scholarly journals Beam Damage Assessment Using Natural Frequency Shift and Machine Learning

2022 ◽  
Author(s):  
Nicoleta Gillich ◽  
Cristian Tufisi ◽  
Christian Sacarea ◽  
Catalin V Rusu ◽  
Gilbert-Rainer Gillich ◽  
...  
Keyword(s):  
Machine Learning ◽  
Natural Frequency ◽  
Damage Assessment ◽  
Modal Parameter ◽  
Learning Methods ◽  
Damage Scenarios ◽  
Crack Location ◽  
Machine Learning Methods ◽  
Frequency Changes ◽  
Artificial Neural Network Ann

Damage detection based on modal parameter changes becomes popular in the last decades. Nowadays are available robust and reliable mathematical relations to predict the natural frequency changes if damage parameters are known. Using these relations, it is possible to create databases containing a large variety of damage scenarios. Damage can be thus assessed by applying an inverse method. The problem is the complexity of the database, especially for structures with more cracks. In this paper, we propose two machine learning methods, namely the random forest (RF) and the artificial neural network (ANN) as search tools. The databases we developed contain damage scenarios for a prismatic cantilever beam with one crack and ideal and non-ideal boundary conditions. The crack assessment is made in two steps. First, a coarse damage location is found from the networks trained for scenarios comprising the whole beam. Afterward, the assessment is made involving a particular network trained for the segment of the beam on which the crack is previously found. Using the two machine learning methods, we succeed to estimate the crack location and severity with high accuracy for both simulation and laboratory experiments. Regarding the location of the crack, which is the main goal of the practitioners, the errors are less than 0.6%. Based on these achievements, we concluded that the damage assessment we propose, in conjunction with the machine learning methods, is robust and reliable.

scholarly journals Comparison of machine learning methods for crack localization

2019 ◽  
Vol 23 (1) ◽  
pp. 125-142
Author(s):  
Helle Hein ◽  
Ljubov Jaanuska
Keyword(s):  
Machine Learning ◽  
Random Forests ◽  
Crack Depth ◽  
Haar Wavelet ◽  
Extensive Investigation ◽  
Learning Methods ◽  
Data Set ◽  
Crack Location ◽  
Machine Learning Methods ◽  
Discrete Transform

In this paper, the Haar wavelet discrete transform, the artificial neural networks (ANNs), and the random forests (RFs) are applied to predict the location and severity of a crack in an Euler–Bernoulli cantilever subjected to the transverse free vibration. An extensive investigation into two data collection sets and machine learning methods showed that the depth of a crack is more difficult to predict than its location. The data set of eight natural frequency parameters produces more accurate predictions on the crack depth; meanwhile, the data set of eight Haar wavelet coefficients produces more precise predictions on the crack location. Furthermore, the analysis of the results showed that the ensemble of 50 ANN trained by Bayesian regularization and Levenberg–Marquardt algorithms slightly outperforms RF.

scholarly journals Classification of Date Fruits into Genetic Varieties Using Image Analysis

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Murat Koklu ◽  
Ramazan Kursun ◽  
Yavuz Selim Taspinar ◽  
Ilkay Cinar
Keyword(s):  
Machine Learning ◽  
Vision System ◽  
Great Effort ◽  
Learning Methods ◽  
External Appearance ◽  
Machine Learning Methods ◽  
Date Fruit ◽  
Artificial Neural Network Ann ◽  
Processing Techniques

A great number of fruits are grown around the world, each of which has various types. The factors that determine the type of fruit are the external appearance features such as color, length, diameter, and shape. The external appearance of the fruits is a major determinant of the fruit type. Determining the variety of fruits by looking at their external appearance may necessitate expertise, which is time-consuming and requires great effort. The aim of this study is to classify the types of date fruit, that are, Barhee, Deglet Nour, Sukkary, Rotab Mozafati, Ruthana, Safawi, and Sagai by using three different machine learning methods. In accordance with this purpose, 898 images of seven different date fruit types were obtained via the computer vision system (CVS). Through image processing techniques, a total of 34 features, including morphological features, shape, and color, were extracted from these images. First, models were developed by using the logistic regression (LR) and artificial neural network (ANN) methods, which are among the machine learning methods. Performance results achieved with these methods are 91.0% and 92.2%, respectively. Then, with the stacking model created by combining these models, the performance result was increased to 92.8%. It has been concluded that machine learning methods can be applied successfully for the classification of date fruit types.

scholarly journals Genome-wide prediction for complex traits under the presence of dominance effects in simulated populations using GBLUP and machine learning methods

2020 ◽  
Vol 98 (6) ◽  
Author(s):  
Anderson Antonio Carvalho Alves ◽  
Rebeka Magalhães da Costa ◽  
Tiago Bresolin ◽  
Gerardo Alves Fernandes Júnior ◽  
Rafael Espigolan ◽  
...  
Keyword(s):  
Machine Learning ◽  
Complex Traits ◽  
Mean Squared Error ◽  
Genetic Effect ◽  
Predictive Ability ◽  
Predictive Performance ◽  
Support Vector ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Artificial Neural Network Ann

Abstract The aim of this study was to compare the predictive performance of the Genomic Best Linear Unbiased Predictor (GBLUP) and machine learning methods (Random Forest, RF; Support Vector Machine, SVM; Artificial Neural Network, ANN) in simulated populations presenting different levels of dominance effects. Simulated genome comprised 50k SNP and 300 QTL, both biallelic and randomly distributed across 29 autosomes. A total of six traits were simulated considering different values for the narrow and broad-sense heritability. In the purely additive scenario with low heritability (h2 = 0.10), the predictive ability obtained using GBLUP was slightly higher than the other methods whereas ANN provided the highest accuracies for scenarios with moderate heritability (h2 = 0.30). The accuracies of dominance deviations predictions varied from 0.180 to 0.350 in GBLUP extended for dominance effects (GBLUP-D), from 0.06 to 0.185 in RF and they were null using the ANN and SVM methods. Although RF has presented higher accuracies for total genetic effect predictions, the mean-squared error values in such a model were worse than those observed for GBLUP-D in scenarios with large additive and dominance variances. When applied to prescreen important regions, the RF approach detected QTL with high additive and/or dominance effects. Among machine learning methods, only the RF was capable to cover implicitly dominance effects without increasing the number of covariates in the model, resulting in higher accuracies for the total genetic and phenotypic values as the dominance ratio increases. Nevertheless, whether the interest is to infer directly on dominance effects, GBLUP-D could be a more suitable method.

scholarly journals Applying Image Processing to the Textile Grading of Fleece Based on Pilling Assessment

Fibers ◽  
2018 ◽  
Vol 6 (4) ◽  
pp. 73 ◽  
Author(s):  
Mei-Ling Huang ◽  
Chien-Chang Fu
Keyword(s):  
Machine Learning ◽  
Image Processing ◽  
Support Vector ◽  
Daubechies Wavelet ◽  
Learning Methods ◽  
Processing Methods ◽  
Machine Learning Methods ◽  
Gaussian Method ◽  
Artificial Neural Network Ann ◽  
Standing Problem

Textile pilling causes an undesirable appearance on the surface of garments, which is a long-standing problem. In this study, textile grading of fleece based on pilling assessment was performed using image processing and machine learning methods. Two image processing methods were used. The first method involved using the discrete Fourier transform combined with Gaussian filtering, and the second method involved using the Daubechies wavelet. Furthermore, binarization was used to segment the textile pilling from the background. Morphological and topological image processing methods were applied to extract the essential characteristics of textile image information to establish a database for the textile. Finally, machine learning methods, namely the artificial neural network (ANN) and the support vector machine (SVM), were used to objectively solve the textile grading problem. When the Fourier-Gaussian method was used, the classification accuracies of the ANN and SVM were 96.6% and 95.3%, and the overall accuracies of the Daubechies wavelet were 96.3% and 90.9%, respectively.

Sign in / Sign up

Export Citation Format

Share Document