Optimal Operation of Domestic and Industrial Sewage Treatment Plants Using Machine Learning Methods
-
Published:2023-10-18
Issue:10
Volume:17
Page:e04124
-
ISSN:1981-982X
-
Container-title:Revista de Gestão Social e Ambiental
-
language:
-
Short-container-title:RGSA
Author:
Silva Sarah Lilian de LimaORCID, Leite Marcos SousaORCID, Fernandes Thalita Cristine Ribeiro LucasORCID, Da Silva Sidinei KleberORCID, De Araújo Antonio Carlos BrandãoORCID
Abstract
Purpose: This study aims to determine the economic and technical feasibility of operating and leasing sewage treatment plants through an application that uses mathematical modeling and Machine Learning techniques for process optimization.
Theoretical Framework: Efficient operation of sewage treatment plants (STPs) is crucial to ensure water quality, minimize environmental impacts, and optimize costs. This study explores how Machine Learning (ML) can model and optimize sewage treatment processes, adapting to real-time conditions.
Method/Design/Approach: The BSM1 model is combined with Machine Learning techniques to create simplified metamodels, enabling optimized results and the development of an application for evaluating economic and technical outcomes.
Results and Conclusion: The reduced metamodel successfully reproduced the Simulink model, achieving satisfactory optimization.
Research Implications: This research benefits water quality improvement, cost reduction, sustainability, innovation, water resource management, awareness, and resilience to extreme weather events, as well as influencing informed policies.
Originality/Value: Efficiency, sustainability, economy, and quality of life are core values in this research, benefiting society, the environment, and the economy.
Publisher
RGSA- Revista de Gestao Social e Ambiental
Subject
Management, Monitoring, Policy and Law,Geography, Planning and Development
Reference21 articles.
1. Alex, J., Benedetti, L., Copp, J., Gernaey, K. V, Jeppsson, U., Nopens, I., Pons, M.-N., Rieger, L., Rosen, C., Steyer, J. P., Vanrolleghem, P., Winkler, S., Magdeburg, I. E. V, Benedetti, G. L., University, L., & Rosen, C. C. (2008). Benchmark Simulation Model no. 1 (BSM1) Benchmark Simulation Model no. 1 (BSM1). In Benchmark Simulation Model (Issue 1). 2. Barreto, K. S. G., Matias, M. I. de A. S., Nogueira, N. W., & De Freitas, R. M. O. (2023). Domestic Effluent Treated for the Cultivation of Anthurium (Anthurium Andraeanum Lind.). Revista de Gestão Social e Ambiental, 17(9), e03228. https://doi.org/10.24857/rgsa.v17n9-005 3. CASAN. Companhia Catarinense de Águas e Saneamento. (n.d) Available at https://www.casan.com.br/menu-conteudo/index/url/ete-estacao-de-tratamento-de-esgotos-sanitarios. Accessed 26/01/2023 4. Clarke, S. M., Griebsch, J. H., & Simpson, T. W. (2005). Analysis of Support Vector Regression for Approximation of Complex Engineering Analyses. Journal of Mechanical Design, 127(6), 1077–1087. https://doi.org/10.1115/1.1897403 5. De la Fuente, R., Erazo, I., & Smith, R. L. (2018). ENABLING INTELLIGENT PROCESSES IN SIMULATION UTILIZING THE TENSORFLOW DEEP LEARNING RESOURCES. 2018 Winter Simulation Conference (WSC), 1108–1119. https://doi.org/10.1109/WSC.2018.8632539
|
|