Lightweight Design of Axle Bridge Based on Kriging Model with Optimal Regression.

Saved in:

Bibliographic Details
Title:	Lightweight Design of Axle Bridge Based on Kriging Model with Optimal Regression.
Authors:	Li, Xiaoke¹ lixiaoke@zzuli.edu.cn, Du, Haiyang¹ 332404040388@zzuli.edu.cn, Jiang, Qianlong² JQL0259@163.com, Ma, Jun¹ majun@zzuli.edu.cn, Ming, Wuyi¹ mingwuyi@gmail.com, Zhu, Heng³ zhuheng@ybsteer.com
Source:	IAENG International Journal of Computer Science. May2026, Vol. 53 Issue 5, p1605-1614. 10p.
Subjects:	Genetic algorithms, Structural optimization, Regression analysis, Design techniques, Fatigue life, Bridge design & construction, Response surfaces (Statistics)
Abstract:	In this paper, a lightweight design method of axle bridge based on Kriging model and genetic algorithm (GA) is proposed. Firstly, 21⁴ samples by full factorial design were selected as the candidate sample library. Then 100 samples were randomly selected as the initial population. Secondly, ANASYS APDL was used to establish the parametric model of axle bridge, which was called to obtain performance responses (including the stress, deformation, and fatigue life) at the initial population. Then the Kriging model was constructed to replace the implicit relationship between the structural parameters and performance responses of axle bridge. To ensure the modeling accuracy, the optimal regression function in Kriging was determined through the correlation coefficient R² and leave one out cross validation (LOOCV). Through selection, crossover and mutation, the optimal individual in each iteration was obtained, and the error between the real value and prediction value by Kriging was calculated. The individual with error larger than the threshold was selected as sequential sample to update the Kriging model. Finally, the optimal axle bridge parameters were obtained. Under the constraints of stress, deformation, and fatigue life, the mass of the axle bridge at the optimal parameters is reduced by 106.5Kg and the mass reduction ratio reaches 22.66%. Therefore, the proposed lightweight method is an effective method to ensure the performance of the axle bridge and reduce the production cost. [ABSTRACT FROM AUTHOR]
	Copyright of IAENG International Journal of Computer Science is the property of International Association of Engineers (IAENG) and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	In this paper, a lightweight design method of axle bridge based on Kriging model and genetic algorithm (GA) is proposed. Firstly, 21⁴ samples by full factorial design were selected as the candidate sample library. Then 100 samples were randomly selected as the initial population. Secondly, ANASYS APDL was used to establish the parametric model of axle bridge, which was called to obtain performance responses (including the stress, deformation, and fatigue life) at the initial population. Then the Kriging model was constructed to replace the implicit relationship between the structural parameters and performance responses of axle bridge. To ensure the modeling accuracy, the optimal regression function in Kriging was determined through the correlation coefficient R² and leave one out cross validation (LOOCV). Through selection, crossover and mutation, the optimal individual in each iteration was obtained, and the error between the real value and prediction value by Kriging was calculated. The individual with error larger than the threshold was selected as sequential sample to update the Kriging model. Finally, the optimal axle bridge parameters were obtained. Under the constraints of stress, deformation, and fatigue life, the mass of the axle bridge at the optimal parameters is reduced by 106.5Kg and the mass reduction ratio reaches 22.66%. Therefore, the proposed lightweight method is an effective method to ensure the performance of the axle bridge and reduce the production cost. [ABSTRACT FROM AUTHOR]
ISSN:	1819656X