Artificial neural networks for rapid WWTP performance evaluation: Methodology and case study
(2007) In Environmental Modelling & Software 22(8). p.1208-1216- Abstract
- Reliable performance evaluation of wastewater treatment plants (WWTPs) can be done by simulating the plant behavior over a wide range of influent disturbances, including series of rain events with different intensity and duration, seasonal temperature variations, holiday effects, etc. Such simulation-based WWTP performance evaluations are in practice limited by the long simulation time of the mechanistic WWTP models. By moderate simplification (avoiding big losses in prediction accuracy) of the mechanistic WWTP model only a limited reduction of the simulation time can be achieved. The approach proposed in this paper combines an influent disturbance generator with a mechanistic WWTP model for generating a limited sequence of training data... (More)
- Reliable performance evaluation of wastewater treatment plants (WWTPs) can be done by simulating the plant behavior over a wide range of influent disturbances, including series of rain events with different intensity and duration, seasonal temperature variations, holiday effects, etc. Such simulation-based WWTP performance evaluations are in practice limited by the long simulation time of the mechanistic WWTP models. By moderate simplification (avoiding big losses in prediction accuracy) of the mechanistic WWTP model only a limited reduction of the simulation time can be achieved. The approach proposed in this paper combines an influent disturbance generator with a mechanistic WWTP model for generating a limited sequence of training data (4 months of dynamic data). An antificial neural network (ANN) is then trained on the available WWTP input-output data, and is subsequently used to simulate the remainder of the influent time series (20 years of dynamic data) generated with the influent disturbance generator. It is demonstrated that the ANN reduces simulation time by a factor of 36, even when including the time needed for the generation of training data and for ANN training. For repeated integrated urban wastewater system simulations that do not require repeated training of the ANN, the ANN reduces simulation time by a factor of 1300 compared to the mechanistic model. ANN prediction of effluent ammonium, BOD5 and total suspended solids was good when compared to mechanistic WWTP model predictions, whereas prediction of effluent COD and total nitrogen concentrations was a bit less satisfactory. With correlation coefficients R-2 > 0.95 and prediction errors lower than 10%, the accuracy of the ANN is sufficient for applications in simulation-based WWTP design and simulation of integrated urban wastewater systems, especially when taking into account the uncertainties related to mechanistic WWTP modeling. (c) 2006 Elsevier Ltd. All rights reserved. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/662718
- author
- Raduly, B ; Gernaey, Krist LU ; Capodaglio, A. G. ; Mikkelsen, P. S. and Henze, M.
- organization
- publishing date
- 2007
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- design, plant, performance evaluation, artificial neural networks, modeling, simulation speed, time series, wastewater treatment plant
- in
- Environmental Modelling & Software
- volume
- 22
- issue
- 8
- pages
- 1208 - 1216
- publisher
- Elsevier
- external identifiers
-
- wos:000246308900013
- scopus:33947712235
- ISSN
- 1364-8152
- DOI
- 10.1016/j.envsoft.2006.07.003
- language
- English
- LU publication?
- yes
- id
- ea906661-0e72-40e4-bdc0-37ef8c1e8d37 (old id 662718)
- date added to LUP
- 2016-04-01 11:52:57
- date last changed
- 2022-04-20 23:14:25
@article{ea906661-0e72-40e4-bdc0-37ef8c1e8d37,
abstract = {{Reliable performance evaluation of wastewater treatment plants (WWTPs) can be done by simulating the plant behavior over a wide range of influent disturbances, including series of rain events with different intensity and duration, seasonal temperature variations, holiday effects, etc. Such simulation-based WWTP performance evaluations are in practice limited by the long simulation time of the mechanistic WWTP models. By moderate simplification (avoiding big losses in prediction accuracy) of the mechanistic WWTP model only a limited reduction of the simulation time can be achieved. The approach proposed in this paper combines an influent disturbance generator with a mechanistic WWTP model for generating a limited sequence of training data (4 months of dynamic data). An antificial neural network (ANN) is then trained on the available WWTP input-output data, and is subsequently used to simulate the remainder of the influent time series (20 years of dynamic data) generated with the influent disturbance generator. It is demonstrated that the ANN reduces simulation time by a factor of 36, even when including the time needed for the generation of training data and for ANN training. For repeated integrated urban wastewater system simulations that do not require repeated training of the ANN, the ANN reduces simulation time by a factor of 1300 compared to the mechanistic model. ANN prediction of effluent ammonium, BOD5 and total suspended solids was good when compared to mechanistic WWTP model predictions, whereas prediction of effluent COD and total nitrogen concentrations was a bit less satisfactory. With correlation coefficients R-2 > 0.95 and prediction errors lower than 10%, the accuracy of the ANN is sufficient for applications in simulation-based WWTP design and simulation of integrated urban wastewater systems, especially when taking into account the uncertainties related to mechanistic WWTP modeling. (c) 2006 Elsevier Ltd. All rights reserved.}},
author = {{Raduly, B and Gernaey, Krist and Capodaglio, A. G. and Mikkelsen, P. S. and Henze, M.}},
issn = {{1364-8152}},
keywords = {{design; plant; performance evaluation; artificial neural networks; modeling; simulation speed; time series; wastewater treatment plant}},
language = {{eng}},
number = {{8}},
pages = {{1208--1216}},
publisher = {{Elsevier}},
series = {{Environmental Modelling & Software}},
title = {{Artificial neural networks for rapid WWTP performance evaluation: Methodology and case study}},
url = {{http://dx.doi.org/10.1016/j.envsoft.2006.07.003}},
doi = {{10.1016/j.envsoft.2006.07.003}},
volume = {{22}},
year = {{2007}},
}