Artificial intelligence techniques in electrochemical processes for water and wastewater treatment: a review

In recent years, artificial intelligence (AI) techniques have been recognized as powerful techniques. In this work, AI techniques such as artificial neural networks (ANNs), support vector machines (SVM), adaptive neuro-fuzzy inference system (ANFIS), genetic algorithms (GA), and particle swarm optimization (PSO), used in water and wastewater treatment processes, are reviewed. This paper describes applications of the mentioned AI techniques for the modelling and optimization of electrochemical processes for water and wastewater treatment processes. Most research in the mentioned scope of study consists of electrooxidation, electrocoagulation, electro-Fenton, and electrodialysis. Also, ANNs have been the most frequent technique used for modelling and optimization of these processes. It was shown that most of the AI models have been built with a relatively low number of samples (< 150) in data sets. This points out the importance of reliability and robustness of the AI models derived from these techniques. We show how to improve the performance and reduce the uncertainty of these developed black-box data-driven models. From the perspectives of both experiment and theory, this review demonstrates how AI techniques can be effectively adapted to electrochemical processes for water and wastewater treatment to model and optimize these processes.

Supplementary Information

The online version contains supplementary material available at 10.1007/s40201-022-00835-w.

Graphite/NiO/Ni Electrode for Electro-oxidation of the Remazol Black 5 Dye

Graphite/NiO/Ni electrode had been fabricated for the electro-oxidation of remazol black 5 dye. The electrode was synthesized by electrodeposition method. Electro-oxidation of 100 ppm remazol black 5 dye was carried out at various concentrations of NaCl, 0.025; 0.05; 0.1; 0.25; and 0.5 M, variations in electro-oxidation time were 15, 30, 45, and 60 minutes, and pH variations were 4, 6, and 8. Cyclic voltammetry test revealed that graphite/NiO/Ni electrode had higher electrocatalytic capability compared to graphite electrode. The X-ray diffraction (XRD) patterns showed the decreasing value of 2θ from 44.6° for Ni to 43.5° for NiO. Scanning Electron Microscopy-Energy Dispersive X-ray (SEM-EDX) showed that NiO/Ni deposited on the graphite surface in the form of solid grains and cracks, FTIR showed that δ(Ni−O) bond appeared at 582–511 cm−1. The decolorization efficiency of remazol black 5 for graphite/NiO/Ni electrode was 100% for 45 minutes of the electro-oxidation process, while the decolorization efficiency of remazol black 5 for graphite electrode was 99.74% for 60 minutes of the electro-oxidation process. Copyright © 2021 by Authors, Published by BCREC Group. This is an open access article under the CC BY-SA License (https://creativecommons.org/licenses/by-sa/4.0). 

Electrochemical Degradation of Crystal Violet Using Ti/Pt/SnO2 Electrode

Today, organic wastes (paints, pigments, etc.) are considered to be a major concern for the pollution of aqueous environments. Therefore, it is essential to find new methods to solve this problem. This research was conducted to study the use of electrochemical processes to remove organic pollutants (e.g., crystal violet (CV)) from aqueous solutions. The galvanostatic electrolysis of CV by the use of Ti/Pt/SnO2 anode, were conducted in an electrochemical cell with 100 mL of solution using Na2SO4 and NaCl as supporting electrolyte, the effect of the important electrochemical parameters: current density (20–60 mA cm−2), CV concentration (10–50 mg L−1), sodium chloride concentration (0.01–0.1 g L−1) and initial pH (2 to 10) on the efficiency of the electrochemical process was evaluated and optimized. The electrochemical treatment process of CV was monitored by the UV-visible spectrometry and the chemical oxygen demand (COD). After only 120 min, in a 0.01 mol L−1 NaCl solution with a current density of 50 mA cm−2 and a pH value of 7 containing 10 mg L−1 CV, the CV removal efficiency can reach 100%, the COD removal efficiency is up to 80%. The process can therefore be considered as a suitable process for removing CV from coloured wastewater in the textile industries.

Adsorption of Organic Pollutants from Cold Meat Industry Wastewater by Electrochemical Coagulation: Application of Artificial Neural Networks

The cold meat industry is considered to be one of the main sources of organic pollutants in the wastewater of the meat sector due to the complex mixture of protein, fats, and dyes present. This study describes electrochemical coagulation (EC) treatment for the adsorption of organic pollutants reported in cold meat industry wastewater, and an artificial neural network (ANN) was employed to model the adsorption of chemical oxygen demand (COD). To depict the adsorption process, the parameters analyzed were current density (2–6 mA cm−2), initial pH (5–9), temperature (288–308 K), and EC time (0–180 min). The experimental results were fit to the Langmuir and Freundlich isotherm equations, while the modeling of the adsorption kinetics was evaluated by means of pseudo-first and pseudo-second-order rate laws. The data reveal that current density is the main control parameter in EC treatment, and 60 min are required for an effective adsorption process. The maximum removal of COD was 2875 mg L−1 (82%) when the following conditions were employed: pH = 7, current density = 6 mA cm−2, and temperature of 298 K. Experimental results obey second-order kinetics with values of the constant in the range of 1.176 × 10−5 ≤ k2 (mg COD adsorbed/g-Al.min) ≤ 1.284 × 10−5. The ANN applied in this research established that better COD removal, 3262.70 mg L−1 (93.22%) with R2 = 0.98, was found using the following conditions: EC time of 30.22 min, initial pH = 7.80, and current density = 6 mA cm−2. The maximum adsorption capacity of 621.11 mg g−1 indicates a notable affinity between the organic pollutants and coagulant metallic ions.

Electrocatalytic oxidative treatment of real textile wastewater in continuous reactor: Degradation pathway and disposability study

Electrocatalytic treatment of real textile wastewater was investigated in continuous electrochemical reactor using dimensionally stable Ti/RuO₂ anode. Effects of various parameters such as: elapsed time, current, pH, retention time on the COD removal, color removal and specific energy consumed were evaluated. Central Composite Design under RSM was used for experimental design, data analysis, optimization, interaction analysis between the various electrochemical parameters and steady state time analysis. GC-MS and UV spectrophotometric analysis of the untreated and treated wastewater were conducted to identify the oxidized and transformed/degraded compounds during the oxidation process, and a suitable degradation mechanism was proposed. Treated wastewater may contain toxic chlorinated compounds due to mediated oxidation by various hydrolyzed chlorine species. Therefore, disposability of treated wastewater was assessed by conducting toxicity bioassay test. The optimal set of operating parameters were found to be elapsed time = 124 min, current = 1.37 A, pH = 5.54 and retention time = 157.6 min to simultaneously achieve COD removal, color removal and specific energy consumed as 86.22%, 94.74% and 0.012 kW h, respectively. GC-MS analysis showed presence of chlorinated compounds in the treated wastewater. The toxicity bioassay test resulted acute toxicity with 100% mortality rate within one minute and one hour exposure with untreated and treated textile wastewater, respectively.

Electro-oxidation of Ofloxacin antibiotic by dimensionally stable Ti/RuO2 anode: Evaluation and mechanistic approach

Present study investigates the potential of Ti/RuO₂ electrode for degradation and mineralization of Ofloxacin (OFLX) antibiotic from synthetic wastewater by electro-oxidation (EO) method, not reported earlier. Effects of various EO parameters such as applied current (I), initial pH, initial OFLX concentration (C₀) and supporting electrolyte concentration on %OFLX removal efficiency and %TOC removal efficiency were systematically studied and reported. Decay kinetics of OFLX by varying C₀ and applied I were also studied. Additionally, mineralization current efficiency and specific energy consumption of OFLX mineralization were evaluated. Moreover, mode of oxidation method involved (direct and/or indirect oxidation) was also explored. Major OFLX transformation products during EO were identified using UPLC-Q-TOF-MS, and possible degradation reaction mechanism was proposed. Furthermore, operating cost analysis was performed to check the economic feasibility of the EO process. The optimum pH and current (I) were found to be ≈6.8 (natural pH of OFLX wastewater) and 1 A, respectively. Mineralization current efficiency decreased from 7.8% to 4.9% with increase in I value from 0.25 to 1 A. ≈80% of OFLX removal in 30 min of electrolysis and 46.3% TOC removal in 240 min of electrolysis at I = 1 A were observed. Pseudo-first-order kinetic model best fitted the experimental data showing R² value ≈ 0.99 for all the C_o and applied I studied.

Prediction of concrete corrosion in sewers with hybrid Gaussian processes regression model

A hybrid Gaussian Processes Regression (GPR) model is to approach the evolution of the corrosion rate and corrosion initiation time, thereby supporting the calculation of service life of sewers.

Photocatalytic Treatment of Binary Mixture of Dyes using UV/TiO2 Process: Calibration, Modeling, Optimization and Mineralization Study

Photocatalytic treatment of a binary dye mixture (Acid Blue 113 (AB113) and Acid Red 114 (AR114)) has been done in a slurry pond reactor using TiO2 as a photocatalyst with UV light irradiation (UV-C). Two different methods, namely multivariate calibration and first order derivative spectrophotometric were used to quantify each dye separately in binary dye solutions. The behavior of the photocatalytic degradation of a binary dye mixture was predicted using an artificial neural network (ANN) model. Five process parameters (initial concentration of AB113 dye, initial concentration of AR114 dye, TiO2 dose, initial pH of the dye mixture and time were used as inputs and decolorization efficiency of AB113 and AR114 were used as output of the ANN. The parametric optimization has been done by the multi-response optimization with desirability function methodology. Optimization by Central Composite Design (CCD) effectively handles the relations among optimizing process variables and its prediction concurred well with the experimental run and artificial neural network (ANN) model. The reaction kinetic rates of decolorization of both dyes (AB113 and AR114) were found to be first order. Total organic carbon (TOC) removal and possible reaction pathway show the total mineralization of both dyes in binary dye mixture.

The prediction of the optimum compositions of a parenteral nanoemulsion system loaded with a low water solubility drug for the treatment of schizophrenia by artificial neural networks

Aripiprazole was encapsulated in a palm kernel oil esters nanoemulsion for the purpose of brain deliveryviaintravenous administration.

Removal of a reactive dye and hexavalent chromium by a reusable bacteria attached electrospun nanofibrous web

Bacteria have been immobilized onto a polysulfone nanofibrous web and used for the removal of reactive dye and heavy metal.