Strain Prediction of Bridge SHM Based on CEEMDAN-ARIMA Model

Abstract

Abstract In this paper, a model based on CEEMDAN-ARIMA is proposed to predict the strain monitoring data for bridge SHM. In view of the problem that the classical time series theory cannot predict the modal overlap-ping data effectively, the CEEMDAN method was used to decompose the strain monitoring data for the bridge SHM. To deal with the large number of components after using CEEMDAN, the PE method (permutation entropy) was used to generate a series of new data sequences according to the degree of randomness. Finally, each new data sequence was predicted and the final prediction is obtained by ARIMA model. The method was used to predict the SHM strain data of a cable-stayed bridge in Shanghai. The results show that the proposed combination method is more accurate than the classical time series theory and is promising for engineering applications.