AI‐Driven Exergy and Thermo‐Economic Optimization of a Tubular Solar Still Integrated With an Evacuated Tube Solar Collector Using Physics‐Informed Neural Networks and Entropy‐Guided Adaptive Search Optimization

Solar desalination systems offer a sustainable and eco‐friendly approach for freshwater production in remote and arid regions by utilizing solar energy to purify saline or contaminated water. However, conventional solar stills suffer from low freshwater productivity and poor thermal performance due to significant heat losses, inefficient utilization of solar energy, and the absence of intelligent prediction and adaptive optimization techniques for operating parameter selection. To address these limitations, the proposed system integrates a Tubular Solar Still with an Evacuated Tube Solar Collector to enhance heat transfer and evaporation performance. A hybrid Physics‐Informed Artificial Neural Network model is employed to accurately predict system performance based on environmental and operational parameters. In addition, thermodynamic and thermo‐economic analyses are performed to evaluate efficiency, identify losses, and ensure economical operation. A novel Entropy‐Guided Adaptive Search Optimization method optimizes basin depth, flow rate, and tilt angle, achieving 88% energy efficiency, freshwater productivity of 10 L/day and a thermo‐economic cost of $0.0170/L.