PENENTUAN DOSIS KOAGULAN PADA PENGOLAHAN AIR MINUM: PENDEKATAN FUZZY BERBASIS DATA DAN PENENTUAN FUZZY SET BERBASIS Z-SCORE
DOI:
https://doi.org/10.47080/0ffxq425Keywords:
Coagulant Prediction, Data-driven, Fuzzy Expert System, Linear RegressionAbstract
direct use of raw water has serious health risks. Therefore, various water treatment processes are needed to make the raw water safe for use in domestic purposes. One important stage in such processing processes is coagulation and flocculation, where chemicals (coagulants) are used to remove colloidal particles and form larger floc that can be easily precipitated through sedimentation and filtration. Determination of the optimal coagulant dosage is essential to achieve the desired water quality. However, jer-test problems, the non-linear nature of water, and the complexity of coagulation theory can make it difficult to determine the optimal dose. Therefore, in this study, a system is proposed that uses a data-based fuzzy approach and fuzzy set determination using z-score to study data patterns and relationships between parameters in the coagulation process. The proposed method utilizes a fuzzy approach to address the non-linear nature of water and the complexity of coagulation theory. The system uses the collected data patterns to develop fuzzy models that can predict optimal coagulant doses based on specific conditions. This approach allows the system to learn from existing data and identify patterns of relationships that may be hidden between relevant parameters. The results showed that the proposed system achieved an RMSE value of 0.7639589866827494, while the MSE value was 0.5836333333333333333. This suggests that the system can provide a fairly accurate prediction of the dose of coagulant required in the coagulation process.
References
Bressane, A., Goulart, A. P. G., Melo, C. P., Gomes, I. G., Loureiro, A. I. S., Negri, R. G., Moruzzi, R., Reis, A. G. dos, Formiga, J. K. S., da Silva, G. H. R., & Thomé, R. F. (2023). A Non-Hybrid Data-Driven Fuzzy Inference System for Coagulant Dosage in Drinking Water Treatment Plant: Machine-Learning for Accurate Real-Time Prediction. Water (Switzerland), 15(6). https://doi.org/10.3390/w15061126
Fang, X., Zhai, Z., Xiong, R., Zhang, L., & Gao, B. (2022). LSTM-based Modelling for Coagulant Dosage Prediction in Wastewater Treatment Plant. Proceedings of the 2022 3rd International Conference on Artificial Intelligence in Electronics Engineering, 23–27. https://doi.org/10.1145/3512826.3512847
Godo-Pla, L., Rodríguez, J. J., Suquet, J., Emiliano, P., Valero, F., Poch, M., & Monclús, H. (2021). Control of primary disinfection in a drinking water treatment plant based on a fuzzy inference system. Process Safety and Environmental Protection, 145, 63–70. https://doi.org/10.1016/j.psep.2020.07.037
Jayaweera, C. D., Othman, M. R., & Aziz, N. (2019). Improved predictive capability of coagulation process by extreme learning machine with radial basis function. Journal of Water Process Engineering, 32, 100977. https://doi.org/https://doi.org/10.1016/j.jwpe.2019.100977
Karamah, E. F., & Lubis, A. O. (n.d.). Pralakuan Koagulasi Dalam Proses Pengolahan Air Dengan Membran: Pengaruh Waktu Pengadukan Pelan Koagulan Aluminium Sulfat Terhadap Kinerja Membran.
Rohimah, L., Rukiastiandari, S., & Siregar, J. (n.d.). Penerapan Logika Fuzzy Metode Sugeno Untuk Optimalisasi Nilai Ekspor Ikan Tuna Hs 160414 Ke Italia. https://doi.org/10.31294/jtk.v4i2
Saritha, V., Srinivas, N., & Srikanth Vuppala, N. V. (2017). Analysis and optimization of coagulation and flocculation process. Applied Water Science, 7(1), 451–460. https://doi.org/10.1007/s13201-014-0262-y
Tahraoui, H., Belhadj, A. E., Moula, N., Bouranene, S., & Amrane, A. (2021). Optimisation and Prediction of the Coagulant Dose for the Elimination of Organic Micropollutants Based on Turbidity. Kemija u Industriji, 11–12. https://doi.org/10.15255/kui.2021.001
Wang, D., Wu, J., Deng, L., Li, Z., & Wang, Y. (2021). A real-time optimization control method for coagulation process during drinking water treatment. Nonlinear Dynamics, 105(4), 3271–3283. https://doi.org/10.1007/s11071-021-06794-5
Yamamura, H., Putri, E. U., Kawakami, T., Suzuki, A., Ariesyady, H. D., & Ishii, T. (2020). Dosage optimization of polyaluminum chloride by the application of convolutional neural network to the floc images captured in jar tests. Separation and Purification Technology, 237, 116467. https://doi.org/https://doi.org/10.1016/j.seppur.2019.116467
1.jpg)
