This study presents a novel hybrid intelligent framework integrating fuzzy logic and artificial neural networks (ANN) to model the erosion-corrosion behavior of glass-fiber-reinforced pipes (GRP) under harsh operating conditions. Experimental data encompassing multiple operational parameters—including abrasive sand concentrations (250 g, 400 g, 500 g), flow rates (0.0067 m3/min, 0.01 m3/min, 0.015 m3/min), chlorine content (0–10 wt.%), and exposure times (1–5 h)—were utilized to develop the computational models. The fuzzy logic system effectively captured qualitative expert knowledge and uncertainty in material degradation processes, while ANN models provided quantitative predictions of erosion and corrosion rates. Results demonstrated good prediction accuracy, with R2 values of 0.81 for corrosion rate and moderate prediction accuracy 0.56 for erosion rate. The analysis revealed that flow rate (correlation: 0.6) and fuzzy severity (0.6) were the most influential parameters, followed by chlorine content (0.41) and sand concentration (0.32). The hybrid model identified optimal operating conditions to minimize material degradation: low sand concentration (250 g), low flow rate (0.0067 m3/min), absence of chlorine, and shorter exposure times. This intelligent modeling approach provides a powerful tool for predictive maintenance, operational optimization, and service life prediction of GRP systems in aggressive environments, bridging the gap between experimental data and computational intelligence for enhanced material performance assessment.
Hydrogen is emerging as a key solution to meet the global transition toward clean and sustainable energy. In this context, the present work investigates hydrogen production by solar-assisted water electrolysis in the presence of dispersed metal oxide powders. Four identical electrolyzers were operated under natural solar irradiation (Condition 1: 11:00–18:00; Condition 2: 11:00–17:00) at a constant applied current of 1.5 A. Three metal oxides (ZnO, MgO, and CuO) were tested individually and then with 1 wt% Al2O3 to evaluate the effect of Al2O3 addition. As single oxides, MgO exhibited the highest cumulative improvement (+46.74% vs. the Witness cell), followed by CuO (+19.57%) and ZnO (+16.30%). After Al2O3 addition, higher normalized hydrogen production was observed under the investigated conditions: ZnO–Al2O3 showed the largest increase (+123.69% vs. ZnO alone, irradiance-normalized basis), followed by MgO–Al2O3 (+59.78%) and CuO–Al2O3 (+47.93%). These results indicate that the effect of Al2O3 addition on hydrogen productivity is strongly oxide-dependent, and identify ZnO–Al2O3 as the most promising system among those tested. Overall, the study provides new insights into the design of oxide-assisted electrolysis systems and supports their potential for further development of solar-driven hydrogen production.