Unlock instant, AI-driven research and patent intelligence for your innovation.

A Heavy Goods Vehicle Traffic Flow Prediction Method Based on Incomplete Positioning Data

A technology for traffic flow and positioning data, applied in the field of intelligent transportation, can solve the problems of heavy trucks without satellite positioning devices, damaged devices, and inability to transmit data in real time, so as to improve road operating conditions and ease traffic congestion.

Inactive Publication Date: 2020-11-24
BEIJING JIAOTONG UNIV
View PDF15 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In reality, there are still a small number of heavy goods vehicles that are not equipped with satellite positioning devices, and there are cases where the device is damaged and cannot transmit data in real time

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 Heavy Goods Vehicle Traffic Flow Prediction Method Based on Incomplete Positioning Data
  • A Heavy Goods Vehicle Traffic Flow Prediction Method Based on Incomplete Positioning Data
  • A Heavy Goods Vehicle Traffic Flow Prediction Method Based on Incomplete Positioning Data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] The following is attached Figure 1-5 The present invention will be described in further detail with specific implementation cases.

[0049] A method for predicting traffic flow of heavy trucks based on non-full sample positioning data according to the present invention mainly includes the following steps:

[0050] Step 1: Based on the vehicle-mounted satellite positioning device, obtain the GPS data of heavy-duty trucks in Zhengzhou City, including recording time, longitude, latitude and license plate number;

[0051] Step 2: Merge the GPS data according to the specified time interval and the position of the road section; specifically, number the urban road network to form a road section ID, and add up the GPS data for each road section ID according to the specified time interval to form a road section attribute and time interval attributes of traffic flow data.

[0052] A sample case is shown in Table 1:

[0053] Table 1 Example of integrated GPS traffic flow data ...

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 a heavy-duty truck traffic flow prediction method based on non-full sample positioning data. Aiming at the problem of incomplete acquisition of GPS traffic flow, a scheme of first enlarging samples and then predicting is proposed. In the sampling expansion method, a piecewise constant coefficient method based on the distribution of the traffic itself is proposed. In the prediction method, a long-short-term cyclic neural network LSTM model that can solve the long-term memory problem is proposed, so as to achieve the goal that the traffic flow of heavy trucks is closer to the actual flow. The invention overcomes the defects of low precision of traditional coils and video flow collection during data collection, uses GPS data of a satellite positioning device to predict traffic flow, and has high precision. The invention provides a set of more comprehensive and comprehensive methods for predicting the traffic flow of heavy trucks, and can play an active role in alleviating the problem of urban traffic congestion and improving the operating efficiency of urban traffic. The invention has practical application value in engineering, and can be transferred and applied in related fields.

Description

technical field [0001] The invention relates to the field of intelligent transportation, in particular to a heavy truck traffic flow prediction method based on non-full sample positioning data. Background technique [0002] Traffic flow prediction is an important research content of intelligent transportation system, its accuracy and real-time performance play an important role in alleviating traffic congestion. Traditional traffic flow forecasting methods are often based on passenger cars, and there are few in-depth discussions on the flow forecasting of heavy goods vehicles. In addition, traditional passenger car flow data acquisition is mainly based on coil detection and video detection, which often has the problems of inaccurate vehicle type detection and missing flow counts. At the same time, there is no way to comprehensively detect all lanes. In 2014, the State promulgated the "Measures for the Dynamic Supervision and Management of Road Transport Vehicles", requiring...

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): G08G1/01G08G1/065G06N3/04
CPCG08G1/0125G08G1/065G06N3/044G06N3/045
Inventor 王晟由董春娇薛松邵春福郑炎
Owner BEIJING JIAOTONG UNIV