Artificial Neural Networks and Genetic Algorithms: An Efficient Modeling and Optimization Methodology for Degradation of Atenolol Using Activated Persulfate with Ultrasound

Atenolol (ATN) is a slowly biodegradable antagonist β-blocker drug and remains in the environment for long period of time. This has harmful effect on human animal bodies. In this study, using activated persulfate with ultrasound degradation ATN was investigated. The independent variables including pH, concentration, dose, contact time, ultrasonic power been studied at 5 levels. Central composite design (CCD) used designing experiments Design Expert 11.0 software. concentration measured high-performance liquid chromatography (HPLC). Genetic algorithms (GA) artificial neural network (ANN) were optimization prediction, respectively. results indicated that optimal conditions experiment (pH 6.79, reaction time 19 min, initial 15.92 mg/L, US 109.56 W, PS dose 1317.88 mg/L), highest efficiency 98.9%. could be represented by pseudo-zero-order kinetics. Also, data well fitted ANN model (R2 = 0.98). showed best pH range to eliminate near neutral GA found an effective tool optimize experimental removal ATN. ultrasonic/persulfate process as useful technique high potential remove from aqueous solutions.