New fundamental period formulae for soil-reinforced concrete structures interaction using machine learning algorithms and ANNs

2021 ◽  
Vol 144 ◽  
pp. 106656
Author(s):  
Dewald Z. Gravett ◽  
Christos Mourlas ◽  
Vicky-Lee Taljaard ◽  
Nikolaos Bakas ◽  
George Markou ◽  
...  
Keyword(s):  
Machine Learning ◽  
Reinforced Concrete ◽  
Learning Algorithms ◽  
Concrete Structures ◽  
Machine Learning Algorithms ◽  
Fundamental Period ◽  
Reinforced Concrete Structures

scholarly journals Research on Engineering Geomechanics Characteristics and CFRP Reinforcement Technology Based on Machine Learning Algorithms

2022 ◽  
Vol 2022 ◽  
pp. 1-12
Author(s):  
Baoqi Yan ◽  
Nuoya Zhang ◽  
Ganggang Lu ◽  
Yue Hui
Keyword(s):  
Machine Learning ◽  
Reinforced Concrete ◽  
Monitoring System ◽  
Condition Monitoring ◽  
Learning Algorithms ◽  
Experimental Studies ◽  
Machine Learning Algorithms ◽  
Natural Exposure ◽  
Condition Monitoring System

We have completed the design of an early warning and evaluation analysis module based on machine learning algorithms. Aiming at the prestressed CFRP-strengthened reinforced concrete bridges under natural exposure, we developed a theoretical model to analyze the long-term prestress loss of reinforced parts and the adhesion behavior of the CFRP-concrete interface under natural exposure conditions. The analysis deeply reveals the technical and engineering geomechanics characteristics of the D bridge. At the same time, through a series of experimental studies on the D bridge condition monitoring system, the data acquisition and transmission, processing and control of the D bridge condition monitoring system, and the bridge condition monitoring and evaluation software are provided. Regarding how to repair the engineering geomechanical characteristics of D bridge, we mentioned the prestressed CFRP reinforcement technology. The prestressed carbon fiber reinforced composite (CFRP) structure made of reinforced concrete (RC) makes better use of the high-strength characteristics of CFRP and changes. It strengthens the stress distribution of the components and improves the overall strength of the components. It is more supported by engineers in the civil engineering and transportation departments. However, most prestressed CFRP-reinforced RC structures are located in natural exposure environments, and the effect of natural exposure environments on the long-term mechanical properties of prestressed C FRP-reinforced RC components is still unclear. This article mainly uses the research on the engineering geomechanics characteristics and reinforcement technology of the bridge body, so that people have a deep understanding of its concept, and provides reasonable use methods and measures for the maintenance and protection of the bridge body in the future. This paper studies the characteristics of engineering geomechanics based on machine learning algorithms and applies them to the research of CFRP reinforcement technology, aiming to promote its better development.

Forecasting US movies box office performances in Turkey using machine learning algorithms

2020 ◽  
Vol 39 (5) ◽  
pp. 6579-6590
Author(s):  
Sandy Çağlıyor ◽  
Başar Öztayşi ◽  
Selime Sezgin
Keyword(s):  
Machine Learning ◽  
Global Economy ◽  
Learning Algorithms ◽  
Forecast Model ◽  
Machine Learning Algorithms ◽  
Gradient Boosting ◽  
High Stakes ◽  
Box Office ◽  
Industry Forecast ◽  
The Impact

The motion picture industry is one of the largest industries worldwide and has significant importance in the global economy. Considering the high stakes and high risks in the industry, forecast models and decision support systems are gaining importance. Several attempts have been made to estimate the theatrical performance of a movie before or at the early stages of its release. Nevertheless, these models are mostly used for predicting domestic performances and the industry still struggles to predict box office performances in overseas markets. In this study, the aim is to design a forecast model using different machine learning algorithms to estimate the theatrical success of US movies in Turkey. From various sources, a dataset of 1559 movies is constructed. Firstly, independent variables are grouped as pre-release, distributor type, and international distribution based on their characteristic. The number of attendances is discretized into three classes. Four popular machine learning algorithms, artificial neural networks, decision tree regression and gradient boosting tree and random forest are employed, and the impact of each group is observed by compared by the performance models. Then the number of target classes is increased into five and eight and results are compared with the previously developed models in the literature.

Intelligent system of English composition scoring model based on improved machine learning algorithm

2020 ◽  
pp. 1-11
Author(s):  
Jie Liu ◽  
Lin Lin ◽  
Xiufang Liang
Keyword(s):  
Machine Learning ◽  
Evaluation System ◽  
Intelligent System ◽  
Learning Algorithm ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Assessment System ◽  
English Composition ◽  
Region Extraction ◽  
Constraint Model

The online English teaching system has certain requirements for the intelligent scoring system, and the most difficult stage of intelligent scoring in the English test is to score the English composition through the intelligent model. In order to improve the intelligence of English composition scoring, based on machine learning algorithms, this study combines intelligent image recognition technology to improve machine learning algorithms, and proposes an improved MSER-based character candidate region extraction algorithm and a convolutional neural network-based pseudo-character region filtering algorithm. In addition, in order to verify whether the algorithm model proposed in this paper meets the requirements of the group text, that is, to verify the feasibility of the algorithm, the performance of the model proposed in this study is analyzed through design experiments. Moreover, the basic conditions for composition scoring are input into the model as a constraint model. The research results show that the algorithm proposed in this paper has a certain practical effect, and it can be applied to the English assessment system and the online assessment system of the homework evaluation system algorithm system.

The Unlearnable Checkerboard Pattern

2019 ◽  
Vol 1 (2) ◽  
pp. 78-80
Author(s):  
Eric Holloway
Keyword(s):  
Machine Learning ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Checkerboard Pattern ◽  
Simple Task

Detecting some patterns is a simple task for humans, but nearly impossible for current machine learning algorithms.  Here, the "checkerboard" pattern is examined, where human prediction nears 100% and machine prediction drops significantly below 50%.

Design of precast reinforced concrete structures of frame buildings: a new set of rules

2019 ◽  
pp. 4-9 ◽  
Keyword(s):  
Reinforced Concrete ◽  
Concrete Structures ◽  
Reinforced Concrete Structures ◽  
Building Frames ◽  
Fine Grained ◽  
Rigid Frame ◽  
Floor Slabs ◽  
Frame Buildings ◽  
Spatial System ◽  
Precast Elements

Currently, prefabricated reinforced concrete structures are widely used for the construction of buildings of various functional purposes. In this regard, has been developed SP 356.1325800.2017 "Frame Reinforced Concrete Prefabricated Structures of Multi-Storey Buildings. Design Rules", which establishes requirements for the calculation and design of precast reinforced concrete structures of frame buildings of heavy, fine-grained and lightweight structural concrete for buildings with a height of not more than 75 m. The structure of the set of rules consists of eight sections and one annex. The document reviewed covers the design of multi-story framed beam structural systems, the elements of which are connected in a spatial system with rigid (partially compliant) or hinged joints and concreting of the joints between the surfaces of the abutting precast elements. The classification of structural schemes of building frames, which according to the method of accommodation of horizontal loads are divided into bracing, rigid frame bracing and framework, is presented. The list of structural elements, such as foundations, columns, crossbars, ribbed and hollow floor slabs and coatings, stiffness elements and external enclosing structures is given; detailed instructions for their design are provided. The scope of the developed set of rules includes all natural and climatic zones of the Russian Federation, except seismic areas with 7 or more points, as well as permafrost zones.

Improvement Of Curvilinear Diagrams Of Concrete Deformation

2019 ◽  
pp. 99-104
Keyword(s):  
Reinforced Concrete ◽  
Peak Load ◽  
Experimental Studies ◽  
Concrete Structures ◽  
Deformation Model ◽  
Reinforced Concrete Structures ◽  
Significant Difference ◽  
Deformation Diagrams

Problems when calculating reinforced concrete structures based on the concrete deformation under compression diagram, which is presented both in Russian and foreign regulatory documents on the design of concrete and reinforced concrete structures are considered. The correctness of their compliance for all classes of concrete remains very approximate, especially a significant difference occurs when using Euronorm due to the different shape and sizes of the samples. At present, there are no methodical recommendations for determining the ultimate relative deformations of concrete under axial compression and the construction of curvilinear deformation diagrams, which leads to limited experimental data and, as a result, does not make it possible to enter more detailed ultimate strain values into domestic standards. The results of experimental studies to determine the ultimate relative deformations of concrete under compression for different classes of concrete, which allowed to make analytical dependences for the evaluation of the ultimate relative deformations and description of curvilinear deformation diagrams, are presented. The article discusses various options for using the deformation model to assess the stress-strain state of the structure, it is concluded that it is necessary to use not only the finite values of the ultimate deformations, but also their intermediate values. This requires reliable diagrams "s–e” for all classes of concrete. The difficulties of measuring deformations in concrete subjected to peak load, corresponding to the prismatic strength, as well as main cracks that appeared under conditions of long-term step loading are highlighted. Variants of more accurate measurements are proposed. Development and implementation of the new standard GOST "Concretes. Methods for determination of complete diagrams" on the basis of the developed method for obtaining complete diagrams of concrete deformation under compression for the evaluation of ultimate deformability of concrete under compression are necessary.

Sign in / Sign up

Export Citation Format

Share Document