Influence of artificial roughness parametric variation on thermal performance of solar thermal collector: An experimental study, response surface analysis and ANN modelling

Kumar, Raj; Nadda, Rahul; Kumar, Sushil; Kaladgi, Abdul Razak; Sharifpur, Mohsen; Aybar, Hikmet Ş.; Saleel, C. Ahamed; Afzal, Asif

doi:10.1016/j.seta.2022.102047

Cited by 17 publications

(9 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An ANN model consists of three layers: the input layer, hidden layer, and output layer . The hidden layer acts as a bridge between the input layer and the output layer, and its bias and weights are adjusted until the difference between the experimental and predicted values is minimized, resulting in a minimal error …”

Section: Methodsmentioning

confidence: 99%

“…31 The hidden layer acts as a bridge between the input layer and the output layer, and its bias and weights are adjusted until the difference between the experimental and predicted values is minimized, resulting in a minimal error. 32 The activation function plays a key role in determining the output of the ANN model. It provides input to the model, sets the threshold value, and shows the weights associated with the input.…”

Section: Scanning Electron Microscopy (Sem)mentioning

confidence: 99%

See 1 more Smart Citation

Glass Fiber-Epoxy Composites with Carbon Nanotube Fillers for Enhancing Properties in Structure Modeling and Analysis Using Artificial Intelligence Technique

Vaddar,

Thatti,

Reddy

et al. 2023

ACS Omega

Self Cite

View full text Add to dashboard Cite

Hybrid composite materials are a form of material that incorporates more than one type of reinforcement into a matrix to attain enhanced qualities. This usually includes the use of nanoparticle fillers in classic advanced composites with fiber reinforcements such as carbon or glass. In the current investigation, the impact of carbon nanopowder filler on the wear and thermal performance of the chopped strand mat E-glass fiber-reinforced epoxy composite (GFREC) were analyzed. Multiwall carbon nanotube (MWCNT) fillers were used; they react with the resin system to contribute a significant improvement of properties in the polymer cross-linking web. The experiments were carried out employing the central composite method of design of experiment (DOE). A polynomial mathematical model was created using response surface methodology (RSM). To forecast the wear rate of composites, four machine learning (ML) regression models were built. The study’s findings indicate that the addition of carbon nanopowder has a substantial impact on the wear behavior of composites. This is mostly owing to the homogeneity created by the carbon nanofillers in uniformly dispersing the reinforcements in the matrix phase. Results revealed that a load of 1.005 kg, a sliding velocity of 1.499 m/s, a sliding distance of 150 m, and 15 wt % of filler were found to be the optimal parameters for the efficient reduction of specific wear rate. Composites with 10 and 20% carbon contents exhibit lower thermal expansion coefficients than plain composites. These composites’ coefficients of thermal expansion fell by 45 and 9%, respectively. If the carbon proportion increases beyond 20%, so will the thermal coefficient of expansion.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Scanning Electron Microscopy (Sem)mentioning

confidence: 99%

Glass Fiber-Epoxy Composites with Carbon Nanotube Fillers for Enhancing Properties in Structure Modeling and Analysis Using Artificial Intelligence Technique

Vaddar,

Thatti,

Reddy

et al. 2023

ACS Omega

Self Cite

View full text Add to dashboard Cite

show abstract

“…e network's neurons calculate a weighted sum w i x i of their input signal y i , for i � 0, 1, 2, ..., n hidden layer, and then use that information to create an output signal. Below is a definition of this function [24]:…”

Section: Artificial Neural Network (Ann)mentioning

confidence: 99%

“…Furthermore, only a small number of studies have discussed how machine learning (ML) approaches might be used to forecast and improve performance [22,23]. However, studies indicate that ML has a great deal of promise for removing bioenergy growth roadblocks [24,25]. Also, the study of hybrid biodiesel usage in CI engines is also limited.…”

Section: Introductionmentioning

confidence: 99%

Experimental Investigation and Prediction of Performance, Combustion, and Emission Features of a Diesel Engine Fuelled with Pumpkin-Maize Biodiesel using Different Machine Learning Algorithms

Magesh¹,

Pushparaj²,

Thakur

et al. 2022

Mathematical Problems in Engineering

Self Cite

View full text Add to dashboard Cite

The current study examines the usage of biodiesel as a diesel substitute that is produced through the transesterification of pumpkin and maize with the addition of a diethyl ether (DEE) additive. Pumpkin-maize (PM) biodiesel and addition of diethyl ether (DEE), as well as their blends of 10%, 20%, 30%, 40%, and 50% with diesel, were used in performance, combustion, and emission examinations under various load conditions. According to the experimental findings, adding 5 ml of the DEE boosts BTE by 31.91 percent (B20 blend) compared to diesel. While the diesel equivalent of BSFC decreases by 9.519%. NO emission dropped by 34.91 percent at peak loads, HC emissions were augmented by 32.43%, and smoke opacity improved by 27.24%. To enhance the engine performance, combustion, and emission features of the substitute biodiesel diesel, the study emphasises the precise mix proportions of PM biodiesel with DEE addition. Using ANN, BTE, and NO were predicted with R2 values of 0.93 and 0.95, respectively. As can be observed, the R2 value for the ANN model was almost one, suggesting that the ANN models had better predictive power than other machine learning (ML) models.

show abstract

“…In addition, electrochemical impedance spectroscopy (EIS) and variable light intensity tests were carried out to investigate the influence of the Al doping ratio on AZO/CsPbBr 3 interface defects. The simulation data and Al-doped ZnO sol prepared by this simple method are expected to be further studied and applied to other photovoltaic devices, such as solar stills, solar air heaters with a double pass (SAHD), hybrid PV/T solar thermal systems, solar thermal collectors (STCs), etc.…”

Section: Introductionmentioning

confidence: 99%

Improved Open-Circuit Voltage of AZO/CsPbBr₃/Carbon Structure Perovskite Solar Cells by an Al-Doped ZnO Electron Transport Layer

Bai

et al. 2023

J. Phys. Chem. C

View full text Add to dashboard Cite

The ZnO/CsPbBr3 heterojunction interface often has poor chemical stability, resulting in the low photovoltaic efficiency of the solar cell. Here, we reported a method to fabricate an electron transport layer (ETL) using an Al element-doped ZnO (AZO) sol to improve the interfacial defects of the ZnO/CsPbBr3 heterojunction. The results showed that the interfacial defects first decreased and then increased with the change of the Al element ratio from 0 to 10%. The device had the least interfacial defects by 7% (atomic ratio) Al doping into ZnO. A 1.27 V open-circuit voltage (V OC) and 6.25% photoelectric conversion efficiency (PCE) were achieved by 7% Al element doping into ZnO in a ZnO/CsPbBr3/carbon structure solar cell. Moreover, the interfacial defect distribution and carrier recombination mechanism of the device were, respectively, illustrated by a varying light intensity test and electrochemical impedance spectroscopy. This work showed that an Al-doped ZnO film prepared by a sol–gel method could significantly improve the performance of solar cells.

show abstract

Influence of artificial roughness parametric variation on thermal performance of solar thermal collector: An experimental study, response surface analysis and ANN modelling

Cited by 17 publications

References 70 publications

Glass Fiber-Epoxy Composites with Carbon Nanotube Fillers for Enhancing Properties in Structure Modeling and Analysis Using Artificial Intelligence Technique

Glass Fiber-Epoxy Composites with Carbon Nanotube Fillers for Enhancing Properties in Structure Modeling and Analysis Using Artificial Intelligence Technique

Experimental Investigation and Prediction of Performance, Combustion, and Emission Features of a Diesel Engine Fuelled with Pumpkin-Maize Biodiesel using Different Machine Learning Algorithms

Improved Open-Circuit Voltage of AZO/CsPbBr₃/Carbon Structure Perovskite Solar Cells by an Al-Doped ZnO Electron Transport Layer

Contact Info

Product

Resources

About

Influence of artificial roughness parametric variation on thermal performance of solar thermal collector: An experimental study, response surface analysis and ANN modelling

Cited by 17 publications

References 70 publications

Glass Fiber-Epoxy Composites with Carbon Nanotube Fillers for Enhancing Properties in Structure Modeling and Analysis Using Artificial Intelligence Technique

Glass Fiber-Epoxy Composites with Carbon Nanotube Fillers for Enhancing Properties in Structure Modeling and Analysis Using Artificial Intelligence Technique

Experimental Investigation and Prediction of Performance, Combustion, and Emission Features of a Diesel Engine Fuelled with Pumpkin-Maize Biodiesel using Different Machine Learning Algorithms

Improved Open-Circuit Voltage of AZO/CsPbBr3/Carbon Structure Perovskite Solar Cells by an Al-Doped ZnO Electron Transport Layer

Contact Info

Product

Resources

About

Improved Open-Circuit Voltage of AZO/CsPbBr₃/Carbon Structure Perovskite Solar Cells by an Al-Doped ZnO Electron Transport Layer