Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A Traffic Exhaust Emissions Prediction Method Based on Deep Residual Network

A technology for exhaust emissions and emissions, applied in forecasting, neural learning methods, biological neural network models, etc., can solve the problems of inability to predict traffic exhaust emissions at the same time, low prediction accuracy, etc., to achieve spatial distribution prediction, The effect of improving accuracy

Active Publication Date: 2022-06-28
东北大学秦皇岛分校
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing traffic exhaust emission prediction methods focus on the construction of future urban traffic emission inventory, or focus on the traffic emission prediction under different working conditions and road conditions. Traffic emissions in a sub-region

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Traffic Exhaust Emissions Prediction Method Based on Deep Residual Network
  • A Traffic Exhaust Emissions Prediction Method Based on Deep Residual Network
  • A Traffic Exhaust Emissions Prediction Method Based on Deep Residual Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The present invention will be further described below with reference to the accompanying drawings and specific embodiments.

[0040] like figure 1 As shown, it is a schematic diagram of the traffic exhaust emission prediction method based on the deep residual network of the present invention. The method for predicting traffic tail gas emissions based on a deep residual network of the present invention includes the following steps:

[0041] Step 1: Divide the area to be predicted into grid areas

[0042] Among them, A ij is the grid at row i and column j in the grid area, i∈{1,2,…,I}, j∈{1,2,…,J}, and each grid in the grid area is square and of equal area.

[0043] In this embodiment, the area to be predicted is Beijing, such as figure 2 As shown, Beijing is divided into 32×32 grid areas, each grid area is 1 square kilometer.

[0044] Step 2: Collect the vehicle GPS trajectory data of the area to be predicted in the t-th time period to form a vehicle GPS traject...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to the technical field of traffic tail gas emission prediction, and provides a traffic tail gas emission prediction method based on a deep residual network. First, divide the area to be predicted into grid areas; then collect the vehicle GPS trajectory data set, holiday conditions and weather data in the area to be predicted in each time period, and calculate the traffic exhaust emissions of each grid in each time period Then construct the holiday-weather-emission sample set, the latest time sample set, the adjacent time sample set, the distant time sample set, and preprocess each sample set; then build a traffic emission prediction model based on the deep residual network, and train model; finally, use the trained traffic emission prediction model to predict the traffic exhaust emissions of each grid within the time period to be predicted. The invention can improve the prediction accuracy of traffic tail gas discharge, and can predict the traffic tail gas discharge of each sub-region in the whole city at the same time.

Description

technical field [0001] The invention relates to the technical field of traffic exhaust emission prediction, in particular to a traffic exhaust emission prediction method based on a deep residual network. Background technique [0002] Traffic pollution is one of the main sources of air pollution. With the transformation of my country's economy and the development of urbanization, the problem of urban air pollution has become more complicated, and the task of prevention and control of urban air pollution has become more arduous. And due to the continuous increase in the number of motor vehicles in the city, traffic pollution has increasingly become the main source of urban air pollution. Therefore, traffic emission prediction is of great significance to the prevention and control of urban air pollution. [0003] Traffic exhaust refers to the harmful pollutants produced by the engine during the incomplete combustion of gasoline or diesel, mainly including nitrogen oxides, hyd...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06Q10/04G06Q50/26G06K9/62G06N3/04G06N3/08
CPCG06Q10/04G06Q50/26G06N3/08G06N3/045G06F18/25G06F18/10G06F18/214
Inventor 曹松松李连江吴朝霞
Owner 东北大学秦皇岛分校
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com