Multipoint multilayer coupling prediction method for wind speed along high-speed railway

Abstract

The invention discloses a multipoint multilayer coupling prediction method for wind speed along a high-speed railway. The method comprises the steps that 1, five auxiliary wind-measuring stations are installed around a target wind-measuring station; 2, after original wind speed data is filtered and disintegrated, wavelet denoising is performed; 3, signals are summated and reconstructed; 4, m auxiliary wind-measuring stations with high significance relative to the target wind-measuring station are selected; 5, prediction models are established for all PF components of subsequences of all frequency layers of the selected auxiliary wind-measuring stations; 6, the PF components of all the frequency layers of the m selected auxiliary wind-measuring stations are used as input, PF components of all frequency layers of the target wind-measuring station are used as output, and a GA-optimized RBF neural network is adopted to perform training; and 7, ahead multistep predicted values of the m auxiliary wind-measuring stations are utilized to obtain an ahead multistep wind speed predicted value of the target wind-measuring station. Through the method, the wind speed along the railway can be subjected to high-precision ahead multistep prediction to be used for effectively dispatching and commanding a train in a strong wind environment of the high-speed railway, and data interruption caused by a hardware fault of a single wind-measuring station can be avoided.

Description

technical field [0001] The invention belongs to the field of railway wind speed prediction, in particular to a multi-point and multi-layer coupling prediction method for wind speed along a high-speed railway. Background technique [0002] my country has a vast territory, and the railway wind environment is complicated, and strong winds often occur in some places. Strong wind is one of the main disasters leading to train accidents, ranging from train outage to severe train crashes. In special wind field areas, such as tunnel entrances, bridges, tuyeres, areas where different wind-shielding facilities meet, and curved road sections, etc., the flow field around the train changes more obviously, and the aerodynamic load changes significantly, making the train more prone to accidents. With the development of my country's railways, the speed of trains is gradually increasing. The shape, traction mode, and structure of the EMU are very different from those of ordinary speed train...

AI Technical Summary

Problems solved by technology

Existing railway wind speed prediction methods are mostly based on a single anemometer station, and the sampling signal is single, which cannot avoid the problems caused by the hardware failure of a single anemometer station

Images