Defined an Optimized Molding for Physical and Mechanical Properties of W-Cu Nanocomposite Through Spark Plasma Sintering Using Gene Expression Programming: The Combination of Artificial Intelligence and Material Science

Created by W.Langdon from gp-bibliography.bib Revision:1.7615

@Article{journals/sncs/ShojaeiK22,

• author = "Mohammdreza Shojaei and Gholam Reza Khayati",
• title = "Defined an Optimized Molding for Physical and Mechanical Properties of {W-Cu} Nanocomposite Through Spark Plasma Sintering Using Gene Expression Programming: The Combination of Artificial Intelligence and Material Science",
• journal = "SN Computer Science",
• year = "2022",
• volume = "3",
• number = "1",
• pages = "Article 37",
• keywords = "genetic algorithms, genetic programming, gene expression programming, cu-w nanocomposite, tungstan copper, spark plasma sintering, powder metallurgy, modeling",
• ISSN = "2661-8907",
• bibdate = "2021-11-08",
• bibsource = "DBLP, http://dblp.uni-trier.de/db/journals/sncs/sncs3.html#ShojaeiK22",
• DOI = "doi:10.1007/s42979-021-00901-4",
• abstract = "Cu-W nanocomposites had many engineering applications due to the unique characteristics including hardness, transverse rupture strength, electrical conductivity, thermal conductivity, and relative density. This study was an attempt to used gene expression programming as a powerful soft computing technique to model the parameters for the synthesis of Copper-Tungsten nanocomposite prepared by spark plasma sintering. First, 97 different reliable experiments were carried out considering the type of Cu and W concentration, temperature, die pressure, and heat rate as input variables. The hardness, transverse rupture modules, electrical conductivity, thermal conductivity, and relative density of nanocomposite defined as output variable separately. An absolute fraction of variance (R2), mean absolute percentage error (MAPE), root relative squared error (RRSE), and mean squared error (MSE) were considered to validate the most appropriate GEP models. Sixfold cross validation was used through testing and training steps of GEP modeling. The results were divided randomly into 68 training sets and 29 testing sets. Finally, the best GEP models were selected for each output parameter. Sensitivity analyses are done to determine the rank of the practical parameters on each investigated properties and revealed that on hardness, transverse rupture modules, electrical conductivity, thermal conductivity, and relative density of nanocomposite, respectively. The results confirmed the ability of GEP for all parameters of Cu-W nanocomposites prepared by spark plasma sintering.",
• notes = "Department of Materials Science and Engineering, Sharif University of Technology, Tehran, Iran",

}

Genetic Programming entries for Mohammdreza Shojaei Gholam Reza Khayati

Citations