A holistic framework for improving the prediction of reverse osmosis membrane performance using machine learning

被引:14
作者
Mohammed, Areej [1 ]
Alshraideh, Hussam [2 ,3 ]
Alsuwaidi, Fatima [1 ]
机构
[1] Amer Univ Sharjah, Dept Ind Engn, Engn Syst Management Program, POB 26666, Sharjah, U Arab Emirates
[2] Amer Univ Sharjah, Dept Ind Engn, POB 26666, Sharjah, U Arab Emirates
[3] Jordan Univ Sci & Technol, Ind Engn Dept, Irbid, Jordan
关键词
Reverse osmosis; Salt rejection; Machine learning; Feature selection; SHAP analysis; ARTIFICIAL NEURAL-NETWORK; DESALINATION; WATER; PRETREATMENT;
D O I
10.1016/j.desal.2023.117253
中图分类号
TQ [化学工业];
学科分类号
0817 ;
摘要
Accurate prediction and modeling of RO membranes performance is crucial in desalination processes for proper process control and operation. Existing models do not consider all process parameters, leading to less understanding of the parameter's importance. In this study, 5 non-ensemble and 7 ensemble machine learning models were employed to predict the performance of RO membrane. Data from a modern RO desalination plant in the UAE was utilized for the models' building. Thirteen input parameters, including operational parameters, water characteristic parameters, and time-dependent parameters, were used to predict salt rejection. The results suggested that ensemble techniques are more capable of predicting the performance of RO membranes. Among ensemble methods, the XGBoost model was found to outperform other models. Recursive feature elimination was integrated with Shapley additive explanation analysis to gain insights into the most influential predictors and confirm the model's ability to comprehend the RO membrane mechanism. The findings highlighted that five parameters are critical for predicting RO membrane performance and could be prioritized for future monitoring to provide timely membrane performance warnings: the membrane's age, feed water temperature, pressure, feed water flow, and chloride concentration. It also indicated that maintaining lower temperatures, increasing feed water pressure, and increasing feed flow can improve process efficiency. The optimal XGBoost model was found to have an outstanding predictive performance with a high R2 (94.75) and a low RMSE (0.181). Ultimately, the framework proposed by this study can serve as a tool to simplify and understand complex membrane processes.
引用
收藏
页数:11
相关论文
共 50 条
[41]   A complementary approach of response surface methodology and an artificial neural network for the optimization and prediction of low salinity reverse osmosis performance [J].
Brooke, Ryan ;
Fan, Linhua ;
Khayet, Mohamed ;
Wang, Xu .
HELIYON, 2022, 8 (09)
[42]   Machine learning - Driven surface grafting of thin-film composite reverse osmosis (TFC-RO) membrane [J].
Tayyebi, Arash ;
Alshami, Ali S. ;
Tayyebi, Erfan ;
Buelke, Chris ;
Talukder, Musabbir Jahan ;
Ismail, Nadhem ;
Al-Goraee, Ashraf ;
Rabiei, Zeinab ;
Yu, Xue .
DESALINATION, 2024, 579
[43]   Alleviating reverse osmosis membrane fouling caused by biopolymers using pre-ozonation [J].
Yin, Zhonglong ;
Wen, Tiancheng ;
Li, Yan ;
Li, Aimin ;
Long, Chao .
JOURNAL OF MEMBRANE SCIENCE, 2020, 595
[44]   Crystallization prediction and reverse engineering framework construction for mold flux based on machine learning methods [J].
Ji, Yi ;
Chen, Jiaxi ;
Zhou, Lejun ;
Wang, Wanlin ;
Qi, Jianghua ;
Liu, Peng ;
Chen, Kui .
MATERIALS TODAY COMMUNICATIONS, 2025, 45
[45]   The effect of feed pH on the performance of a reverse osmosis membrane [J].
Hoang, T. ;
Stevens, G. ;
Kentish, S. .
DESALINATION, 2010, 261 (1-2) :99-103
[46]   A Holistic Approach on Airfare Price Prediction Using Machine Learning Techniques [J].
Kalampokas, Theofanis ;
Tziridis, Konstantinos ;
Kalampokas, Nikolaos ;
Nikolaou, Alexandros ;
Vrochidou, Eleni ;
Papakostas, George A. .
IEEE ACCESS, 2023, 11 :46627-46643
[47]   Improving Machine Learning Prediction Performance for Premature Termination of Psychotherapy [J].
Bohus, Martin ;
Gimbel, Stephan ;
Goerg, Nora ;
Humm, Bernhard G. ;
Schueller, Martin ;
Steffens, Marc ;
Vonderlin, Ruben .
ARTIFICIAL INTELLIGENCE: METHODOLOGY, SYSTEMS, AND APPLICATIONS, AIMSA 2018, 2018, 11089 :141-151
[48]   Performance prediction of roadheaders using ensemble machine learning techniques [J].
Seker, Sadi Evren ;
Ocak, Ibrahim .
NEURAL COMPUTING & APPLICATIONS, 2019, 31 (04) :1103-1116
[49]   Effect of Electric Field on Membrane Fouling and Membrane Performance in Reverse Osmosis Treatment of Brackish Water [J].
Fu, Caixia ;
Yi, Xuenong ;
Gao, Yuqiong .
APPLIED SCIENCES-BASEL, 2024, 14 (02)
[50]   Reverse osmosis membrane element integrity evaluation using imperfection model [J].
Niewersch, Claudia ;
Rieth, Christopher ;
Hailemariam, Leaelaf ;
Oriol, Guillem Gilabert ;
Warczok, Justyna .
DESALINATION, 2020, 476