Wastewater Treatment Plants (WWTPs) are necessary infrastructure for protecting the environment and public health, but modeling and predicting performance has been an ongoing challenge for engineers working within a WWTP and regulators of the environment. For many years the Activated Sludge Model No. 1 (ASM1) has been the standard for simulating biological treatment processes, but the conventional implementations in MATLAB do not provide the user-friendly interface, the predictive intelligence, or the ability to logically store data as required for practical application. The proposed smart WWTP simulation framework provides an integrated simulation of ASM1 and an ANN model in a single, simple to use environment (the framework) that will enable operational assessment and performance forecasting regarding Wastewater Treatment Plants. The planned result is the ability to generate, automatically, detailed multi-sheet excels reports that summarize the configuration of the network used to train the ANN, display training performance curves, provide a comparison of predicted with actual outputs, include measures of plant efficiency, and include complete system logs from the entire system into one shareable document. Trained ANN models will be saved in. MAT format for immediate re-use in the future, thereby alleviating the computational effort of retraining the ANN multiple times. Users will be provided with pre-processed datasets and specific access instructions related to the platform in order to make use of the framework. The goal of the framework is to provide usable ANN models to users who have little experience with using MATLAB.

Keywords—ASM1, ANN, Wastewater Treatment, MATLAB, Machine Learning, Prediction, Automated Reporting, UI Simulation

[1]  R. S. Asiwal, S. K. Sar, S. Singh, and M. Sahu, "Wastewater Treatment by Effluent Treatment Plants," SSRG International Journal of Civil Engineering, vol. 3, no. 12, pp. 29–35, Dec. 2016. [2]  X. Chen, Z. Xu, L. Yao, and N. Ma, "Processing Technology Selection for Municipal Sewage Treatment Based on a Multi-Objective Decision Model under Uncertainty," International Journal of Environmental Research and Public Health, vol. 15, no. 3, p. 448, 2018. [3]  "Waste Water Treatment," European Green Capital Award Nantes, pp. 149–152, 2013. [4]  J. Dhote, S. Ingole, and A. Chavhan, "Review on Wastewater Treatment Technologies," International Journal of Engineering Research & Technology, vol. 1, no. 5, pp. 1–11, 2012. [5]  M. K. David, "A Review Paper on Industrial Wastewater Treatment Processes," 2016. [6]  N. S. Topare, S. J. Attar, and M. M. Manfe, "Sewage/Wastewater Treatment Technologies: A Review," Scientific Reviews & Chemical Communications, vol. 1, no. 1, pp. 18–24, 2011. [7]  H.-W. Chen, S.-K. Ning, R.-F. Yu, and M.-S. Hung, "Optimizing the Monitoring Strategy of Wastewater Treatment Plants by Multiobjective Neural Networks Approach," Environmental Monitoring and Assessment, vol. 125, pp. 325–332, 2007. [8]  D. Güçlü and Ş. Dursun, "Artificial Neural Network Modelling of a Large-Scale Wastewater Treatment Plant Operation," Bioprocess and Biosystems Engineering, vol. 33, pp. 1051–1058, 2010. [9]  R. Zhang and X. Hu, "Prediction of Wastewater Treatment Plants Performance Based on Neural Networks," in Proc. ICICA, LNCS 7030, pp. 367–374, 2011. [10]      M. Djeddou, H. Aouatef, and I. Loukam, "Wastewater Treatment Plant Performances Modelling Using Artificial Neural Networks," in Proc. International Conference, 2018. [11]      M. Djeddou and B. Achour, "Prediction of Sludge Volume Index in Wastewater Treatment Plants Using ANN," Larhyss Journal, no. 24, pp. 351–370, 2015. [12]      I. N. Ottenheijm, A. Fischer, and J. F. Colton, "Modelling the Performance of Water Treatment Plants Using Artificial Neural Networks – A Literature Review," 2014. [13]      V. Sousa, J. P. Matos, and N. Matias, "Evaluation of Artificial Intelligence Tool Performance and Uncertainty for Predicting Sewer Structural Condition," Automation in Construction, vol. 44, pp. 84–91, 2014. [14]      E. Doğan, R. Köklü, and B. Şengörür, "Estimation of Biological Oxygen Demand Using Artificial Neural Network," 2002. [15]      Ö. Çınar, "New Tool for Evaluation of Performance of Wastewater Treatment Plant: Artificial Neural Network," Process Biochemistry, vol. 40, pp. 2980–2984, 2005. [16]      M. S. Nasr, M. A. E. Moustafa, H. A. E. Seif, and G. El Kobrosy, "Application of ANN for Prediction of Wastewater Treatment Plant Performance," Alexandria Engineering Journal, vol. 51, pp. 37–43, 2012. [17]      L. Berthod et al., "QSPR for Predicting Sorption of Pharmaceuticals to Sewage Sludge," Science of the Total Environment, vol. 579, pp. 1512–1520, 2017. [18]      G. Onkal-Engin, I. Demir, and S. N. Engin, "Relationship between Sewage Odour and BOD Using Neural Networks," Environmental Modelling & Software, vol. 20, pp. 843–850, 2005. [19]      Siemens AG, "Optimization of Sewage Treatment Plants by Advanced Process Control," White Paper, 2015. [20]      S. I. Abba and G. Elkiran, "Effluent Prediction of COD Using ANN," Procedia Computer Science, vol. 120, pp. 156–163, 2018. [21]      Y. Patil, P. Raut, Y. Patil, and S. Dhurve, "Design of Sewage Treatment Plant Units," IJSRET, vol. 7, no. 3, pp. 177–181, 2018. [22]      P. N. Wakode and S. U. Sayyad, "Performance Evaluation of 25MLD STP at Kalyan," AJER, vol. 3, no. 3, pp. 310–316, 2014. [23]      A. Biswas et al., "Study and Modification of Sewage Treatment Plant at Jaspur," IJIRST, vol. 4, no. 10, 2018. [24]      D. P. B. T. B. Strik et al., "Prediction of Trace Compounds in Biogas Using MATLAB ANN Toolbox," Environmental Modelling & Software, vol. 20, pp. 803–810, 2005. [25]      M. Solaimany-Aminabad, A. Maleki, and M. Hadi, "Prediction of Water Treatment Plant Influent Characteristics Using ANN," J Adv Environ Health Res, vol. 1, no. 2, pp. 89–100, 2013. [26]      S. Areerachakul, P. Junsawang, and A. Pomsathit, "Prediction of Dissolved Oxygen Using ANN," in Proc. ICCCM, pp. 524–526, 2011. [27]      N. Hazali, N. A. Wahab, and S. Ibrahim, "Modelling and Evaluation of SBR Using ANN," IJECE, vol. 7, no. 3, pp. 1620–1627, 2017.