Results in Engineering · 2024 · 39 citations · 81 references
EngineeringMaterials EngineeringMaterials ScienceMachine LearningNanomaterialsNanotechnologyEnergy ConversionGraphene NanomaterialsHybrid NanomaterialsNanoenergy MaterialsNanostructured Energy MaterialsNeural NetworksBayesian NetworksBayesian Neural NetworksComputational NanotechnologyEnergy Conversion EfficiencyEnergy Conversion NanomaterialsMxenesSolar Energy ConversionThermophysical Properties
Accurately predicting thermo-physical properties (TPPs) of MXene/graphene-based nanofluids is crucial for photovoltaic/thermal solar systems, driving focused research on developing precise TPP predictive models. This study presents optimized multi-layer perceptron neural network (MLPNN) models, leveraging Bayesian optimization to refine architectural and training hyperparameters, including hidden layers, neurons, activation functions, standardization, and regularization terms. A comparative analysis of Bayesian acquisition functions—the probability of improvement (POI), lower confidence bound (LCB), expected improvement (EI), expected improvement plus (EIP), expected improvement per second plus (EIPSP), and expected improvement per second (EIPS)—demonstrated that the POI-MLPNN achieves the most accurate results, as evidenced by the lowest MAPE of 1.0923 % and exceptional consistency with an R-value of 0.99811. The EI-MLPNN and EIP-MLPNN models recorded the same outputs. The EI/EIP-MLPNN (R = 0.99668) model excels in consistency over LCB-MLPNN (R = 0.99529) and EIPSP-MLPNN (R = 0.99667). The optimized models offer a reliable, cost-efficient alternate for experimental and computational TPP analyses. Leveraging insights from these models enables better control over nanofluid TPPs in solar systems, enhancing energy conversion efficiency. • MXene/graphene-based nanofluids, applicable in photovoltaic/thermal solar systems, are investigated. • The optimized Bayesian-based MLPNN models are developed for predicting the viscosity of the nanofluids. • Effects of Bayesian acquisition functions on the performance of optimized models are analyzed. • Models offer a potent and cost-effective alternative to experimental analyses.
81
Multilayer feedforward networks are universal approximators
Kurt Hornik, Maxwell B. Stinchcombe, Halbert White · Neural Networks · 1989 · 21.2K citations
Approximation capabilities of multilayer feedforward networks
Kurt Hornik · Neural Networks · 1991 · 6.1K citations
Graphene-Based Antibacterial Paper
Wenbing Hu, Cheng Peng, Weijie Luo et al. · ACS Nano · 2010 · 2K citations
Natural Sciences, Materials Engineering, Materials Science +17