Metaheuristic least squares support vector machine-based lateral strength modelling of reinforced concrete columns subjected to earthquake loads

Состояние проблемы. Железобетонные элементы изготавливаются, как правило, по трем основным технологиям - вибрированием, центрифугированием и виброцентрифугированием. Однако все основные расчетные зависимости для определения их несущей способности выведены, исходя из основного постулата - постоянства и равенства характеристик бетона по сечению, что реализуется лишь в вибрированных колоннах. Результаты. В рамках диаграммного подхода предложены итерационный, приближенный и упрощенный способы расчета несущей способности железобетонных вибрированных, центрифугированных и виброцентрифугированных колонн. Выводы. Расчет по диаграммному подходу показал существенно более подходящую сходимость с опытными данными, чем расчет по методике норм, а также дал лучшие результаты при использовании дифференциальных характеристик бетона, чем при использовании интегральных и, тем более, нормативных характеристик бетона. Statement of the problem. Reinforced concrete elements are typically manufactured according to three basic technologies - vibration, centrifugation and vibrocentrifugation. However, all the basic calculated dependencies for determining their bearing capacity were derived using the main postulate, i.e., the constancy and equality of the characteristics of concrete over the cross section, which is implemented only in vibrated columns. Results. Within the framework of the diagrammatic approach, iterative, approximate and simplified methods of calculating the bearing capacity of reinforced concrete vibrated, centrifuged and vibrocentrifuged columns are proposed. Conclusions. The calculation according to the diagrammatic approach showed a significantly better convergence with the experimental data than that using the method of norms, and also performs better when using differential characteristics of concrete than when employing integral and particularly standard characteristics of concrete.

Download Full-text

Q-learning System Based on Cooperative Least Squares Support Vector Machine

ACTA AUTOMATICA SINICA ◽

10.3724/sp.j.1004.2009.00214 ◽

2009 ◽

Vol 35 (2) ◽

pp. 214-219 ◽

Cited By ~ 3

Author(s):

Xue-Song WANG ◽

Xi-Lan TIAN ◽

Yu-Hu CHENG ◽

Jian-Qiang YI

Keyword(s):

Support Vector Machine ◽

Least Squares ◽

Learning System ◽

Support Vector ◽

Q Learning

Download Full-text

Experimental Study on the Effect of Moisture Content on Hysteretic Behavior of Reinforced Concrete Columns

The Open Civil Engineering Journal ◽

10.2174/1874149501812010047 ◽

2018 ◽

Vol 12 (1) ◽

pp. 47-61

Author(s):

Wenjuan Lv ◽

Baodong Liu ◽

Ming Li ◽

Lin Li ◽

Pengyuan Zhang

Keyword(s):

Reinforced Concrete ◽

Energy Dissipation ◽

Moisture Content ◽

Early Stage ◽

Damping Ratio ◽

Concrete Columns ◽

Hysteretic Behavior ◽

Cyclic Test ◽

Experimental Result ◽

Reinforced Concrete Columns

Background: For reinforced concrete structures under different humid conditions, the mechanical properties of concrete are significantly affected by the moisture content, which may result in a great change of the functional performance and bearing capacity. Objective: This paper presents an experiment to investigate the influence of the moisture content on the dynamic characteristics and hysteretic behavior of reinforced concrete column. Results: The results show that the natural frequency of reinforced concrete columns increases quickly at an early stage of immersion, but there is little change when the columns are close to saturation; the difference between the natural frequencies before and after cyclic test grows as the moisture content rises. The damping ratio slightly decreases first and then increases with the increase of moisture content; the damping ratio after the cyclic test is larger than before the test due to the development of the micro-cracks. Conclusion: The trend of energy dissipation is on the rise with increasing moisture content, although at an early stage, it decreases slightly. According to the experimental result, a formula for the moisture content on the average energy dissipation of reinforced concrete columns is proposed.

Download Full-text

Predicting Ink Transfer Rate of 3D Additive Printing Using EGBO Optimized Least Squares Support Vector Machine Model

Mathematical Problems in Engineering ◽

10.1155/2020/8642430 ◽

2020 ◽

Vol 2020 ◽

pp. 1-12

Author(s):

Shengpu Li ◽

Yize Sun

Keyword(s):

Support Vector Machine ◽

Prediction Model ◽

Least Squares ◽

Transfer Rate ◽

Coefficient Of Determination ◽

Percentage Error ◽

Support Vector ◽

Experimental Sample ◽

Machine Model ◽

Ink Transfer

Ink transfer rate (ITR) is a reference index to measure the quality of 3D additive printing. In this study, an ink transfer rate prediction model is proposed by applying the least squares support vector machine (LSSVM). In addition, enhanced garden balsam optimization (EGBO) is used for selection and optimization of hyperparameters that are embedded in the LSSVM model. 102 sets of experimental sample data have been collected from the production line to train and test the hybrid prediction model. Experimental results show that the coefficient of determination (R2) for the introduced model is equal to 0.8476, the root-mean-square error (RMSE) is 6.6 × 10 (−3), and the mean absolute percentage error (MAPE) is 1.6502 × 10 (−3) for the ink transfer rate of 3D additive printing.

Download Full-text