2026-10-18T23:47:37Zhttps://ebyu-rdlopen.rawdatalibrary.net/oai/request

oai:ebyu-rdlopen.rawdatalibrary.net:ebyu/103282026-10-18T20:36:51Zopenairedrivercom_ebyu_10000col_ebyu_10001

Machine Learning-Based Performance Analysis of Solar Thermal Storage Tanks with Fin-Configured Phase Change MaterialsÇolak, Andaç BaturKılınç, Cumaartificial neural networksBayesian Regularizationlatent heat energy storageparaffin waxsurrogate modelingBayesian networksComputational fluid dynamicsDigital storageFins (heat exchange)Heat storageLearning systemsMachine learningMean square errorOptimizationSolar concentratorsSolar energySolar heatingStorage (materials)Thermal conductivityThermal energyVertical stabilizersHeat distributionLiquid fractionMachine-learningNeural-networksPhase ChangeReynold numberStorage tankLatent heatNeural networksSolar thermal energy storage systems play a vital role in bridging the gap between intermittent solar availability and continuous energy demand; however, their efficiency is severely constrained by the inherently low thermal conductivity of phase change materials. Integrating physical heat transfer enhancements, such as radial fins, offers a practical solution, but evaluating these non-linear thermal dynamics across diverse design configurations typically incurs heavy computational costs. To address this challenge, this research investigates an artificial intelligence-based predictive framework capable of accurately modeling complex phase change dynamics in fin-configured storage tanks. Utilizing high-fidelity 2D Computational Fluid Dynamics simulation data of a stainless-steel double-tube storage tank filled with RT-50 paraffin wax across 10, 20, and 29 fin configurations, a Multi-Layer Perceptron Artificial Neural Network trained with the Bayesian Regularization algorithm was developed. The model predicts liquid fraction, latent heat distribution, and buoyancy-driven natural convection (Reynolds number) based on fin count and time. The optimal architecture, featuring 30 hidden neurons, achieved exceptional predictive precision, yielding a coefficient of determination of 0.99999, along with individual Mean Squared Error values of 1.29 × 10−3 for liquid fraction, 5.73 × 10−1 for latent heat distribution, and 2.64 × 10−5 for Reynolds number, with average prediction deviation rates consistently below 0.5%. These results demonstrate that high-precision surrogate modeling can effectively replace computationally intensive numerical simulations, offering significant practical implications for the real-time thermal monitoring, rapid design optimization, and intelligent control of advanced solar energy storage technologies. © 2026 by the authors.Multidisciplinary Digital Publishing Institute (MDPI)2026Articlehttps://rdlopen.rawdatalibrary.net/r/ebyu/10328https://doi.org/10.3390/en191741691996-1073enEnergiesinfo:eu-repo/semantics/openAccessinfo:eu-repo/semantics/articlehttps://ebyu-rdlopen.rawdatalibrary.net/tr/items/ebyu/10328