An urban bus emission rate estimation method based on a gradient lifting regression tree

Abstract

The invention discloses an urban bus emission rate estimation method based on a gradient lifting regression tree. Firstly, according to the measured bus emission data, a Lagrangian interpolation method is used for standardized processing to obtain the emission data per second. Secondly, the VSP (Vehicle Specific Power) is used to characterize the current operating conditions of the bus, and the influence of the previous driving state on the emission is considered to establish a quantitative model of the emission rate. Finally, the gradient lifting regression tree is used to train data and adjus the parameters, the bus emission rate estimation model is obtained. The invention considers the common influence of the current time operation condition and the previous driving state on the currenttime emission rate, The non-parametric method of gradient lifting regression tree model is used to improve the estimation accuracy of bus emission rate, which has practical significance for controlling traffic exhaust emissions and optimizing road environment, and overcomes the complex nonlinear relationship between bus emission rate and various influencing factors.

Description

technical field [0001] The invention belongs to the field of intelligent transportation technology and traffic environment, and in particular relates to a method for estimating the emission rate of urban buses based on a gradient lifting regression tree. Background technique [0002] The pollution problem caused by urban traffic has attracted the attention of countries all over the world. As a heavy-duty vehicle, buses shuttle through the city every day. Therefore, estimating and evaluating the emission characteristics of buses has practical significance for the management and control of urban traffic pollution. At present, there are some motor vehicle emission models in the world, such as the MOVES model of the US EPA, the COPERT model developed by the European Commission, and the CMEM model developed by the University of California, Riverside, etc. Most of these models are developed based on foreign traffic emission data For the complex road traffic environment in China, t...

AI Technical Summary

Problems solved by technology

At present, there are some motor vehicle emission models in the world, such as the MOVES model of the US EPA, the COPERT model developed by the European Commission, and the CMEM model developed by the University of California, Riverside, etc. Most of these models are developed based on foreign traffic emission data For the complex road traffic environment in China, the model is not fully applicable. At the same time, some fuel types are not available in some current models. For example, MOVES currently does not support the emission characteristics estimation of liquefied natural gas buses.

[0003] In terms of urban bus emission rate estimation, because the vehicles will be affected by the complex road traffic environment during the actual driving process, the bus emission rate and road traffic parameters present a complex nonlinear relationship, and the simple linear regression method cannot be used accurately. Quantifying the relationship between explanatory variables and emission rates

At the same time, only using the single regression tree model, it is impossible to accurately extract the information characteristics of the explanatory variables and it is easy to cause overfitting of the emission estimation model

Images