A method for testing the technical conditions of bridges

Abstract

The invention provides a method for predicting the technical condition of a bridge, which mainly comprises the following steps: (1) obtaining the distribution law of the technical condition of the bridge through on-site investigation, data collection and data analysis; 2) according to that distribution rule, finding the correspond bridge, determining the influencing factors of the bridge technicalcondition and calculating and generating the eigenvector of the prediction model; (3) according to the influencing factors and influence degree parameters, the construction, training and reliabilityanalysis of the bridge technical condition prediction model based on the long-term and short-term memory cycle depth network being carried out; (4) inputting the bridge data into the model establishedin the step (3) for calculation, and obtaining the prediction result of the bridge technical condition. Through the use of long-term and short-term memory depth network, the bridge technical status prediction model which can automatically revise the weight of influencing factors is constructed to solve the problem of inaccurate prediction results caused by the indeterminacy of influencing factorsand influencing degree parameters in the current bridge technical status prediction method.

Description

technical field [0001] The invention belongs to the field of bridge structure safety performance testing, and relates to a bridge technical condition testing method and a testing system, in particular to an LSTM RNN-based bridge technical condition testing method and a testing system. Background technique [0002] my country's highway and bridge construction is in the stage of large-scale construction, and will soon enter the stage of paying equal attention to bridge construction and maintenance. At present, the maintenance of bridges in our country belongs to passive maintenance, that is, only the bridges with discovered diseases or degraded technical conditions are repaired. In the current situation of insufficient maintenance funds, passive maintenance, low utilization rate of maintenance resources, simple maintenance measures, and low maintenance level. According to the relevant provisions of the "Technical Condition Evaluation Standards for Highway Bridges" (JTG / T H21)...

AI Technical Summary

Problems solved by technology

However, it is difficult to accurately define the influencing factors and weights of supervised forecasting model methods based on artificial neural networks, and the accuracy of weights directly affects the degree of deviation of the algorithm's forecast results.

Images