Multivariate Analysis of Composition Features to Perform Linear Predictions of Rubber Blends Tensile Strength

2017 ◽  
Vol 872 ◽  
pp. 77-82
Author(s):  
Roberto Fernandez Martinez ◽  
Pello Jimbert ◽  
Ana Okariz ◽  
Teresa Guraya
Keyword(s):  
Mechanical Properties ◽  
Tensile Strength ◽  
Multivariate Analysis ◽  
Multivariate Linear Model ◽  
Rubber Blends ◽  
Tensile Strength Test ◽  
Taguchi Design Of Experiments ◽  
Input Variables ◽  
The Relationship ◽  
Selection Of

The goal in this work is to build a multivariate linear model to predict tensile strength since is one of the most significant mechanical properties of carbon-black reinforced rubber blends. This model is based in the relationship between the final mechanical properties and the material composition, with the advantage of using this model to improve the design of the composition of the blend. In order to predict this relevant physical attribute of rubber blends a linear regression is performed, but previously a multivariate analysis of the data is done to get a better accuracy in the validation of the model. The number of used instances and the values are determined by a Taguchi design of experiments, and the output values are obtained from the tensile strength test following the corresponding standard. After the performance of the multivariate analysis where the input variables are under a detail study, a selection of the best features help to improve the accuracy of the model, passing from a 24.80% to a 20.60% of error.

Modeling of the Mechanical Properties of Carbon-Black Reinforced Rubber Blends by Machine Learning Techniques

2014 ◽  
Vol 627 ◽  
pp. 97-100 ◽  
Author(s):  
R. Fernandez-Martinez ◽  
R. Hernandez ◽  
J. Ibarretxe ◽  
Pello Jimbert ◽  
M. Iturrondobeitia ◽  
...  
Keyword(s):  
Machine Learning ◽  
Mechanical Properties ◽  
Carbon Black ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Efficient Design ◽  
Rubber Blends ◽  
Taguchi Design Of Experiments ◽  
Physical Attributes ◽  
Input Variables

Mastering the relationship between the final mechanical properties of carbon black reinforced rubber blends and their composition is a key advantage for an efficient design of the composition of the blend. In this work, some models to predict three relevant physical attributes of rubber blends — modulus at 100% deformation, Shore A hardness, and tensile strength — are built by machine learning methods and subsequently evaluated. Linear regression, artificial neural networks, support vector machine, and regression trees are used to generate the models. The number of used samples and the values for the input variables is determined by a Taguchi design of experiments, and prior to the modeling the uncertainty of the experimental data was analyzed.

Size Effect on Mechanical Properties of LVL

2014 ◽  
Vol 887-888 ◽  
pp. 824-829
Author(s):  
Qing Fang Lv ◽  
Ji Hong Qin ◽  
Ran Zhu
Keyword(s):  
Mechanical Properties ◽  
Tensile Strength ◽  
Compressive Strength ◽  
Size Effect ◽  
Tensile Test ◽  
Compression Test ◽  
Test Results ◽  
Laminated Veneer Lumber ◽  
Object Of Study ◽  
The Relationship

Laminated veneer lumber is taken as an object of study, and use LVL specimens of different sizes for compression test and tensile test. The goal of the experiment is to investigate the size effect on compressive strength and tensile strength as well as the influence of the secondary glued laminated face, which appears in the secondary molding processes. The results show that both compressive strength and tensile strength have the size effect apparently and the existence of the secondary glued laminated face lower the compressive strength of LVL specimens. Afterwards, the relationship between compressive strength and volume along with tensile strength and area are obtained by the test results.

scholarly journals AN INVESTIGATION ON THE EFFECTS OF MICRO-PARAMETERS ON THE STRENGTH PROPERTIES OF ROCK

2021 ◽  
Vol 36 (1) ◽  
pp. 111-119
Author(s):  
Behzad Jafari Mohammadabadi ◽  
Kourosh Shahriar ◽  
Hossein Jalalifar ◽  
Kaveh Ahangari
Keyword(s):  
Mechanical Properties ◽  
Numerical Simulation ◽  
Tensile Strength ◽  
Compressive Strength ◽  
Friction Coefficient ◽  
Critical Stress ◽  
Friction Angle ◽  
Strength Properties ◽  
Brazilian Tensile Strength ◽  
The Relationship

Rocks are formed from particles and the interaction between those particles controls the behaviour of a rock’s mechanical properties. Since it is very important to conduct extensive studies about the relationship between the micro-parameters and macro-parameters of rock, this paper investigates the effects of some micro-parameters on strength properties and the behaviour of cracks in rock. This is carried out by using numerical simulation of an extensive series of Uniaxial Compressive Strength (UCS) and Brazilian Tensile Strength (BTS) tests. The micro-parameters included the particles’ contact modulus, the contact stiff ness ratio, bond cohesion, bond tensile strength, the friction coefficient and the friction angle, and the mechanical properties of chromite rock have been considered as base values of the investigation. Based on the obtained results, it was found that the most important micro-parameters on the behaviour of rock in the compressive state are bond cohesion, bond tensile strength, and the friction coefficient. Also, the bond tensile strength showed the largest effect under tensile conditions. The micro-parameter of bond tensile strength increased the rock tensile strength (up to 5 times), minimized destructive cracks and increased the corresponding strain (almost 2.5 times) during critical stress.

Mechanical Properties of Al 6063 Processed with Equal Channel Angular Extrusion under Varying Process Parameters

2021 ◽  
Vol 54 ◽  
pp. 23-32
Author(s):  
T.M. Azeez ◽  
Lateef O. Mudashiru ◽  
T.B. Asafa ◽  
A.A. Adeleke ◽  
Peter Pelumi Ikubanni
Keyword(s):  
Mechanical Properties ◽  
Tensile Strength ◽  
Process Parameters ◽  
Equal Channel Angular Extrusion ◽  
Design Expert ◽  
Software Analysis ◽  
Angular Extrusion ◽  
Output Factors ◽  
The Relationship ◽  
Optimum Input

Mechanical properties of extruded aluminum are known to significantly depend on the process parameters such as temperature, numbers of extrusion pass and extrusion load among others. This implies that these properties can be influenced by tuning the process parameters. Herein, the effects of these parameters on the tensile strength and hardness of aluminum 6063 series were investigated by using equal channel angular extrusion (ECAE). Experiments were designed using Design Expert software. Analysis of variance (ANOVA) was then used to investigate the main and interactions effects of the process parameters. An empirical mathematical model was generated that shows the relationship between the input and output variables using response surface methodology. Temperature was found to be the most significant factor while extrusion load was the least factor that influenced the hardness and tensile strength which were the output factors. There was a significant increase in tensile strength and hardness after extrusion at different mix of factors. The optimum input variable was discovered at 1020.58 kN, 489.67°C and 3 numbers of extrusion passes.

Prediction of tensile strength of polymer carbon nanotube composites using practical machine learning method

2020 ◽  
pp. 002199832095354 ◽  
Author(s):  
Tien-Thinh Le
Keyword(s):  
Machine Learning ◽  
Mechanical Properties ◽  
Tensile Strength ◽  
Carbon Nanotube ◽  
Polymer Matrix ◽  
Mean Squared Error ◽  
Gaussian Process Regression ◽  
Weight Fraction ◽  
Percentage Error ◽  
Input Variables

This paper is devoted to the development and construction of a practical Machine Learning (ML)-based model for the prediction of tensile strength of polymer carbon nanotube (CNTs) composites. To this end, a database was compiled from the available literature, composed of 11 input variables. The input variables for predicting tensile strength of nanocomposites were selected for the following main reasons: (i) type of polymer matrix, (ii) mechanical properties of polymer matrix, (iii) physical characteristics of CNTs, (iv) mechanical properties of CNTs and (v) incorporation parameters such as CNT weight fraction, CNT surface modification method and processing method. As the problem of prediction is highly dimensional (with 11 dimensions), the Gaussian Process Regression (GPR) model was selected and optimized by means of a parametric study. The correlation coefficient (R), Willmott’s index of agreement (IA), slope of regression, Mean Absolute Percentage Error (MAPE), Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE) were employed as error measurement criteria when training the GPR model. The GPR model exhibited good performance for both training and testing parts (RMSE = 5.982 and 5.327 MPa, MAE = 3.447 and 3.539 MPa, respectively). In addition, uncertainty analysis was also applied to estimate the prediction confidence intervals. Finally, the prediction capability of the GPR model with different ranges of values of input variables was investigated and discussed. For practical application, a Graphical User Interface (GUI) was developed in Matlab for predicting the tensile strength of nanocomposites.

An assessment into mechanical properties and microstructural behavior of TIG welded Ti-6Al-4V titanium alloy

2020 ◽  
Vol 10 (3) ◽  
pp. 281-292 ◽  
Author(s):  
Saurabh Dewangan ◽  
Suraj Kumar Mohapatra ◽  
Abhishek Sharma
Keyword(s):  
Mechanical Properties ◽  
Tensile Strength ◽  
Weight Ratio ◽  
High Strength ◽  
Hardness Test ◽  
Content Type ◽  
Ti Alloys ◽  
Microstructure And Mechanical Properties ◽  
Grade 5 ◽  
Selection Of

PurposeTitanium (Ti) alloys are in high demand in manufacturing industries all over the world. The property like high strength to weight ratio makes Ti alloys highly recommended for aerospace industries. Ti alloys possess good weldability, and therefore, they were extensively investigated with regard to strength and metallurgical properties of welded joint. This study aims to deal with the analysis of strength and microstructural changes in Ti-6Al-4V (Grade 5) alloy after tungsten inert gas (TIG) welding.Design/methodology/approachTwo pair of Ti alloy plates were welded in two different voltages, i.e. 24 and 28 V, with keeping the current constant, i.e. 80 A It was a random selection of current and voltage values to check the performance of welded material. Both the welded plates were undergone through some mechanical property analysis like impact test, tensile test and hardness test. In addition, the microstructure of the welded joints was also analyzed.FindingsIt was found that hardness and tensile properties gets improved with an increment in voltage, but this effect was reverse for impact toughness. A good corroboration between microstructure and mechanical properties, such as tensile strength, hardness and toughness, was reported in this work. Heat distribution in both the welded plates was simulated through ANSYS software to check the temperature contour in the plates.Originality/valueA good corroboration between microstructure and mechanical properties, such as tensile strength, hardness and toughness, was reported in this study.

Relationship between Knitting Parameters and Mechanical Properties of Warp Knitting Mesh Fabric

2012 ◽  
Vol 627 ◽  
pp. 374-377 ◽  
Author(s):  
Lei Zhang ◽  
Jin Hua Jiang ◽  
Nan Liang Chen
Keyword(s):  
Mechanical Properties ◽  
Tensile Strength ◽  
Side Length ◽  
Two Parameters ◽  
The Relationship

The warp knitting parameters are important to determine the knitting process and the mechanical properties of warp knitting mesh fabric. In this work, the relationship between different knitting parameters (mesh side length and the let-off value) and the mechanical properties were studied. The effect of knitting parameters on the tensile strength and elongation was investigated by experiment. As a result, the relationship between the mechanical properties and the two parameters was found, and the optimization values of two parameters which could improve the isotropy of mesh fabric were given.

Comparison of Shear, Compressive and Tensile Characteristics of Cast Irons

1973 ◽  
Vol 15 (1) ◽  
pp. 53-60 ◽  
Author(s):  
R. D. Adams ◽  
M. A. O. Fox
Keyword(s):  
Mechanical Properties ◽  
Tensile Strength ◽  
Design Criteria ◽  
Matrix Structure ◽  
Proof Stress ◽  
Cast Irons ◽  
The Matrix ◽  
The Relationship ◽  
Graphite Inclusions ◽  
Strength And Ductility

Cast irons were produced with variations in the quantity and shape of the free graphite inclusions and in the matrix structure to investigate the relationship between the shear, compressive and tensile mechanical properties. Differences were observed which may have a significant effect on design criteria for cast irons. For example, the ratio of shear to tensile strengths decreased from about 1·25 to 0·577 and the ratio of 0·1 per cent proof stress in compression to that in tension decreased from approximately 2 to 11 as the tensile strength (and ductility) were increased.

Sign in / Sign up

Export Citation Format

Share Document