Large-span bridge vibration response prediction method under typhoon action based on data driving

Abstract

The invention discloses a large-span bridge vibration response prediction method under typhoon action based on data driving. The large-span bridge vibration response prediction method comprises the following steps: S1, calculating a plurality of typhoon characteristic parameters, and extracting bridge vibration response caused by typhoon from bridge vibration response monitoring data; S2, dividingthe typhoon characteristic parameters and the bridge vibration response caused by the typhoon into a training set and a test set; S3, inputting the training set into a quantile random forest (QRF), obtaining an optimal hyper-parameter of the QRF by adopting a Bayesian optimization algorithm, comparing the importance of each parameter of typhoon characteristics by combining the optimal QRF, and determining a final input characteristic; and S4, inputting the corresponding typhoon characteristic parameters in the test set into the QRF according to an input characteristic comparison result, and taking an output value as a typhoon-induced response probability prediction value. For the large-span bridge vibration response prediction method, the accuracy and efficiency of the prediction result are obviously higher than those of other parameter optimization methods or finite element model methods, and the uncertainty of the prediction process can be considered.

Description

Technical field: [0001] The invention relates to the field of bridge wind engineering, combines machine learning and Bayesian optimization methods, and based on data-driven probabilistic prediction of the vibration response of long-span bridges under the action of typhoons, specifically relates to data-driven prediction of the vibration response of long-span bridges under the action of typhoons method. Background technique: [0002] The softness of long-span bridges makes their sensitivity to wind loads increase sharply, and the vibration response of bridges under strong / typhoon action is becoming more and more prominent, which may cause strength or fatigue damage of bridge components. There are mainly four methods for studying bridge wind vibration problems: theoretical analysis, wind tunnel experiment, numerical simulation and field measurement. After decades of development, wind tunnel experiments, theoretical analysis, and numerical calculations can be used to study bri...

AI Technical Summary

Problems solved by technology

However, the research of machine learning methods in the field of bridge wind engineering is still in its infancy, so there is an urgent need for machine learning algorithms to study the structural response under typhoon from a data-driven perspective and improve the accuracy of prediction results

Images