An Offline Digital-Twin-Assisted Decision-Support Framework for Dynamic RO Under Kuwait Solar-Availability Conditions
Membranes, cilt.16, sa.9, 2026 (SCI-Expanded, Scopus)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 16 Sayı: 9
- Basım Tarihi: 2026
- Doi Numarası: 10.3390/membranes16090281
- Dergi Adı: Membranes
- Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Chemical Abstracts Core, Compendex, INSPEC, Directory of Open Access Journals, Academic Search Ultimate (EBSCO), Natural Science Collection (ProQuest), Biological Science Database (ProQuest), Engineering Source (EBSCO), Health Research Premium Collection (ProQuest), Materials Science & Engineering Collection (ProQuest), Technology Collection (ProQuest)
- Anahtar Kelimeler: dynamic pressure operation, Kuwait, machine learning, offline digital twin, permeate flow rate, photovoltaic desalination, reverse osmosis, specific energy consumption
- Ankara Yıldırım Beyazıt Üniversitesi Adresli: Evet
Özet
Reverse osmosis (RO) desalination is a major technology for freshwater production in arid regions, but its energy demand becomes more challenging when the system is supplied by variable renewable energy. This study presents an offline digital-twin-assisted decision-support framework for dynamic RO under Kuwait solar-availability conditions. Within this framework, the predictive models are driven primarily by the dynamic RO process variables, while NASA Prediction Of Worldwide Energy Resources (POWER) data provide the Kuwait solar-availability context, and the PV power margin serves as a scenario-level energy indicator. The purpose is to predict instantaneous permeate flow rate, estimate specific energy consumption, and identify energy-efficient operating conditions using machine learning. Kuwait City was used as the solar case-study location. Hourly solar and meteorological data were obtained from NASA POWER, while dynamic RO membrane data were obtained from the open experimental wave desalination dataset published by the National Renewable Energy Laboratory (NREL) through Data.gov and the Marine and Hydrokinetic Data Repository. The RO dataset includes steady-state, ramp, sinusoidal, and Wave Energy Converter SIMulator (WEC-Sim) pressure/flow experiments. The process-flow image used in the system description was also taken from the same NREL dataset and is cited in the figure caption. The raw RO files were cleaned, harmonized, and transformed into a process-informed modeling dataset. Derived features included pressure rate, recovery ratio, salt rejection, estimated pump power, specific energy consumption (SEC), PV power margin, and rolling pressure/flow features. Three supervised regression models were tested: Gradient Boosting, Random Forest, and XGBoost. A representative subset of 60,000 records was used to preserve the main experimental conditions while reducing redundancy in the densely sampled sequential data. Results show that permeate flow rate can be predicted with high accuracy using Gradient Boosting (R2 = 0.981; RMSE = 0.161 L/min). The moderate energy prediction performance yielded an R2 of 0.654 and RMSE of 7.570 kWh/m3 for Random Forest. The accuracy of permeate conductivity predictions was lower (R2 = 0.257; RMSE = 245.44 µS/cm) because membrane and feed characterizing parameters should be included for an adequate water quality control. The proposed approach is best suited as an offline decision-support framework for dynamic RO process analysis.