Ultrahigh prediction method for track irregularity based on random oscillation sequence grey model

Abstract

The invention discloses an ultrahigh prediction method for track irregularity based on a random oscillation sequence grey model. The method comprises the following steps: a data preprocessing step: averaging detected height deviations of a left track surface and a right track surface to obtain an equal-interval average height deviation sequence; a preliminary prediction step: performing random oscillation sequence grey prediction based on the grey model to obtain a preliminary prediction height deviation; a prediction correction step: correcting the preliminary prediction height residual error based on the height residual error average value to obtain a corrected height residual error, and performing normalization processing; an Elman neural network optimization step: optimizing an initial weight and a threshold value of the Elman neural network through an ant lion algorithm so as to obtain an optimized Elman neural network; and an ultra-high prediction step: obtaining an orbit prediction correction height residual error based on the optimized Elman neural network. According to the method, the random oscillation sequence grey model and the Elman neural network are combined, so that the defect that a random oscillation sequence prediction result is not ideal is overcome, and an ultrahigh prediction result is more accurate.

Description

technical field [0001] The invention relates to the field of track detection, in particular to a method for superelevation prediction of track irregularity based on a random oscillation sequence gray model. Background technique [0002] The detection of the safety status of urban rail transit operation is an important part of ensuring rail operation. The existing methods can dynamically and accurately detect the parameters of the rail. However, how to analyze and predict the quality of the rail from the data detected on the rail? Detection research is critical. [0003] Most of the current research is on the prediction of track comprehensive quality TQI. According to the experimental results, the combination method of gray prediction and neural network is more accurate in its prediction; [0004] Super high is different from TQI, it is a random oscillation sequence, but the traditional gray prediction is only suitable for exponential growth data types, it is not good for ra...

AI Technical Summary

Problems solved by technology

[0004] Super high is different from TQI, it is a random oscillation sequence, but the traditional gray prediction is only suitable for exponential growth data types, it is not good for random oscillation sequence prediction, and cannot fit the change trend of the sequence, which leads to the random oscillation sequence Large error in prediction results

Images