Recent developments of carbon-based nanomaterials research have made it possible to use them for a wide range of environmental, material development, and energy-related applications. Graphene, CNT, quantum dots, nano-diamond, and graphene oxide are examples of carbon-based nanomaterials. The development of nanocomposites has drawn a lot of attention lately, with synthesis and application receiving. Recently, there has been a lot of interest in the synthesis of AI-created nanoparticles using artificial intelligence. This work focuses on the synthesis of carbon-based nanocomposites and application of current AI tools to better understand the properties of carbon derivative material, and this information can be applied to the development and application of materials for solution of society's problem. To explain the synthetic and derivation process, adaptive neuro-fuzzy inference systems and ANN may be efficient. Derivations of the nanomaterials are the output of the models, which have various inputs such as catalyst dosage, particle size, concentration, content, exposure time.
Top1. Introduction
Presently, there is a lot of effort in the field of nanocomposite materials, which could have a significant impact on our society. Nanomaterials can be categorized according to their dimensions. 0D materials, such as fullerenes, metallic nanoparticles, and quantum dots (QDs), have all dimensions below 100 nm. 1D materials, exemplified by carbon nanotubes (CNTs), possess two dimensions that are each less than 100 nm. In contrast, 2D materials, like graphene, exhibit nanoscale characteristics in only one dimension. Finally, 3D materials, like dendrimers, lack restrictions to the nano-scale in any dimension. The application of nanofillers to polymers to impart particular and apparent property improvements is still showing significant advancements among the remarkably wide range of expanding research areas (Díez-Pascual, 2022b; Pokropivny & Skorokhod, 2007; Sahoo et al., 2010). Composite materials that are attached with graphene and carbon nanotubes are considered to be promising. Graphene oxide (GO) or graphene (G), carbon nanotubes (SWCNTs and MWCNTs), carbon nanoparticles (CNPs), and carbon nanotubes (SWCNTs) have drawn significant attention due to their distinct structural regularity, chemical inertness, electrical conductivity, mechanical stability, high surface area and thermal stability. Due to their tiny size and physicochemical properties influenced by shape, carbon nanocomposites have garnered significant attention in the catalysis domain. Specifically, carbon-based nanocomposites, incorporating metal nanostructures and carbon materials (predominantly graphene and carbon nanotubes), have demonstrated exceptional catalytic activity in organic reactions.
A wide range of industries, including the material sciences, agricultural, biomedical and pharmaceutical have discovered the great value of the catalytic products made with carbon nanocomposites. Many Various nanoparticles have been reported to support graphene or carbon nanotube (CNT) catalysts for a range of organic transformations. The pharmacological, biological, agricultural, and material sciences are just a few of the industries that find great value in catalytic products (Beletskaya & Cheprakov, 2000). While modelling approaches such as linear correlativity and multilinear regression models are widely employed to describe the adsorption process, their applicability and accuracy are limited. Conversely, machine learning methods driven by data provide a valuable tool for delving into the intricate relationship between biochar properties and adsorption capacities (Beletskaya & Cheprakov, 2000).
Machine learning can be used to classify, forecast, optimize, and cluster methods. A model of Artificial Intelligence (AI) is developed to find out the Young's modulus, or the behaviour, of composites made of polymers and carbon nanotubes (CNTs). It is suggested that artificial intelligence (AI) be used to get over challenges encountered when researching the characteristics of innovative composite materials, such as the resource- and time-consuming aspect of other numerical approaches' experimental studies (Beletskaya & Cheprakov, 2000). The polymer dielectric constant and energy bandgap are predicted using Convolutional Neural Networks, when it comes to mechanical performance. A neural network is also used to predict the mechanical characteristics of pure propylene PP and its blends (Beletskaya & Cheprakov, 2000)(Kufel & Kuciel, 2019). AI and ML are excellent options for researching and creating cutting-edge materials using data that already exists, which helps to fulfil the primary goal of the MGI announcement. As demonstrated by the results in other research fields (such as image recognition, civil engineering, or geology) (Kumar et al., 2019; Nhat-Duc et al., 2018; Thanh Duong et al., 2020; Ward et al., 2018). The literature contains a number of research studies that use both analytical and numerical methods to determine the effective properties of CNT nanocomposites. Molecular dynamics, multiscale methods, and continuum mechanics are some examples of such approaches. The modified Halpin-Tsai equations applied to find out the effective properties of carbon nanotube (CNT) nanocomposites. The equation utilized into consideration parameters like the length, diameter, and strength of the CNTs (Le, 2020; Le & Le, 2021; Papon et al., 2011).