Track foundation differential settlement identification method based on GRU neural network

Abstract

The invention relates to a track foundation differential settlement identification method based on a GRU neural network. The method comprises sensitive factor calculation and foundation differential settlement intelligent identification. The method has the beneficial effects that through numerical simulation, a train-track-monolithic track bed two-dimensional model is established, the working condition of differential settlement of the foundation is introduced, the dynamic response of each train track is calculated, and the correlation between each dynamic response and differential settlement of the foundation is analyzed. Finally, the response of the vertical acceleration of the vehicle body to the foundation differential settlement is obvious, the regularity is high, and the vertical acceleration can serve as a sensitive factor to recognize the foundation differential settlement. The data acquisition of the vertical acceleration of the vehicle body is relatively simple and easy to realize compared with the dynamic response of other vehicle rails, and the time travel curve of the acquired vertical acceleration of the vehicle body is continuous. The method has very strong guiding significance for monitoring and controlling the differential settlement of the foundations of railways and urban rail transit at present.

Description

technical field [0001] The invention relates to the field of track engineering and underground engineering, more specifically, to a method for identifying differential settlement of track foundation based on GRU neural network. Background technique [0002] In recent years, with the development of my country's economy and the rapid growth of urban population, people's life rhythm is accelerating, and the traffic requirements for daily travel are getting higher and higher. Obviously, traditional road traffic can no longer meet people's growing needs. In order to solve this problem, the state vigorously develops railway and urban rail transit business, and continuously achieves historic breakthroughs in operating routes and mileage. With the rapid development of railway and urban rail transit, the problem of rail and subway tunnel damage has become increasingly prominent, affecting people's normal travel and even causing major economic and property losses. The uneven settleme...

AI Technical Summary

Problems solved by technology

The uneven settlement of the track foundation is seriously detrimental to the normal use of the track structure, causing the running train to bump and even derail, which has an adverse effect on the safety and comfort of the train

[0003] For the monitoring of uneven settlement of the track foundation, before the 1990s, the method used for deformation monitoring was the classic ground measurement method. The railway can only be operated when there is no train running or the subway is out of service, and it takes a lot of manpower; from the 1990s to the beginning of the 21st century, with the development of communication technology and electronic technology, my country has successively developed a batch of suitable for railway subgrade Instruments for settlement monitoring, such as observation piles, settlement plates, settlement meters, etc., but they are also vulnerable to damage, and the accuracy is easily affected by external interference; with the rapid development of computer technology, a leap from manual measurement to automatic monitoring has been realized , digital photogrammetry technology, optical fiber sensor monitoring technology, three-dimensional laser scanning technology, etc., have obvious advantages over previous monitoring methods, but the cost of automatic monitoring technology is relatively high, and the feedback data still needs to be interpreted by professionals, and the labor cost is high

[0004] To sum up, the monitoring of uneven settlement of track foundation is very important for railway and urban rail transit, but the current monitoring technology needs to be improved

Images