Bridge Monitoring Data Prediction Based on LightGBM Transformer Model

Le résumé fourni par la source

Data prediction is crucial for the accuracy of analysis results in the field of bridge monitoring. Traditional methods have difficulty in fully structuring features to process data. This paper proposes a data prediction method that combines deep learning and LightGBM algorithm, focusing on the prediction of deflection data of Honglian Bridge as the research object in order to improve the accuracy of prediction. The experimental results show that the LightGBM Transformer model has significantly improved prediction accuracy, with root mean square error and mean absolute error reduced to 0.0610 and 0.0504, compared with using the Transformer model alone. The low level of error in the prediction of bridge deflection data indicates its high application value and competitiveness in the field of bridge monitoring. This study validates the effectiveness of the LightGBM Transformer model in predicting bridge deflection data, demonstrating its successful application with excellent results.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.