An urban rail short-time passenger flow prediction method based on modal decomposition and deep learning

Abstract

The invention discloses an urban rail short-time passenger flow prediction method based on modal decomposition and deep learning. The urban rail short-time passenger flow prediction method comprises aCEEMDAN decomposition stage and a Fine-to-Colarse reconstruction stage and a GRU prediction stage. The invention provides an urban rail transit short-time traffic flow prediction model integrating aCEEMDAN and a GRU. The advantages of two models are fully combined, the CEEMDAN is utilized to decompose original passenger flow data into limited IMFs with local characteristics and different frequencies and allowances, so that the non-stable and non-linear characteristics of the data are obtained, and Fine-to-Colarse reconstruction method is introduced. The method comprises the following steps:reconstructing the IMFs by using a code reconstruction method; a decomposition result is reconstructed into a high-frequency item, a low-frequency item and a trend item, data information is fully reserved while the IMFs dimension is reduced, and finally the IMFs dimension is used as input of a GRU model to obtain time sequence characteristics of data and predict urban rail transit short-time traffic flow.

Description

technical field [0001] The invention relates to a method for predicting short-term passenger flow of urban rail based on modal decomposition and deep learning. Background technique [0002] Due to its large capacity, fast speed and low energy consumption, urban rail transit has become one of the main public transportation to alleviate traffic congestion and meet the travel needs of urban residents in metropolitan areas. Passenger flow forecast results are the main basic documents for urban rail transit operation and management. Among them, medium and long-term passenger flow forecast results are an important basis for urban rail transit planning and construction, while short-term passenger flow forecast results can support urban rail transit operation planning, passenger flow induction, and emergency management. Management and other decisions have important guiding significance for adjusting passenger travel behavior, reducing passenger congestion, and improving urban rail t...

AI Technical Summary

Problems solved by technology

[0009] To sum up, there have been a lot of research on short-term passenger flow or traffic flow prediction of urban rail transit at home and abroad, but the above-mentioned models have not fully utilized the characteristics of time series, non-stationarity and nonlinearity of short-term passenger flow data. The accuracy and robustness of short-term passenger flow forecasting are of great significance

Images