Modeling and Optimization of Hybrid Fenton and Ultrasound Process for Crystal Violet Degradation Using AI Techniques

Abstract

This study conducts a comprehensive investigation to optimize the degradation of crystal violet (CV) dye using the Fenton process. The main objective is to improve the efficiency of the Fenton process by optimizing various physicochemical factors such as the Fe2+ concentration, H2O2 concentration, and pH of the solution. The results obtained show that the optimal dosages of Fe2+ and H2O2 giving a maximum CV degradation (99%) are 0.2 and 3.13 mM, respectively. The optimal solution pH for CV degradation is 3. The investigation of the type of acid for pH adjustment revealed that sulfuric acid is the most effective one, providing 100% yield, followed by phosphoric acid, hydrochloric acid, and nitric acid. Furthermore, the examination of sulfuric acid concentration shows that an optimal concentration of 0.1 M is the most effective for CV degradation. On the other hand, an increase in the initial concentration of the dye leads to a reduction in the hydroxyl radicals formed (HO•), which negatively impacts CV degradation. A concentration of 10 mg/L of CV gives complete degradation of dye within 30 min following the reaction. Increasing the solution temperature and stirring speed have a negative effect on dye degradation. Moreover, the combination of ultrasound with the Fenton process resulted in a slight enhancement in the CV degradation, with an optimal stirring speed of 300 rpm. Notably, the study incorporates the use of Gaussian process regression (GPR) modeling in conjunction with the Improved Grey Wolf Optimization (IGWO) algorithm to accurately predict the optimal degradation conditions. This research, through its rigorous investigation and advanced modeling techniques, offers invaluable insights and guidelines for optimizing the Fenton process in the context of CV degradation, thereby achieving the twin goals of cost reduction and environmental impact minimization.

Efficiency of Hydrogen Peroxide and Fenton Reagent for Polycyclic Aromatic Hydrocarbon Degradation in Contaminated Soil: Insights from Experimental and Predictive Modeling

“…Gaussian regression, also known as Gaussian process regression, stands as a sophisticated approach in machine learning for modeling probabilistic functions from observed data [28]. Unlike parametric regression models that impose specific assumptions on the data distribution, Gaussian processes embrace a non-parametric approach, thereby offering increased flexibility to represent complex relationships among variables [29].…”

“…The procedure for estimating the target function involves leveraging the properties of this distribution by using the observed data to update estimates of the mean and covariance [32]. This Bayesian approach offers the advantage of robust modeling while allowing precise quantification of uncertainty, which proves particularly useful in cases where data are limited or noisy [28]. Gaussian regression represents a powerful and flexible tool in the field of artificial intelligence, offering an elegant probabilistic method for modeling and predicting complex phenomena [30].…”

“…This graphical representation facilitated the identification of any systematic deviations or patterns in the model's predictions across different phases [33]. Additionally, a second analytical approach was employed, where an error histogram was constructed to visualize the distribution of residuals for each phase (Figure 8b) [28,33]. This method allowed for a deeper exploration of the discrepancies between predicted and observed values, shedding light on potential outliers or areas of inconsistency.…”