Machine learning and multilayer perceptron enhanced CFD approach for improving design on latent heat storage tank

Li, Yuanji; Huang, Xinyu; Huang, Xiaoyong; Gao, Xinyu; Hu, Rukun; Xiao, Tian

doi:10.1016/j.apenergy.2023.121458

Cited by 42 publications

(4 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The MLP, a widely utilized feed-forward backpropagation artificial neural network, comprises an input layer, at least one hidden layer, and an output layer. In each layer, the fundamental unit is referred to as a neuron, encompassing a summation unit and a non-linear activation function denoted as φ(x) [28,29]. The architecture of the developed model is shown in Figure 4.…”

Section: Machine Learning Modelmentioning

confidence: 99%

See 1 more Smart Citation

Machine learning predictions and optimization for thermal energy storage in cylindrical encapsulated phase change material

İzgi

2024

International Journal of Energy Studies

View full text Add to dashboard Cite

Accurate prediction of melting time is crucial in designing Thermal Energy Storage (TES) systems based on cylindrically encapsulated Phase Change Materials (PCMs). The melting time of a cylindrical encapsulated PCM directly correlates with the energy stored in the system. This study introduces a precise prediction model for the total melting time of cylindrically encapsulated PCM, utilizing a machine learning algorithm. The model, developed with the Multilayer Perceptron (MLP) method, demonstrated superior performance compared to the correlation equation proposed in the literature. The Mean Absolute Percentage Error (MAPE) value for the correlation equation was 16.68%, while the MLP model achieved a significantly lower MAPE of 4.07%, indicating its success in capturing the intricate relationship between input parameters and melting time. Furthermore, optimization results using the Non-dominated Sorting Genetic Algorithm II (NSGA-II) underscore the importance of striking a balance between stored energy and power during the design process. Maximizing stored energy (81.78 kJ) minimizes power (12.69 W), and vice versa, maximizing power (73.38 W) minimizes stored energy (37.10 kJ). In the case of equal weighting for stored energy and power in the design (56.05 kJ and 38.89 W, respectively), a 31.5% decrease in energy and a 206.5% increase in power were observed compared to the scenario where energy is maximized. Additionally, a 44% decrease in power and a 51.1% increase in energy were noted compared to the case where power is maximized. These findings collectively highlight the robustness and effectiveness of the developed MLP model in accurately predicting melting time and providing optimal solutions for energy storage parameters.

show abstract

Section: Machine Learning Modelmentioning

confidence: 99%

“…The architecture of the developed model is shown in Figure 4. is passed through a non-linear activation function [28,29].…”

Section: Machine Learning Modelmentioning

confidence: 99%

Machine learning predictions and optimization for thermal energy storage in cylindrical encapsulated phase change material

İzgi

2024

International Journal of Energy Studies

View full text Add to dashboard Cite

show abstract

“…Since the Industrial Revolution, the high-carbon industrial modus operandi, characterized by significant natural resource consumption and vast greenhouse gas emissions, has escalated numerous environmental issues [1][2][3][4]. Climate change, environmental pollution, and energy security have emerged as global challenges, posing severe threats to human survival and development [5,6].…”

Section: Introductionmentioning

confidence: 99%

Carbon Emission Prediction and the Reduction Pathway in Industrial Parks: A Scenario Analysis Based on the Integration of the LEAP Model with LMDI Decomposition

Feng,

Xu,

Gao

et al. 2023

Energies

Self Cite

View full text Add to dashboard Cite

Global climate change imposes significant challenges on the ecological environment and human sustainability. Industrial parks, in line with the national climate change mitigation strategy, are key targets for low-carbon revolution within the industrial sector. To predict the carbon emission of industrial parks and formulate the strategic path of emission reduction, this paper amalgamates the benefits of the “top-down” and “bottom-up” prediction methodologies, incorporating the logarithmic mean divisia index (LMDI) decomposition method and long-range energy alternatives planning (LEAP) model, and integrates the Tapio decoupling theory to predict the carbon emissions of an industrial park cluster of an economic development zone in Yancheng from 2020 to 2035 under baseline (BAS) and low-carbon scenarios (LC1, LC2, and LC3). The findings suggest that, in comparison to the BAS scenario, the carbon emissions in the LC1, LC2, and LC3 scenarios decreased by 30.4%, 38.4%, and 46.2%, respectively, with LC3 being the most suitable pathway for the park’s development. Finally, the paper explores carbon emission sources, and analyzes emission reduction potential and optimization measures of the energy structure, thus providing a reference for the formulation of emission reduction strategies for industrial parks.

show abstract

“…To address this issue, scholars have proposed various enhancements of phase-change heat storage structures. These improvements include the addition of fins [20][21][22], metallic foams [23][24][25], heat pipes [26][27][28], and nanofluids [29][30][31] to PCMs to accelerate the charging-discharging course. Li et al [32] carried out a numerical study on the heat storage effect of PCM at different metallic foam filling rates, revealing that the shortest complete melting time was reached at a filling rate of 95%.…”

Section: Introductionmentioning

confidence: 99%

Thermo-Economic Performance Analysis of Modified Latent Heat Storage System for Residential Heating

Gao,

Li,

et al. 2023

Energies

Self Cite

View full text Add to dashboard Cite

Solar energy is a sustainable source that can be effectively utilized to address winter heating challenges in buildings. To ensure the efficient application of solar energy for heating purposes and to maintain reliable performance of the heating system, the integration of phase-change materials (PCMs) in thermal energy storage (TES) systems has emerged as a crucial auxiliary approach. This study focuses on the design and simulation of four TES structures: smooth, finned, metallic foam, and metallic foam-finned tubes. It explores their thermal characteristics, such as complete melting time and heat flux, under various flow conditions. Additionally, a residential building in Xi’an is selected as the object, where the proposed solar energy phase-change TES system is employed to meet the heating demand. Economic indicators, including initial investment and investment payback period, are estimated using a static evaluation method. The results highlight that the complete melting time of the TES unit with a metallic foam-finned tube is 4800 s, which is 88.3% less than the smooth tube. Finally, based on the actual project, it is determined that the metallic foam-finned heating system, with an HTF flow rate of 0.25 m/s, requires the fewest TES devices (914) and has a payback period of 13 months.

show abstract

Machine learning and multilayer perceptron enhanced CFD approach for improving design on latent heat storage tank

Cited by 42 publications

References 47 publications

Machine learning predictions and optimization for thermal energy storage in cylindrical encapsulated phase change material

Machine learning predictions and optimization for thermal energy storage in cylindrical encapsulated phase change material

Carbon Emission Prediction and the Reduction Pathway in Industrial Parks: A Scenario Analysis Based on the Integration of the LEAP Model with LMDI Decomposition

Thermo-Economic Performance Analysis of Modified Latent Heat Storage System for Residential Heating

Contact Info

Product

Resources

About