Analysis and Prediction of Railway Infrastructure Deformation Monitoring Data Based on Fractional Order Statistical Theory

Abstract

The deformation monitoring system of railway infrastructure comes with many non-Gaussian behaviors. These behaviors are the typical fractional order characteristics which are hard to analyze by traditional methods. This paper presents a detail fractional order statistical theory to capture the key deformation feature and further achieve active warning of railway infrastructure. Initially, $\alpha $ -stable distribution is applied to reveal the non-Gaussian features hidden in the monitored time series. Then, long-range correlation and multifractal properties are extracted by the fractional order statistical method. After that, a novel fractional Bi-long short term memory model (F-BiLSTM) capture long-term trends characteristic and simulate stochastic process of the monitoring system. The proposed method is used to predict the deformation of railway infrastructure and obtained the superior prediction performances.

Keywords

• Railway infrastructure
• deformation analysis
• fractional order theory
• long-range correlation
• BiLSTM model