<abstract xmlns="http://www.w3.org/1999/xhtml">
<p>Bridge joint bearing capacity analysis is difficult to fit the requirements of the era of big data. The traditional way of bridge-bearing capacity numerical analysis exists in the wave of digital development of big data information, the Internet of Things, and artificial intelligence technology like a wild development. The traditional way of under the problem: is efficiency, engineering analysis is not accurate, data information paper, work responsibility is not in place, technical equipment, etc. This paper revolves around the numerical simulation analysis of the load-bearing capacity at the joints of symmetrical cantilever-assembled bridges based on the logistic regression model by finding literature to understand the concept and algorithm of the logistic regression model, construct logistic regression model based on dichotomous dependent variable logistic regression algorithm, logistic regression model parameter estimation, logistic regression. The three aspects of the model evaluation index are studied. The numerical simulation analysis of the load-bearing capacity at the symmetrical cantilever joint based on the logistic regression model, the shear strength calculation at the bridge joint, and the bridge longitudinal bar slip deformation are calculated, respectively, and then the actual value of the bridge load bearing capacity is derived. Simulation in the bridge bearing capacity at 0kN, 5kN, 10kN, 15kN, 20kN, 25kN, and 30kN, the model algorithm evaluation index under the three indicators of prediction rate, accuracy, deviation of the verification analysis. The results show that the prediction rate of the logistic regression model algorithm based on the load carrying capacity up to 30kN is 84%, the accuracy rate is 94%, and the deviation is 11%, and the three index values have better performance compared with the one-dimensional linear regression model algorithm and the multiple linear regression model algorithms. This study is beneficial to extend the bridge structural analysis function and make the bridge load capacity assessment more automatic; it can facilitate the comparison of historical data of bridge tests, longitudinal change of indicators at different testing time points, and grasp the current situation and change trend of bridges. Thus it is of great historical significance to the development of the Chinese bridge infrastructure industry.</p>
</abstract>

Bridge joint bearing capacity analysis is difficult to fit the requirements of the era of big data. The traditional way of bridge-bearing capacity numerical analysis exists in the wave of digital development of big data information, the Internet of Things, and artificial intelligence technology like a wild development. The traditional way of under the problem: is efficiency, engineering analysis is not accurate, data information paper, work responsibility is not in place, technical equipment, etc. This paper revolves around the numerical simulation analysis of the load-bearing capacity at the joints of symmetrical cantilever-assembled bridges based on the logistic regression model by finding literature to understand the concept and algorithm of the logistic regression model, construct logistic regression model based on dichotomous dependent variable logistic regression algorithm, logistic regression model parameter estimation, logistic regression. The three aspects of the model evaluation index are studied. The numerical simulation analysis of the load-bearing capacity at the symmetrical cantilever joint based on the logistic regression model, the shear strength calculation at the bridge joint, and the bridge longitudinal bar slip deformation are calculated, respectively, and then the actual value of the bridge load bearing capacity is derived. Simulation in the bridge bearing capacity at 0kN, 5kN, 10kN, 15kN, 20kN, 25kN, and 30kN, the model algorithm evaluation index under the three indicators of prediction rate, accuracy, deviation of the verification analysis. The results show that the prediction rate of the logistic regression model algorithm based on the load carrying capacity up to 30kN is 84%, the accuracy rate is 94%, and the deviation is 11%, and the three index values have better performance compared with the one-dimensional linear regression model algorithm and the multiple linear regression model algorithms. This study is beneficial to extend the bridge structural analysis function and make the bridge load capacity assessment more automatic; it can facilitate the comparison of historical data of bridge tests, longitudinal change of indicators at different testing time points, and grasp the current situation and change trend of bridges. Thus it is of great historical significance to the development of the Chinese bridge infrastructure industry.

Numerical simulation analysis of load-bearing capacity at joints of symmetrical cantilever-assembled bridges based on the logistic regression model

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

Bridge joint bearing capacity analysis is difficult to fit the requirements of the era of big data. The traditional way of bridge-bearing capacity numerical...

Numerical simulation analysis of load-bearing capacity at joints of symmetrical cantilever-assembled bridges based on the logistic regression model

Online veröffentlicht: 09. Aug. 2023

Seitenbereich: -

Eingereicht: 04. Okt. 2022

Akzeptiert: 17. Feb. 2023

DOI: https://doi.org/10.2478/amns.2023.2.00160

Schlüsselwörter
Big data, Logistic model algorithm, Evaluation index, Bridge load bearing capacity, Simulation analysis

© 2023 Xiaochuan Cao et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Numerical simulation analysis of load-bearing capacity at joints of symmetrical cantilever-assembled bridges based on the logistic regression model

Online veröffentlicht: 09. Aug. 2023

Seitenbereich: -

Eingereicht: 04. Okt. 2022

Akzeptiert: 17. Feb. 2023

DOI: https://doi.org/10.2478/amns.2023.2.00160

SchlüsselwörterBig data, Logistic model algorithm, Evaluation index, Bridge load bearing capacity, Simulation analysis

© 2023 Xiaochuan Cao et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Schlüsselwörter
Big data, Logistic model algorithm, Evaluation index, Bridge load bearing capacity, Simulation analysis