Method for predicting short-term icing thickness of stay cable based on GA-WOA-GRNN network

Abstract

A method for predicting the short-term icing thickness of a stay cable based on a GA-WOA-GRNN network comprises the following steps: 1, according to the growth rule of stay cable icing, selecting influence factors with relatively large correlation of stay cable icing, and determining a training set and a test set of sample data; 2, normalizing sample data; 3, dividing the normalized data into a plurality of groups by using a cross validation method, taking each group of data as an input sample of a GRNN prediction model, taking a corresponding icing thickness value as an output value of the model, and constructing a GRNN model training sample matrix; 4, optimizing a smooth factor sigma of a GRNN network algorithm by using a GA-WOA optimization algorithm, and taking a mean square error between an output value of a training sample and an actual value as a fitness function to obtain a minimum error prediction model; and predicting the short-term icing thickness of the stay cable through the steps.

Description

Technical field[0001]The present invention relates to bridge structural disaster prevention and mitigation and safety early warning areas, and specific relatives of cable-covered thickness predictions.Background technique[0002]It is an important bridge type of large span bridge with the bridge. Under the water temperature of winter wet, the surface of the winter kerly is very easy to have ice, induce disasters in different modes. Firstly, the ice will change the shape of the cable cross section, form an unstable aerodynamic shape, resulting in a large amplitude of the zealic phenomenon, which causes cracking of the outer PE tube of the cable, resulting in rust damage of the squash and the anchor system, The performance and safety of the bridge structure. Second, when the ice is treated with temperature changes or structural vibrations, ice-falling phenomenon occurs, seriously threatening the safety of bridged vehicles and pedestrians.[0003]At present, for the wintering prediction of...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to establish a short-term icing prediction model for cable-stayed cables with high prediction accuracy and strong generalization ability, to provide support for early warning and other decision-making for cable-stayed cable anti-icing and disaster reduction work, to solve the problem of existing cable-stayed cables In winter icing prediction, it is necessary to rely on a large number of samples and cannot accurately predict the technical problems of short-term icing; the invention can also solve the problem that the genetic algorithm is complex and the whale algorithm is easy to fall into local optimum, greatly improving the calculation speed and actual processing speed

Images