A Prediction Method of Bridge Structure Safety Monitoring Data

Abstract

The invention relates to a bridge structure safety monitoring data prediction method, and belongs to the technical field of bridge health monitoring. The method includes the following steps that (1) bridge monitoring data are selected to serve as an object to be analyzed, and the future development trend of the object to be analyzed is predicted; (2) sample data of the bridge monitoring data are selected, an auto regressive moving average (ARMA) is trained through the sample data, and the monitoring variable value of the next moment is predicted through the ARMA; (3) a least squares support vector machine (LS-SVM) is trained through the sample data, and the monitoring variable value of the next moment is predicted through the LS-SVM; (4) the prediction result of the ARMA and the prediction result of the LS-SVM serve as input samples, the fuzzy membership degree is given to the input samples, a least squares fuzzy support vector machine (LS-FSVM) is trained, the monitoring variable value of the next moment is predicted through the LS-FSVM, and the value is the final prediction result of the method. By means of the bridge structure safety monitoring data prediction method, on-line, real-time prediction can be conducted on bridge structure safety monitoring information, and the error is smaller and the accuracy is higher compared with a traditional method.

Description

Technical field [0001] The invention belongs to the technical field of bridge health monitoring, and relates to a method for predicting bridge structure safety monitoring data, in particular to a method for predicting bridge structure safety monitoring data based on an autoregressive moving average model-based quadratic fuzzy least squares support vector machine. Background technique [0002] The construction and maintenance of bridges is an important part of a country's infrastructure and plays an important role in the country's construction and people's lives. In recent years, with the rapid development of bridge construction, the forms and functions of bridge structures have become increasingly complex, and the scale of projects has become larger and larger. However, bridge safety accidents have occurred from time to time, and the potential safety hazards of bridge structures are widespread. In the United States, about 575,000 bridges are inspected at least once every two year...

AI Technical Summary

Problems solved by technology

However, despite the continuous progress of modern technical means, the signals obtained by long-term monitoring often contain the joint effects of various factors, random and sudden interference sources are more and more complex, making accurate signal prediction is still not easy work

Images