Experimental Investigation and Artificial Neural Network-Based Prediction of Thermal Conductivity of Metal Oxide-Enhanced Organic Phase-Change Materials

International Journal of Energy Research, Journal Year: 2024, Volume and Issue: 2024, P. 1 - 18

Published: Feb. 14, 2024

This research article presents a comprehensive study on the prediction of thermal conductivity (TC) as primary outcome for an artificial neural network (ANN) model in context nanoenhanced phase change materials (NEPCMs). To improve predictive accuracy and to reduce variation within NEPCM dataset, targeted dataset was employed, consisting exclusively NEPCMs synthesized using paraffin wax (PW) metal oxide nanoparticles. Unlike existing empirical models that predict TC without simultaneously considering multiple factors influencing it, this integrates factors, providing more accurate conductivity. Additionally, explores impact synthesis parameters performance NEPCMs, focusing examination such melting temperature pure material (PCM), nanoparticle size, composition. The characterizations demonstrate outstanding thermophysical properties particularly terms conductivity, enthalpy, stability compared their respective base PCM. An ANN demonstrates exceptional correlation (>99%) with reported reliable tool forecasting similar categories. backpropagation predicts mean squared error (MSE) 0.031124 eight epochs. used exhibits high fit values, $R$ -values 0.99825, 0.99208, 0.9824 training, validation, testing, respectively. These values closely match experimentally determined TC, less than 4% error.

Language: Английский

---

A data-driven model for a liquid desiccant regenerator equipped with an evacuated tube solar collector: Random forest regression, support vector regression and artificial neural network

Energy, Journal Year: 2024, Volume and Issue: 295, P. 130932 - 130932

Published: March 9, 2024

Language: Английский

---

An optimal solutions-guided deep reinforcement learning approach for online energy storage control

Applied Energy, Journal Year: 2024, Volume and Issue: 361, P. 122915 - 122915

Published: March 7, 2024

Language: Английский

---

Suppressing solar PV output fluctuations by designing an efficient hybrid energy storage system controller

Unconventional Resources, Journal Year: 2024, Volume and Issue: 4, P. 100077 - 100077

Published: Jan. 1, 2024

The stochastic nature of solar photovoltaics (PV), marked by high-frequency voltage fluctuations due to dynamic climatic conditions such as cloud cover and temperature variations, presents a significant challenge power quality stability, especially in microgrids. This variability poses threat the stability electronic devices responsible for control monitoring, potentially compromising grid's stability. To address this challenge, energy storage systems (ESS) are commonly employed. In study, we develop hybrid system (HESS) incorporating battery, supercapacitor, fuel cell. primary aim is adjust inverter photovoltaic using newly developed proportional-integral (PI) model predictive (MPC) controllers within HESS framework. Importantly, controller eliminates need precise knowledge parameters offers robustness, insensitivity parameter changes, resilience time-varying external disturbances, ensuring satisfactory performance. By mitigating fluctuations, generated can be seamlessly integrated into grid, significantly reducing costs associated with device damage path. Notably, integrate proposed an RLC series load IGBT inverter. assess performance system, four distinct scenarios examined. These involve altering PV system's location testing two systems, namely battery cell, which separately designed components 14-bus microgrid.

Language: Английский

---

An improved microgrid energy management system based on hybrid energy storage system using ANN NARMA-L2 controller

Journal of Energy Storage, Journal Year: 2024, Volume and Issue: 98, P. 113096 - 113096

Published: July 31, 2024

Language: Английский

---