scholarly journals Nondestructive Testing of Mechanical Properties of Bamboo–Wood Composite Container Floor by Image Processing

Forests ◽  
2021 ◽  
Vol 12 (11) ◽  
pp. 1535
Author(s):  
Zhilin Jiang ◽  
Yi Liang ◽  
Zihua Su ◽  
Aonan Chen ◽  
Jianping Sun
Keyword(s):  
Mechanical Properties ◽  
Image Processing ◽  
Correlation Coefficients ◽  
Modulus Of Rupture ◽  
Support Vector ◽  
Wood Composite ◽  
Ann Models ◽  
The Common ◽  
The Mean ◽  
Artificial Neural Network Ann

The bamboo–wood composite container floor (BWCCF) has been wildly utilized in transportation in recent years. However, most of the common approaches of mechanics detection are conducted in a time-consuming and resource wasting way. Therefore, this paper aims to provide a frugal and highly efficient method to predict the short-span shear stress, the modulus of rupture (MOR) and the modulus of elasticity (MOE) of the BWCCF. Artificial neural network (ANN) models were developed and support vector machine (SVM) models were constructed for comparative study by taking the characteristic parameters of image processing as input and the mechanical properties as output. The results show that the SVM models can output better values than the ANN models. In a prediction of the three mechanical properties by SVMs, the correlation coefficients (R) were determined as 0.899, 0.926, and 0.949, and the mean absolute percentage errors (MAPE) were obtained, 6.983%, 5.873%, and 4.474%, respectively. The performance measures show the strong generalization of the SVM models. The discoveries in this work provide new perspectives on the study of mechanical properties of the BWCCF combining machine learning and image processing.

Prediction of the optimal FSW process parameters for joints using machine learning techniques

2021 ◽  
Vol 63 (12) ◽  
pp. 1104-1111
Author(s):  
Furkan Sarsilmaz ◽  
Gürkan Kavuran
Keyword(s):  
Mechanical Properties ◽  
Tensile Strength ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Ann Model ◽  
Friction Stir ◽  
Learning Techniques ◽  
Svm Model ◽  
Artificial Neural Network Ann ◽  
Fsw Parameters

Abstract In this work, a couple of dissimilar AA2024/AA7075 plates were experimentally welded for the purpose of considering the effect of friction-stir welding (FSW) parameters on mechanical properties. First, the main mechanical properties such as ultimate tensile strength (UTS) and hardness of welded joints were determined experimentally. Secondly, these data were evaluated through modeling and the optimization of the FSW process as well as an optimal parametric combination to affirm tensile strength and hardness using a support vector machine (SVM) and an artificial neural network (ANN). In this study, a new ANN model, including the Nelder-Mead algorithm, was first used and compared with the SVM model in the FSW process. It was concluded that the ANN approach works better than SVM techniques. The validity and accuracy of the proposed method were proved by simulation studies.

Investigation of trap efficiency of retention dams

2017 ◽  
Vol 18 (2) ◽  
pp. 450-459 ◽  
Author(s):  
Abbas Parsaie ◽  
Samad Ememgholizadeh ◽  
Amir Hamzeh Haghiabi ◽  
Amir Moradinejad
Keyword(s):  
Fuzzy Inference ◽  
Kernel Functions ◽  
Support Vector ◽  
Inference System ◽  
Trap Efficiency ◽  
Neuro Fuzzy ◽  
Management Plans ◽  
Longitudinal Slope ◽  
The Mean ◽  
Artificial Neural Network Ann

Abstract In this paper, the trap efficiency (TE) of retention dams was investigated using laboratory experiments. To map the relation between TE and involved parameters, artificial intelligence (AI) methods including artificial neural network (ANN), adaptive neuro fuzzy inference system (ANFIS) and support vector machine (SVM) were utilized. Results of experiments indicated that the range of TE varies between 30 and 98%; hence, this structure can be recommended to control sediment transport in watershed management plans. Experimental results showed that by increasing the longitudinal slope of streams, TE decreases. This finding was observed for Vf/Vs parameter, as well. By increasing the mean diameter grain size (D50) and specific gravity of sediments (Gs), TE increases. Results of all applied AI models demonstrated that all of them have suitable performance; however, the minimum data dispersivity was observed in SVM outcomes. It is notable that the best performance of transfer, membership and kernel functions were related to tansig, gaussmf and radial basis function (RBF) for ANN, SVM and ANFIS, respectively.

Mechanical properties prediction for carbon nanotubes/epoxy composites by using support vector regression

2015 ◽  
Vol 29 (05) ◽  
pp. 1550016 ◽  
Author(s):  
W. D. Cheng ◽  
C. Z. Cai ◽  
Y. Luo ◽  
Y. H. Li ◽  
C. J. Zhao
Keyword(s):  
Mechanical Properties ◽  
Carbon Nanotubes ◽  
Support Vector Regression ◽  
Correlation Coefficients ◽  
Epoxy Composites ◽  
Percentage Error ◽  
Support Vector ◽  
Data Set ◽  
Highly Nonlinear ◽  
Mechanical Properties Prediction

Studies have shown there are several process/geometry parameters affecting the mechanical properties of the carbon nanotubes/epoxy composites. The relationship between the response and process/geometry parameters is highly nonlinear and quite complicated. It is very valuable to have an accurate model to estimate the response under different process/geometry parameters. In this paper, the support vector regression (SVR) combined with particle swarm optimization (PSO) for its parameter optimization was employed to construct mathematical models for prediction of mechanical properties of the carbon nanotubes/epoxy composites according to an experimental data set. The leave-one-out cross-validation (LOOCV) test results by SVR models support that the generalization ability of SVR model is high enough. The statistical mean absolute percentage error for tensile strength, elongation and elastic modulus are 3.96%, 3.14% and 2.62%, the correlation coefficients (R2) achieve as high as 0.991, 0.990 and 0.997, respectively. This study suggests that the established SVR model can be used to accurately foresee the mechanical properties of carbon nanotubes/epoxy composites and can be used to optimize designing or controlling of the experimental process/geometry in practice.

scholarly journals Experimental study on LBL beams

2019 ◽  
Vol 275 ◽  
pp. 01026
Author(s):  
Chenjie Zhao ◽  
Xiaohong Xiong ◽  
Zhenhua Xiong ◽  
Kangwen Wu ◽  
Zhen Cao ◽  
...  
Keyword(s):  
Mechanical Properties ◽  
Experimental Study ◽  
Elastic Modulus ◽  
Standard Deviation ◽  
Cross Section ◽  
Beam Theory ◽  
Bending Moment ◽  
Modulus Of Rupture ◽  
Loading Process ◽  
The Mean

Six specimens were made and tested to study the mechanical properties of LBL beams. The mean ultimate loading value is 68.39 MPa with a standard deviation of 6.37 MPa, giving a characteristic strength (expected to be exceeded by 95% of specimens) of 57.91 MPa, and the mean ultimate deflection is 53.3 mm with a standard deviation of 5.5 mm, giving the characteristic elastic modulus of 44.3 mm. The mean ultimate bending moment is 20.18 kN.m with a standard deviation of 1.88 kN.m, giving the characteristic elastic modulus of 17.08 kN.m. The mean elastic modulus is 9688 MPa with a standard deviation of 1765 MPa, giving the characteristic elastic modulus of 6785 MPa, and the mean modulus of rupture is 93.3 MPa with a standard deviation of 8.6 MPa, giving the characteristic elastic modulus of 79.2 MPa. The strain across the cross-section for all LBL beams is basically linear throughout the loading process, following standard beam theory.

A Novel SVM-Based Method for Seismic First-Arrival Detecting

2010 ◽  
Vol 29-32 ◽  
pp. 973-978 ◽  
Author(s):  
Ming Chen ◽  
Yong Li ◽  
Jun Xie
Keyword(s):  
Support Vector ◽  
The Novel ◽  
Ann Model ◽  
Seismic Record ◽  
Feature Vectors ◽  
Svm Model ◽  
First Arrival ◽  
Ann Models ◽  
Novel Method ◽  
Artificial Neural Network Ann

First arrivals detecting on seismic record is important at all times. A novel support vector machine (SVM)-based method for seismic first-arrival pickup is proposed in this research. Firstly, the multi-resolution wavelet decomposition is used to de-noise the seismic record. And then, feature vectors are extracted from the denoise data. Finally, both SVM and artificial neural network (ANN) models are employed to train and predict the feature vectors. Experimental results demonstrate that the SVM model gives better accuracy than the ANN model. It is promising that the novel method is very prospective.

Suspended sediment dynamics in a tributary of the Saint John River, New Brunswick

2011 ◽  
Vol 38 (2) ◽  
pp. 221-232 ◽  
Author(s):  
Hélène Higgins ◽  
André St-Hilaire ◽  
Simon C. Courtenay ◽  
Katy A. Haralampides
Keyword(s):  
New Brunswick ◽  
Suspended Sediment ◽  
System Analysis ◽  
Correlation Coefficients ◽  
Sediment Concentration ◽  
Ann Model ◽  
Absolute Deviation ◽  
Saint John ◽  
Ann Models ◽  
Artificial Neural Network Ann

Historical hydrometeorological and suspended sediment concentration (SSC) data from the Kennebecasis River, a tributary of the Saint John River in New Brunswick, Canada, were investigated to help understand what drives high sediment transport in that system. Analysis of correlation coefficients between SSC and potential drivers at various time steps suggested that multiple regressions would not be optimal for this purpose, and that lagged flow (Q) and precipitation should be taken into account in any model. A frequency analysis involving annual maxima of SSC, Q, and precipitation events revealed there is no systematic unique driver of extreme annual SSC or high annual loads. Finally, artificial neural network (ANN) models were developed to verify whether the variables examined previously would yield better results in a nonlinear context. Network inputs were mean temperature, Q, Q(t–1), Q(t–2), and day-of-year. Using daily loads directly as a target in the network yielded satisfactory results, with 88% of the variance explained by the model and a mean absolute deviation between estimated and real annual loads of 16%. The ANN model systematically outperformed multiple linear regressions.

scholarly journals Prediction of mean wave overtopping at simple sloped breakwaters using kernel-based methods

2021 ◽  
Author(s):  
Shabnam Hosseinzadeh ◽  
Amir Etemad-Shahidi ◽  
Ali Koosheh
Keyword(s):  
Neural Network ◽  
Sensitivity Analysis ◽  
Gaussian Process Regression ◽  
Structural Features ◽  
Support Vector ◽  
Ann Model ◽  
Wave Overtopping ◽  
Taylor Diagram ◽  
The Mean ◽  
Artificial Neural Network Ann

Abstract The accurate prediction of the mean wave overtopping rate at breakwaters is vital to have a safe design. Hence, providing a robust tool as a preliminary estimator can be useful for practitioners. Recently, soft computing tools such as artificial neural network (ANN) have been developed as alternatives to traditional overtopping formulae. The goal of this paper is to assess the capabilities of two kernel-based methods namely Gaussian process regression (GPR) and support vector regression for the prediction of mean wave overtopping rate at sloped breakwaters. An extensive dataset taken from EurOtop (2018) database, including rubble mound structures with permeable core, straight slopes, without berm, and crown wall, was employed to develop the models. Different combinations of the important dimensionless parameters representing structural features and wave conditions were tested based on the sensitivity analysis for developing the models. The obtained results were compared with those of the ANN model and the existing empirical formulae. The modified Taylor diagram was used to compare the models graphically. The results showed the superiority of kernel-based models, especially the GPR model over the ANN model and empirical formulae. In addition, the optimal input combination was introduced based on accuracy and the number of input parameters criteria. Finally, the physical consistencies of developed models were investigated the results, of which demonstrated the reliability of kernel-based models in terms of delivering physics of overtopping phenomenon.

Predicting mechanical properties of clear wood from Acacia mangium provenances using ultrasound

BioResources ◽  
2021 ◽  
Vol 16 (4) ◽  
pp. 8309-8319
Author(s):  
Doan Van Duong ◽  
Masumi Hasegawa
Keyword(s):  
Mechanical Properties ◽  
Compression Strength ◽  
Modulus Of Elasticity ◽  
Dynamic Modulus ◽  
Significant Positive Correlation ◽  
Correlation Coefficients ◽  
Acacia Mangium ◽  
Longitudinal Direction ◽  
Modulus Of Rupture ◽  
Clear Wood

Ultrasound was considered as a means for determining mechanical properties of clear wood in six different Acacia mangium provenances from a trial forest planted in Vietnam. A total of 30 trees (5 trees from each provenance) with no major defects were selected, and a 50-cm-long log was obtained at 1.3 m above the ground from each tree for the assessment of mechanical properties. The measured average ultrasound velocities for provenances tested in the longitudinal direction ranged from 4094 m/s to 4271 m/s. The predicted average dynamic modulus of elasticity (Ed) values varied from 7.42 GPa to 8.70 GPa among provenances. The Ed indicated significant positive correlation coefficients with modulus of elasticity (0.64 to 0.96), modulus of rupture (0.44 to 0.87), and compression strength (0.54 to 0.92) for provenances examined in this study. The results indicated that the use of ultrasound was feasible to determine the mechanical properties of A. mangium provenances planted in Vietnam.

scholarly journals Classification by a stacking model using CNN features for COVID-19 infection diagnosis

2021 ◽  
pp. 1-16
Author(s):  
Yavuz Selim Taspinar ◽  
Ilkay Cinar ◽  
Murat Koklu
Keyword(s):  
Machine Learning ◽  
Classification Performance ◽  
Support Vector ◽  
Clinical Environment ◽  
X Ray ◽  
Left Behind ◽  
Study Results ◽  
Chest X Ray ◽  
Ann Models ◽  
Artificial Neural Network Ann

Affecting millions of people all over the world, the COVID-19 pandemic has caused the death of hundreds of thousands of people since its beginning. Examinations also found that even if the COVID-19 patients initially survived the coronavirus, pneumonia left behind by the virus may still cause severe diseases resulting in organ failure and therefore death in the future. The aim of this study is to classify COVID-19, normal and viral pneumonia using the chest X-ray images with machine learning methods. A total of 3,486 chest X-ray images from three classes were first classified by three single machine learning models including the support vector machine (SVM), logistics regression (LR), artificial neural network (ANN) models, and then by a stacking model that was created by combining these 3 single models. Several performance evaluation indices including recall, precision, F-score, and accuracy were computed to evaluate and compare classification performance of 3 single four models and the final stacking model used in the study. As a result of the evaluations, the models namely, SVM, ANN, LR, and stacking, achieved 90.2%, 96.2%, 96.7%, and 96.9%classification accuracy, respectively. The study results indicate that the proposed stacking model is a fast and inexpensive method for assisting COVID-19 diagnosis, which can have potential to assist physicians and nurses to better and more efficiently diagnose COVID-19 infection cases in the busy clinical environment.

scholarly journals Stability of yield and yield components in maize hybrids

Genetika ◽  
2009 ◽  
Vol 41 (2) ◽  
pp. 215-224 ◽  
Author(s):  
Radomir Cvarkovic ◽  
Gordana Brankovic ◽  
Irena Calic ◽  
Nenad Delic ◽  
Tomislav Zivanovic ◽  
...  
Keyword(s):  
Correlation Coefficients ◽  
Sum Of Squares ◽  
Environment Interaction ◽  
Common Variance ◽  
Stability Parameters ◽  
Maize Hybrids ◽  
The Common ◽  
The Mean ◽  
The Absolute ◽  
Rank Differences

Two-year grain yield and 1000-grains mass data of 24 maize hybrids of FAO maturity groups 400, 500, 600, 700 were analyzed. Investigations were performed at the two environments in two years. Nonparametric methods of the Kubinger and the van der Laan-de Kroon showed genotype x environment interaction for both investigated features, and method of Hildebrand showed interaction for 1000-grains mass. Maize hybrids stability was estimated with stability parameters: Si(1)- the mean of the absolute rank differences over environments, Si(2)- the common variance of the ranks, Si(3).and Si(6): the sum of the absolute deviations and sum of squares of rank for each genotype relative to the mean of ranks, respectively. On the basis of the stability parametar values, the most stable and the most unstable hybrids were estimated for each FAO maturity group, for both investigated features. Correlation coefficients between both investigated features and stability parameters and for all pairs of stability parameters were computed. In spite of the positive correlations estimated between all four stability parameters, we can make two groups: the first group formed: Si(1)- the mean of the absolute rank differences over environments and Si(2)- the common variance of the ranks and the second group formed: Si(3) and Si(6)- the sum of the absolute deviations and sum of squares of rank for each genotype relative to the mean of ranks respectively.

Sign in / Sign up

Export Citation Format

Share Document