Optimization methodology based on neural networks and box-behnken design applied to photocatalysis of acid red 114 dye

Abstract

The present work deals with the modeling and optimization of photocatalytic degradation (UV/TiO<sub>2</sub>) of aqueous solution of Acid Red 114 (AR114) dye using Artificial Neural Networks (ANN) and RSM. Photocatalytic treatment of AR114 has been executed using suspension TiO<sub>2</sub>catalyst for commercial applications exposed to ultraviolet irradiation in a shallow pond reactor. ANN optimization has been applied to for predicting the behavior of photocatalysis. The input parameters used for analysis of aqueous dye solution are - TiO<sub>2</sub> dose, pH of the dye solution, initial dye concentration, UV light intensity, time and area/volume, and time whereas the outputs are evaluated in form of degradation and decolorization efficiency of AR114. The outcomes of ANN optimization have been experimentally validated. Results achieved establish ANN modeling as a good predictive model. Parameteric optimization using multi-parameter optimization has been employed with desirability function approach. Results obtained from RSM are in line as per the results of ANN modeling as well as experimental. First order kinetics is use to effectively express degradation and decolorization of AR114 dyes. Total organic carbon (TOC) removal and GC-MS study of the dye shows the total mineralization and formation of non-toxic intermediate products.

Response Surface Methodology: Photocatalytic Degradation Kinetics of Basic Blue 41 Dye Using Activated Carbon with TiO2

“…Furthermore, the optimum conditions obtained were confirmed and verified experimentally which was closer to the predicted results with less than 2% deviation. This is agreeable to other studies suggesting RSM is economically viable for experimental optimizations based on its predictability with precision [ 27 , 28 ].…”

“…The fit statistics, as presented in Table 3 , show that the predicted R 2 of 0.886 and 0.893 for color and turbidity, respectively, were in reasonable agreement with the adjusted R 2 of 0.966 and 0.975, where their difference is less than 0.2, suggesting good predictability of the models. Considering the acceptable threshold value of R 2 , which should be greater than or equal to 0.8, it becomes more relevant when it is closer to 1 [ 27 , 28 ]. The statistical significance ( p < 0.05) of the model and its validity are tested by using the ANOVA ( Table 4 and Table 5 ), with additional information such as the Fisher variation ratio (F-value), adequate precision, coefficient of variance (CV), probability value (Prob > F) and lack of fit.…”

“…In response to this fact, optimization becomes an option to improve photocatalytic degradation efficiency. Herein response surface methodology (RSM) is proven as an effectual tool for process optimization with multi-complex operational factors [ 26 , 27 , 28 ]. A Box Behnken design (BBD), a type of RSM, has shown to be very efficient as compared to the central composite design (CCD) in estimating the correlation coefficient ( R 2 ) for a specified model, reduced experimental errors and good data fitness in the design, modeling and optimization of a process [ 24 , 28 ].…”

Artificial neural network modeling of cefixime photodegradation by synthesized CoBi2O4 nanoparticles

“…The use of validation data was to test network generalization and to stop training if generalization stops. The test data provided a fully independent network performance measurement during and following training (Ayoubi-Feiz et al 2019).The modeling of the photodegradation of CFX was carried out by MATLAB R2014a which has been widely used(Medarević et al 2016;Ayoubi-Feiz et al 2019;Tabatabai-Yazdi et al 2019;Zulfiqar et al 2019;Garg et al 2020). The model parameters are described in Table1.…”

High-Throughput Zwitterion-Modified MoS2 Membranes: Preparation and Application in Dye Desalination

“…2 It has been reported that approximately 15% of the dye is discharged as wastewater from the industries, which will cause serious environmental pollution and resource waste. 3 Even more serious is that most dyes are carcinogenic and will pose a severe threat to human health if they exist in water bodies. Therefore, it is of great significance to realize near-zero emission and resource utilization of dyes.…”