A self-adaptive decomposition prediction method of wind speed along high-speed railway with strong wind

Abstract

The invention provides a wind speed adaptive decomposition prediction method along a strong wind high speed railway; the method comprises the following steps: 1, setting auxiliary wind measurement stations; 2, filtering wind speed data; 3, decomposing filter each group of data; 4, filtering each group of decomposed data; 5, carrying out signal reconstruction for each group of filtered IMF components and R components; 6, selecting m auxiliary wind measurement stations with high association with a target wind measurement station in the present period; 7, building a CS optimized wavelet nerve network model; 8, inputting wind speed values measured by m auxiliary wind measurement stations into the trained model, thus obtaining the wind speed predicted value of the target wind measurement station. The wind speed adaptive decomposition prediction method along the strong wind high speed railway can predict the wind speed along the railway with high precision under various landforms and weather conditions, thus effectively prediction errors and prediction interruptions caused by hardware faults of a single wind measurement station.

Description

technical field [0001] The invention belongs to the field of railway wind speed prediction, in particular to an adaptive decomposition prediction method for wind speed along a strong wind high-speed railway. Background technique [0002] my country has a vast territory and a long coastline, and strong winds often occur in many areas. Wind power is a precious resource. However, strong winds will deteriorate the aerodynamic performance and lateral stability of trains, making trains prone to derailment, overturning and other accidents. Train safety accidents caused by strong winds have occurred in all countries in the world. In order to prevent these accidents, many scholars have carried out various researches. Among them, since the dispatching command of the railway department must be accurate and advanced, the wind speed prediction along the railway line has become one of the core research contents. [0003] Wind speed is affected by various factors and has strong randomnes...

AI Technical Summary

Problems solved by technology

At present, the wind speed prediction methods along the railway line are mostly based on the wind speed data of a single anemometer station, no matter in a specific section or in a common section. The sampling signal is single, and the anti-interference is poor. It is impossible to avoid prediction errors and prediction interruptions caused by the hardware failure of a single anemometer station.

The existing wind speed prediction methods based on spatial correlation are mostly aimed at large-scale wind farms, and the locations of wind measuring stations are far apart, so the prediction accuracy is not high; or the short-term prediction accuracy is not high because of large time scale analysis; or The flow field analysis method is used, and the calculation time is long; it is difficult to fully meet the requirements of railway dispatching and commanding

Images