Application of machine learning and Box-Behnken design in optimizing engine characteristics operated with a dual-fuel mode of algal biodiesel and waste-derived biogas

Sharma, Prabhakar; Sahoo, Bibhuti Bhusan; Said, Zafar; Hadiyanto, Hadiyanto; Nguyen, Xuan Phuong; Nižetić, Sandro; Huang, Zuohua; Hoang, Anh Tuan; Li, Changhe

doi:10.1016/j.ijhydene.2022.04.152

Cited by 65 publications

(20 citation statements)

References 86 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, there is no proven approach for estimating the number or sizes of hidden layers. , The number of hidden layers can be modified depending on the scale of the problem, the quality, and the quantity of data. As a result, neurons are regularly adjusted depending on iterations during the training to achieve the optimal amount. , The construction of a predictive MLP-ANN model necessitates the establishment of a training stage. When multiple input and output groups are supplied to build a network, the prediction process regulates weight and bias values.…”

Section: Most Relevant Machine Learning Techniquesmentioning

confidence: 99%

“…As a result, neurons are regularly adjusted depending on iterations during the training to achieve the optimal amount. 84,85 The construction of a predictive MLP-ANN model necessitates the establishment of a training stage. When multiple input and output groups are supplied to build a network, the prediction process regulates weight and bias values.…”

Section: Most Relevant Machine Learning Techniquesmentioning

confidence: 99%

See 1 more Smart Citation

Recent Advances in Machine Learning Research for Nanofluid-Based Heat Transfer in Renewable Energy System

Sharma¹,

Said

Kumar³

et al. 2022

Energy Fuels

Self Cite

208

View full text Add to dashboard Cite

Nanofluids have gained significant popularity in the field of sustainable and renewable energy systems. The heat transfer capacity of the working fluid has a huge impact on the efficiency of the renewable energy system. The addition of a small amount of high thermal conductivity solid nanoparticles to a base fluid improves heat transfer. Even though a large amount of research data is available in the literature, some results are contradictory. Many influencing factors, as well as nonlinearity and refutations, make nanofluid research highly challenging and obstruct its potentially valuable uses. On the other hand, data-driven machine learning techniques would be very useful in nanofluid research for forecasting thermophysical features and heat transfer rate, identifying the most influential factors, and assessing the efficiencies of different renewable energy systems. The primary aim of this review study is to look at the features and applications of different machine learning techniques employed in the nanofluid-based renewable energy system, as well as to reveal new developments in machine learning research. A variety of modern machine learning algorithms for nanofluid-based heat transfer studies in renewable and sustainable energy systems are examined, along with their advantages and disadvantages. Artificial neural networks-based model prediction using contemporary commercial software is simple to develop and the most popular. The prognostic capacity may be further improved by combining a marine predator algorithm, genetic algorithm, swarm intelligence optimization, and other intelligent optimization approaches. In addition to the well-known neural networks and fuzzy- and gene-based machine learning techniques, newer ensemble machine learning techniques such as Boosted regression techniques, K-means, K-nearest neighbor (KNN), CatBoost, and XGBoost are gaining popularity due to their improved architectures and adaptabilities to diverse data types. The regularly used neural networks and fuzzy-based algorithms are mostly black-box methods, with the user having little or no understanding of how they function. This is the reason for concern, and ethical artificial intelligence is required.

show abstract

Section: Most Relevant Machine Learning Techniquesmentioning

confidence: 99%

Section: Most Relevant Machine Learning Techniquesmentioning

confidence: 99%

Recent Advances in Machine Learning Research for Nanofluid-Based Heat Transfer in Renewable Energy System

Sharma¹,

Said

Kumar³

et al. 2022

Energy Fuels

Self Cite

208

View full text Add to dashboard Cite

show abstract

“…Since an isothermal condition is assumed in this work, and the pressure difference is quite small, the gas–liquid interfacial tension is believed to be constant and thus not considered. Based on the Box–Behnken design, − a response surface analysis with four factors and three levels is performed. The influences of pressure difference, drilling mud density, drilling mud viscosity, and fracture width on the leakage rate and gas invasion rate are quantified.…”

Section: Influences Of Engineering and Geological Parameters On Gas–l...mentioning

confidence: 99%

Numerical Simulation of Gas–Liquid Gravity Displacement in Vertical Fractures during Drilling of Carbonate Formations

Peng

Deng

et al. 2023

ACS Omega

View full text Add to dashboard Cite

In petroleum drilling, carbonate formations characterized by natural fractures can result in troublesome gas–liquid gravity displacement, which refers to the phenomenon that the drilling mud leakage and gas kick are simultaneously triggered. This work focuses on clarifying the mechanism of gas–liquid displacement in vertical fractures during the drilling of carbonate formations and investigating the characteristics of gas–liquid displacement under various conditions. First, the bottom hole pressure allowing for gas–liquid gravity displacement is analyzed, which determines the coexistence condition of leakage and kick in vertical fractures. Then, a theoretical model of gas–liquid displacement flow in a vertical fracture is established. To verify the reliability and accuracy of the model, the results of numerical simulation are compared with those of a visualization experiment. The development process and flow characteristics of gas–liquid displacement in the fracture under different conditions are numerically simulated. The effects of pressure difference, drilling mud property, and fracture geometry on the gas–liquid displacement rate are analyzed. It is found that the drilling mud leakage rate increases with the increase of fracture width, fracture height, and drilling mud density, while it decreases with the increase of pressure difference and fracture length. The gas invasion rate increases with the increase of fracture width, fracture height, and pressure difference, while it decreases with the increase of drilling mud density and fracture length. The equations for leakage rate and gas invasion rate are derived by the response surface method, and the methods for mitigating gas–liquid gravity displacement are discussed. It is expected that the present work provides a better understanding of the gas–liquid gravity displacement in carbonate formations.

show abstract

“…Short time period, a smaller number of experiments, and the identification of parameters that largely affect the output are the key features of RSM which makes it a more acceptable statistical approach. [12] Design of experiments (DOE) is a methodical and organized strategy for planning,execution and evaluation of experiments aimed at optimizing processes. [13] The fundamental objective is to systematically and efficiently investigate the variables that influence a process, ultimately speculating the best condition to achieve desired results.…”

Section: Introductionmentioning

confidence: 99%

Process Optimization Using Box‐Behnken Design for the Solvent Extraction and Separation of Iron, Cobalt, and Nickel from Simulated Crud Solution

Panda,

Mishra

2024

ChemistrySelect

View full text Add to dashboard Cite

The corrosion product deposit (crud) found on the surface of the fuel rod of the pressurized water reactors (PWRs) chiefly made up of nickel ferrite. Fe, Co, Ni and Cr are the major elements exist in PWR crud. Ascribable to the simplicity in execution, handling, and option for recyclability, solvent extraction technique has been broadly used in nuclear energy sector. In the present investigation, the recovery of iron, cobalt, and nickel has been studied from simulated crud solution in nitrate medium using a novel hydrophobic menthol‐decanoic acid‐based deep eutectic solvent. Process parameters such as pH, DES concentration and shaking time were considered as input variables, and concentration of Fe, Co, and Ni as response variables for the design of experiments. Response surface methodology via Box‐Behnken design using polynomial quadratic model was selected for optimization of solvent extraction experiments. A total of 17 runs were conducted and the results were used for optimization purpose. Complete separation of Co/Fe and Co/Ni is achievable under various extraction conditions. As per the BBD analysis, the optimization conditions obtained were pH=1.9, [DES]=2.99 mol/L and shaking duration=18.27 min. Under these conditions,the amount of Fe, Co and Ni extracted were found as 32.29 g/L, 0.2111 g/L, and 19.83 g/L, respectively.

show abstract

Application of machine learning and Box-Behnken design in optimizing engine characteristics operated with a dual-fuel mode of algal biodiesel and waste-derived biogas

Cited by 65 publications

References 86 publications

Recent Advances in Machine Learning Research for Nanofluid-Based Heat Transfer in Renewable Energy System

Recent Advances in Machine Learning Research for Nanofluid-Based Heat Transfer in Renewable Energy System

Numerical Simulation of Gas–Liquid Gravity Displacement in Vertical Fractures during Drilling of Carbonate Formations

Process Optimization Using Box‐Behnken Design for the Solvent Extraction and Separation of Iron, Cobalt, and Nickel from Simulated Crud Solution

Contact Info

Product

Resources

About