Intersection traffic adaptive control optimization decision method and system based on electric police data
By using a multiple linear regression model based on electronic traffic enforcement data, the adaptive traffic control at intersections was optimized, solving the problem of traditional strategies lacking specificity, improving intersection capacity and reducing traffic congestion.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SUZHOU IND PARK SURVEYING MAPPING & GEOINFORMATION CO LTD
- Filing Date
- 2023-11-27
- Publication Date
- 2026-06-09
Smart Images
Figure CN117636629B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of intersection traffic signal optimization, and in particular to an intersection traffic adaptive control optimization decision-making method and system based on electronic police data. Background Technology
[0002] With rapid urban development and a dramatic increase in the number of motor vehicles, traffic congestion has gradually become a major problem restricting urban development. Traditional adaptive signal control decision-making methods typically derive signal control schemes based on real-time monitoring, using limited traffic factors such as queue length and flow rate. These schemes lack detailed decision-making for controlling intersections with different characteristics. This lack of specificity in adaptive control strategies leads to low intersection capacity and frequent traffic congestion. Summary of the Invention
[0003] Purpose of the invention: To propose an adaptive traffic control optimization decision-making method for intersections based on electronic traffic enforcement data, and further to propose a system for implementing the above optimization decision-making method. While ensuring the signal control effect, the system can provide corresponding decision-making schemes for intersections with different characteristics, thereby effectively solving the above-mentioned problems existing in the prior art.
[0004] Firstly, a method for adaptive traffic control optimization decision-making at intersections based on electronic traffic enforcement data is proposed, with the following steps:
[0005] S1. At single-point fixed control intersections, a single-point adaptive control scheme is activated. After the traffic flow stabilizes, vehicle passage data at different times is collected through electronic police equipment.
[0006] S2. Match the periodic traffic flow data in the vehicle passage data, calculate the intersection capacity based on the periodic traffic flow data, calculate the intersection capacity evaluation index based on the capacity, and obtain the adaptive intersection control effect.
[0007] S3. Using the adaptive intersection control effect as the dependent variable and the intersection traffic flow, vehicle type, signal cycle, and driving behavior collected by the electronic police equipment as independent variables, a multiple linear regression model is established.
[0008] S4. Perform multiple linear regression analysis on the multiple linear regression model, and provide optimization decision suggestions based on the analysis results and preset decision criteria to help optimize the adaptive control intersection.
[0009] In a further embodiment of the first aspect, the vehicle data in step S1 includes vehicle passage time, vehicle type, vehicle entrance, vehicle lane, and driving behavior.
[0010] Step S2 involves matching and obtaining periodic traffic flow data from the vehicle passage data, including:
[0011] By matching the vehicle passage time with the periodic and phase operation data of the adaptive control system, the periodic flow data under the adaptive control mode is obtained;
[0012] Based on the vehicle passage time and the single-point fixed control cycle scheme, the cycle flow data under single-point fixed control is obtained.
[0013] In a further embodiment of the first aspect, the capacity of a single-point signalized intersection is obtained based on the periodic traffic flow data under the single-point fixed control:
[0014]
[0015] In the formula, C d Q represents the capacity of a single-point signalized intersection. dn This represents the periodic flow data under single-point fixed control, where T0 represents the fixed period duration of the intersection.
[0016] In a further embodiment of the first aspect, the capacity of the adaptive intersection is obtained based on the periodic traffic flow data under the adaptive control mode:
[0017]
[0018] In the formula, C z Q represents the capacity of an adaptive intersection. zn T represents the periodic flow data in adaptive control mode. n This indicates the adaptive cycle duration of the intersection.
[0019] In a further embodiment of the first aspect, the step S2 of calculating the intersection capacity evaluation index based on the capacity includes:
[0020] Based on the capacity C of the single-point signalized intersection d Adaptive intersection capacity C z The intersection capacity evaluation index was calculated as follows:
[0021]
[0022] In the formula, P t This represents the intersection capacity evaluation index, where P... t This is initially used as a criterion for determining whether to enable adaptive control.
[0023] In a further embodiment of the first aspect, obtaining the adaptive intersection control effect in step S2 includes:
[0024] The intersection capacity evaluation index P tAs an indicator for evaluating the effectiveness of adaptive intersection control, the expression for the effectiveness of adaptive intersection control is as follows:
[0025]
[0026] In the formula, E adapt Indicates the effectiveness of adaptive intersection control; C d Indicates the capacity of a single-point signalized intersection; C z This indicates the capacity of an adaptive intersection.
[0027] In a further embodiment of the first aspect, the expression for the multiple linear regression model in step S3 is as follows:
[0028] E adapt =β0+β1X1+β2X2+β3X3+β4X4+ε
[0029] In the formula, E adapt The adaptive intersection control effect is represented by X1, X2, X3, and X4, which represent intersection traffic flow, vehicle type, signal cycle, and driving behavior, respectively; β0 is a constant term; β1, β2, β3, and β4 represent the regression coefficients of intersection traffic flow, vehicle type, signal cycle, and driving behavior, respectively; ε is the error term.
[0030] Wherein, the vehicle type represents the proportion of trucks; the driving behavior represents the proportion of abnormal behavior.
[0031] In a further embodiment of the first aspect, step S4 involves performing multiple linear regression analysis on the multiple linear regression model, including:
[0032] Use statistical software to perform multiple linear regression analysis and calculate the regression coefficients.
[0033] The model was subjected to a significance test, and the F-test was used to determine the model's fit.
[0034] Perform a t-test on multiple independent variables to determine whether the selected independent variables have a significant effect on the dependent variable;
[0035] Using the coefficient of determination R 2 The goodness of fit of the model is evaluated, and the linear regression hypothesis is determined by the residual plot of the model.
[0036] In a further embodiment of the first aspect, the provision of optimization decision suggestions in step S4 includes:
[0037] Determine the influence relationship of different independent variables on the adaptive intersection control effect; the influence relationship includes positive influence, negative influence, and no influence;
[0038] Based on the aforementioned influencing relationships, the following decision-making recommendations are provided:
[0039] The positive impact is to increase the periodic traffic flow at the current adaptive intersection; for example, by improving road connectivity and providing more accurate traffic information to attract more vehicles to use the intersection.
[0040] For the negative impact, the adaptive cycle setting range is narrowed to reduce vehicle waiting time and improve traffic efficiency.
[0041] If there is no impact, then no action will be taken on the current adaptive intersection.
[0042] A second aspect of the present invention provides an adaptive traffic control optimization decision system for intersections, the system comprising:
[0043] The data collection module is used to enable the single-point adaptive control scheme at single-point fixed control intersections. After the traffic flow stabilizes, the electronic police equipment collects vehicle data at different time periods.
[0044] The data processing unit is used to match and obtain the periodic traffic flow data in the vehicle passage data, calculate the intersection capacity based on the periodic traffic flow data, calculate the intersection capacity evaluation index based on the capacity, and obtain the adaptive intersection control effect.
[0045] The analysis module is used to establish a multiple linear regression model by taking the adaptive intersection control effect as the dependent variable and the intersection traffic flow, vehicle type, signal cycle, and driving behavior collected by the electronic police equipment as independent variables.
[0046] The decision module is used to perform multiple linear regression analysis on the multiple linear regression model, and provide optimization decision suggestions based on the analysis results and preset decision criteria to help optimize the adaptive control intersection.
[0047] Compared with existing technologies, this invention has the following advantages: This invention introduces a data analysis-based evaluation method to assess the effectiveness of adaptive control and support corresponding decision-making. By collecting a large amount of traffic data and combining it with advanced mathematical models and analysis techniques, traffic conditions can be accurately assessed, providing a scientific and reasonable basis for traffic signal control decisions. This data analysis and optimization method based on electronic traffic enforcement data can help optimization personnel make different decisions for intersections with different characteristics, identify key influencing factors of intersection congestion, and make targeted optimizations, thereby improving the effectiveness of adaptive control at intersections. Attached Figure Description
[0048] Figure 1 This is a flowchart of an intersection traffic adaptive control optimization decision-making method based on electronic police data.
[0049] Figure 2 This is a graph showing the results of a multiple linear regression analysis model.
[0050] Figure 3 This is a graph of coefficients from a multiple linear regression analysis.
[0051] Figure 4 This is a schematic diagram of an intersection traffic adaptive control optimization decision-making system. Detailed Implementation
[0052] In the following description, numerous specific details are set forth in order to provide a more thorough understanding of the invention. However, it will be apparent to those skilled in the art that the invention can be practiced without one or more of these details. In other instances, certain technical features well-known in the art have not been described in order to avoid obscuring the invention.
[0053] Example 1:
[0054] This embodiment discloses a feasible scheme for an adaptive traffic control optimization decision-making method at intersections, with the following specific steps:
[0055] 1) Collect and organize data through electronic police and signal control systems, establish a multiple linear regression model based on the collected data, and analyze and evaluate the adaptive effect of the intersection.
[0056] 2) Evaluate the adaptive operation effect based on the multiple linear regression model.
[0057] 3) Based on the model results, derive corresponding suggested decision-making solutions.
[0058] Step 1) above involves the following steps in the data collection and processing of the electronic alarm and signal control systems:
[0059] 1.1) Obtain vehicle passage data at adaptive control intersections through electronic police equipment. The data includes vehicle passage time, vehicle type, vehicle entrance, corresponding lane, driving behavior, etc.
[0060] 1.2) Obtain the phase and cycle operation information of the adaptive control intersection through the signal control system, including the adaptive cycle operation time point, cycle duration and phase duration, etc.
[0061] 1.3) Process the electronic traffic enforcement system data and match the data by the electronic traffic enforcement system vehicle passage time, adaptive cycle operation time point and cycle duration to obtain the intersection traffic flow within a single adaptive operation cycle.
[0062] 1.4) Calculate intersection capacity based on the adaptive cycle. Intersection capacity refers to the traffic flow through the intersection per unit time. To analyze the capacity of adaptive intersections, the unit time is specified as the intersection's signal cycle, facilitating a comparison of the unit cycle capacity before and after adaptive control is implemented. The following is the calculation formula for single-point signal control at the intersection:
[0063]
[0064] Among them, C d Q represents the capacity of a single-point signalized intersection. dn T0 represents the traffic flow within a fixed cycle at the intersection, and T0 represents the duration of the fixed cycle at the intersection.
[0065] The following are the calculation formulas for the adaptive intersection scenario:
[0066]
[0067] Among them, C z Q represents the capacity of an adaptive intersection. zn T represents the traffic flow during the intersection's adaptive cycle. n This indicates the adaptive cycle duration of the intersection.
[0068]
[0069] Among them, P t This represents the intersection capacity evaluation index, where P... t This is initially used as a criterion for determining whether to enable adaptive control.
[0070] Once the conditions for enabling adaptive control are met, the effectiveness of adaptive control is characterized by the intersection capacity evaluation index.
[0071]
[0072] Step 2) above involves the following steps in the analysis of the multiple linear regression model:
[0073] 2.1) A multiple linear regression model was established with the adaptive intersection control effect as the dependent variable (Y) and the intersection traffic flow, vehicle type (proportion of trucks), signal cycle and driving behavior (proportion of abnormal behavior) data as independent variables (X).
[0074] Y=β0+β1X1+β2X2+β3X3+β4X4+ε
[0075] Where β0 is the constant term, β1 to β4 are the regression coefficients of each independent variable, and ε is the error term.
[0076] 2.2) Use statistical software to perform multiple linear regression analysis and calculate the regression coefficients.
[0077] 2.3) Perform a significance test on the model and use the F-test to judge the model's fit.
[0078] 2.4) Perform a t-test on multiple independent variables to determine whether the selected independent variables have a significant effect on the dependent variable.
[0079] 2.5) Using the coefficient of determination R 2 The goodness of fit of the model is evaluated, and the linear regression hypothesis is determined by the residual plot of the model.
[0080] The decision-making and optimization measures in step 3) above include the following steps:
[0081] 3.1) Determine the influence of different independent variables on the effect of adaptive intersection control.
[0082] 3.2) Develop reference standards for relevant decisions based on expert advice and experience in handling related issues.
[0083] Table 1 below shows the decision-making methods and measures.
[0084] Table 1: Decision-making methods and measures
[0085]
[0086]
[0087] Example 2:
[0088] To facilitate understanding of the present invention, Example 2 is given below using the adaptive control intersection of Zhonghuayuan Road and Fengjing Road in Kunshan City, Suzhou City as an example:
[0089] 1) Select the intersection of Zhonghuayuan Road and Fengjing Road—a standard four-phase single-point signal-controlled intersection—and record the daily electronic traffic enforcement data under the fixed timing scheme. Enable the single-point adaptive control scheme. After the traffic flow stabilizes in adaptive control mode, obtain vehicle passage data for different time periods at the intersection through the electronic traffic enforcement system. Vehicle passage data is shown in Table 2. Adaptive cycle operation information data is shown in Table 3.
[0090] Table 2: Vehicle Passage Data
[0091] Serial Number Over time Lane name driving direction 1 9:00:00 Lane 1 From east to west 2 9:00:03 Lane 1 From east to west 3 9:00:10 Lane 3 From south to north 4 9:00:15 Lane 4 From east to west 5 9:00:20 Lane 4 From east to west … … … … 7803 15:59:59 Lane 1 From east to west
[0092] Table 3: Adaptive Cyclic Operation Information Data
[0093]
[0094]
[0095] 2) Data cleaning and processing are performed to match the vehicle passage time points of the electronic police system with the cycle and phase operation data of the adaptive control system, resulting in cycle flow data under adaptive control mode. Based on the vehicle passage time points of the electronic police system and the single-point fixed control cycle scheme, cycle flow data under single-point fixed timing control is obtained. Table 4 shows the cycle flow under adaptive mode; Table 5 shows the cycle flow under single-point control mode.
[0096] Table 4: Periodic Flow in Adaptive Mode
[0097] Serial Number Period start time cycle Phase 1 Phase Two Phase Three Phase Four End time of cycle Periodic traffic flow 1 9:00:26 186 35 33 61 57 9:03:32 80 2 9:03:32 184 26 44 61 53 9:06:36 90 3 9:06:36 156 31 26 51 48 9:09:12 58 4 9:09:12 146 35 26 59 26 9:11:38 53 5 9:11:38 149 35 26 38 50 9:14:07 36 6 9:14:07 178 32 36 49 61 9:17:05 59 7 9:17:05 171 33 26 52 60 9:19:56 68 8 9:19:56 174 39 32 46 57 9:22:50 68 … … … … … … … … … 135 16:00:58 184 26 49 61 48 16:04:02 0
[0098] Table 5: Periodic Flow Rate under Single-Point Control Mode
[0099]
[0100]
[0101] 3) The intersection capacity C is derived based on the periodic flow rate under adaptive control mode and the periodic flow rate under single-point fixed mode. z =0.42, C d =0.38, then P t =0.11, Y=11% satisfies the adaptive control activation condition.
[0102] 4) Under the condition that the adaptive control is enabled, a multiple linear regression model is established with intersection traffic flow, vehicle type (proportion of trucks), signal cycle and driving behavior data (proportion of abnormal behavior) as independent variables (X) and adaptive control effect as dependent variable (Y).
[0103] Y=β0+β1X1+β2X2+β3X3+β4X4+ε
[0104] 5) Select 100 data points as a sample and use SPASS statistical software to calculate the multiple linear regression coefficients. Table 6 shows the results of the linear regression analysis.
[0105] Table 6: Results of Linear Regression Analysis
[0106]
[0107] 6) As can be seen from Table 6 above, the model formula is: Traffic capacity = 0.439 + 0.005 * periodic traffic flow - 0.002 * period - 0.009 * vehicle type - 0.002 * driving behavior. The model R-squared value is 0.986, which means that periodic traffic flow, period, vehicle type, and driving behavior can explain 98.6% of the changes in traffic capacity.
[0108] 7) When the model was tested with the F-test, it was found that the model passed the F-test (F = 1654.392, p = 0.000 < 0.05), which means that at least one of the following factors—periodic traffic flow, cycle, vehicle type, and driving behavior—has an impact on traffic capacity. In addition, the test for multicollinearity of the model showed that all VIF values in the model were less than 5, which means that there is no multicollinearity problem; and the DW value was near the number 2, which means that the model has no autocorrelation and there is no correlation between the sample data. The model is good.
[0109] 8) The final detailed analysis shows that: the regression coefficient for cyclical traffic flow is 0.005 (t = 76.319, p = 0.000 < 0.01), indicating that cyclical traffic flow has a significant positive impact on traffic capacity. The regression coefficient for cycle is -0.002 (t = -32.873, p = 0.000 < 0.01), indicating that cycle has a significant negative impact on traffic capacity. The regression coefficient for vehicle type (proportion of trucks) is -0.009 (t = -1.531, p = 0.129 > 0.05), indicating that vehicle type does not have a significant impact on traffic capacity. The regression coefficient for driving behavior (proportion of abnormal behavior) is -0.002 (t = -0.196, p = 0.845 > 0.05), indicating that driving behavior does not have a significant impact on traffic capacity.
[0110] 9) The summary analysis shows that the cyclical traffic flow at this intersection has a significant positive impact on traffic capacity. Simultaneously, the cycle time has a significant negative impact on traffic capacity. However, vehicle type (proportion of trucks) and driving behavior (proportion of abnormal behaviors) do not have a significant impact on traffic capacity.
[0111] 10) Therefore, based on the results of the analysis module and the decision criteria, corresponding decision-making measures are taken:
[0112] 1. Increase intersection cycle traffic flow: Since cycle traffic flow has a positive impact on traffic capacity, measures can be considered to increase intersection traffic flow. For example, improving road connectivity and providing more accurate traffic information can attract more vehicles to use the intersection.
[0113] 2. Narrow the adaptive cycle setting range: The cycle has a negative impact on traffic capacity. It is advisable to appropriately shorten the cycle setting range of traffic lights to reduce vehicle waiting time and improve traffic efficiency.
[0114] 3. In addition, the types of vehicles and driving behavior at this intersection have not been significantly affected, so they can be temporarily disregarded.
[0115] Example 3:
[0116] This embodiment proposes an intersection traffic adaptive control optimization decision-making system 500, which includes a data collection module 501, a data processing unit 502, an analysis module 503, and a decision-making module 504. The data collection module 501 is used to activate a single-point adaptive control scheme at a fixed-point control intersection. After the traffic flow stabilizes, it collects vehicle passage data at different time periods using electronic traffic enforcement equipment. The data processing unit 502 is used to match and obtain periodic flow data from the vehicle passage data, calculate the intersection capacity based on the periodic flow data, and calculate the intersection capacity evaluation index based on the capacity to obtain the adaptive intersection control effect. The analysis module 503 is used to establish a multiple linear regression model, using the adaptive intersection control effect as the dependent variable and the intersection traffic flow, vehicle type, signal cycle, and driving behavior collected by the electronic traffic enforcement equipment as independent variables. The decision-making module 504 is used to perform multiple linear regression analysis on the multiple linear regression model, and based on the analysis results and preset decision criteria, provides optimization decision suggestions to help optimize the adaptive control intersection.
[0117] As described above, although the invention has been shown and described with reference to specific preferred embodiments, it should not be construed as limiting the invention itself. Various changes in form and detail may be made without departing from the spirit and scope of the invention as defined in the appended claims.
Claims
1. A method for adaptive traffic control optimization decision-making at intersections based on electronic traffic enforcement system (ECS) data, characterized in that, include: S1. At single-point fixed control intersections, a single-point adaptive control scheme is activated. After the traffic flow stabilizes, vehicle passage data at different times is collected through electronic police equipment. S2. Match the periodic traffic flow data in the vehicle passage data, calculate the intersection capacity based on the periodic traffic flow data, calculate the intersection capacity evaluation index based on the capacity, and obtain the adaptive intersection control effect. The calculation of the intersection capacity evaluation index based on the traffic capacity includes: Traffic capacity based on single-point signalized intersections Adaptive intersection capacity The intersection capacity evaluation index was calculated as follows: In the formula, This indicates the indicators for evaluating the capacity of intersections. This is initially used as a criterion for determining whether to enable adaptive control; The obtained adaptive intersection control effect includes: Intersection capacity evaluation indicators As an indicator for evaluating the effectiveness of adaptive intersection control, the expression for the effectiveness of adaptive intersection control is as follows: In the formula, This indicates the effectiveness of adaptive intersection control; S3. Using the adaptive intersection control effect as the dependent variable and the intersection traffic flow, vehicle type, signal cycle, and driving behavior collected by the electronic police equipment as independent variables, a multiple linear regression model is established. The expression for the multiple linear regression model is as follows: In the formula, , , , These represent traffic flow, vehicle type, signal cycle, and driving behavior at the intersection, respectively. It is a constant term; , , , These represent the intersection traffic flow regression coefficient, vehicle type regression coefficient, signal cycle regression coefficient, and driving behavior regression coefficient, respectively; ε is the error term. Wherein, the vehicle type represents the proportion of trucks; the driving behavior represents the proportion of abnormal behavior; S4. Perform multiple linear regression analysis on the multiple linear regression model, and provide optimization decision suggestions based on the analysis results and preset decision criteria to help optimize the adaptive control intersection.
2. The intersection traffic adaptive control optimization decision-making method according to claim 1, characterized in that, The vehicle data mentioned in step S1 includes vehicle passage time, vehicle type, vehicle entrance, vehicle lane, and driving behavior; Step S2 involves matching and obtaining periodic traffic flow data from the vehicle passage data, including: By matching the vehicle passage time with the periodic and phase operation data of the adaptive control system, the periodic flow data under the adaptive control mode is obtained; Based on the vehicle passage time and the single-point fixed control cycle scheme, the cycle flow data under single-point fixed control is obtained.
3. The intersection traffic adaptive control optimization decision-making method according to claim 2, characterized in that, Based on the periodic traffic flow data under the single-point fixed control, the capacity of the single-point signalized intersection is obtained: In the formula, Indicates the capacity of a single-point signalized intersection. This represents periodic flow data under single-point fixed control. This indicates the fixed cycle duration of the intersection.
4. The intersection traffic adaptive control optimization decision-making method according to claim 3, characterized in that, Based on the periodic traffic flow data under the adaptive control mode, the capacity of the adaptive intersection is obtained: In the formula, This indicates the capacity of an adaptive intersection. This represents the periodic flow data under adaptive control mode. This indicates the adaptive cycle duration of the intersection.
5. The intersection traffic adaptive control optimization decision-making method according to claim 1, characterized in that, Step S4 involves performing multiple linear regression analysis on the multiple linear regression model, including: Use statistical software to perform multiple linear regression analysis and calculate the regression coefficients. The model was subjected to a significance test, and the F-test was used to determine the model's fit. Perform a t-test on multiple independent variables to determine whether the selected independent variables have a significant effect on the dependent variable; Using the coefficient of determination The goodness of fit of the model is evaluated, and the linear regression hypothesis is determined by the residual plot of the model.
6. The intersection traffic adaptive control optimization decision-making method according to claim 1, characterized in that, The optimization decision suggestions provided in step S4 include: Determine the influence relationship of different independent variables on the adaptive intersection control effect; the influence relationship includes positive influence, negative influence, and no influence; Based on the aforementioned influencing relationships, the following decision-making recommendations are provided: For the aforementioned positive impact, the periodic traffic flow at the current adaptive intersection is increased; For the aforementioned negative impact, the adaptive cycle setting range is reduced; If there is no impact, then no action will be taken on the current adaptive intersection.
7. A traffic adaptive control optimization decision-making system for intersections, used to execute the traffic adaptive control optimization decision-making method for intersections according to any one of claims 1 to 6, characterized in that, include: The data collection module is used to enable the single-point adaptive control scheme at single-point fixed control intersections. After the traffic flow stabilizes, the electronic police equipment collects vehicle data at different time periods. The data processing unit is used to match and obtain the periodic traffic flow data in the vehicle passage data, calculate the intersection capacity based on the periodic traffic flow data, calculate the intersection capacity evaluation index based on the capacity, and obtain the adaptive intersection control effect. The analysis module is used to establish a multiple linear regression model by taking the adaptive intersection control effect as the dependent variable and the intersection traffic flow, vehicle type, signal cycle, and driving behavior collected by the electronic police equipment as independent variables. The decision module is used to perform multiple linear regression analysis on the multiple linear regression model, and provide optimization decision suggestions based on the analysis results and preset decision criteria to help optimize the adaptive control intersection.