Integration of selected AI methods into a simulation tool for urban wastewater systems – towards practical application
-
Michael Ogurek
,
Jens Alex
Abstract
State-of-the-art modelling tools and dynamic simulations have become important tools for planning and operational decision making in the environmental sector, including wastewater treatment plants. Due to increasing regulatory requirements (energy savings, treatment performance, GHG footprint), the practical application of these instruments is becoming more challenging. AI methods could be a solution to support users in the application of domain-specific modelling and simulation tools. This contribution presents first steps towards the integration of the AI methods Bayesian Networks (BN) and Artificial Neural Networks (ANN) into a modelling and simulation tool for urban waste water systems, including example applications.
Zusammenfassung
State-of-the-art Modellierungswerkzeuge und dynamische Simulationen sind zu wichtigen Instrumenten für die Planung und betriebliche Entscheidungsfindung im Umweltsektor, einschließlich Kläranlagen, geworden. Aufgrund steigender gesetzlicher Anforderungen (Energieeinsparungen, Reinigungsleistung, Treibhausgasbilanz) wird die praktische Anwendung dieser Instrumente immer anspruchsvoller. KI-Methoden könnten eine Lösung sein, um Nutzer bei der Anwendung von domänenspezifischen Modellierungs- und Simulationswerkzeugen zu unterstützen. In diesem Beitrag werden erste Schritte zur Integration der KI-Methoden Bayes'sche Netze (BN) und Künstliche Neuronale Netze (ANN) in ein Modellierungs- und Simulationswerkzeug für kommunale Abwassersysteme vorgestellt, einschließlich Anwendungsbeispielen.
Funding source: German Federal Ministry for Economic Affairs and Climate Action
Award Identifier / Grant number: 49VF210005
About the authors
Michael Ogurek studied Water Management and Engineering Ecology at the Magdeburg University of Applied Sciences and is working at ifak – Institut für Automation und Kommunikation e.V. Magdeburg in Department of Water & Energy since 2002. The focus of his work is the development of simulation systems and project work in the field of modelling and simulation of wastewater systems.
Dr. Jens Alex is the Head of the Department of Water & Energy at ifak – Institut für Automation und Kommunikation e.V. Magdeburg. His main areas of work are model development (wastewater processes), development of simulation systems, simulation studies with joint consideration of processes and automation and development of process controllers in the field of wastewater (wastewater treatment plant/sewer network).
Dr. Manfred Schütze is Deputy Head of the Water & Energy Department at ifak – Institut für Automation und Kommunikation e. V. Magdeburg. He has experience in sewer system model building and application; his current work includes model development and application for sewer systems, integrated modelling of urban water systems, and real time control of urban water systems. He obtained his Diplom (Master) degree in Mathematics from University of Hannover in 1994 and his PhD degree from Imperial College in London in 2001.
Acknowledgments
The authors would like to thank the German Federal Ministry for Economic Affairs and Climate Action for funding the project “Framework for AI-based plant design tools for water and wastewater systems” (49VF210005).
-
Research ethics: Not applicable.
-
Author contributions: The authors have accepted responsibility for the entire content of this manuscript and approved its submission.
-
Competing interests: The authors state no conflict of interest.
-
Research funding: German Federal Ministry for Economic Affairs and Climate Action (49VF210005).
-
Data availability: Not applicable.
References
[1] P. Baumann, A. Gahr, U. Pachaly, F. Uecker, F. Obenaus, and C. Wolf, “KI-basierte Assistenzsysteme in der Abwasserwirtschaft,” KA Korrespondenz Abwasser, Abfall, vol. 70, no. 10, pp. 770–780, 2023.Suche in Google Scholar
[2] W. P. Wagner, “Trends in expert system development – a longitudinal content analysis of over thirty years of expert system case studies,” Expert Syst. Appl., vol. 76, no. 10, pp. 85–96, 2017. https://doi.org/10.1016/j.eswa.2017.01.028.Suche in Google Scholar
[3] A. Paszke, et al.., “PyTorch: an imperative style, high-performance deep learning library,” in Advances in Neural Information Processing Systems (NeurIPS), 2019.Suche in Google Scholar
[4] Y. Jia, et al.., “Caffe: convolutional architecture for fast feature embedding,” in Proceedings of the 22nd ACM International Conference on Multimedia, 2014, pp. 675–678.10.1145/2647868.2654889Suche in Google Scholar
[5] Modelica Association. Modelica® – A Unified Object-Oriented Language for Systems Modeling, Language Specification, 2023. Available at: https://modelica.org.Suche in Google Scholar
[6] A. Tudis, L. Rogovchenko-Buffoni, P. Fritzson, and A. Garro, “Model-based dependability analysis of physical systems with modelica,” Model. Simulat. Eng., vol. 2017, pp. 1–15, 2017. https://doi.org/10.1155/2017/1578043.Suche in Google Scholar
[7] H. Renninger and H. von Hasseln, “Object-orientated dynamic Bayesian network templates for modelling mechatronic systems,” in International Workshop on Principles of Diagnosis (DX-02), Proceedings, 2002.Suche in Google Scholar
[8] J. Alex, “Simulationsplattform zum integrierten Prozess- und Automatisierungsentwurf von Abwassersystemen,” Automatisierungstechnik, vol. 63, no. 7, pp. 553–563, 2015. https://doi.org/10.1515/auto-2014-1163.Suche in Google Scholar
[9] M. Henze, W. Gujer, T. Mino, and M. van Loosdrecht, “Activated sludge models ASM1, ASM2, ASM2D and ASM3,” IWA Scientific and Technical Report no. 9, London, UK, IWA Publishing, 2000.Suche in Google Scholar
[10] J. Alex and M. Ogurek, “Simulation als Tool zur Quantifizierung von Kapazitätsreserven. Wiener Mitteilungen,” Band, vol. 252, pp. 147–166, 2020.Suche in Google Scholar
[11] O. Schraa, L. Rieger, J. Alex, and I. Miletic, “Ammonia-based aeration control with optimal SRT control: improved performance and lower energy consumption,” Water Sci. Technol., vol. 79, no. 1, pp. 63–72, 2019. https://doi.org/10.2166/wst.2019.032.Suche in Google Scholar PubMed
[12] J. Alex, L. Rieger, and O. Schraa, “Comparison of advanced fine-bubble aeration control concepts with respect to energy efficiency and robustness,” in WEFTEC 2016, Session 405: Keeping Aeration Under Control, New Orleans, USA, 2016.10.2175/193864716819713169Suche in Google Scholar
[13] O. Schraa, L. Rieger, and J. Alex, “Development of a model for activated sludge aeration systems: linking air supply, distribution, and demand,” Water Sci. Technol., vol. 75, no. 3, pp. 552–560, 2017. https://doi.org/10.2166/wst.2016.481.Suche in Google Scholar PubMed
[14] J. Alex, “Keynote: design and runtime environment for model-based predictive controllers in water management,” in 13th IWA Conference on Instrumentation, Control & Automation – ICA, 2022.Suche in Google Scholar
[15] H. Al-As’ad, et al.., “Development and application of a predictive model for advanced wastewater treatment by adsorption onto powdered activated carbon,” Water Res., vol. 217, 2022, Art. no. 118427, https://doi.org/10.1016/j.watres.2022.118427.Suche in Google Scholar PubMed
[16] J. Pearl, Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference, San Francisco, CA, Morgan Kaufmann Publishers Inc., 1988.Suche in Google Scholar
[17] D. Koller and N. Friedman, Probabilistic Graphical Models: Principles and Techniques, Cambridge, MA, MIT Press, 2009.Suche in Google Scholar
[18] T. Minka, J. Winn, J. Guiver, Y. Zaykov, D. Fabian, and J. Bronskill, “Infer.NET 0.3, microsoft research Cambridge,” 2018. Available at: http://dotnet.github.io/infer.Suche in Google Scholar
[19] D. E. Rumelhart, G. E. Hinton, and R. J. Williams, “Learning representations by back-propagating errors,” Nature, vol. 323, no. 6088, pp. 533–536, 1986. https://doi.org/10.1038/323533a0.Suche in Google Scholar
[20] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning, Cambridge, MA, MIT Press, 2016.Suche in Google Scholar
[21] M. Abadi, et al.., “Tensorflow: a system for large-scale machine learning,” in 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16), 2016, pp. 265–283.Suche in Google Scholar
[22] F. Chollet, et al.., Keras, GitHub, 2015. Available at: https://github.com/fchollet/keras.Suche in Google Scholar
[23] SciSharp, Keras.NET, GitHub, 2019. Available at: https://github.com/SciSharp/Keras.NET.Suche in Google Scholar
[24] D. P. Kingma and J. Ba, “Adam: a method for stochastic optimization,” in International Conference on Learning Representations (ICLR), Poster, 2015.Suche in Google Scholar
© 2024 Walter de Gruyter GmbH, Berlin/Boston
Artikel in diesem Heft
- Frontmatter
- Editorial
- Advanced water management
- Survey
- Advances in dissolved oxygen prediction and control methods in aquaculture: a review
- Methods
- Probabilistic multi-step ahead streamflow forecast based on deep learning
- A new assessment method on co-occurring mountain and plain floods based on copula functions
- Application
- Prescriptive analytics for low and high water management in German waterways
- Tools
- Integration of selected AI methods into a simulation tool for urban wastewater systems – towards practical application
- NiMo 4.0 – Enabling advanced data analytics with AI for environmental governance in the water domain
Artikel in diesem Heft
- Frontmatter
- Editorial
- Advanced water management
- Survey
- Advances in dissolved oxygen prediction and control methods in aquaculture: a review
- Methods
- Probabilistic multi-step ahead streamflow forecast based on deep learning
- A new assessment method on co-occurring mountain and plain floods based on copula functions
- Application
- Prescriptive analytics for low and high water management in German waterways
- Tools
- Integration of selected AI methods into a simulation tool for urban wastewater systems – towards practical application
- NiMo 4.0 – Enabling advanced data analytics with AI for environmental governance in the water domain
