Electrocoagulation-based AZO DYE (P4R) Removal Rate Prediction Model using Deep Learning

作     者：Meryem Akoulih Smail Tigani Fouzia Byoud Meryem El Rharib Rachid Saadane Samuel Pierre Abdellah Chehri Sanae El Ghachtouli 

作者机构：IME Lab Faculty of Science Hassan 2 University 20250 Casablanca Morocco Research and Development Unit Accsellium LLC Fez Morocco Electrical Engineering Department SIRC-LaGeS Hassania School of Public Labors 20250 Casablanca Morocco Department of Computer and Software Engineering Polytechnique Montréal Montréal Québec Canada Department of Mathematics and Computer Science Royal Military College of Canada Kingston ON 11 K7K 7B4 Canada 

出 版 物：《Procedia Computer Science》 

年 卷 期：2024年第236卷

页      面：51-58页

主　　题：Electrocoagulation Wastewater Azo dye Deep learning 

摘      要：This article presents a study on the effectiveness of electrocoagulation (EC) for the removal of azo dyes from wastewater. The analysis was performed using a combination of statistical methods, including density estimation, correlation analysis, and deep learning for electrocoagulation performance prediction. The results showed that electrocoagulation was able to effectively remove azo dyes from the wastewater, considering the energy consumption and the mass of flocs being important factors in the process. Deep Learning (DL) is used to build our predictive model using the datasets collected during the experimentation stage. Overall, the findings suggest that electrocoagulation is a promising technique for the treatment of wastewater containing azo dyes, and that the use of statistical and machine learning methods can aid in the optimization of the process.