scholarly journals Practical Hybrid Machine Learning Approach for Estimation of Ultimate Load of Elliptical Concrete-Filled Steel Tubular Columns under Axial Loading

2020 ◽  
Vol 2020 ◽  
pp. 1-19 ◽  
Author(s):  
Tien-Thinh Le
Keyword(s):  
Machine Learning ◽  
Load Capacity ◽  
Axial Loading ◽  
Steel Tube ◽  
Coefficient Of Determination ◽  
Inference System ◽  
Elliptical Cross ◽  
Real Coded Genetic Algorithm ◽  
Hybrid Machine ◽  
Cfst Columns

In this study, a hybrid machine learning (ML) technique was proposed to predict the bearing capacity of elliptical CFST columns under axial load. The proposed model was Adaptive Neurofuzzy Inference System (ANFIS) combined with Real Coded Genetic Algorithm (RCGA), denoted as RCGA-ANFIS. The evaluation of the model was performed using the coefficient of determination (R2) and root mean square error (RMSE). The results showed that the RCGA-ANFIS (R2 = 0.974) was more reliable and effective than conventional gradient descent (GD) technique (R2 = 0.952). The accuracy of the present work was found superior to the results published in the literature (R2 = 0.776 or 0.768) when predicting the load capacity of elliptical CFST columns. Finally, sensitivity analysis showed that the thickness of the steel tube and the minor axis length of the elliptical cross section were the most influential parameters. For practical application, a Graphical User Interface (GUI) was developed in MATLAB for researchers and engineers and to support the teaching and interpretation of the axial behavior of CFST columns.

scholarly journals COVID-19 Pandemic Prediction for Hungary; a Hybrid Machine Learning Approach

2020 ◽  
Author(s):  
Amir Mosavi
Keyword(s):  
Machine Learning ◽  
Prediction Models ◽  
Future Research ◽  
Complex Nature ◽  
Learning Approach ◽  
Epidemiological Models ◽  
Inference System ◽  
Proper Actions ◽  
Machine Learning Approach ◽  
Hybrid Machine

Several epidemiological models are being used around the world to project the number of infected individuals and the mortality rates of the COVID-19 outbreak. Advancing accurate prediction models is of utmost importance to take proper actions. Due to a high level of uncertainty or even lack of essential data, the standard epidemiological models have been challenged regarding the delivery of higher accuracy for long-term prediction. As an alternative to the susceptible-infected-resistant (SIR)-based models, this study proposes a hybrid machine learning approach to predict the COVID-19 and we exemplify its potential using data from Hungary. The hybrid machine learning methods of adaptive network-based fuzzy inference system (ANFIS) and multi-layered perceptron-imperialist competitive algorithm (MLP-ICA) are used to predict time series of infected individuals and mortality rate. The models predict that by late May, the outbreak and the total morality will drop substantially. The validation is performed for nine days with promising results, which confirms the model accuracy. It is expected that the model maintains its accuracy as long as no significant interruption occurs. Based on the results reported here, and due to the complex nature of the COVID-19 outbreak and variation in its behavior from nation-to-nation, this study suggests machine learning as an effective tool to model the outbreak. This paper provides an initial benchmarking to demonstrate the potential of machine learning for future research.

scholarly journals Development of Hybrid Machine Learning Models for Predicting the Critical Buckling Load of I-Shaped Cellular Beams

2019 ◽  
Vol 9 (24) ◽  
pp. 5458 ◽  
Author(s):  
Hai-Bang Ly ◽  
Tien-Thinh Le ◽  
Lu Minh Le ◽  
Van Quan Tran ◽  
Vuong Minh Le ◽  
...  
Keyword(s):  
Machine Learning ◽  
Mean Squared Error ◽  
Optimization Techniques ◽  
Buckling Load ◽  
Steel Beams ◽  
Beam Length ◽  
Inference System ◽  
Critical Buckling Load ◽  
Flange Thickness ◽  
Hybrid Machine

The principal purpose of this work is to develop three hybrid machine learning (ML) algorithms, namely ANFIS-RCSA, ANFIS-CA, and ANFIS-SFLA which are a combination of adaptive neuro-fuzzy inference system (ANFIS) with metaheuristic optimization techniques such as real-coded simulated annealing (RCSA), cultural algorithm (CA) and shuffled frog leaping algorithm (SFLA), respectively, to predict the critical buckling load of I-shaped cellular steel beams with circular openings. For this purpose, the existing database of buckling tests on I-shaped steel beams were extracted from the available literature and used to generate the datasets for modeling. Eight inputs, considered as independent variables, including the beam length, beam end-opening distance, opening diameter, inter-opening distance, section height, web thickness, flange width, and flange thickness, as well as one output of the critical buckling load of cellular steel beams considered as a dependent variable, were used in the datasets. Three quality assessment criteria, namely correlation coefficient (R), root mean squared error (RMSE) and mean absolute error (MAE) were employed for assessment of three developed hybrid ML models. The obtained results indicate that all three hybrid ML models have a strong ability to predict the buckling load of steel beams with circular openings, but ANFIS-SFLA (R = 0.960, RMSE = 0.040 and MAE = 0.017) exhibits the best effectiveness as compared with other hybrid models. In addition, sensitivity analysis was investigated and compared with linear statistical correlation between inputs and output to validate the importance of input variables in the models. The sensitivity results show that the most influenced variable affecting beam buckling capacity is the beam length, following by the flange width, the flange thickness, and the web thickness, respectively. This study shows that the hybrid ML techniques could help in establishing a robust numerical tool for beam buckling analysis. The proposed methodology is also promising to predict other types of failure, as well as other types of perforated beams.

scholarly journals COVID-19 Pandemic Prediction for Hungary: A Hybrid Machine Learning Approach

2020 ◽  
Author(s):  
Gergo Pinter ◽  
Imre Felde ◽  
Amir Mosavi ◽  
Pedram Ghamisi ◽  
Richard Gloaguen
Keyword(s):  
Machine Learning ◽  
Prediction Models ◽  
Future Research ◽  
Complex Nature ◽  
Learning Approach ◽  
Epidemiological Models ◽  
Inference System ◽  
Proper Actions ◽  
Machine Learning Approach ◽  
Hybrid Machine

Several epidemiological models are being used around the world to project the number of infected individuals and the mortality rates of the COVID-19 outbreak. Advancing accurate prediction models is of utmost importance to take proper actions. Due to a high level of uncertainty or even lack of essential data, the standard epidemiological models have been challenged regarding the delivery of higher accuracy for long-term prediction. As an alternative to the susceptible-infected-resistant (SIR)-based models, this study proposes a hybrid machine learning approach to predict the COVID-19 and we exemplify its potential using data from Hungary. The hybrid machine learning methods of adaptive network-based fuzzy inference system (ANFIS) and multi-layered perceptron-imperialist competitive algorithm (MLP-ICA) are used to predict time series of infected individuals and mortality rate. The models predict that by late May, the outbreak and the total morality will drop substantially. The validation is performed for nine days with promising results, which confirms the model accuracy. It is expected that the model maintains its accuracy as long as no significant interruption occurs. Based on the results reported here, and due to the complex nature of the COVID-19 outbreak and variation in its behavior from nation-to-nation, this study suggests machine learning as an effective tool to model the outbreak. This paper provides an initial benchmarking to demonstrate the potential of machine learning for future research.

Axial strength prediction of steel tube confined concrete columns using a hybrid machine learning model

Structures ◽  
2022 ◽  
Vol 36 ◽  
pp. 765-780
Author(s):  
Ngoc-Tri Ngo ◽  
Thi-Phuong-Trang Pham ◽  
Hoang An Le ◽  
Quang-Trung Nguyen ◽  
Thi-Thao-Nguyen Nguyen
Keyword(s):  
Machine Learning ◽  
Concrete Columns ◽  
Learning Model ◽  
Steel Tube ◽  
Confined Concrete ◽  
Strength Prediction ◽  
Axial Strength ◽  
Machine Learning Model ◽  
Hybrid Machine

scholarly journals Nonlinear Analysis of Circular Concrete Filled Steel Tube Columns under Axial Loading

2019 ◽  
Vol 8 (12) ◽  
pp. 688-692
Keyword(s):  
Carrying Capacity ◽  
Axial Loading ◽  
Steel Tube ◽  
Load Carrying Capacity ◽  
Building Structures ◽  
Inelastic Behavior ◽  
Concrete Filled Steel Tube ◽  
Load Carrying ◽  
Cfst Columns ◽  
Von Mises

Concrete filled steel tube (CFST) columns are composite member mainly consists of concrete infilled in steel tube. In current construction industry, CFST columns are preferred to provide lateral resistance in both unbraced and braced building structures. In this paper, finite element studies were carried out on concrete filled steel tube columns under an axial composite loading by using ABAQUS/CAE. The inelastic behavior of concrete and steel tube was defined to the model by using concrete damaged plasticity model (CDP) and Johnson-cook model respectively which is available in ABAQUS/CAE. The diameters of columns were considered as 100 mm, 125 mm and 150 mm, whereas the length of columns was kept constant, i.e. 600 mm for all models. The thickness of steel tube was considered as 4 mm and 5 mm for all diameters of columns. The concrete infilled of grade M30 was used in this study. The simulations were carried out against composite loading to study the response of CFST columns in terms of load carrying capacity, displacement and von-mises stresses. The mesh conversion study was also carried out to obtain the best size of mesh corresponding to the experimental load carrying capacity of CFST columns

scholarly journals Effect of MS Rings’ Confinement on Lateral Deformations of M 25 Grade Circular RCC Columns under Axial Compression Loads

2020 ◽  
Vol 9 (5) ◽  
pp. 221-223
Keyword(s):  
Mild Steel ◽  
Axial Compression ◽  
Experimental Work ◽  
Load Capacity ◽  
Compressive Load ◽  
Steel Tube ◽  
Lateral Deformation ◽  
Steel Pipes ◽  
Long Time ◽  
Cfst Columns

Confinement has been always a key concern area for researchers in present and in past also. The metal confinement of RCC columns has been extensively used from long time like concrete-filled steel tube (CFST) columns etc. In the present work mild steel rings have been used as confining material. In this paper based on experimental work, it is aimed to improve the axial compression strength and lateral deformation characteristics of circular RCC columns confined by mild steel (MS) rings. Total 45 nos. of specimen of size 150 mm dia. and 300 mm height were prepared during the experimental work. These specimen were tested and results were analyzed.These MS rings confined circular RCC columns of M 25 grade concrete were experimentally studied for different variables like (i) % of column main vertical steel bars (ii) thickness of MS rings (iii) spacing of MS rings. It was found that the MS ring confinement effectively helped in reducing lateral deformation of circular RCC column specimen resulting in improved axial compressive load capacity of circular RCC columns also. As MS rings are made up of conventional material i.e. mild steel pipes, the technique has a vast application area. In rural part of India this technique can be conviniently used for the efficient confinement of RCC columns.

scholarly journals Axial behaviour of concrete filled steel tube stub columns: a review

2018 ◽  
Author(s):  
Soner Güler ◽  
Fuat Korkut ◽  
Namik Yaltay ◽  
Demet Yavuz
Keyword(s):  
Cross Section ◽  
Axial Load ◽  
Load Capacity ◽  
Local Buckling ◽  
Bending Moment ◽  
Steel Tube ◽  
High Rise ◽  
Axial Load Capacity ◽  
The Cross ◽  
Cfst Columns

Concrete-filled steel tubular (CFST) columns are widely used in construction of high-rise buildings and peers of bridges to increase the lateral stiffness of the buildings, the axial load capacity, ductility, toughness, and resistance of corrosion of the columns. The CFST columns have much superior characteristics compared with traditionally reinforced concrete columns. The position of the concrete and steel tube in the cross-section of the CFST column is the most appropriate solution in terms of the strength and ductility. The steel tube, which is placed outside of the cross-section of the column, withstand the bending moment effectively. The concrete that is placed into the steel tube delay the local buckling of the steel tube and increase the axial load capacity of the column due to continually lateral confining. This paper presents a review on experimental results of the axial behavior of CFST columns performed by various researchers.

scholarly journals COVID-19 Pandemic Prediction for Hungary; a Hybrid Machine Learning Approach

2020 ◽  
Author(s):  
Gergo Pinter ◽  
Imre Felde ◽  
Amir Mosavi ◽  
Pedram Ghamisi ◽  
Richard Gloaguen
Keyword(s):  
Machine Learning ◽  
Prediction Models ◽  
Future Research ◽  
Complex Nature ◽  
Learning Approach ◽  
Epidemiological Models ◽  
Inference System ◽  
Proper Actions ◽  
Machine Learning Approach ◽  
Hybrid Machine

AbstractSeveral epidemiological models are being used around the world to project the number of infected individuals and the mortality rates of the COVID-19 outbreak. Advancing accurate prediction models is of utmost importance to take proper actions. Due to a high level of uncertainty or even lack of essential data, the standard epidemiological models have been challenged regarding the delivery of higher accuracy for long-term prediction. As an alternative to the susceptible-infected-resistant (SIR)-based models, this study proposes a hybrid machine learning approach to predict the COVID-19 and we exemplify its potential using data from Hungary. The hybrid machine learning methods of adaptive network-based fuzzy inference system (ANFIS) and multi-layered perceptron-imperialist competitive algorithm (MLP-ICA) are used to predict time series of infected individuals and mortality rate. The models predict that by late May, the outbreak and the total morality will drop substantially. The validation is performed for nine days with promising results, which confirms the model accuracy. It is expected that the model maintains its accuracy as long as no significant interruption occurs. Based on the results reported here, and due to the complex nature of the COVID-19 outbreak and variation in its behavior from nation-to-nation, this study suggests machine learning as an effective tool to model the outbreak. This paper provides an initial benchmarking to demonstrate the potential of machine learning for future research.

Sign in / Sign up

Export Citation Format

Share Document