An analysis method for predicting exhaust emission of urban pollution vehicle

Abstract

The present application relates to the technical field of smart city, and provides an analysis method for predicting urban pollution vehicle exhaust emission, comprising: calculating monitoring device attribution, obtaining monitoring data through the monitoring device to form a data set A; obtaining vehicle information data, setting pollution emission weight values of different vehicles to form a data set B; calculating total pollution emission weight values of all vehicles passing through each time interval of each district according to the data set A and the data set B to form a data set D; calculating pollution emission amounts corresponding to unit weight values according to annual pollution gas emission statistical data of each district and the data set D to form a data set E; predicting future traffic flow, and predicting future pollution emission values according to the predicted future traffic flow. The present application can predict future exhaust harmful gas emission amount in advance; based on the prediction result in the future, auxiliary decisions of environmental prevention and traffic management can be made in advance, and decision basis for smart city business is provided.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of smart city, and particularly relates to an analysis method for predicting urban pollution automobile exhaust emission. BACKGROUND

[0002] With the development of big data and artificial intelligence technology, the demand based on data intelligence emerges as the times require. The concept of smart city and urban brain gives birth to the technology system of data and AI algorithm fusion. The big data technology based on GreenPlum ecology seamlessly connects the Postgis spatial geographic information data computing engine and the Madlib complete machine learning engine, so that the AI method based on big data has the possibility of efficient implementation.

[0003] Motor vehicle exhaust emission has gradually become one of the main sources of urban air pollutants in China. It is beneficial to the convenient, efficient evaluation of urban motor vehicle exhaust emission control measures and the improvement of urban atmospheric environment to evaluate the motor vehicle exhaust emission level by means of intelligent transportation combined with emission model. At present, the digital city field can collect the required data such as relevant data of environmental inspection bureau and vehicle information data of traffic bureau, but there is no ready-made solution and specific landing method.

[0004] Therefore, how to provide an analysis method for predicting urban pollution automobile exhaust emission becomes a technical problem to be solved. SUMMARY

[0005] Therefore, the present application aims to provide a method compatible with big data and Gis analysis, machine learning, which uses environmental monitoring statistical data, traffic network data and vehicle information data of traffic management agencies to predict and analyze exhaust emission, and solves the technical problem of motor vehicle exhaust emission evaluation in related smart city environmental detection and analysis.

[0006] The present application provides an analysis method for predicting urban pollution automobile exhaust emission, comprising:

[0007] Step S1: calculating the attribution of monitoring equipment, obtaining monitoring data through the monitoring equipment to form a data set A, the data set A comprising: monitoring equipment identifier, time interval, vehicle flow monitored by the monitoring equipment in real time, license plate number, and attribution county;

[0008] Step S2: obtaining vehicle information data, setting pollution emission weight values of different vehicles to form a data set B, the data set B comprising: vehicle type, license plate number, displacement, and urban population of each type of vehicle;

[0009] Step S3: According to the data set A and the data set B, the total pollution emission weight value of all vehicles passing through each county in each time interval is calculated to form a data set D, which includes: time interval, county, total pollution emission weight value;

[0010] Step S4: According to the annual pollution gas emission statistical data of each county and the data set D, the pollution emission corresponding to the unit weight value is calculated to form a data set E, which includes: the pollution gas emission corresponding to each unit weight value;

[0011] Step S5: Predict the future traffic flow, and predict the future pollution emission value according to the predicted future traffic flow.

[0012] Further, in step S1, the calculation of the attribution of the monitoring device includes: obtaining the latitude and longitude coordinates of the monitoring device, road network data, high-precision map data, and using the Postgis function to calculate the attribution of the monitoring device.

[0013] Further, in step S2, the pollution emission weight value of different vehicles is set, including: obtaining the displacement information of the vehicle according to different license plate numbers, and setting the pollution emission weight value of the vehicle according to different displacements.

[0014] Further, in step S3, according to the data set A and the data set B, the total pollution emission weight value of all vehicles passing through each county in each time interval is calculated, including: the product of each type of vehicle and the corresponding pollution emission weight value obtained by each monitoring in each county in each time interval is summed to obtain the total pollution emission weight value Ky of each monitoring, and the total pollution emission weight value K of all monitoring devices in each county in each time interval is summed to obtain the total pollution emission weight value K of all monitoring devices in each county in each time interval.

[0015] Further, in step S4, according to the annual pollution gas emission statistical data of each county and the data set D, the pollution emission corresponding to the unit weight value is calculated, including:

[0016] S41: Obtain the annual pollution gas emission statistical data of each county to form a data set C, which includes: annual statistical value of each pollution gas emission, and the corresponding county;

[0017] S42: According to the annual pollution gas emission statistical data of each county, the total pollution emission T of each gas in each time interval of each county is determined;

[0018] S43: Correlate the data set C and the data set D, and query the total pollution emission weight value K of all monitoring devices in each county in each time interval;

[0019] S44: divide the total amount of pollution emissions T of each gas in each time interval in each district in step S42 by the total weight K of all pollution emission values obtained by monitoring in each time interval in each district in step S43 to obtain the emission amount E of each pollution gas corresponding to the unit weight.

[0020] Further, in step S5, predicting the future traffic volume includes: using the ARIMA method of Madlib / Plpython to train and infer the machine learning model of time series prediction of the traffic volume of each monitoring device through the historical data of data set A, and calculating the traffic volume of each time interval in the future to obtain data set Af of each monitoring device, wherein the data set Af includes: traffic volume, license plate number and district.

[0021] Further, in step S5, predicting the future pollution emission value according to the predicted future traffic volume includes: replacing the data set A in step S3 with the predicted future traffic volume data set Af, and calculating the total weight of pollution emissions of all vehicles passing through each district in each time interval according to the data set Af and the data set B.

[0022] Further, in step S5, calculating the total weight of pollution emissions of all vehicles passing through each district in each time interval according to the data set Af and the data set B includes: summing the product of each type of vehicle and the corresponding pollution emission weight obtained by monitoring in each district in each time interval in the future to obtain the total weight Kf of pollution emissions of each monitoring device, and summing the total weight Kf of pollution emissions of all monitoring devices to obtain the total weight Kfs of pollution emission values obtained by monitoring in each district in each time interval in the future.

[0023] Further, in step S5, predicting the future pollution emission value includes: the future pollution emission value Pf is the product of the total weight Kfs of pollution emission values obtained by monitoring in each district in each time interval in the future and the emission amount E of each pollution gas corresponding to the unit weight.

[0024] Further, in step S1, calculating the attribution of the monitoring device further includes: obtaining the longitude and latitude coordinates of the monitoring device and the longitude and latitude coordinates of the center of each district, calculating the distance between the monitoring device and the center of each district through st_distance, sorting the calculated distances, and determining the attribution of the monitoring device according to the smallest distance.

[0025] The analysis method for predicting the city pollution automobile exhaust emission of the application can predict the future exhaust harmful gas emission amount in advance; based on the prediction result in the future, the auxiliary decision of environmental prevention and traffic management can be made in advance, and the decision basis for smart city business is provided; the business data of different departments are combined, and the data value and intelligent solution are excavated. BRIEF DESCRIPTION OF DRAWINGS

[0026] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0027] Figure 1 The flow chart of the analysis method for predicting the exhaust emission of urban pollution vehicles according to the exemplary first embodiment of the present application.

[0028] Figure 2 The flow chart of the analysis method for predicting the exhaust emission of urban pollution vehicles according to the exemplary fourth embodiment of the present application. DETAILED DESCRIPTION

[0029] The embodiments of the present application will be described in detail below with reference to the drawings.

[0030] It should be noted that the following embodiments and the features in the embodiments can be combined with each other without conflict; and all other embodiments obtained by those skilled in the art on the basis of the embodiments in the present disclosure without creative labor are within the scope of protection of the present disclosure.

[0031] It should be noted that the various aspects of the embodiments described below are within the scope of the appended claims. It should be apparent that the aspects described herein can be embodied in a wide variety of forms and that any specific structure and / or function described herein is merely illustrative. Based on the present disclosure, any one of the aspects described herein can be implemented independently of any other aspect and various embodiments of two or more of these aspects can be combined in various ways. For example, an apparatus can be implemented or a method can be practiced using any number of the aspects set forth herein. In addition, such an apparatus can be implemented or such a method can be practiced using other structure and / or functionality in addition to or other than one or more of the aspects set forth herein.

[0032] Figure 1 The flow chart of the analysis method for predicting the exhaust emission of urban pollution vehicles according to the exemplary first embodiment of the present application is shown in FIG. 1, which comprises the following steps. Figure 1

[0033] Step S1: Calculate the attribution of the monitoring device, obtain monitoring data through the monitoring device, form a data set A, and the data set A includes: monitoring device identification, time interval, vehicle flow monitored by the monitoring device in real time, license plate number, and the attribution of the county;

[0034] ​Step S2: obtaining vehicle information data, setting pollution emission weight values of different vehicles, and forming a data set B, wherein the data set B includes: vehicle type, license plate number, displacement, and urban ownership of each type of vehicle;

[0035] Step S3: calculating total pollution emission weight values of all vehicles passing through each time interval in each district according to the data set A and the data set B, and forming a data set D, wherein the data set D includes: time interval, district, and total pollution emission weight value;

[0036] Step S4: calculating pollution emission values corresponding to unit weight values according to annual pollution gas emission statistical data of each district and the data set D, and forming a data set E, wherein the data set E includes: pollution gas emission values corresponding to each unit weight value;

[0037] Step S5: predicting future traffic flow, and predicting future pollution emission values according to the predicted future traffic flow.

[0038] In step S1 of the embodiment, the calculation of the attribution of the monitoring device includes: obtaining the longitude and latitude coordinates of the monitoring device, road network data, and high-precision map data, and calculating the attribution of the monitoring device by using a Postgis function.

[0039] In step S1 of the embodiment, the calculation of the attribution of the monitoring device also includes: obtaining the longitude and latitude coordinates of the monitoring device and the longitude and latitude coordinates of the center of each district, calculating the distance between the monitoring device and the center of each district by using st_distance, sorting the calculated distances, and determining the attribution of the monitoring device according to the smallest distance.

[0040] The second exemplary embodiment of the present application provides a method for analyzing and predicting urban pollution automobile exhaust emission. Figure 1 In step S2 of the preferred embodiment of the method, the setting of pollution emission weight values of different vehicles includes: obtaining displacement information of vehicles according to different license plate numbers, setting pollution emission weight values of vehicles according to different displacements, and specifically, setting the exhaust pollution emission weight value of a 1.0T vehicle as 1, the exhaust pollution emission weight value of a 2.0T vehicle as 2, the exhaust pollution emission weight value of a 3.0T vehicle as 3, the pollution emission weight value of a new energy pure electric vehicle as 0, and the emission weight value of a plug-in hybrid 1.5T vehicle as 0.75.

[0041] The third exemplary embodiment of the present application provides a method for analyzing and predicting urban pollution automobile exhaust emission. Figure 1In a preferred embodiment of the method, in step S3, the total pollution emission weight value of all vehicles passing through each county in each time interval is calculated according to the data set A and the data set B, including: summing the product of each type of vehicle and the corresponding pollution emission weight value obtained by each monitoring in each county in each time interval to obtain the total pollution emission weight value Ky of each monitoring, and summing the total pollution emission weight value Ky of all monitoring devices to obtain the total pollution emission weight value K of all monitoring obtained in each county in each time interval.

[0042] Figure 2 A flowchart of an analysis method for predicting urban pollution vehicle exhaust emission according to an exemplary fourth embodiment of the present application, this embodiment is Figure 1 In a preferred embodiment of the method, in step S4 of the method, the pollution emission amount corresponding to the unit weight is calculated according to the annual pollution gas emission statistical data of each county and the data set D, including:

[0043] S41: Obtain the annual pollution gas emission statistical data of each county to form a data set C, the data set C including: annual statistical value of each pollution gas emission, and the corresponding county;

[0044] S42: Determine the total pollution emission amount T of each gas in each time interval of each county according to the annual pollution gas emission statistical data of each county;

[0045] S43: Correlate the data set C and the data set D to query the total pollution emission weight value K of all monitoring obtained in each time interval of each county;

[0046] S44: Divide the total pollution emission amount T of each gas in each time interval of each county in step S42 by the total pollution emission weight value K of all monitoring obtained in each time interval of each county obtained by querying in step S43 to obtain the pollution gas emission amount E corresponding to the unit weight.

[0047] An analysis method for predicting urban pollution vehicle exhaust emission is provided in an exemplary fifth embodiment of the present application, this embodiment is Figure 1 In a preferred embodiment of the method, in step S5, the future traffic flow is predicted, including: using the historical data of the data set A, using the ARIMA method of Madlib / Plpython to train and infer the machine learning model of time series prediction of the traffic flow of each monitoring device, and calculating the traffic flow of each time interval in the future to obtain the data set Af of each monitoring device, the data set Af including: traffic flow, license plate number, and the corresponding county.

[0048] In the embodiment, the future pollution emission value is predicted according to the predicted future traffic flow, and the calculation of the total weight value of pollution emission of all vehicles passing through each county in each time interval according to the data set Af and the data set B includes: replacing the data set A in step S3 with the predicted future traffic flow data set Af, and calculating the total weight value of pollution emission of all vehicles passing through each county in each time interval according to the data set Af and the data set B.

[0049] In the embodiment, the total weight value of pollution emission of all vehicles passing through each county in each time interval is calculated according to the data set Af and the data set B, and the calculation includes: summing the product of each type of vehicle and the corresponding pollution emission weight value obtained by each monitoring in each time interval in each county to obtain the total weight value of pollution emission Kf of each monitoring, and summing the total weight value of pollution emission Kf of all monitoring devices to obtain the total weight value of pollution emission Kfs obtained by all monitoring in each time interval in each county in the future.

[0050] In the embodiment, the future pollution emission value is predicted, and the future pollution emission value Pf is the product of the total weight value of pollution emission Kfs obtained by all monitoring in each time interval in each county in the future and the corresponding pollution gas emission E of each unit weight value.

[0051] The fifth exemplary embodiment of the present application provides a method for predicting and analyzing urban pollution vehicle exhaust emission,

[0052] The above is only a specific embodiment of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method of analyzing urban pollution automobile exhaust emission prediction, characterized by, The method comprises: Step S1: calculating the monitoring device attribution, obtaining monitoring data through the monitoring device, forming a data set A, the data set A comprising: monitoring device identification, time interval, vehicle flow monitored by the monitoring device in real time, license plate number, and the attribution of the county; Step S2: obtaining vehicle information data, setting the pollution emission weight value of different vehicles, forming a data set B, the data set B comprising: vehicle type, license plate number, displacement, and the urban holding amount of each type of vehicle; Step S3: calculating the total pollution emission weight value of all vehicles passing through each county in each time interval according to the data set A and the data set B, forming a data set D, the data set D comprising: time interval, attribution of the county, and total pollution emission weight value; Step S4: calculating the pollution emission amount corresponding to the unit weight value according to the annual pollution gas emission statistical data of each county and the data set D, forming a data set E, the data set E comprising: the pollution gas emission amount corresponding to each unit weight value; Step S5: predicting future vehicle flow, and predicting future pollution emission value according to the predicted future vehicle flow; In step S3, the total pollution emission weight value of all vehicles passing through each county in each time interval is calculated according to the data set A and the data set B, which comprises: summing the product of each type of vehicle and the corresponding pollution emission weight value obtained by each monitoring in each county in each time interval to obtain the total pollution emission weight value Ky of each monitoring, and summing the total pollution emission weight value Ky of all monitoring devices to obtain the total pollution emission weight value K of all monitoring obtained in each county in each time interval; In step S4, the pollution emission amount corresponding to the unit weight value is calculated according to the annual pollution gas emission statistical data of each county and the data set D, which comprises: S41: obtaining the annual pollution gas emission statistical data of each county, forming a data set C, the data set C comprising: annual statistical value of each pollution gas emission and the attribution of the county; S42: determining the total pollution emission amount T of each gas in each time interval of each county according to the annual pollution gas emission statistical data of each county; S43: correlating the data set C and the data set D, and querying to obtain the total pollution emission weight value K of all monitoring obtained in each county in each time interval; S44: dividing the total pollution emission amount T of each gas in each time interval of each county in step S42 by the total pollution emission weight value K of all monitoring obtained in each county in each time interval obtained by querying in step S43 to obtain the pollution gas emission amount E corresponding to each unit weight value; In step S5, the future vehicle flow is predicted, which comprises: training and reasoning a machine learning model for time series prediction of vehicle flow of each monitoring device by using the ARIMA method of Madlib / Plpython through the historical data of the data set A, calculating the vehicle flow of each time interval in the future to obtain a data set Af of each monitoring device, the data set Af comprising: vehicle flow, license plate number, and the attribution of the county; In step S5, the future pollution emission value is predicted according to the predicted future traffic flow, including: replacing the data set A in step S3 with the predicted future traffic flow data set Af, and calculating the total pollution emission weight of all vehicles passing through each county in each time interval according to the data set Af and the data set B; In step S5, the total pollution emission weight of all vehicles passing through each county in each time interval is calculated according to the data set Af and the data set B, including: summing the product of each type of vehicle and the corresponding pollution emission weight obtained by each monitoring in each time interval in each county to obtain the total pollution emission weight Kf of each monitoring, and summing the total pollution emission weight Kf of all monitoring devices to obtain the total pollution emission value weight Kfs of all monitoring obtained in each county in each time interval in the future. In step S5, the future pollution emission value is predicted, including: the future pollution emission value Pf is the product of the total pollution emission value weight Kfs obtained by all monitoring in each county in each time interval in the future and the corresponding pollution gas emission E of the unit weight.

2. The method of claim 1, wherein the method is used for predicting the emission of exhaust gas from a city-polluted vehicle. In step S1, the monitoring device attribution is calculated, including: obtaining the longitude and latitude coordinates of the monitoring device, road network data, and high-precision map data, and using the Postgis function to calculate the monitoring device attribution.

3. The method of claim 1, wherein the method is used for predicting the emission of exhaust gas from a city-polluted vehicle. In step S2, the pollution emission weight of different vehicles is set, including: obtaining the displacement information of the vehicle according to different license plate numbers, and setting the pollution emission weight of the vehicle according to different displacements.

4. The method of claim 1, wherein the method is used for predicting the emission of exhaust gas from a city-polluted vehicle. In step S1, the monitoring device attribution is calculated, further including: obtaining the longitude and latitude coordinates of the monitoring device and the longitude and latitude coordinates of the county center, calculating the distance between the monitoring device and the county center by using the st_distance in the Postgis function, sorting the calculated distances, and determining the attribution of the monitoring device according to the smallest distance.

Images