Research on prediction method of cable tower pre-bias based on model fusion

Hao Zhu; Yao Xiao; Yong Wei Wang; Yi Guang Yang

doi:10.1117/12.2661049

16 December 2022 Research on prediction method of cable tower pre-bias based on model fusion

Hao Zhu, Yao Xiao, Yong Wei Wang, Yi Guang Yang

Proceedings Volume 12500, Fifth International Conference on Mechatronics and Computer Technology Engineering (MCTE 2022); 125003U (2022) https://doi.org/10.1117/12.2661049
Event: 5th International Conference on Mechatronics and Computer Technology Engineering (MCTE 2022), 2022, Chongqing, China

Abstract

Traditional construction monitoring is labor-intensive and faces the problems of lengthy calculation cycles and high experience requirements. Oriented by data-driven, a method for pre-bias prediction of cable towers based on model fusion is proposed. First, collect and build an experimental data set containing 125 samples. After data preprocessing, establish SVR and KNN models with initial parameters. And conduct model evaluation after cross-validation and hyperparameter optimization. Second, utilize the mean absolute error (MAE) to define the loss function of the fusion model, and obtain the fusion weight of the weak learner. The weighted average method is used to fuse the SVR and KNN models. The deep integration of SVR and KNN is realized at the model decision level, which further improves the model fitting performance and the reliability of the prediction results. Finally, the performance of each model is evaluated based on the proposed comprehensive evaluation index. The experimental results demonstrate that the SVR and KNN models perform well on tasks with small sample sizes, and the fusion model has an MAE of 1.361, MAPE of 0.149, RMSE of 2.08, and 2 R of 0.997 on the test set. The research method and content have greatly improved the precision and efficiency of the pre-bias control of the tower. Which can be used to improve and extend the existing finite element analysis method.

Citation Download Citation

Hao Zhu, Yao Xiao, Yong Wei Wang, and Yi Guang Yang "Research on prediction method of cable tower pre-bias based on model fusion", Proc. SPIE 12500, Fifth International Conference on Mechatronics and Computer Technology Engineering (MCTE 2022), 125003U (16 December 2022); https://doi.org/10.1117/12.2661049

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available