Forecasting the effluent COD of refinery wastewater treatment plant using artificial intelligence
Journal of Behdasht dar Arseh (i.e., Health in the Field),
Vol. 11 No. 3 (1402),
21 May 2024
,
Page 19-30
https://doi.org/10.22037/jhf.v11i3.42836
Abstract
Background and Aims: Wastewater treatment plants are systems that can contribute to the health of the industry and the environment provided that they function properly. Mathematical and statistical simulators coupled with various models can be used to alleviate the costs of monitoring and managing wastewater treatment systems.
Materials and Methods: This is a retrospective descriptive- analytical study. Considering the complexity of biological processes along with the advances in data processing methods, algorithms (ANN) and M5 model tree were used in this study in order to make a modelto estimate the effluent COD in the sanitary wastewater treatment plant of one of the country's refineries. ANN and M5 were developed through learning and testing stages based on daily data of five consecutive years (2015-2020). Various statistical indicators such as MSE and R were used to evaluate the models. Ethical considerations were observed in all stages of the study.
Results: In the ANN model with 100 hidden layers, through the training step, the amount of MSE and R respectively decreased and increased, compared to the two modes of 10 and 30 hidden layers. This is why 100 layers were chosen for this model. Also, in the M5 tree model, R-SqOptimal = 0.6147 was calculated by selecting independent data as input, which is significant at the 0.05 level. In other words, with 95% confidence, the developed model is considered sufficiently logical for predicting CODout. The results showed that the ANN model outperformed M5 model tree for predicting effluent COD with a coefficient of determination equal to 0.90 and 0.61, respectively.
Conclusion: Both models have high robustness, reliability and generalizability. Therefore, ANN and M5 model tree data mining techniques can be successfully used for environmental decision-making and estimation of lost data in wastewater treatment plants.
- Wastewater treatment plant, Modeling, Artificial neural networks, M5 model tree, Quality parameters of wastewater
How to Cite
References
- Yel E, Yalpir S. Prediction of primary treatment effluent parameters by fuzzy inference system (FIS) approach. Procedia Computer Science 2011; 3:659-65.
- Fresner J. Cleaner production as a means for effective environmental management. Journal of Cleaner Production 1998; 6(3-4):171-79.
- Türkmenler H, Murat P. Performance assessment of advanced biological wastewater treatment plants using artificial neural networks. International Journal of Engineering Technologies 2017; 3(3):151-56.
- Mjalli FS, Al-Asheh S, Alfadala HE. Use of artificial neural network black-box modeling for the prediction of wastewater treatment plants performance. Journal of Environmental Management 2007; 83(3):329-38.
- Ward J, Ward P, Saint Ch, Mantzioris E. The urban agriculture revolution. Water: Journal of the Australian Water Association 2014; 41(1):69-74.
- Ramírez Y, Kraslawski A, Cisternas LA. Decision-support framework for the environmental assessment of water treatment systems. Journal of Cleaner Production 2019; 225:599-609. Doi: 10.1016/j.jclepro.2019.03.319.
- Najafzadeh M, Zeinolabedini M. Prognostication of waste water treatment plant performance using efficient soft computing models: An environmental evaluation. Measurement 2019; 138:690-701. Doi: 10.1016/j.measurement.2019.02.014.
- Hamada M, Adel Zaqoot H, Abu Jreiban A. Application of artificial neural networks for the prediction of Gaza wastewater treatment plant performance-Gaza strip. Journal of Applied Research in Water and Wastewater 2018; 5(1):399-406.
- Abiodun OI, Jantan A, Omolara AE, Dada KV, Mohamed NA, Arshad H. State-of-the-art in artificial neural network applications: A survey. Heliyon 2018; 4(11):e00938. Doi: 10. 1016/ j. heliyon. 2018.e00938.
- Hand D, Mannila H, Smyth P. Principles of data mining: a comprehensive highly technical look at the math and science behind extracting useful information from large databases. Massachusetts: Massachusetts Institute of Technology Press; 2001.
- Wan J, Huang M, Ma Y, Guo W, Wang Y, Zhang H, et al. Prediction of effluent quality of a paper mill wastewater treatment using an adaptive network-based fuzzy inference system. Applied Soft Computing 2011; 11(3):3238-46.
- Guo H, Jeong K, Lim J, Jo J, Kim YM, Park JP, et al. Prediction of effluent concentration in a wastewater treatment plant using machine learning models. Journal of Environmental Sciences 2015; 32:90-101.
- Manu DS, Thalla AK. Artificial intelligence models for predicting the performance of biological wastewater treatment plant in the removal of Kjeldahl Nitrogen from wastewater. Applied Water Science 2017; 7:3783-91. Doi: 10.1007/s13201-017-0526-4.
- Granata F, Papirio S, Esposito G, Gargano R., De Marinis G. Machine learning algorithms for the forecasting of wastewater quality indicators. Water 2017; 9(2):105. Doi: 10. 3390/ w9020105.
- Zare Abyaneh H. Evaluation of multivariate linear regression and artificial neural networks in prediction of water quality parameters. Journal of Environmental Health Science and Engineering 2014; 12:1-8. Doi: 10.1186/2052-336X-12-40.
- Abstract Viewed: 330 times