Artificial neural network modelling of As(III) removal from water by novel hybrid material

• Published in: Process safety and environmental protection Vol. 93; pp. 249 - 264
• Main Authors: Mandal, S., Mahapatra, S.S., Sahu, M.K., Patel, R.K.
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.01.2015
• Subjects: Adsorbents; Adsorption; Agitation; Algorithms; ANN; Arsenic; Back propagation; Contact; Hybrid materials; Mathematical models; ANN; Adsorption; Arsenic; Hybrid materials
• ISSN: 0957-5820; 1744-3598
• DOI: 10.1016/j.psep.2014.02.016

•A cost effective novel adsorbent is proposed for As(III) removal from water.•Removal efficiency of the adsorbent is tested over a wide range of pH (1–12).•Using 9g of adsorbent, 10mg As in 1L water could be reduced to 0.01mgL−1 in 30min.•The material can be regenerated and reused up to five adsorption cycles.•ANN modelling of AS(III) removal process reasonably predicts the removal efficiency. The present study reported a method for removal of As(III) from water solution by a novel hybrid material (Ce-HAHCl). The hybrid material was synthesized by sol–gel method and was characterized by XRD, FTIR, SEM–EDS and TGA–DTA. Batch adsorption experiments were conducted as a function of different variables like adsorbent dose, pH, contact time, agitation speed, initial concentration and temperature. The experimental studies revealed that maximum removal percentage is 98.85 at optimum condition: pH=5.0, agitation speed=180rpm, temperature=60°C and contact time=80min using 9gL−1 of adsorbent dose for initial As(III) concentration of 10mgL−1. Using adsorbent dose of 10gL−1, the maximum removal percentage remains same with initial As(III) concentration of 25mgL−1 (or 50mgL−1). The maximum adsorption capacity of the material is found to be 182.6mgg−1. Subsequently, the experimental results are used for developing a valid model based on back propagation (BP) learning algorithm with artificial neural networking (BP-ANN) for prediction of removal efficiency. The adequacy of the model (BP-ANN) is checked by value of the absolute relative percentage error (0.293) and correlation coefficient (R2=0.975). Comparison of experimental and predictive model results show that the model can predict the adsorption efficiency with acceptable accuracy.