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.

• Klíčová slova
• artificial neural networks (ANN), caffeine, nanofiltration (NF), paracetamol, response surface methodology (RSM),
• Publikační typ
• časopisecké články MeSH

Ibuprofen separation from water by adsorption and pertraction processes has been studied, comparing 16 different membranes. Tailor-made membranes based on Matrimid, Ultem, and diaminobenzene/diaminobenzoic acid with various contents of zeolite and graphene oxide, have been compared to the commercial polystyrene, polypropylene, and polydimethylsiloxane polymeric membranes. Experimental results revealed lower ibuprofen adsorption onto commercial membranes than onto tailor-made membranes (10-15% compared to 50-70%). However, the mechanical stability of commercial membranes allowed the pertraction process application, which displayed a superior quantity of ibuprofen eliminated. Additionally, the saturation of the best-performing commercial membrane, polydimethylsiloxane, was notably prevented by atomic layer deposition of (3-aminopropyl)triethoxysilane.

• Klíčová slova
• atomic layer deposition, dense polymer membrane, ibuprofen, water treatment,
• Publikační typ
• časopisecké články MeSH

The article first summarizes case studies on the three basic types of treated water used in power plants and heating stations. Its main focus is Czechia as the representative of Eastern European countries. Water as the working medium in the power industry presents the three most common cycles-the first is make-up water for boilers, the second is cooling water and the third is represented by a specific type of water (e.g., liquid waste mixtures, primary and secondary circuits in nuclear power plants, turbine condensate, etc.). The water treatment technologies can be summarized into four main groups-(1) filtration (coagulation) and dosing chemicals, (2) ion exchange technology, (3) membrane processes and (4) a combination of the last two. The article shows the ideal industry-proven technology for each water cycle. Case studies revealed the economic, technical and environmental advantages/disadvantages of each technology. The percentage of technologies operated in energetics in Eastern Europe is briefly described. Although the work is conceived as an overview of water treatment in real operation, its novelty lies in a technological model of the treatment of turbine condensate, recycling of the cooling tower blowdown plus other liquid waste mixtures, and the rejection of colloidal substances from the secondary circuit in nuclear power plants. This is followed by an evaluation of the potential novel technologies and novel materials.

• Klíčová slova
• CapEx, OpEx, SDI, boilers, capacitive deionization, colloidal particles, electrodeionization, electrodialysis, energy, forward osmosis, heating station, ion exchange, membrane distillation, membrane processes, payback period, power generation, reverse osmosis, shock electrodialysis, turbine condensate, ultrafiltration, water treatment,
• Publikační typ
• časopisecké články MeSH