Method for predicting wind speed along railway through integrating actual measurement data of multiple wind measurement stations

Abstract

The invention discloses a method for predicting the wind speed along a railway through integrating the actual measurement data of multiple wind measurement stations, and the method comprises the following steps: 1, installing auxiliary wind measurement stations at the position of a target wind measurement station, and collecting the wind speed data; 2, carrying out the filtering processing of a wind speed data sample; 3, removing high-frequency jump characteristics through two-layer wavelet decomposition, and extracting the low-frequency data of the last layer; 4, selecting the data of m auxiliary wind measurement stations with the higher significance with the data of the target wind measurement station; 5, carrying out the two-layer wavelet decomposition of the low-frequency data layers of the target wind measurement station and the selected m auxiliary wind measurement stations; 6, training a PSO-MLP neural network model; 7, inputting the actual measurement wind speed values measured by the m auxiliary wind measurement stations into a prediction model, and obtaining a wind speed prediction value of the target wind measurement station. The method provided by the invention can effectively improve the prediction precision of the wind speed along the railway, guarantees the stability of the prediction model, and can avoid prediction interruption caused by a single-wind-measurement-station sensor hardware fault.

Description

technical field [0001] The invention belongs to the field of railway wind speed prediction, in particular to a wind speed prediction method along a railway that integrates measured data from multiple wind measuring stations. Background technique [0002] Wind seriously affects the safety and stability of train operation, and it is easy to cause train safety accidents, which brings challenges to the safe operation of railways and causes huge economic losses and casualties to countries all over the world. To this end, some countries have established railway strong wind monitoring and early warning systems. This type of system usually includes wind speed and direction information, road conditions along the railway, train information, etc. When the wind speed in a section exceeds a certain limit, the system will issue a speed limit or shutdown order. Since the command and dispatch of the railway needs to be forward-looking and accurate, high-precision wind speed prediction is o...

AI Technical Summary

Problems solved by technology

The real-time performance of these two methods is poor, and it is difficult to meet the requirements of wind speed prediction along the railway

Images