland
Online publication date: 2020-12-31
Publication date: 2020-12-01
Civil and Environmental Engineering Reports 2020;30(4):188–200
The paper discusses the use of an artificial neural network to control the operation of wastewater treatment plants with activated sludge. The task of the neural network in this case is to calculate (predict) the readings of the probe measuring the concentration of nitrate nitrogen (V) in one of the biological reactor tanks. Neural networks are known for their ability to universal approximation of virtually any relationship, including the function of many variables, but the process of “training” the network requires the presentation of many sets of input data and corresponding expected results. This is a difficulty in the case of wastewater treatment plants, because some key process parameters are usually not measured online (samples are taken and measurements are taken in the laboratory), and even if they are, the time intervals are large. Bearing in mind the aforementioned difficulty, this work uses a set of input data consisting only of information that can be measured with measuring probes. As a result of the conducted experiments a high compliance of the probe’s prediction with the expected values was obtained. The paper also presents data preparation and the network “training” process.
Buscema M 1998. Back Propagation Neural Networks. Substance Use & Misuse, 33(2).
Copp, J (Ed.) 2002. The COST Simulation Benchmark: Description and Simulator Manual. Luxembourg: Office for Official Publications of the European Community.
Dymaczewski, Z [red.] 2011. Sewage treatment plant operator’s guide (Poradnik eksploatatora oczyszczalni ścieków). Poznań Polskie Zrzeszenie Inżynierów i Techników Sanitarnych Oddział Wielkopolski.
Kristianti, N et al. 2018. Prediction of Peat Forest Fires Using Wavelet and Backpropagation, IJITEE, Vol. 2, No. 2.
Lichuan, Liu, Kuo, SM and Zhou, M 2009. Virtual sensing techniques and their applications, International Conference on Networking, Sensing and Control, Okayama, pp. 31-36.
Nissen, S 2003. Implementation of a Fast Artificial Neural Network Library (FANN). Copenhagen: Department of Computer Science, University of Copenhagen.
Nissen, S et al.. FANN - Fast Artificial Neural Network Library, < http://leenissen.dk/fann/wp/>, access 2020-11-30.
Rosenblatt, F 1958. The Perceptron: A Probabilistic Model for information Storage and Organization in The Brain, Psychological Review, 65(6).
Sadecka, Z 2010. Basics of biological wastewater treatment (Podstawy biologicznego oczyszczania ścieków) Warszawa: Wydawnictwo Seidel- Przywecki.
Shao, S et al. 2019. Extended Kalman Filter Method based on Backpropagation Neural Network in Current Sensor Online Calibration, IOP Conf. Series: Materials Science and Engineering 631.
Stokes, AJ, West, JR, Forster, CF and Davies, WJ 2000. Understanding some of the differences between the COD- and BOD- based models offered in STOAT. Water Res., 34(4).
Tadeusiewicz, R 2001. Introduction to neural networks (Wprowadzenie do sieci neuronowych) Kraków: StatSoft Polska.
Velandia, NS et al. 2017. Applications of Deep Neural Networks, Internetional Journal of Systems Signal Control and Engineering Application 10 (1-6), 61-76.
Wąsik, E, Chmielowski, K, Studziński, J and Szeląg, B 2018. Application of artificial neural networks to forecasting total nitrogen content in secondary effluent from treatment plants (Zastosowanie sztucznych sieci neuronowych do prognozowania zawartości azotu ogólnego w odpływie z oczyszczalni ścieków) Ochrona Środowiska, Vol. 40 No. 1.