Patrick Ehi Imoisili , Mamookho Elizabeth Makhatha , Tien-Chien Jen
{"title":"Artificial Intelligence prediction and optimization of the mechanical strength of modified Natural Fibre/MWCNT polymer nanocomposite","authors":"Patrick Ehi Imoisili , Mamookho Elizabeth Makhatha , Tien-Chien Jen","doi":"10.1016/j.jsamd.2024.100705","DOIUrl":null,"url":null,"abstract":"<div><p>Artificial Intelligence (AI), techniques like artificial neural networks (ANN), and machine learning have been used to solve a variety of engineering problems. In this study, Multiwall Carbon Nanotube (MWCNT) and Natural Fibres (NF) from plantain (<em>Musa Paradisiaca</em>) fiber (PF), were utilized to prepare a reinforced hybrid polymer nanocomposite for advanced composite applications. A chemical solution containing potassium permanganate (KMnO<sub>4</sub>) in acetone (C<sub>3</sub>H<sub>6</sub>O) was applied to modify the fibers to alter their surface and improve adhesion and interaction between the PF/polymer matrix. To predict and optimize the tensile strength (TS) of the prepared PF/MWCNT hybrid nanocomposite (PFMNC), the ANN model with hyper-parameter optimization in a single-layer-perceptron architecture of 3-5-1 was used with 5 neurons in the hidden layer, and Box-Behnken Design (BBD) was utilized. Scanning electron microscope (SEM) micrographs demonstrate that KMnO<sub>4</sub> modification has impacted the TS of the hybridized nanocomposite. Mechanical Test results show that these variables impacted the TS of the PFMNC as shown by analysis of variance (ANOVA) with R<sup>2</sup> = 0.9986. The expected findings were nearly identical to the experimental results. The model predicted an optimal tensile strength of 46.1563 Mpa. To substantiate the reliability of the empirical experimental investigation, TS analysis was performed at predicted optimal settings. TS results showed an average strength of 45.4401 Mpa. About 98.45 % of the projected tensile strength is accounted for by the model. The present study has demonstrated the effectiveness of the ANN-BBD modeling technique in achieving the appropriate mechanical property values quickly, reducing production costs, and preserving resources.</p></div>","PeriodicalId":17219,"journal":{"name":"Journal of Science: Advanced Materials and Devices","volume":null,"pages":null},"PeriodicalIF":6.7000,"publicationDate":"2024-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2468217924000364/pdfft?md5=e1d1656564b31966c62da19fab0039b8&pid=1-s2.0-S2468217924000364-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Science: Advanced Materials and Devices","FirstCategoryId":"88","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2468217924000364","RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MATERIALS SCIENCE, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0
Abstract
Artificial Intelligence (AI), techniques like artificial neural networks (ANN), and machine learning have been used to solve a variety of engineering problems. In this study, Multiwall Carbon Nanotube (MWCNT) and Natural Fibres (NF) from plantain (Musa Paradisiaca) fiber (PF), were utilized to prepare a reinforced hybrid polymer nanocomposite for advanced composite applications. A chemical solution containing potassium permanganate (KMnO4) in acetone (C3H6O) was applied to modify the fibers to alter their surface and improve adhesion and interaction between the PF/polymer matrix. To predict and optimize the tensile strength (TS) of the prepared PF/MWCNT hybrid nanocomposite (PFMNC), the ANN model with hyper-parameter optimization in a single-layer-perceptron architecture of 3-5-1 was used with 5 neurons in the hidden layer, and Box-Behnken Design (BBD) was utilized. Scanning electron microscope (SEM) micrographs demonstrate that KMnO4 modification has impacted the TS of the hybridized nanocomposite. Mechanical Test results show that these variables impacted the TS of the PFMNC as shown by analysis of variance (ANOVA) with R2 = 0.9986. The expected findings were nearly identical to the experimental results. The model predicted an optimal tensile strength of 46.1563 Mpa. To substantiate the reliability of the empirical experimental investigation, TS analysis was performed at predicted optimal settings. TS results showed an average strength of 45.4401 Mpa. About 98.45 % of the projected tensile strength is accounted for by the model. The present study has demonstrated the effectiveness of the ANN-BBD modeling technique in achieving the appropriate mechanical property values quickly, reducing production costs, and preserving resources.
期刊介绍:
In 1985, the Journal of Science was founded as a platform for publishing national and international research papers across various disciplines, including natural sciences, technology, social sciences, and humanities. Over the years, the journal has experienced remarkable growth in terms of quality, size, and scope. Today, it encompasses a diverse range of publications dedicated to academic research.
Considering the rapid expansion of materials science, we are pleased to introduce the Journal of Science: Advanced Materials and Devices. This new addition to our journal series offers researchers an exciting opportunity to publish their work on all aspects of materials science and technology within the esteemed Journal of Science.
With this development, we aim to revolutionize the way research in materials science is expressed and organized, further strengthening our commitment to promoting outstanding research across various scientific and technological fields.