Chijioke Elijah Onu

The integration of computational intelligence techniques into pharmaceutical wastewater treatment offers promising opportunities to improve process efficiency and minimize operational costs. This study compares the predictive capabilities of Response Surface Methodology (RSM) and Artificial Neural Network (ANN) models in forecasting the rejection efficiencies of caffeine and paracetamol using AFC 40 and AFC 80 nanofiltration (NF) membranes. Experiments were conducted under varying operating conditions, including transmembrane pressure, feed concentration, and flow rate. The predictive performance of both models was evaluated using statistical metrics such as the Coefficient of Determination (R²), Root Mean Square Error (RMSE), Marquardt’s Percentage Squared Error Deviation (MPSED), Hybrid fractional error function (HYBRID), and Average Absolute Deviation (AAD). Both models demonstrated strong predictive accuracy, with R² values of 0.9867 and 0.9832 for RSM and ANN, respectively, in AFC 40 membranes, and 0.9769 and 0.9922 in AFC 80 membranes. While both approaches closely matched the experimental results, the ANN model consistently yielded lower error values and higher R² values, indicating superior predictive performance. These findings support the application of ANNs as a robust modelling tool in optimizing NF membrane processes for pharmaceutical removal.

The integration of computational intelligence techniques into pharmaceutical wastewater treatment offers promising opportunities to improve process efficiency and minimize op-erational costs. This study compares the predictive capabilities of Response Surface Methodology (RSM) and Artificial Neural Network (ANN) models in forecasting the rejec-tion efficiencies of caffeine and paracetamol using AFC 40 and AFC 80 nanofiltration (NF) membranes. Experiments were conducted under varying operating conditions, including transmembrane pressure, feed concentration, and flow rate. The predictive performance of both models was evaluated using statistical metrics such as the Coefficient of Determina-tion (R²), Root Mean Square Error (RMSE), Marquardt’s Percentage Squared Error Devia-tion (MPSED), Hybrid fractional error function (HYBRID), and Average Absolute Devia-tion (AAD). Both models demonstrated strong predictive accuracy, with R² values of 0.9867 and 0.9832 for RSM and ANN, respectively, in AFC 40 membranes, and 0.9769 and 0.9922 in AFC 80 membranes. While both approaches closely matched the experimental results, the ANN model consistently yielded lower error values and higher R², indicating superior predictive performance. These findings support the application of ANN as a ro-bust modelling tool in optimizing NF membrane processes for pharmaceutical removal.

Pyrolytic oil usually contains high nitrogen and sulphur content which reduces its efficiency in addition to posing crucial environmental and health concerns. Hence the need for desulphurization and denitrogenation of pyrolytic oil obtained from waste tire for efficient application. Freshly prepared Ni-Cr adsorbent impregnated with TiO₂-SiO₂ catalyst was used as the adsorbent in the treatment of the pyrolytic oil through adsorption process. Effect of operating time and catalyst ratio were investigated. The result showed that both operating time and catalyst ratio influenced the percentage removal of sulphur and nitrogen. TiO₂:SiO₂ catalyst ratio of 2:3 gave 78.38%sulphur removal while ratio of 5:0 gave 89.80% nitrogen removal. The effect of time indicated that 78.84% and 93.98% removal of sulpur and nitrogen were obtained respectively after 120 minutes. For optimal simultaneous removal of both sulphur and nitrogen, a mixing ratio of 1:4 was obtained. The study showed that Ni-Cr/TiO₂-SiO₂ can be an effective adsorbent in desulphurization and denitrogenation of crude tire pyrolytic oil.

Chicken bone coagulant (CBC) containing high grade hydroxyapatite (HPA) has been applied in the coag-flocculation of abattoir effluent. The influence of process variables (pH, initial concentration, dosage, Temperature, and settling time) on the effluent final turbidity was investigated. Also, the accuracies of two modelling techniques (Response surface methodology, RSM and Artificial neutral network, ANN) in predicting the non-linear nature of the system were compared. The optimization result indicates a final turbidity of 4.96 mg/L (corresponding to 98.28 % removal efficiency) at pH = 6.7, dosage = 1.003 g/L, initial conc. = 182.2 mg/L, coagulation temp. = 345 K and settling time of 36 min. Meanwhile, effluent pH was spotted as the most significant variable, with p-value <0.01%. Furthermore, the error analysis result portrayed the supremacy of ANN over RSM in data prediction accuracy as it signified lower error values (Mean square error, MSE = 13.11 and Absolute average relative deviation, AARD = 1.43%) when compared to those of RSM (MSE = 37.78, AARD = 5.93%). Thus, it was demonstrated that ANN is a better tool for optimization study of the present system.

The sorption mechanisms, point of zero charge, and isosteric heats involved in the adsorptive dephenolization of aqueous solutions using thermally modified corn cob (TMCC) were studied at different initial phenol concentrations (100–500 mg/l), TMCC dosage (0.4–2.0 g), contact time (5–60 min), pH (2–10), and temperature (30–60°C). Analysis of the adsorbent material showed that it possessed the properties typical of a good adsorbent. The adsorption experiments revealed that phenol uptake is favored by an increase in TMCC dosage and contact time and a decrease in temperature and concentration of phenol in the solution. The experimental data were well-fitted to the Sips, Langmuir, Toth, and Redlich–Peterson isotherm models. Thermodynamic studies suggested that the sorption of phenol onto TMCC is feasible, spontaneous, and endothermic. The isosteric heats of adsorption obtained are in the range 47.43-79.38 kJ/mol, confirming that the adsorption process is predominantly a physical process depicting the van der Waals interactions, and it is inversely proportional to surface loading. The analysis of the adsorption mechanisms showed that the intraparticle, film, and pore diffusion mechanisms were significantly involved in the phenol adsorption process. The involvement of electrostatic attraction, electron-donor interaction, and hydrogen bonding was also demonstrated. The point of zero charge () was obtained at a pH of 5.83; being slightly lower than the optimum pH of 6 indicates that the sorbent surface is obviously not negatively charged at . The discoveries of this study have shown that the dephenolization process is feasible, spontaneous, endothermic, dominated by a physical process, and governed by intraparticle, film, and pore diffusion mechanisms.