Numerical Evaluation of Parabolic-Trough Solar Collector Performance Enhancement Using Hybrid Nanofluids and Fuzzy Logic-Neural Network Integration

Enhancing the efficiency of parabolic-trough solar collectors (PTSCs) remains a pivotal objective for advancing solar-energy technology and fostering long-term energy sustainability. Accordingly, the present study examines the thermal-and exergy-performance gains attainable when Al 2 O 3 —CuO hybrid nanofluids, formulated in a HitecXL base, replace conventional working fluids. All simulations were carried out under the representative climatic conditions of Duba, Saudi Arabia. To predict collector behavior, a suite of data-driven models, ARIMA, CNN, and LSTM, was deployed; among them, the encoder–decoder LSTM (ED-LSTM) consistently produced the most accurate forecasts. Building on these predictions, a fuzzy-logic/neural-network (FL-NN) controller was introduced to adjust operating parameters in real time, thereby maximizing performance. The integrated configuration achieved a day-average thermal efficiency of 65.69% and an exergy efficiency of 31.94%, both measurably elevate higher than baseline figures. Parametric analysis further showed that higher flow rates and greater nanoparticle volume fractions elevate both efficiencies, whereas increased inlet temperature raises exergy efficiency yet diminishes thermal efficiency. Incremental efficiency gains observed at larger nanofluid fractions confirm their promise for future optimization. Collectively, the findings demonstrate that combining hybrid nanofluids with AI-guided control strategies can deliver more efficient and adaptable solar-energy systems.