Passenger capacity prediction method based on intelligent function combination optimization GM (1, 1) model

Abstract

The invention relates to a passenger capacity prediction method based on an intelligent function combination optimization GM (1, 1) model. The prediction method includes the following steps that: step1, constructing a passenger capacity prediction model; step 2, searching values of parameters c and M in the passenger capacity prediction model by utilizing a genetic algorithm; performing optimizing to obtain optimal values of the parameters c and M; and forming an optimized passenger capacity prediction model. The method has the advantages that according to the passenger capacity prediction method based on the intelligent function combination optimization GM (1, 1) model, compared with an existing method, a traditional exponential function transformation index value and a trigonometric function transformation normalization value are standardized, and then the smoothness and the level ratio deviation of an initial sequence can be improved at the same time.

Description

technical field [0001] The invention belongs to the field of road network traffic planning system, and in particular relates to a method for predicting passenger volume based on intelligent function combination optimization GM (1,1) model. Background technique [0002] The passenger traffic prediction based on the GM(1,1) model has been widely used in the field of passenger traffic forecasting due to the small number of samples required and high prediction accuracy, such as literature 1 Chen L, Tian B, Lin W, et al.Analysis and prediction of the discharge characteristics of the lithium–ion battery based on the Greysystem theory[J].Power Electronics Iet,2015,8(12):2361-2369, literature 2Chu C T,Chang Y S.A gray prediction GM(1,1)fall detection signal analysis and implement in wearable device[C] / / Microsystems, Packaging, Assembly and Circuits Technology Conference.IEEE,2016:251-254, literature 3Liu F, Xu G.Unequal spacing greysystem GM(1,1)model in settlement monitoring[C] / / ...

AI Technical Summary

Problems solved by technology

However, there is a problem in literature 8 and literature 12. The combination optimization of exponential function and trigonometric function causes the initial sequence to meet the applicable range of trigonometric functions due to the use of trigonometric functions. At this time, the original sequence needs to be preprocessed. The traditional preprocessing is to make The original sequence satisfies any number that meets the requirements of the applicable range of the function. Similarly, Document 6 does not point out how to determine the value of the bottom of the exponential function. At the same time, Document 6, Document 8 and Document 12 only prove that the transformation function can improve the initial sequence Smoothness, lack of evidence for reduction in scale deviation

Images