Мақола

DEVELOPMENT OF AN ANN-BASED PREDICTIVE MODEL FOR THE EFFICIENT TREATMENT OF INDUSTRIAL WASTEWATER

Alisher Khudoyberdi ugli RakhimovKarshi State Technical University. Address: 20, Shahrisabz street, Shahrisabz, Uzbekistan, 181306. E-mail: [email protected], Phone: +998993015567;Hasan Siddiq ugli MurodovKarshi State Technical University. Address: 20, Shahrisabz street, Shahrisabz, Uzbekistan, 181306. E-mail: [email protected], Phone: +998995962486;Farrukh Bakhtiyorovich IgitovTashkent institute of chemical technology. Address: Navoi Street, 32, Tashkent, Uzbekistan, 100011. E-mail: [email protected], Phone: +998995382862;Shuhrat Ahmadjonovich MutalovAngren university. Address: Fleyshmaxer ko‘chasi, 2-uy, Toshkent vil, Angren sh. 110200. E-mail: [email protected], Phone: +9989465845988;Jaloliddin EshbobaevTashkent institute of chemical technology. Address:.Navoi Street, 32, Tashkent, Uzbekistan, 100011. E-mail: [email protected], Phone: +998938032741

Himičeskaâ tehnologiâ. Kontrolʹ i upravlenie/Chemical Technology. Control and Managementjournal2025en

ABI

Аннотация

The effective removal of free chlorine ions from industrial wastewater is critical to ensure process safety, minimize equipment corrosion, and protect aquatic environments. In this study, a laboratory-scale activated carbon filtration system was developed and tested to treat chlorine-contaminated water collected from sludge collectors at industrial facilities. A total of 200 experimental trials were conducted under varied operational conditions, including changes in flow rate, initial chlorine concentration, pressure, pH, temperature, and activated carbon dosage. The resulting dataset was used to train a predictive model based on a feedforward backpropagation artificial neural network (ANN) implemented in MATLAB. The ANN model demonstrated excellent performance, achieving a mean squared error (MSE) of 9.63 × 10⁻⁵ and a high regression coefficient (R = 0.9665) across all data. The model’s predictive capability was validated through detailed performance plots, error histograms, and regression analysis. The results confirm that the ANN can reliably estimate residual chlorine concentrations based on key process variables, making it a valuable tool for optimizing activated carbon filter operations and enhancing intelligent control in industrial wastewater treatment systems. This research highlights the potential of integrating AI-based modeling with traditional water purification technologies to improve process efficiency and environmental sustainability.

Ҳали таржима қилинмаган

Мавзулар

Water Quality Monitoring and Analysis

Идентификаторлар

DOI: 10.59048/2181-1105.1685

Иқтибослар ва манбалар

0 та иқтибос13 та фойдаланилган манба

Кўрсаткичлар — AkademScholar