Öz
Wastewater management poses a global challenge. Integrating data-driven models has significantly enhanced treatment facilities' design and operational efficiency. In this study, an Artificial Neural Network (ANN) algorithm was adapted as a time-series forecasting model to predict effluent TN (Total Nitrogen) and TP (Total Phosphorus) concentrations in a real municipal wastewater treatment plant (WWTP). For this purpose, six independent TN and TP models were developed and evaluated using Mean Absolute Percentage Error (MAPE, %) and Root Mean Square Error (RMSE) metrics. Based on these criteria, all models demonstrated similar performance, with MAPE and RMSE values for TN forecasting at approximately 12% and 1.4, respectively, in the test phase. The MAPE was approximately 30% for TP forecasting, and RMSE was 0.25. Upon completing the modeling studies, one model was integrated into a user-friendly graphical user interface (GUI) and tested with actual data, allowing users to obtain results with a single click.
Anahtar Kelimeler
Wastewater treatment plant total nitrogen total phosphorus modelling gui design
Destekleyen Kurum
TÜBİTAK (The Scientific and Technological Research Council of Turkey) for financial support through the 2219 International Postdoctoral Research Fellowship Program for Turkish Citizens
Teşekkür
I would like to thank TÜBİTAK (The Scientific and Technological Research Council of Turkey) for financial support through the 2219 International Postdoctoral Research Fellowship Program for Turkish Citizens. I also acknowledge water utility in USA for providing the data and express my gratitude to my supervisor, Prof. Dr. Tanju Karanfil, for his valuable insights and encouragement.
Kaynakça
- Abba, S., Elkiran, G., & Nourani, V. (2021). Improving novel extreme learning machine using PCA algorithms for multi-parametric modeling of the municipal wastewater treatment plant. Desalination and Water Treatment, 215, 414-426. https://doi.org/10.5004/dwt.2021.26903
- Akhtar, N., Ishak, M. I. S., Bhawani, S. A., & Umar, K. (2021). Various natural and anthropogenic factors responsible for water quality degradation: A review. Water, 13, 2660. https://doi.org/10.3390/w13192660
- Archontoulis, S. V., & Miguez, F. E. (2015). Nonlinear regression models and applications in agricultural research. Agronomy Journal, 107(3), 786–798. https://doi.org/10.2134/agronj2012.0506
- El-Rawy, M., Abd-Ellah, M. K., Fathi, H., & Ahmed, A. K. A. (2021). Forecasting effluent and performance of wastewater treatment plant using different machine learning techniques. Journal of Water Process Engineering, 44, 102380. https://doi.org/10.1016/j.jwpe.2021.102380
- Hansen, L. D., Stokholm-Bjerregaard, M., & Durdevic, P. (2022). Modeling phosphorous dynamics in a wastewater treatment process using Bayesian optimized LSTM. Computers and Chemical Engineering, 160, 107738. https://doi.org/10.1016/j.compchemeng.2022.107738
- Haykin, S. (1999). Neural networks: A comprehensive foundation (2nd ed.). Prentice Hall.
- Ly, Q. V., Truong, H., Ji, B., Nguyen, X. C., Cho, K. H., Ngo, H. H., & Zhang, Z. (2022). Exploring potential machine learning application based on big data for prediction of wastewater quality from different full-scale wastewater treatment plants. Science of the Total Environment, 832, 154930. https://doi.org/10.1016/j.scitotenv.2022.154930
- Manav-Demir, N., Gelgor, H. B., Oz, E., Ilhan, F., Ulucan-Altuntaş, K., Tiwary, A., & Debik, E. (2022). Effluent parameters prediction of a biological nutrient removal (BNR) process using different machine learning methods: A case study. Journal of Environmental Management, 351, 119899. https://doi.org/10.1016/j.jenvman.2023.119899
- Manu, D. S., & Thalla, A. K. (2017). Artificial intelligence models for predicting the performance of biological wastewater treatment plant in the removal of Kjeldahl nitrogen from wastewater. Applied Water Science, 7, 3783-3791. https://doi.org/10.1007/s13201-017-0526-4
- Mohammadi, F., Yavari, Z., Mohammadi, F., & Rahimi, S. (2022). Prediction the performance of full scale wastewater treatment plant with A-B process using artificial neural network and genetic algorithm. International Journal of Environmental Health Engineering, 11(1), 1-7. https://doi.org/10.4103/ijehe.ijehe_52_20
- Oliveira, P., Fernandes, B., Analide, C., & Novais, P. (2021). Forecasting energy consumption of wastewater treatment plants with a transfer learning approach for sustainable cities. Electronics, 10, 1149. https://doi.org/10.3390/electronics10101149
- Safeer, S., Pandey, R. P., Rehman, B., Hasan, S. W., & Ullah, A. (2022). A review of artificial intelligence in water purification and wastewater treatment: Recent advancements. Journal of Water Process Engineering, 49, 102974. https://doi.org/10.1016/j.jwpe.2022.102974
- Sravan, J. S., Matsakas, L., & Sarkar, O. (2024). Advances in biological wastewater treatment processes: Focus on low-carbon energy and resource recovery in biorefinery context. Bioengineering, 11(3), 1-15. https://doi.org/10.3390/bioengineering11030281
- Wang, R., Yu, Y., Chen, Y., Pan, Z., Li, X., Tan, Z., & Zhang, J. (2022). Model construction and application for effluent prediction in wastewater treatment plant: Data processing method optimization and process parameters integration. Journal of Environmental Management, 302, 114020. https://doi.org/10.1016/j.jenvman.2021.114020
- Xu, Y., Zeng, X., Bernard, S., & He, Z. (2021). Data-driven prediction of neutralizer pH and valve position towards precise control of chemical dosage in a wastewater treatment plant. Journal of Cleaner Production, 348, 131360. https://doi.org/10.1016/j.jclepro.2022.131360
- Yu, T., & Bai, Y. (2018). A comparative study of extreme learning machine, least squares support vector machine, and back propagation neural network for outlet total phosphorous prediction. In Prognostics and System Health Management Conference (pp. 717-722).
- Zhao, L., Dai, T., Qiao, Z., Sun, P., Hao, J., & Yang, Y. (2020). Application of artificial intelligence to wastewater treatment: A bibliometric analysis and systematic review of technology, economy, management, and wastewater reuse. Process Safety and Environmental Protection, 133, 169-182. https://doi.org/10.1016/j.psep.2019.11.014
Öz
Atıksu yönetimi, dünya genelinde önemli bir zorluk teşkil etmektedir. Veriye dayalı modellerin entegrasyonu, arıtma tesislerinin tasarım ve işletim verimliliğini artırmıştır. Bu çalışmada, yapay sinir ağı algoritması (ANN) evsel atıksu arıtım tesisinde çıkış akımı toplam azot (TN) ve toplam fosfor (TP) parametrelerinin tahmini için zaman serisi öngörüsü yapacak şekilde modifiye edilmiştir. Bu amaçla, 6 farklı ve bağımsız TN ve TP modelleri geliştirilmiştir. Model performansı, Ortalama mutlak yüzde hatası (MAPE, %) ve Hataların Karesinin Ortalamasının Karekökü (RMSE) ile değerlendirilmiştir. Bu kriterlere göre tüm alternatif modeller benzer performans sergilemiştir. Çıkış akımı toplam azot (TN) tahmin modellerinin test fazında MAPE ve RMSE değerleri sırasıyla %12 ve 1.4 civarında elde edilmiştir. Çıkış akımı toplam fosfor (TP) için MAPE değeri yaklaşık %30, RMSE ise 0.25 olarak hesaplanmıştır. Modelleme çalışmaları tamamlandıktan sonra, bir model kullanıcı dostu bir grafik kullanıcı arayüzüne (GUI) entegre edilmiştir ve gerçek verilerle test edilmiştir. Bu, kullanıcıya tek tıklama ile sonuç alma imkânı sunmaktadır.
Anahtar Kelimeler
Atıksu Arıtım Tesisi toplam azot toplam fosfor modelleme grafiksel arayüz tasarımı
Kaynakça
- Abba, S., Elkiran, G., & Nourani, V. (2021). Improving novel extreme learning machine using PCA algorithms for multi-parametric modeling of the municipal wastewater treatment plant. Desalination and Water Treatment, 215, 414-426. https://doi.org/10.5004/dwt.2021.26903
- Akhtar, N., Ishak, M. I. S., Bhawani, S. A., & Umar, K. (2021). Various natural and anthropogenic factors responsible for water quality degradation: A review. Water, 13, 2660. https://doi.org/10.3390/w13192660
- Archontoulis, S. V., & Miguez, F. E. (2015). Nonlinear regression models and applications in agricultural research. Agronomy Journal, 107(3), 786–798. https://doi.org/10.2134/agronj2012.0506
- El-Rawy, M., Abd-Ellah, M. K., Fathi, H., & Ahmed, A. K. A. (2021). Forecasting effluent and performance of wastewater treatment plant using different machine learning techniques. Journal of Water Process Engineering, 44, 102380. https://doi.org/10.1016/j.jwpe.2021.102380
- Hansen, L. D., Stokholm-Bjerregaard, M., & Durdevic, P. (2022). Modeling phosphorous dynamics in a wastewater treatment process using Bayesian optimized LSTM. Computers and Chemical Engineering, 160, 107738. https://doi.org/10.1016/j.compchemeng.2022.107738
- Haykin, S. (1999). Neural networks: A comprehensive foundation (2nd ed.). Prentice Hall.
- Ly, Q. V., Truong, H., Ji, B., Nguyen, X. C., Cho, K. H., Ngo, H. H., & Zhang, Z. (2022). Exploring potential machine learning application based on big data for prediction of wastewater quality from different full-scale wastewater treatment plants. Science of the Total Environment, 832, 154930. https://doi.org/10.1016/j.scitotenv.2022.154930
- Manav-Demir, N., Gelgor, H. B., Oz, E., Ilhan, F., Ulucan-Altuntaş, K., Tiwary, A., & Debik, E. (2022). Effluent parameters prediction of a biological nutrient removal (BNR) process using different machine learning methods: A case study. Journal of Environmental Management, 351, 119899. https://doi.org/10.1016/j.jenvman.2023.119899
- Manu, D. S., & Thalla, A. K. (2017). Artificial intelligence models for predicting the performance of biological wastewater treatment plant in the removal of Kjeldahl nitrogen from wastewater. Applied Water Science, 7, 3783-3791. https://doi.org/10.1007/s13201-017-0526-4
- Mohammadi, F., Yavari, Z., Mohammadi, F., & Rahimi, S. (2022). Prediction the performance of full scale wastewater treatment plant with A-B process using artificial neural network and genetic algorithm. International Journal of Environmental Health Engineering, 11(1), 1-7. https://doi.org/10.4103/ijehe.ijehe_52_20
- Oliveira, P., Fernandes, B., Analide, C., & Novais, P. (2021). Forecasting energy consumption of wastewater treatment plants with a transfer learning approach for sustainable cities. Electronics, 10, 1149. https://doi.org/10.3390/electronics10101149
- Safeer, S., Pandey, R. P., Rehman, B., Hasan, S. W., & Ullah, A. (2022). A review of artificial intelligence in water purification and wastewater treatment: Recent advancements. Journal of Water Process Engineering, 49, 102974. https://doi.org/10.1016/j.jwpe.2022.102974
- Sravan, J. S., Matsakas, L., & Sarkar, O. (2024). Advances in biological wastewater treatment processes: Focus on low-carbon energy and resource recovery in biorefinery context. Bioengineering, 11(3), 1-15. https://doi.org/10.3390/bioengineering11030281
- Wang, R., Yu, Y., Chen, Y., Pan, Z., Li, X., Tan, Z., & Zhang, J. (2022). Model construction and application for effluent prediction in wastewater treatment plant: Data processing method optimization and process parameters integration. Journal of Environmental Management, 302, 114020. https://doi.org/10.1016/j.jenvman.2021.114020
- Xu, Y., Zeng, X., Bernard, S., & He, Z. (2021). Data-driven prediction of neutralizer pH and valve position towards precise control of chemical dosage in a wastewater treatment plant. Journal of Cleaner Production, 348, 131360. https://doi.org/10.1016/j.jclepro.2022.131360
- Yu, T., & Bai, Y. (2018). A comparative study of extreme learning machine, least squares support vector machine, and back propagation neural network for outlet total phosphorous prediction. In Prognostics and System Health Management Conference (pp. 717-722).
- Zhao, L., Dai, T., Qiao, Z., Sun, P., Hao, J., & Yang, Y. (2020). Application of artificial intelligence to wastewater treatment: A bibliometric analysis and systematic review of technology, economy, management, and wastewater reuse. Process Safety and Environmental Protection, 133, 169-182. https://doi.org/10.1016/j.psep.2019.11.014
Ayrıntılar
| Birincil Dil | İngilizce |
|---|---|
| Konular | Atıksu Arıtma Süreçleri, Su Arıtma Süreçleri, Süreç Kontrolü ve Simülasyonu |
| Bölüm | Kimya Mühendisliği |
| Yazarlar | |
| Yayımlanma Tarihi | 3 Mart 2025 |
| Gönderilme Tarihi | 13 Kasım 2024 |
| Kabul Tarihi | 20 Aralık 2024 |
| Yayımlandığı Sayı | Yıl 2025Cilt: 28 Sayı: 1 |
