Mechanical behaviour and microscopic analysis of epoxy and E-glass reinforced banyan fibre composites with the application of artificial neural network and deep neural network for the automatic prediction of orientation

2020 ◽  
Vol 55 (2) ◽  
pp. 213-234 ◽  
Author(s):  
Suraj Shyam ◽  
Shivam Kaul ◽  
Nirav Kalsara ◽  
T Narendiranath Babu
Keyword(s):  
Neural Network ◽  
Mechanical Behaviour ◽  
Deep Neural Networks ◽  
Microscopic Analysis ◽  
Natural Fibre ◽  
X Ray ◽  
Fibre Composites ◽  
The Matrix ◽  
Naoh Solution ◽  
Made In

This paper deals with the testing of tensile and flexural behaviour of epoxy-reinforced natural fibre composites, for which Banyan fibres have been selected as the natural fibre. Variations are made in the orientation of the fibres to determine which orientation made the composite the strongest. The fibre strands are arranged in different orientations, such as the uniaxial, biaxial and criss-cross arrangements, to differentiate between the orientations and observe which arrangement exhibited the best mechanical behaviour. The fibres are initially washed with 0.5% weight/volume (w/v) NaOH solution, following which specimens of the composites are made using wooden moulds designed according to ASTM standards. Biaxial layers of E-glass are incorporated into the matrix in an attempt to enhance the mechanical properties of the specimen. The variances observed in the Young’s modulus are analysed to understand the factors that majorly impacted it. For a better understanding of the results, the chemical functional groups and the microstructure of the samples are analysed with the aid of Fourier-Transform Infrared Spectroscopy (FTIR), Field Emission Scanning Electron Microscopy (FESEM) and X-Ray powder Diffraction (XRD). Additionally, predictive models are simulated using Artificial and Deep Neural Networks to recognise patterns in the data, by varying specific parameters. The results obtained indicated that Banyan fibre composites can replace conventionally-used materials and serve real-world purposes better.

Entropy estimation of the fragments of chest X-ray images

2021 ◽  
pp. 20-26
Author(s):  
Aleksei Aleksandrovich Rumyantsev ◽  
Farkhad Mansurovich Bikmuratov ◽  
Nikolai Pavlovich Pashin
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Binary Classification ◽  
Statistical Characteristics ◽  
Type I ◽  
Deep Convolutional Neural Networks ◽  
Preliminary Calculation ◽  
X Ray ◽  
The Matrix ◽  
Chest X Ray

The subject of this research is medical chest X-ray images. After fundamental pre-processing, the accumulated database of such images can be used for training deep convolutional neural networks that have become one of the most significant innovations in recent years. The trained network carries out preliminary binary classification of the incoming images and serve as an assistant to the radiotherapist. For this purpose, it is necessary to train the neural network to carefully minimize type I and type II errors. Possible approach towards improving the effectiveness of application of neural networks, by the criteria of reducing computational complexity and quality of image classification, is the auxiliary approaches: image pre-processing and preliminary calculation of entropy of the fragments. The article provides the algorithm for X-ray image pre-processing, its fragmentation, and calculation of the entropy of separate fragments. In the course of pre-processing, the region of lungs and spine is selected, which comprises approximately 30-40% of the entire image. Then the image is divided into the matrix of fragments, calculating the entropy of separate fragments in accordance with Shannon’s formula based pm the analysis of individual pixels. Determination of the rate of occurrence of each of the 255 colors allows calculating the total entropy. The use of entropy for detecting pathologies is based on the assumption that its values differ for separate fragments and overall picture of its distribution between the images with the norm and pathologies. The article analyzes the statistical values: standard deviation of error, dispersion. A fully connected neural network is used for determining the patterns in distribution of entropy and its statistical characteristics on various fragments of the chest X-ray image.

Identification of Thoracic Diseases by Exploiting Deep Neural Networks (Preprint)

2020 ◽  
Author(s):  
Albahli Saleh ◽  
Ali Alkhalifah
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Deep Neural Networks ◽  
Medical Image Analysis ◽  
Medical Community ◽  
Learning Models ◽  
X Ray ◽  
Chest Disease

BACKGROUND To diagnose cardiothoracic diseases, a chest x-ray (CXR) is examined by a radiologist. As more people get affected, doctors are becoming scarce especially in developing countries. However, with the advent of image processing tools, the task of diagnosing these cardiothoracic diseases has seen great progress. A lot of researchers have put in work to see how the problems associated with medical images can be mitigated by using neural networks. OBJECTIVE Previous works used state-of-the-art techniques and got effective results with one or two cardiothoracic diseases but could lead to misclassification. In our work, we adopted GANs to synthesize the chest radiograph (CXR) to augment the training set on multiple cardiothoracic diseases to efficiently diagnose the chest diseases in different classes as shown in Figure 1. In this regard, our major contributions are classifying various cardiothoracic diseases to detect a specific chest disease based on CXR, use the advantage of GANs to overcome the shortages of small training datasets, address the problem of imbalanced data; and implementing optimal deep neural network architecture with different hyper-parameters to improve the model with the best accuracy. METHODS For this research, we are not building a model from scratch due to computational restraints as they require very high-end computers. Rather, we use a Convolutional Neural Network (CNN) as a class of deep neural networks to propose a generative adversarial network (GAN) -based model to generate synthetic data for training the data as the amount of the data is limited. We will use pre-trained models which are models that were trained on a large benchmark dataset to solve a problem similar to the one we want to solve. For example, the ResNet-152 model we used was initially trained on the ImageNet dataset. RESULTS After successful training and validation of the models we developed, ResNet-152 with image augmentation proved to be the best model for the automatic detection of cardiothoracic disease. However, one of the main problems associated with radiographic deep learning projects and research is the scarcity and unavailability of enough datasets which is a key component of all deep learning models as they require a lot of data for training. This is the reason why some of our models had image augmentation to increase the number of images without duplication. As more data are collected in the field of chest radiology, the models could be retrained to improve the accuracies of the models as deep learning models improve with more data. CONCLUSIONS This research employs the advantages of computer vision and medical image analysis to develop an automated model that has the clinical potential for early detection of the disease. Using deep learning models, the research aims to evaluate the effectiveness and accuracy of different convolutional neural network models in the automatic diagnosis of cardiothoracic diseases from x-ray images compared to diagnosis by experts in the medical community.

Experimental study on drilling characteristics of the hybrid sisal–jute fibre epoxy composites

2021 ◽  
pp. 251659842110154
Author(s):  
Harpreet Singh ◽  
Bhishm Dewangan ◽  
P. K. Jain
Keyword(s):  
Surface Roughness ◽  
Research Work ◽  
Experimental Studies ◽  
Microscopic Analysis ◽  
Natural Fibre ◽  
Drilling Process ◽  
Twist Drill ◽  
Fibre Composites ◽  
Geometry Configuration ◽  
Machining Operations

Natural fibre composites have received worldwide attention due to their good mechanical properties, lightweight and low density. Due to these advantages, the natural fibre composites have been used in various engineering applications. Drilling is one of the most frequent machining operations performed on hybrid sisal–jute polymer composites, to assemble the numerous structural components by using mechanical joining process. Furthermore, the machining of fibre reinforced composite material has attracted several researchers because of its non-homogeneous and anisotropic structure. The present research work concerns with the experimental studies on the drilling process of hybrid sisal–jute epoxy composite, using three different types of drill geometry (twist drill, step drill and core drill). The significance of the current work aims to reveal the effect of drill geometry configuration and drilling parameters in terms of drilling-induced force and damages (delamination and surface roughness) for the drilling of hybrid natural fibre composites. Drilling forces, drilling-induced damages and hole quality attributes were experimentally investigated for different drill geometries. The delamination and surface roughness type damages are revealed by microscopic analysis with the help of scanning electron microscope (SEM). The results show that twist drill is best suited for the hole- and force-induced damages.

Tensile and flexural properties of Tampico fibres and E-glass fibre composites reinforced with epoxy resin

2021 ◽  
pp. 146442072110357
Author(s):  
T Narendiranath Babu ◽  
E Rajkumar ◽  
George George ◽  
Jefferson Jobai ◽  
D Rama Prabha
Keyword(s):  
Mechanical Properties ◽  
Fourier Transform ◽  
Infrared Spectroscopy ◽  
Bending Strength ◽  
Lattice Structure ◽  
Natural Fibre ◽  
Flexural Properties ◽  
X Ray Diffraction ◽  
X Ray ◽  
Fibre Composites

The focus of our study was to evaluate and compare the mechanical properties, namely tensile and bending strength of natural fibre composites. Natural fibre composites are composites consisting of fibres made from plants and animals. The natural fibre chosen for this study was Tampico fibre. The moulds were made according to ASTM D638 and D790 standards for both tensile and bending specimens. The first set of composites were arranged in three different orientations namely uniaxial, biaxial and criss-cross. The moulds were prepared using the hand-lay-up technique. These fibres were combined with Epoxy LY-556 pitch and Hardener HY-951 in a specific proportion to make the composite. The second set of composites included an additional variant in the form of biaxial E-glass fibres of 270GSM density, to compare the differences in the mechanical strength. The X-ray diffraction and Fourier-transform infrared spectroscopy were performed on the specimen to understand the lattice structure and prevalent bonds formed within the composites.

Mechanical properties of natural fibre polymer composites

2017 ◽  
Vol 37 (9) ◽  
pp. 879-895 ◽  
Author(s):  
Agnivesh Kumar Sinha ◽  
Harendra K. Narang ◽  
Somnath Bhattacharya
Keyword(s):  
Mechanical Properties ◽  
Interfacial Adhesion ◽  
Review Paper ◽  
Natural Fibre ◽  
Reinforced Composites ◽  
The Past ◽  
Fibre Composites ◽  
To Come ◽  
Fibre Reinforced Composites ◽  
Made In

Abstract Extensive efforts have been made in the last decade for the development of natural fibre composites. This development paved the way for engineers and researchers to come up with natural fibre composites (NFCs) that exhibit better mechanical properties. The present review is based on the mechanical properties of jute, abaca, coconut, kenaf, sisal, and bamboo fibre-reinforced composites. Before selecting any NFC for a particular application, it becomes necessary to understand its compatibility for the same, which can be decided by knowing its mechanical properties such as tensile, flexural, and impact strengths. This review paper emphasises on the factors influencing the mechanical properties of NFCs like the type of matrix and fibre, interfacial adhesion, and compatibility between matrix and fibre. Efforts are also made to unveil the research gaps from the past literatures, as a result of which it is inferred that there is very limited work published in the field of vibration incorporating potential fillers such as red mud and fly ash with NFCs.

Grading of Biofibres for Use in Natural Fibre Composites

2011 ◽  
Vol 410 ◽  
pp. 23-23
Author(s):  
A. Crosky ◽  
Mindy Loo ◽  
Mohd Zakaria ◽  
Paresh Parmar ◽  
Andrew Beehag ◽  
...  
Keyword(s):  
Mechanical Behaviour ◽  
Fibre Composite ◽  
Mass Density ◽  
Natural Fibre ◽  
Cross Sectional Area ◽  
Environmental Benefits ◽  
Natural Fibres ◽  
Sectional Area ◽  
Cross Sectional ◽  
Fibre Composites

Natural fibres obtained from plant sources are attractive as a replacement for glass fibres in fibre reinforced plastic composites because of their environmental benefits. However, unlike synthetic fibres, natural plant fibres show considerable variability in their mechanical properties due to the effects of climate, soil quality, time of harvest, etc. Variability in properties of the fibres translates into variability in the properties of products made from natural fibre composites and this is a major obstacle to the more widespread use of these materials. One way to accommodate fibre variability would be to test the mechanical behaviour of samples from incoming batches of fibres and assign a grade to each batch, which could then be taken into account when the fibres are subsequently used to produce composite products. However, conventional methods of determining mechanical behaviour require test samples of constant cross-sectional area but, unfortunately, this is not the case for natural fibres which vary in shape, width and lumen size, from place to place along the fibre. Insight as to how to deal with such variability is provided from the textiles industry where strength is determined as a function of linear mass density rather than cross-sectional area. This paper examines the feasibility of using a similar approach for grading natural fibres for use in natural fibre composite products.

scholarly journals The Effect of Jackfruit Skin Powder and Fiber Bleaching Treatment in PLA Composites with Incorporation of Thymol

Polymers ◽  
2020 ◽  
Vol 12 (11) ◽  
pp. 2622
Author(s):  
Muhammad Najib Ahmad Marzuki ◽  
Intan Syafinaz Mohamed Amin Tawakkal ◽  
Mohd Salahuddin Mohd Basri ◽  
Siti Hajar Othman ◽  
Siti Hasnah Kamarudin ◽  
...  
Keyword(s):  
Food Packaging ◽  
Fibre Composite ◽  
Low Cost ◽  
Thermal Characterization ◽  
Natural Fibre ◽  
Poly Lactic Acid ◽  
Tropical Fruit ◽  
Fibre Composites ◽  
The Matrix ◽  
Bleaching Treatment

Food packaging has seen a growth in the use of materials derived from renewable resources such as poly(lactic acid) (PLA). However, the initial costs to produce bioplastics are typically high. Tropical fruit waste as naturally sourced fibres, such as jackfruit skin, can be used as a cost-reducing filler for PLA. The main objective in this study is to fabricate a low-cost natural fibre-reinforced polymer that potentially applies in packaging with the aid of bleaching treatment. The treatment shows a rougher surface fibre in Scanning electron microscopy (SEM) micrographs and it is expected to have better mechanical locking with the matrix, and this is found similar with a Fourier-transform infrared spectroscopy (FTIR) analysis. Unfortunately, fibre insertion does find low tensile performances, yet bleached-fibre composites improved its performance significantly. A similar situation was found in the thermal characterization where a low-thermal stability natural fibre composite has lower thermal behaviour and this increased with bleaching treatment. Besides, bleached-fibre composites have a longer service period. Besides, a 15 wt% thymol insertion inhibits the growth of Gram-positive bacteria in the composites and the non-treated fibre composite has better thymol effects. The 30 wt% of the bleached-fibre insertion composite has a high potential to reduce the cost of bioplastic products with minimum alterations of overall performances.

scholarly journals Development of Wood-Ash/Resin Polymer Matrix Composite for Body Armour Application

2016 ◽  
Vol 1 (1) ◽  
Author(s):  
Olawale M Sanusi ◽  
Olufemi D Komolafe ◽  
Tunde D Ogundana ◽  
Mesach O Olaleke ◽  
Yunusa Y Sanni
Keyword(s):  
Matrix Composite ◽  
Polymer Matrix ◽  
Research Work ◽  
Microscopic Analysis ◽  
Wood Ash ◽  
Polymer Matrix Composite ◽  
X Ray ◽  
Body Armour ◽  
The Matrix ◽  
The Impact

This research work formulated and developed a polymer matrix composite (PMC) for body armour application by adopting hand lay-up processing method in producing the epoxy resin-wood ash composite. The usual waste from wood after combustion, wood ash, was used as the additive in the development of the PMC. Chemical composition of the prepared wood ash was determined using X-ray florescence spectrometry. The mechanical properties of the developed PMC was evaluated and discovered to have been enhanced through the inclusion of the wood ash particles. 2.3% inclusion of wood ash resulted in the tensile strength value of 104 N/mm2against 86 N/mm2 for neat reinforced resin. The impact strength of the PMC increased from 50 J/mm2 (without wood ash) to 112 J/mm2 while 25.4 HRF was recorded for the hardness value of the PMC with wood ash against 23.4 HRF for the neat reinforced PMC. The microscopic analysis also revealed that the wood ash particles were uniformly distributed in the matrix without indication of segregation. When subjected to ballistic tests, the developed PMC successfully arrested the 9 x 19 mm ammunitions after perforating some layers of the sandwiched sample. The research is therefore applicable for the protection of torso.

Mechanical Characterization of Polypropylene Natural Fibre Composites

2011 ◽  
Vol 383-390 ◽  
pp. 2737-2740 ◽  
Author(s):  
Sd Jacob Muthu ◽  
Ratnam Paskaramoorthy
Keyword(s):  
Mechanical Properties ◽  
Mechanical Characterization ◽  
Fibre Surface ◽  
Alkaline Treatment ◽  
Natural Fibre ◽  
Fibre Composites ◽  
The Matrix ◽  
Pp Composites ◽  
Fibre Loading

Using polypropylene (PP) as matrix and kenaf mat as reinforcement, composite test samples were fabricated by compression molding. Thereafter, the effect of fibre loading and the alkaline fibre surface treatment on the mechanical properties were studied. The kenaf/PP composites were found to have better mechanical properties than the polymer matrix. As expected, the interfacial bonding between the matrix and the fibres improved considerably when the fibres were subjected to alkaline treatment.

Sign in / Sign up

Export Citation Format

Share Document