Rail train operation state prediction method based on a deep neural network structure model

Abstract

The invention provides a rail train operation state prediction method based on a deep neural network structure model, and the method comprises the steps: obtaining the real-time data of a rail train operation state, and carrying out the preprocessing of the data; establishing a deep neural network structure model according to the preprocessed data; dividing the preprocessed data into a training data set and a verification data set, and training and verifying the deep neural network structure model through the training data set and the verification data set; And carrying out online prediction on the rail transit train through the verified deep neural network structure model. According to the method, a dynamic model is established on the basis of comprehensively considering the difference factors between vehicle individuals and the operation environment, and powerful support is provided for operation of a train in a complex environment.

Description

technical field [0001] The invention relates to the technical field of rail traffic management and control, in particular to a method for predicting the running state of rail trains based on a deep neural network structure model. Background technique [0002] Urban rail transit has the characteristics of saving land, large transportation volume, low energy consumption, fast, punctual and environmental protection, and is a resource-saving and environment-friendly transportation mode. Urban rail transit not only facilitates the travel of citizens and relieves urban traffic congestion, but also reduces the pressure on energy consumption and urban carbon emissions to a certain extent, and drives the economic development along the line. In order to further meet the needs of social and economic development and alleviate the pressure of traffic travel in large cities, my country is vigorously developing urban rail transit. [0003] At present, more than 90% of newly-built subway l...

AI Technical Summary

Problems solved by technology

However, due to the high complexity of the system in the prior art, the train dynamics model is affected by many factors, such as track humidity, external weather and traction / brake shoe loss, etc.

At present, many train dynamic models only use a simple linear first-order control model, which cannot accurately reflect the change of train model parameters.

Especially in rainy and snowy weather, changes in the wheel-rail adhesion coefficient and other related parameters will lead to changes in the train dynamics model, and the train is more sensitive to system traction and braking parameters. Changes, cannot effectively adapt to the automatic operation of trains in rainy and snowy weather

Therefore, in the current urban rail transit, it will switch to the manual driving mode in the case of rainy and snowy weather, which reduces the operating efficiency of the system

[0004] At present, in practical applications, the dynamic model of the train realizes the tracking control of acceleration and speed through a feedback adjustment method. and wheel-rail friction coefficient and other factors

At the same time, due to the differences between individual vehicles and the environment, the adaptability of the model parameters is poor, and the model is difficult to be widely used in actual circuits. In the process of model application, a large number of tests and corrections must be carried out according to the individual model to achieve better performance.

Images