Driver car following behavior and vehicle emission influence analysis method and system

Abstract

The invention provides a driver car following behavior and vehicle emission influence analysis method and system, and relates to the related technical field of traffic engineering and environmental sciences, and the method comprises the steps: S1, extracting driver feature indexes according to the vehicle trajectory data of a car following fleet, and carrying out the visualization of the vehicle space-time trajectory according to the vehicle trajectory data; s2, a heterogeneity parameter of a driver is obtained through measurement of a vehicle space-time trajectory diagram, and the number of vehicle following times of the driver is obtained through statistics by combining an improved Newell model and a dynamic time warping algorithm; s3, acquiring driving environment parameters, vehicle technical condition parameters and vehicle operation condition parameters according to the vehicle track data of the vehicle following fleet, inputting the parameters into the localized MOVES model, and estimating to obtain emission factors of road traffic pollutants; and S4, constructing a semi-parameter generalized additive model to analyze a non-linear association relationship between the vehicle following behavior of the driver and the emission factors of the road traffic pollutants.

Description

Technical Field

[0001] The present invention relates to the technical field related to traffic engineering and environmental science, and in particular to a method and system for analyzing the impact of driver following behavior and vehicle emissions. Background Art

[0002] Research shows that different driving styles significantly affect pollutant emissions: aggressive driving produces significantly more carbon emissions than gentle and stable driving. Therefore, incorporating driving behavior into traffic emissions assessments is crucial to accurately reflect actual emissions.

[0003] Currently, following a car is a common driving behavior experienced by drivers. In areas such as urban main roads, intersections, and near overpasses, vehicles are forced to maintain a small distance between vehicles and frequently accelerate and decelerate. However, existing technologies still have shortcomings in driving behavior modeling and traffic pollution assessment. Commonly used microscopic following models assume uniform driving responses and fail to fully capture the differences in driver following behaviors in real traffic. As a result, the vehicle trajectories they generate often fail to truly reflect different driving habits. In addition, vehicle types, road conditions, and driving habits vary from region to region, making it difficult for a unified model to carefully assess the impact of different driving behaviors on pollutant emissions.

[0004] Based on the above, it can be seen that existing technologies lack an in-depth characterization of the relationship between real driving behavior characteristics and emissions, making it difficult to meet the needs of refined management of traffic emissions. In addition, existing technologies have not yet fully established a quantitative correlation between driving behavior differences and traffic emissions, resulting in a lack of reliable basis for targeted emission reduction measures. Summary of the Invention

[0005] The purpose of the present invention is to provide a method and system for analyzing the impact of driver following behavior and vehicle emissions, and to propose a driving behavior identification method that integrates vehicle trajectory data, an improved Newell model, and a dynamic time warping algorithm. The method can accurately quantify the frequency of driver following behavior and driving stability, and on this basis, construct a semi-parametric generalized additive model to reveal the nonlinear correlation between various driving behavior independent variables and typical traffic pollutant emission factors. The present invention not only significantly improves the precision of driving behavior modeling, but also enhances the scientific nature and operability of emission estimation.

[0006] In order to solve the above technical problems, the present invention adopts the following solutions: A method for analyzing the impact of driver following behavior on vehicle emissions, the method comprising the following steps: S1. deriving a fleet of vehicles by filtering vehicle trajectory data, extracting driver characteristic indicators based on the vehicle trajectory data of the fleet, and visualizing the spatiotemporal trajectories of the vehicles based on the vehicle trajectory data; S2. Measure the driver's heterogeneity parameters using the vehicle's spatiotemporal trajectory graph. The heterogeneity parameters are used to introduce into an improved Newell model. The improved Newell model is combined with a dynamic time warping algorithm to statistically obtain the number of times a driver follows a vehicle, thereby characterizing the heterogeneity of the driver's following behavior. S3. Driving environment parameters, vehicle technical condition parameters, and vehicle operating condition parameters are collected based on the vehicle trajectory data of the following vehicle fleet, and these parameters are input into the localized MOVES model to estimate emission factors of road traffic pollutants; S4. Construct a semi-parametric generalized additive model to analyze the nonlinear correlation between driver following behavior and emission factors of road traffic pollutants.

[0007] A further preferred technical solution is: the driver characteristic indicators include maximum speed, minimum speed, average speed, speed standard deviation, maximum acceleration, minimum acceleration, average acceleration, acceleration standard deviation, average positive acceleration, average negative acceleration, positive acceleration standard deviation, and negative acceleration standard deviation.

[0008] A further preferred technical solution is: in S1, the process of visualizing the spatiotemporal trajectory of the vehicle according to the vehicle trajectory data is: The vehicle's travel time and corresponding spatial position are obtained based on the vehicle trajectory data of the following vehicle fleet, and the vehicle's travel time and spatial position are plotted into a two-dimensional image to form a vehicle time-space trajectory diagram.

[0009] A further preferred technical solution is: in S2, the process of measuring the driver's heterogeneity parameters using the vehicle's spatiotemporal trajectory diagram is: SA1. Use tools to measure the density and flow of the following vehicle fleet. Then, use the Newell following model and the absolute speed and density of the driver during the actual following period to calculate the actual time delay parameter. SA2, calculate the ideal time hysteresis parameters using the Newell car following model and preset constants; SA3, calculated based on actual time hysteresis parameters and ideal time hysteresis parameters , the calculation formula is: ,in, is the actual time hysteresis parameter, is the ideal time hysteresis parameter; SA4, according to the formula Calculate quantitative indicators ; SA5. Standardized quantitative indicators , that is, the actual following time and distance are scaled down to 1min*1km.

[0010] A further preferred technical solution is: in S2, the process of using the improved Newell model combined with the dynamic time warping algorithm to obtain the number of times the driver follows the vehicle is: SB1. Obtain the time series trajectory data of the preceding and following vehicles in the current road section based on the vehicle trajectory data of the following vehicle fleet, and perform piecewise linear approximation processing on the time series trajectory data to obtain a trajectory point set; SB2. Construct a cost matrix based on the difference in vehicle speed or spatial position to quantify the matching cost between trajectory points, and add constraints when constructing the cost matrix; SB3. Use the dynamic time warping algorithm to backtrack the path to obtain the optimal matching path and obtain the characteristic points of the following vehicle's response to the behavior of the preceding vehicle; SB4. Count the total number of matching points based on the optimal matching path and record it as the number of times the driver follows the vehicle.

[0011] A further preferred technical solution is: in S3, the process of estimating the emission factors of road traffic pollutants is: Based on the vehicle trajectory data of the following vehicle fleet, the driving environment parameters, vehicle technical condition parameters and vehicle operating condition parameters are input into the MOVES model; The driving environment parameters include the length and slope of the road section, the vehicle technical condition parameters include the age distribution and inspection and maintenance system, and the vehicle operating condition parameters include speed and acceleration; The operating condition classification method is used to map the driver's following behavior to the operating mode defined in the MOVES model, and the localized emission factor library is called to output the emission factors of road traffic pollutants.

[0012] A further preferred technical solution is: the driver characteristic index is an independent variable used to characterize the driver's following behavior and is related to speed and acceleration, and step S4 includes the following steps: S41. Divide the emission factor by the number of times you follow a vehicle to obtain the emissions from a single following behavior; S42. Use variance inflation factors to check standardized quantitative indicators Collinearity with driver characteristic indicators: independent variables with VIF values ​​greater than the preset value in the inspection results will be deleted; S43, use backward elimination method to screen independent variables; S44, estimating model parameters of the analysis model by using a maximum likelihood estimation method; S45, evaluating the analysis module by calculating the degree of fit between the predicted value of the analysis model and the actual observed value; S46. Combine the descriptive statistical results and partial dependence diagrams of the analysis model to visually analyze and explain the relationship between the independent variables and emission factors.

[0013] A further preferred technical solution is: in S1, the process of obtaining the following vehicle fleet by screening the vehicle trajectory data is: SC1. Filtering individual vehicles based on the vehicle trajectory data to obtain a first vehicle, wherein the lateral position of the first vehicle on the lane does not change during an observation period; SC2, comparing the longitudinal position of the first vehicle during the observation period to obtain a vehicle sequence that is tracked one by one in a specific lane; SC3. Determine the order of the leading and trailing vehicles in the vehicle sequence, filter out the driving trajectories of the leading and trailing vehicles for a preset time period, and record them as vehicle trajectory data.

[0014] A system for analyzing the impact of driver-following behavior and vehicle emissions, applying the aforementioned method for analyzing the impact of driver-following behavior and vehicle emissions, comprises: Data processing and analysis module: This module filters vehicle trajectory data to obtain a fleet of vehicles, extracts driver characteristic indicators based on the vehicle trajectory data of the fleet, and visualizes the spatiotemporal trajectories of vehicles based on the vehicle trajectory data; Driver Following Behavior Extraction Module: This module uses the vehicle's spatiotemporal trajectory graph to measure and obtain driver heterogeneity parameters. These heterogeneity parameters are then introduced into an improved Newell model. The improved Newell model is then combined with a dynamic time warping algorithm to statistically calculate the number of times a driver follows a vehicle, thereby characterizing the heterogeneity of driver following behavior. Emission factor calculation module: Based on the vehicle trajectory data collected from the fleet, driving environment parameters, vehicle technical condition parameters, and vehicle operating condition parameters are obtained and input into the localized MOVES model to estimate the emission factors of road traffic pollutants; Analysis model construction module: Construct a semi-parametric generalized additive model to analyze the nonlinear correlation between driver following behavior and emission factors of road traffic pollutants.

[0015] Beneficial effects of the present invention: The present invention provides a method and system for analyzing the impact of driver following behavior on vehicle emissions. To address the problem that existing technologies lack an in-depth characterization of the relationship between real driving behavior characteristics and emissions, making it difficult to meet the needs of refined traffic emission management, an improved driving behavior modeling and emission assessment technical solution is proposed. By combining real road driving trajectory data to extract the driver's driving characteristic parameters, a quantitative indicator of the driver's behavior deviation from the ideal following state is introduced into the improved Newell model. , combining it with the dynamic time warping algorithm, can accurately identify the frequency of following vehicles and achieve a comprehensive characterization of driving behavior heterogeneity; then, the localized MOVES model is used to accurately estimate vehicle emissions; finally, a semi-parametric generalized additive model is constructed, which enables the present invention to reveal the nonlinear correlation between various driving behavior independent variables and typical traffic pollutant emission factors.

[0016] Based on the above principles, the present invention has the following technical advantages and effects compared with the prior art: (1) Accurately quantifying driving behavior differences: Proposed quantitative indicators It not only reflects the deviation between instantaneous driving response and ideal behavior, but also takes into account the cumulative effect of time series. It can effectively capture the driver's behavioral stability and deviation trend during traffic fluctuations, improving the accuracy and completeness of driving style recognition. (2) Enhanced model adaptability and interpretability: The constructed semi-parametric generalized additive model (GAM) comprehensively considers the nonlinear relationship between variables, taking into account the flexibility and interpretability of the model, and effectively reveals the nonlinear response patterns of different speed and acceleration behaviors to various pollutant emission factors; (3) Achieve micro-level emission prediction: Combining the localized MOVES model with natural vehicle trajectory data, it is possible to achieve quantitative estimation of vehicle emission factors at high spatial and temporal resolution, providing a micro-level decision-making basis for ecological driving behavior assessment and traffic emission reduction strategy formulation; (4) Improving the scientificity and practicality of traffic emission modeling: The method of the present invention realizes a complete chain from original trajectory collection, vehicle following behavior recognition to nonlinear modeling and pollutant correlation analysis. It has good scalability and embeddability and is suitable for multiple application scenarios such as intelligent connected vehicle systems, urban traffic emission monitoring platforms, and on-board green driving assistance systems. In summary, the present invention has achieved breakthroughs in the accuracy of vehicle-following behavior recognition, quantitative modeling of driving behavior differences, and emission response curve fitting capabilities. It has significantly improved the adaptability of existing traffic emission analysis models to actual complex driving behaviors and provided key technical support for the realization of a green intelligent transportation system. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a schematic diagram of the overall concept of a method for analyzing the impact of driver following behavior and vehicle emissions in Example 1 of the present invention; Figure 2 This is a schematic diagram of a specific process of obtaining statistics on the number of times a driver follows a vehicle in Example 1 of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the accompanying drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, rather than all the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and is in no way intended to limit the present invention and its application or use. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0019] Unless otherwise specifically stated, the relative arrangement of components and steps, the numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention.

[0020] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0021] Additionally, descriptions of well-known structures, functions, and configurations may be omitted for clarity and conciseness. Those skilled in the art will recognize that various changes and modifications can be made to the examples described herein without departing from the spirit and scope of the present disclosure.

[0022] Technologies, methods and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, such technologies, methods and equipment should be considered part of the authorization specification.

[0023] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0024] The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments: Example 1 Because existing technologies still have shortcomings in driving behavior modeling and traffic pollution assessment. On the one hand, the commonly used microscopic following car model assumes a uniform driving response and fails to fully describe the differences in driver following behavior in real traffic, resulting in the vehicle driving trajectories it generates often failing to truly reflect different driving habits. For example, the existing Newell model, because it does not take into account the heterogeneity of drivers' driving behavior, will cause significant errors in emission estimates. On the other hand, existing motor vehicle emission estimates mainly rely on general emission calculation models, which are based on standardized operating conditions and average driving patterns. If it is directly applied to actual traffic in a specific area without local correction, its measurement accuracy is often difficult to guarantee. Vehicle types, road conditions and driving habits vary in different regions, and it is difficult for a unified model to carefully evaluate the impact of different driving behaviors on pollutant emissions.

[0025] Based on the above, it can be seen that existing technologies lack a deep understanding of the relationship between real-world driving behavior and emissions, making it difficult to meet the needs of refined traffic emissions management. Furthermore, existing technologies have yet to fully establish a quantitative correlation between driving behavior differences and traffic emissions, resulting in a lack of reliable basis for targeted emission reduction measures.

[0026] Therefore, the present invention proposes a method for analyzing the impact of driver following behavior on vehicle emissions. This method integrates vehicle trajectory data, an improved Newell model, and a dynamic time warping algorithm to identify driving behavior. This method accurately quantifies the frequency of driver following behavior and driving stability. Based on this, a semi-parametric generalized additive model is constructed to reveal the nonlinear correlation between various driving behavior independent variables and typical traffic pollutant emission factors. This method not only significantly improves the sophistication of driving behavior modeling but also enhances the scientific nature and operability of emission estimation. Specifically, the present invention is suitable for use in real-time traffic emissions monitoring systems, intelligent driving decision-making systems, and transportation low-carbon strategy evaluation platforms, and has promising application prospects.

[0027] A method for analyzing the impact of driver following behavior on vehicle emissions, the method comprising the following steps: S1. deriving a fleet of vehicles by filtering vehicle trajectory data, extracting driver characteristic indicators based on the vehicle trajectory data of the fleet, and visualizing the spatiotemporal trajectories of the vehicles based on the vehicle trajectory data; S2. Measure the driver's heterogeneity parameters using the vehicle's spatiotemporal trajectory graph. The heterogeneity parameters are used to introduce into an improved Newell model. The improved Newell model is combined with a dynamic time warping algorithm to statistically obtain the number of times a driver follows a vehicle, thereby characterizing the heterogeneity of the driver's following behavior. S3. Driving environment parameters, vehicle technical condition parameters, and vehicle operating condition parameters are collected based on the vehicle trajectory data of the following vehicle fleet, and these parameters are input into the localized MOVES model to estimate emission factors of road traffic pollutants; S4. Construct a semi-parametric generalized additive model to analyze the nonlinear correlation between driver following behavior and emission factors of road traffic pollutants.

[0028] Based on the above principles, the overall concept of the method for analyzing the impact of driver-following behavior and vehicle emissions proposed in the present invention mainly includes a data processing and analysis module, a driver-following behavior extraction module, an emission factor calculation module, and an analysis model construction module. Steps S1-S4 can be implemented in these four modules.

[0029] like Figure 1As shown, in the data processing and analysis module, the vehicle trajectory data is screened to obtain a following vehicle fleet. Driver characteristic indicators are extracted based on the vehicle trajectory data of the following vehicle fleet. At the same time, the vehicle's spatiotemporal trajectory is visualized based on the vehicle trajectory data to construct driver characteristic indicators.

[0030] like Figure 1 As shown, in the driver following behavior extraction module, an improved Newell model is proposed based on the classic Newell following model and driver heterogeneity theory in the prior art. This improved Newell model can quantify the behavioral differences between drivers during the actual following process, thereby obtaining driver heterogeneity. Driver heterogeneity is then characterized by measuring the driver heterogeneity parameter using the vehicle spatiotemporal trajectory graph. Simultaneously, the improved Newell model is combined with the dynamic time warping algorithm to statistically determine the number of times a driver follows a vehicle. This demonstrates that the present invention measures driver behavior through driver heterogeneity and the number of times a driver follows a vehicle, quantifying the behavioral differences between drivers during the actual following process through the heterogeneity parameter and the number of times a driver follows a vehicle.

[0031] like Figure 1 As shown in the figure, in the emission factor calculation module, driving environment parameters, vehicle technical condition parameters and vehicle operating condition parameters are integrated to construct a localized MOVES model, that is, a localized mobile source emission calculation model. The emission factors of road traffic pollutants can be accurately estimated through the localized mobile source emission calculation model.

[0032] like Figure 1 As shown, in the analysis model construction module, the impact of driver behavior is analyzed, and an analysis module is established. In the present invention, a semi-parametric generalized additive model is selected to analyze the nonlinear correlation between the driver's following behavior and the emission factors of road traffic pollutants, and suggestions can be made on driving strategies.

[0033] A further preferred technical solution is: In S1, the vehicle trajectory data in the present invention uses natural driving trajectory data. This allows the present invention to deeply characterize the relationship between real driving behavior characteristics and emissions, meeting the requirements of refined traffic emissions management and providing a reliable basis for emission reduction measures. The specific content of the vehicle trajectory data is shown in Table 1.

[0034] Table 1 Specific content of natural driving trajectory data In order to filter out the following vehicle convoys and avoid the compound effects of overtaking or other driving behaviors, in the present invention, Python software can be used to set filtering conditions to filter the original CSV format vehicle trajectory data. The specific filtering process is as follows: SC1. Filtering individual vehicles based on the vehicle trajectory data to obtain a first vehicle, wherein the lateral position of the first vehicle on the lane does not change during an observation period; SC2, comparing the longitudinal position of the first vehicle during the observation period to obtain a vehicle sequence that is tracked one by one in a specific lane; SC3. Determine the order of the leading and trailing vehicles in the vehicle sequence, filter out the driving trajectories of the leading and trailing vehicles for a preset period of time, and record them as vehicle trajectory data. The preset period of time is at least 15 seconds.

[0035] After obtaining a following vehicle fleet combination that meets the above screening conditions, twelve speed- and acceleration-related parameters, namely driver characteristic indicators, can be extracted according to the formula in Table 2 to characterize the driver's following behavior.

[0036] Table 2 Driver characteristic indicators A further preferred technical solution is as follows: in S1, the process of visualizing the spatiotemporal trajectory of the vehicle based on the vehicle trajectory data includes obtaining the vehicle's travel time and corresponding spatial position based on the vehicle trajectory data of the following vehicle fleet, and plotting the vehicle's travel time and spatial position into a two-dimensional image to form a vehicle spatiotemporal trajectory graph. Specifically, Matlab can be used to plot the vehicle's travel time and spatial position into a two-dimensional image.

[0037] A further preferred technical solution is: in S2, the process of measuring the driver's heterogeneity parameters using the vehicle's spatiotemporal trajectory diagram is: SA1. Use tools to measure the density and flow of the following vehicle fleet. Then, use the Newell following model and the absolute speed and density of the driver during the actual following period to calculate the actual time delay parameter. Specifically, the density and flow of the following vehicle fleet can be measured using the trajectory explorer tool; then, the formula in the Newell model can be used to calculate the density and flow of the following vehicle fleet. Get a series of time delays of the following driver during the actual following period , that is, the actual time hysteresis parameter , u is the absolute speed of the traffic wave, k is the density of the traffic flow; SA2, calculate the ideal time hysteresis parameters using the Newell car following model and preset constants; Specifically, based on the formula in the Newell model Assuming that the wave speed u of the following driver is constant during the ideal following period, k can be extracted based on the Edie method, and the ideal time hysteresis parameter can be obtained. ; SA3, calculated based on actual time hysteresis parameters and ideal time hysteresis parameters , the calculation formula is: ,in, is the actual time hysteresis parameter, is the ideal time hysteresis parameter; SA4, according to the formula Calculate quantitative indicators ; SA5. Standardized quantitative indicators , that is, the actual following time and distance are scaled to 1min*1km; it can be seen that the proposed quantitative indicators It not only reflects the deviation between instantaneous driving response and ideal behavior, but also takes into account the time series accumulation effect. It can effectively capture the driver's behavioral stability and deviation trend during traffic oscillation, and improve the accuracy and completeness of driving style recognition.

[0038] A further preferred technical solution is: in S2, the process of using the improved Newell model combined with the dynamic time warping algorithm to obtain the number of times the driver follows the vehicle is: SB1. Obtain the time series trajectory data of the preceding and following vehicles in the current road section based on the vehicle trajectory data of the following vehicle fleet, and perform piecewise linear approximation processing on the time series trajectory data to obtain a trajectory point set; SB2. Construct a cost matrix based on the difference in vehicle speed or spatial position to quantify the matching cost between trajectory points, and add constraints when constructing the cost matrix; SB3. Use the dynamic time warping algorithm to backtrack the path to obtain the optimal matching path and obtain the characteristic points of the following vehicle's response to the behavior of the preceding vehicle; SB4. Count the total number of matching points based on the optimal matching path and record it as the number of times the driver follows the vehicle.

[0039] Based on the above principles, the statistics of the number of car following are further explained: To quantify the emission impact of each car-following behavior, the number of car-following events in the observation data needs to be calculated. Based on the Newell car-following model, this paper combines the improved Newell model with the dynamic time warping algorithm to obtain the number of car-following events of the driver. The specific process is as follows: like Figure 2As shown, first, the time series trajectory data of the front and rear vehicles in the target section, that is, the front and rear vehicle trajectory data, are obtained, and the trajectory data is piecewise linearly approximated to obtain a set of feature points of the trajectory; then, a cost matrix is ​​constructed. Specifically, in the process of constructing the cost matrix, the cost matrix is ​​calculated based on the speed data, and then the cumulative cost matrix is ​​calculated through time and space constraints. Finally, constraints are added, and the constraints include boundary constraints, monotonicity constraints, and continuity constraints; then, the dynamic time warping algorithm is used to backtrack the path to obtain the optimal matching path, and the feature points of the rear vehicle's response to the front vehicle's behavior are found to obtain the stimulus-response matching points of the front and rear vehicles; and the stimulus-response matching points of the front and rear vehicles are standardized and converted into the number of following behavior responses within unit time * unit distance (1min*1km). The purpose is to eliminate the influence of trajectory data with different following time lengths on the total number of matching points and perform time standardization on the total number of matching points.

[0040] Specifically, for quantifying the matching cost between trajectory points, the above constraints include the following constraints: a. The reaction time is greater than zero to avoid physical unreasonableness; b. The following distance is greater than zero to ensure driving safety; c. The matching path must meet the continuity and monotonicity of the starting boundary and time sequence; d. Introduce nonlinear penalty terms to prevent non-physical matching results.

[0041] Specifically, the idea of ​​the dynamic time warping algorithm is as follows: The first step is to input two simplified time series data, namely vehicle trajectory data, which respectively represent the data of the speed or position changes of the two vehicles over time; The second step is to initialize the cost matrix D as follows: Initialize the matrix D: the dimensions are (len(sequence1) + 1) x (len(sequence2) + 1); The third step is to set the boundary conditions, usually the cost of the starting point is 0, as follows: D[0][0]= 0; Step 4: Fill in the cost matrix as follows: For i from 1 to len (sequence 1): For j from 1 to len (sequence 2): Calculate the current cost C(i, j) = abs(sequence1[i] - sequence2[j]) #Calculate the cumulative cost and select the minimum matching path; D[i][j]= C(i,j) + min(D[i-1][j], D[i][j-1], D[i-1][j-1]); Step 5: Backtrack to find the optimal matching path, as follows: optimal_path = empty list i = len(sequence1) j = len(sequence2) #Backtrack from the end point to the starting point When i>0 and j>0: Add (i, j) to optimal_path # Backtracking path: choose the direction with the minimum cumulative cost If D[i-1][j]<= D[i][j-1] and D[i-1][j]<= D[i-1][j-1]: i = i-1 Otherwise if D[i][j-1]<= D[i-1][j] and D[i][j-1]<= D[i-1][j-1]: j = j-1 otherwise: i = i-1 j = j-1 Step 6: Calculate the driver's reaction time, vehicle distance and other parameters as follows: For each matching point (i, j) in optimal_path: Calculate the total number of matching points sumD Return optimal_path, sumD Step 7: Output the optimal matching path and calculate the total number of matching points based on the matching results.

[0042] A further preferred technical solution is: in S3, the process of estimating the emission factors of road traffic pollutants is: Based on the vehicle trajectory data of the following vehicle fleet, the driving environment parameters, vehicle technical condition parameters and vehicle operating condition parameters are input into the MOVES model; The driving environment parameters include the length and slope of the road section, the vehicle technical condition parameters include the age distribution and inspection and maintenance system, and the vehicle operating condition parameters include speed and acceleration; The operating condition classification method is used to map the driver's following behavior to the operating mode defined in the MOVES model, and the localized emission factor library is called to output the emission factors of road traffic pollutants.

[0043] The MOVES model refers to the Motor Vehicle Emission Simulator model, which is localized based on the actual traffic environment characteristics to estimate the emission factors of road traffic pollutants. Specifically, to adapt to the actual conditions of the study area, the MOVES model requires localized input parameters as shown in Table 3: Table 3 Input parameters In summary, based on the collected vehicle trajectory data, driving environment parameters, vehicle technical condition parameters, and vehicle operating condition parameters are input into the MOVES model. The operating condition classification method is used to map the driver's following behavior to the operating mode defined in the MOVES model. The localized emission factor library is called to output the emission factors of road traffic pollutants, which can achieve an accurate estimation of the emission impact of specific driving behaviors.

[0044] A further preferred technical solution is: since the driver characteristic index is an independent variable used to characterize the driver's following behavior and is related to speed and acceleration, step S4 includes the following steps: S41. Divide the emission factor by the number of times you follow a vehicle to obtain the emissions from a single following behavior; S42. Use variance inflation factors to check quantitative indicators Collinearity with driver characteristic indicators: independent variables with VIF values ​​greater than the preset value in the inspection results will be deleted; S43, use backward elimination method to screen independent variables; S44, estimating model parameters of the analysis model by using a maximum likelihood estimation method; S45, evaluating the analysis module by calculating the degree of fit between the predicted value of the analysis model and the actual observed value; S46. Combine the descriptive statistical results and partial dependence diagrams of the analysis model to visually analyze and explain the relationship between the independent variables and emission factors.

[0045] Based on the above principles, the analysis of the impact of driver following behavior and vehicle emissions is further elaborated: Because most existing technologies for modeling the relationship between driving behavior and traffic emissions rely on linear models, it is difficult to reveal the potential nonlinear effects between variables and cannot accurately capture the non-constant impact of driving behavior parameters (such as acceleration, speed fluctuations, etc.) on emission factors within different numerical ranges.

[0046] Therefore, the present invention proposes to construct a semi-parametric generalized additive model that combines a generalized linear model and smoothing function technology, which can effectively analyze the complex nonlinear relationship between driving behavior and various pollutant emission factors.

[0047] Specifically, the construction steps are as follows: (1) The emission pollution factor is divided by the number of times of following a vehicle to obtain the emission generated by a single following behavior; (2) Check the independent variables (quantitative indicators ) and the collinearity between the other twelve independent variables related to speed and acceleration. Specifically, the variance inflation factor was used to check the quantitative indicators. Collinearity with driver characteristic indicators: Variables with VIF values ​​greater than 10 were deleted to ensure that there was no strong collinearity between the independent variables entering the analysis model. (3) Variable selection: The backward elimination method is used to screen the independent variables, which can eliminate variables with small contributions to the model and retain variables with high significance to improve the interpretability and simplicity of the model; (4) Model solution: Estimating model parameters using the maximum likelihood estimation method can ensure the stability and effectiveness of the fitting; (5) Model evaluation: The fitting effect of the model can be evaluated by calculating the degree of fit between the model prediction value and the actual observation value; (6) Result analysis: Combining the model descriptive statistical results and partial dependence diagrams, the relationship between variables and target factors can be visually analyzed and interpreted.

[0048] In summary, the present invention provides a method and system for analyzing the impact of driver following behavior and vehicle emissions. To address the problem that the existing technology lacks an in-depth characterization of the relationship between real driving behavior characteristics and emissions, making it difficult to meet the needs of refined management of traffic emissions, an improved driving behavior modeling and emission assessment technical solution is proposed. By combining real road driving trajectory data to extract the driver's driving characteristic parameters, a quantitative indicator of the driver's behavior deviation from the ideal following state is introduced into the improved Newell model. , combining it with the dynamic time warping algorithm, can accurately identify the frequency of following vehicles and achieve a comprehensive characterization of driving behavior heterogeneity; then, the localized MOVES model is used to accurately estimate vehicle emissions; finally, a semi-parametric generalized additive model is constructed, which enables the present invention to reveal the nonlinear correlation between various driving behavior independent variables and typical traffic pollutant emission factors.

[0049] Example 2 A system for analyzing the impact of driver-following behavior and vehicle emissions, applying the aforementioned method for analyzing the impact of driver-following behavior and vehicle emissions, comprises: Data processing and analysis module: This module filters vehicle trajectory data to obtain a fleet of vehicles, extracts driver characteristic indicators based on the vehicle trajectory data of the fleet, and visualizes the spatiotemporal trajectories of vehicles based on the vehicle trajectory data; Driver Following Behavior Extraction Module: This module uses the vehicle's spatiotemporal trajectory graph to measure and obtain driver heterogeneity parameters. These heterogeneity parameters are then introduced into an improved Newell model. The improved Newell model is then combined with a dynamic time warping algorithm to statistically calculate the number of times a driver follows a vehicle, thereby characterizing the heterogeneity of driver following behavior. Emission factor calculation module: Based on the vehicle trajectory data collected from the fleet, driving environment parameters, vehicle technical condition parameters, and vehicle operating condition parameters are obtained and input into the localized MOVES model to estimate the emission factors of road traffic pollutants; Analysis model construction module: Construct a semi-parametric generalized additive model to analyze the nonlinear correlation between driver following behavior and emission factors of road traffic pollutants.

[0050] The above description is merely a preferred embodiment of the present invention and does not constitute any form of limitation to the present invention. Based on the technical essence of the present invention and within the spirit and principles of the present invention, any simple modification, equivalent replacement and improvement of the above embodiment shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. A method for analyzing the impact of driver following behavior and vehicle emissions, characterized in that: The method comprises the following steps: S1. deriving a fleet of vehicles by filtering vehicle trajectory data, extracting driver characteristic indicators based on the vehicle trajectory data of the fleet, and visualizing the spatiotemporal trajectories of the vehicles based on the vehicle trajectory data; S2. Measure the driver's heterogeneity parameters using the vehicle's spatiotemporal trajectory graph. The heterogeneity parameters are used to introduce into an improved Newell model. The improved Newell model is combined with a dynamic time warping algorithm to statistically obtain the number of times a driver follows a vehicle, thereby characterizing the heterogeneity of the driver's following behavior. S3. Driving environment parameters, vehicle technical condition parameters, and vehicle operating condition parameters are collected based on the vehicle trajectory data of the following vehicle fleet, and these parameters are input into the localized MOVES model to estimate emission factors of road traffic pollutants; S4. Construct a semi-parametric generalized additive model to analyze the nonlinear correlation between driver following behavior and emission factors of road traffic pollutants.

2. The method for analyzing the impact of driver following behavior and vehicle emissions according to claim 1, characterized in that: The driver characteristic indicators include maximum speed, minimum speed, average speed, speed standard deviation, maximum acceleration, minimum acceleration, average acceleration, acceleration standard deviation, average positive acceleration, average negative acceleration, positive acceleration standard deviation, and negative acceleration standard deviation.

3. The method for analyzing the impact of driver following behavior and vehicle emissions according to claim 1, characterized in that: In S1, the process of visualizing the vehicle's spatiotemporal trajectory based on the vehicle trajectory data is as follows: The vehicle's travel time and corresponding spatial position are obtained based on the vehicle trajectory data of the following vehicle fleet, and the vehicle's travel time and spatial position are plotted into a two-dimensional image to form a vehicle time-space trajectory diagram.

4. The method for analyzing the impact of driver following behavior and vehicle emissions according to claim 1, characterized in that: In S2, the process of obtaining the driver's heterogeneity parameters by measuring the vehicle's spatiotemporal trajectory graph is as follows: SA1. Use tools to measure the density and flow of the following vehicle fleet. Then, use the Newell following model and the absolute speed and density of the driver during the actual following period to calculate the actual time delay parameter. SA2, calculate the ideal time hysteresis parameters using the Newell car following model and preset constants; SA3, calculated based on actual time hysteresis parameters and ideal time hysteresis parameters , the calculation formula is: ,in, is the actual time hysteresis parameter, is the ideal time hysteresis parameter; SA4, according to the formula Calculate quantitative indicators ; SA5. Standardized quantitative indicators , that is, the actual following time and distance are scaled down to 1min*1km.

5. The method for analyzing the impact of driver following behavior and vehicle emissions according to claim 4, characterized in that: In S2, the process of using the improved Newell model combined with the dynamic time warping algorithm to obtain the number of times a driver follows a car is as follows: SB1. Obtain the time series trajectory data of the preceding and following vehicles in the current road section based on the vehicle trajectory data of the following vehicle fleet, and perform piecewise linear approximation processing on the time series trajectory data to obtain a trajectory point set; SB2. Construct a cost matrix based on the difference in vehicle speed or spatial position to quantify the matching cost between trajectory points, and add constraints when constructing the cost matrix; SB3. Use the dynamic time warping algorithm to backtrack the path to obtain the optimal matching path and obtain the characteristic points of the following vehicle's response to the behavior of the preceding vehicle; SB4. Count the total number of matching points based on the optimal matching path and record it as the number of times the driver follows the vehicle.

6. The method for analyzing the impact of driver following behavior and vehicle emissions according to claim 1, characterized in that: In S3, the process of estimating the emission factors of road traffic pollutants is as follows: Based on the vehicle trajectory data of the following vehicle fleet, the driving environment parameters, vehicle technical condition parameters and vehicle operating condition parameters are input into the MOVES model; The driving environment parameters include the length and slope of the road section, the vehicle technical condition parameters include the age distribution and inspection and maintenance system, and the vehicle operating condition parameters include speed and acceleration; The operating condition classification method is used to map the driver's following behavior to the operating mode defined in the MOVES model, and the localized emission factor library is called to output the emission factors of road traffic pollutants.

7. The method for analyzing the impact of driver following behavior and vehicle emissions according to claim 4, characterized in that: The driver characteristic index is an independent variable related to speed and acceleration and used to characterize the driver's following behavior. Step S4 includes the following steps: S41. Divide the emission factor by the number of times you follow a vehicle to obtain the emissions from a single following behavior; S42. Use variance inflation factors to check standardized quantitative indicators Collinearity with driver characteristic indicators: independent variables with VIF values ​​greater than the preset value in the inspection results will be deleted; S43, use backward elimination method to screen independent variables; S44, estimating model parameters of the analysis model by using a maximum likelihood estimation method; S45, evaluating the analysis module by calculating the degree of fit between the predicted value of the analysis model and the actual observed value; S46. Combine the descriptive statistical results and partial dependence diagrams of the analysis model to visually analyze and explain the relationship between the independent variables and emission factors.

8. The method for analyzing the impact of driver following behavior and vehicle emissions according to claim 1, characterized in that: In S1, the process of obtaining the following vehicle fleet by filtering the vehicle trajectory data is as follows: SC1. Filtering individual vehicles based on the vehicle trajectory data to obtain a first vehicle, wherein the lateral position of the first vehicle on the lane does not change during an observation period; SC2, comparing the longitudinal position of the first vehicle during the observation period to obtain a vehicle sequence that is tracked one by one in a specific lane; SC3. Determine the order of the leading and trailing vehicles in the vehicle sequence, filter out the driving trajectories of the leading and trailing vehicles for a preset time period, and record them as vehicle trajectory data.

9. A driver following behavior and vehicle emission impact analysis system, characterized in that: The method for analyzing the impact of driver following behavior and vehicle emissions as described in any one of claims 1 to 8 is applied, comprising: Data processing and analysis module: This module filters vehicle trajectory data to obtain a fleet of vehicles, extracts driver characteristic indicators based on the vehicle trajectory data of the fleet, and visualizes the spatiotemporal trajectories of vehicles based on the vehicle trajectory data; Driver Following Behavior Extraction Module: This module uses the vehicle's spatiotemporal trajectory graph to measure and obtain driver heterogeneity parameters. These heterogeneity parameters are then introduced into an improved Newell model. The improved Newell model is then combined with a dynamic time warping algorithm to statistically calculate the number of times a driver follows a vehicle, thereby characterizing the heterogeneity of driver following behavior. Emission factor calculation module: Based on the vehicle trajectory data collected from the fleet, driving environment parameters, vehicle technical condition parameters, and vehicle operating condition parameters are obtained and input into the localized MOVES model to estimate the emission factors of road traffic pollutants; Analysis model construction module: Construct a semi-parametric generalized additive model to analyze the nonlinear correlation between driver following behavior and emission factors of road traffic pollutants.

Images