CN115565373B - Expressway tunnel accident real-time risk prediction method, device, equipment and medium - Google Patents
Expressway tunnel accident real-time risk prediction method, device, equipment and medium Download PDFInfo
- Publication number
- CN115565373B CN115565373B CN202211170362.6A CN202211170362A CN115565373B CN 115565373 B CN115565373 B CN 115565373B CN 202211170362 A CN202211170362 A CN 202211170362A CN 115565373 B CN115565373 B CN 115565373B
- Authority
- CN
- China
- Prior art keywords
- accident
- data
- tunnel
- import
- traffic flow
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 230000008676 import Effects 0.000 claims abstract description 89
- 238000013058 risk prediction model Methods 0.000 claims abstract description 49
- 208000024891 symptom Diseases 0.000 claims abstract description 24
- 239000002243 precursor Substances 0.000 claims abstract description 23
- 238000012549 training Methods 0.000 claims abstract description 19
- 230000004927 fusion Effects 0.000 claims description 45
- 238000004590 computer program Methods 0.000 claims description 20
- 230000001419 dependent effect Effects 0.000 claims description 9
- 238000007499 fusion processing Methods 0.000 claims description 9
- 238000007477 logistic regression Methods 0.000 claims description 7
- 238000012512 characterization method Methods 0.000 claims description 4
- 230000000875 corresponding effect Effects 0.000 description 45
- 230000008569 process Effects 0.000 description 8
- 238000001514 detection method Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 6
- 238000012360 testing method Methods 0.000 description 6
- 230000004044 response Effects 0.000 description 4
- 206010039203 Road traffic accident Diseases 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000002265 prevention Effects 0.000 description 3
- 238000013145 classification model Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009440 infrastructure construction Methods 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/048—Detecting movement of traffic to be counted or controlled with provision for compensation of environmental or other condition, e.g. snow, vehicle stopped at detector
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/065—Traffic control systems for road vehicles by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count
Abstract
The application is applicable to the technical field of traffic safety, and provides a method, a device, equipment and a medium for predicting real-time risk of expressway tunnel accidents, wherein the method comprises the following steps: acquiring accident data, import and export traffic flow data and weather data of a target tunnel in a preset historical time period; acquiring import and export traffic flow data and weather data corresponding to each accident of a target tunnel in a preset historical time period, and acquiring comparison data of the import and export traffic flow data and the weather data; taking the import and export traffic flow data, weather data and comparison data as an experimental data set; extracting accident pre-symptom characteristics affecting tunnel accident risks based on the experimental data set; training a tunnel accident real-time risk prediction model based on the experimental data set and the accident precursor characteristics; and predicting the tunnel accident risk in real time based on the trained tunnel accident real-time risk prediction model. The method and the system can predict the accident risk of the expressway tunnel in real time.
Description
Technical Field
The application belongs to the technical field of traffic safety, and particularly relates to a method, a device, equipment and a medium for predicting real-time risk of expressway tunnel accidents.
Background
Tunnels are considered as important sections of highways due to their important roles in reducing transit time, protecting ecological environment, improving highway operation, etc. With the gradual development of infrastructure construction, expressway traffic mileage is continuously increased. The number of tunnels has increased significantly over the past few years and is still growing continuously.
However, since tunnels are generally less illuminated than open roads and have a semi-closed space structure, they may affect the behavior of drivers, thereby more easily causing traffic collisions and further causing collision accidents to occur. Therefore, research aimed at improving the traffic safety of tunnels has a certain significance for improving the safety level of expressway systems.
At present, most of researches on tunnel traffic safety are focused on the statistical analysis of collision characteristics, collision frequency and factors affecting injury severity of collision data based on historical accident record data, and lack of real-time performance, so that the method has a certain limitation in practical application. In recent years, real-time risk analysis prediction of accidents becomes a hotspot, however, the current real-time risk prediction of expressway tunnel traffic accidents is still in a blank stage.
Disclosure of Invention
The embodiment of the application provides a method, a device, equipment and a medium for predicting real-time risk of expressway tunnel accidents, which can solve the problem that the expressway tunnel accident risk cannot be predicted in real time.
In a first aspect, an embodiment of the present application provides a real-time risk prediction method for an expressway tunnel accident, including:
acquiring accident data and import-export traffic flow data of a target tunnel in a preset historical time period;
respectively matching target import and export traffic flow data within n minutes before the accident occurs from the import and export traffic flow data according to each accident in the accident data, and determining weather data of the area where the target tunnel is located within n minutes before the accident occurs; n is an integer, and n is more than or equal to 5 and less than or equal to 15;
respectively carrying out fusion processing on the traffic flow data of the target import and export corresponding to each accident and the weather data to obtain accident fusion data of the accident, and obtaining comparison data of the accident fusion data;
taking accident fusion data and comparison data corresponding to all accidents in the accident data as an experimental data set;
determining accident precursors characteristic affecting tunnel accident risk based on the experimental data set;
Based on an experimental data set, training a tunnel accident real-time risk prediction model by taking accident precursor characteristics as independent variables and whether an accident occurs as the dependent variables, so as to obtain a trained tunnel accident real-time risk prediction model;
collecting import and export traffic flow data of a target tunnel every n minutes and weather data of an area where the target tunnel is located; the import and export traffic flow data collected each time are the import and export traffic flow data in n minutes before the collection time, and the weather data collected each time are the weather data in n minutes before the collection time;
and extracting accident pre-symptom characteristic data from the acquired import and export traffic flow data and weather data according to independent variables of the tunnel accident real-time risk prediction model aiming at the import and export traffic flow data and the weather data acquired each time, and predicting tunnel accident risk based on the accident pre-symptom characteristic data and the trained tunnel accident real-time risk prediction model.
Optionally, determining, based on the experimental dataset, an accident pre-characterization that affects a risk of the tunnel accident, comprising:
defining a variable for each type of data in the experimental data set, and taking the type of data as the variable data;
Calculating a correlation value between the defined variables using the spearman correlation coefficient;
selecting a target variable from the defined variables according to the calculated correlation value;
calculating the influence value of each target variable on the tunnel accident risk by using a conditional Logistic regression model;
and determining accident premonition features influencing the tunnel accident risk according to the calculated influence values.
Optionally, selecting a target variable from the defined variables according to the calculated correlation value, including:
if the correlation value greater than the preset correlation value exists in the calculated correlation values, respectively calculating correlation coefficients between two variables corresponding to the correlation values and whether the accident occurs or not, and deleting the variable corresponding to the smaller correlation coefficient;
and taking other variables except the deleted variable in all the defined variables as target variables.
Optionally, determining the accident pre-characterization affecting the risk of the tunnel accident according to the calculated impact value includes:
and taking the target variable with the influence value smaller than or equal to the preset influence value and the target variable corresponding to the weather data as the accident pre-symptom characteristic for influencing the tunnel accident risk.
Optionally, the import and export traffic flow data includes: inlet flow, inlet average occupancy, inlet average vehicle speed, outlet flow, outlet average occupancy, and outlet average vehicle speed.
Optionally, obtaining the comparison data of the accident fusion data includes:
and obtaining control data of the accident fusion data by using a case control method.
In a second aspect, an embodiment of the present application provides a real-time risk prediction device for an expressway tunnel accident, including:
the first acquisition module is used for acquiring accident data and import-export traffic flow data of the target tunnel in a preset historical time period;
the data matching module is used for respectively matching the target import and export traffic flow data within n minutes before the accident happens from the import and export traffic flow data aiming at each accident in the accident data, and determining weather data of the area where the target tunnel is located within n minutes before the accident happens; n is an integer, and n is more than or equal to 5 and less than or equal to 15;
the second acquisition module is used for respectively carrying out fusion processing on the traffic flow data of the target import and export corresponding to the accident and the weather data aiming at each accident to obtain accident fusion data of the accident and acquiring comparison data of the accident fusion data;
The first determining module is used for taking accident fusion data and comparison data corresponding to all accidents in the accident data as an experimental data set;
a second determining module for determining, based on the experimental data set, accident precursors characteristic affecting the risk of tunnel accident;
the model training module is used for training a tunnel accident real-time risk prediction model based on the experimental data set by taking the accident precursor characteristics as independent variables and taking whether the accident occurs as dependent variables to obtain a trained tunnel accident real-time risk prediction model;
the data acquisition module is used for acquiring import and export traffic flow data of the target tunnel and weather data of the area where the target tunnel is located every n minutes; the import and export traffic flow data collected each time are the import and export traffic flow data in n minutes before the collection time, and the weather data collected each time are the weather data in n minutes before the collection time;
the risk prediction module is used for extracting accident pre-symptom characteristic data from the acquired import and export traffic flow data and weather data according to independent variables of the tunnel accident real-time risk prediction model aiming at the import and export traffic flow data and the weather data acquired each time, and predicting the tunnel accident risk based on the accident pre-symptom characteristic data and the trained tunnel accident real-time risk prediction model.
In a third aspect, an embodiment of the present application provides a terminal device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor implements the method for predicting real-time risk of an accident in a highway tunnel when executing the computer program.
In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, where a computer program is stored, where the computer program when executed by a processor implements the method for predicting real-time risk of an accident in a highway tunnel.
The scheme of the application has the following beneficial effects:
in the embodiment of the application, accident data, import and export traffic flow data and related weather data of the tunnel in a preset historical time period are analyzed to obtain import and export traffic flow data and weather data corresponding to each accident of the tunnel in the preset historical time period, and the import and export traffic flow data and the weather data corresponding to each accident are used as accident fusion data of the accident; then, aiming at each accident of the tunnel in a preset historical time period, acquiring comparison data corresponding to accident fusion data of the accident, and taking the accident fusion data and the comparison data corresponding to all the accidents in the preset historical time period as an experimental data set; analyzing the experimental data set, determining accident pre-symptom characteristics which have obvious influence on tunnel accident risk, and training a tunnel accident real-time risk prediction model based on the experimental data set by taking the accident pre-symptom characteristics as independent variables and whether an accident occurs as dependent variables to obtain a trained tunnel accident real-time risk prediction model; finally, the tunnel accident risk is predicted in real time based on the import and export traffic flow data, the weather data and the trained tunnel accident real-time risk prediction model which are acquired in real time, so that the real-time prediction of the expressway tunnel accident risk is realized, and further, a reference is provided for tunnel accident prevention measures, so that the driving safety of vehicles in a tunnel is improved by intervention in advance.
Other advantages of the present application will be described in detail in the detailed description section that follows.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following description will briefly introduce the drawings that are needed in the embodiments or the description of the prior art, it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a real-time risk prediction method for highway tunnel accidents according to an embodiment of the present application;
FIG. 2 is a schematic view of the ROC curve of a test result of the present application;
fig. 3 is a schematic structural diagram of a real-time risk prediction device for expressway tunnel accident according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of a terminal device according to an embodiment of the present application.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system configurations, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.
It should be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It should also be understood that the term "and/or" as used in this specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
As used in this specification and the appended claims, the term "if" may be interpreted as "when..once" or "in response to a determination" or "in response to detection" depending on the context. Similarly, the phrase "if a determination" or "if a [ described condition or event ] is detected" may be interpreted in the context of meaning "upon determination" or "in response to determination" or "upon detection of a [ described condition or event ]" or "in response to detection of a [ described condition or event ]".
In addition, in the description of the present application and the appended claims, the terms "first," "second," "third," and the like are used merely to distinguish between descriptions and are not to be construed as indicating or implying relative importance.
Reference in the specification to "one embodiment" or "some embodiments" or the like means that a particular feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the application. Thus, appearances of the phrases "in one embodiment," "in some embodiments," "in other embodiments," and the like in the specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments" unless expressly specified otherwise. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless expressly specified otherwise.
Aiming at the problem that the accident risk of the expressway tunnel cannot be predicted in real time at present, the embodiment of the application provides a method for predicting the accident risk of the expressway tunnel in real time, which comprises the steps of analyzing accident data, import and export traffic flow data and related weather data of the tunnel in a preset historical time period to obtain import and export traffic flow data and weather data corresponding to each accident of the tunnel in the preset historical time period, and taking the import and export traffic flow data and the weather data corresponding to each accident as accident fusion data of the accident; then, aiming at each accident of the tunnel in a preset historical time period, acquiring comparison data corresponding to accident fusion data of the accident, and taking the accident fusion data and the comparison data corresponding to all the accidents in the preset historical time period as an experimental data set; analyzing the experimental data set, determining accident pre-symptom characteristics which have obvious influence on tunnel accident risk, and training a tunnel accident real-time risk prediction model based on the experimental data set by taking the accident pre-symptom characteristics as independent variables and whether an accident occurs as dependent variables to obtain a trained tunnel accident real-time risk prediction model; finally, the tunnel accident risk is predicted in real time based on the import and export traffic flow data, the weather data and the trained tunnel accident real-time risk prediction model which are acquired in real time, so that the real-time prediction of the expressway tunnel accident risk is realized, and further, a reference is provided for tunnel accident prevention measures, so that the driving safety of vehicles in a tunnel is improved by intervention in advance.
The method for predicting the real-time risk of the expressway tunnel accident provided by the application is exemplified by the following description with reference to specific embodiments.
The embodiment of the application provides a real-time risk prediction method for expressway tunnel accidents, which can be executed by terminal equipment or by a device (such as a chip) applied to the terminal equipment. As an example, the terminal device may be a tablet, a server, a notebook, or the like, which is not limited in the embodiment of the present application.
As shown in fig. 1, the method for predicting real-time risk of expressway tunnel accident provided by the embodiment of the application includes the following steps:
and 11, acquiring accident data and import-export traffic flow data of the target tunnel in a preset historical time period.
The target tunnel is used for carrying out real-time risk prediction of accidentsA tunnel to be measured; the preset history period may be set according to actual conditions, for example, set to be about one year; the accident data comprise recorded data of all accidents of the target tunnel in a preset historical time period, wherein the recorded data comprise descriptive information such as places, time and the like of the accidents; the import and export traffic flow data includes: inlet flow, inlet average occupancy, inlet average vehicle speed, outlet flow, outlet average occupancy, and outlet average vehicle speed. The inlet flow rate refers to the number of vehicles passing through a detector (the detector is a detector arranged at the inlet of a target tunnel) in unit time, and the unit is: the number of vehicles passing the detector in a vehicle/hour, e.g. 5 minutes, is N, inlet flow The average occupancy of the entrance refers to the time T of existence of vehicles in a certain detection section or detection area at the entrance of the target tunnel v Ratio to the statistical total time T (e.g. 5 minutes); the average import speed refers to the average speed of the vehicle passing through a detector (the detector is arranged at the import of the target tunnel) in unit time, and the unit is kilometers per hour; similarly, the exit flow rate refers to the number of vehicles passing through a detector (which is a detector provided at the exit of the target tunnel) per unit time, in units of: the number of vehicles passing the detector in a vehicle/hour, e.g. 5 minutes, is N, the outlet flowThe average occupancy of the exit refers to the time T of existence of vehicles in a certain detection section or detection area at the exit of the target tunnel v Ratio to the statistical total time T (e.g. 5 minutes); the exit average vehicle speed refers to the average of the vehicle speed per unit time in km/h through a detector, which is a detector provided at the exit of the target tunnel.
In particular, in some embodiments of the present application, the accident data and the import-export traffic flow data may be obtained from a website of the relevant traffic department. It can be understood that after the accident data and the import-export traffic flow data are obtained from the related websites, the recorded data of the accident with the missing information and the misjudgment can be deleted to ensure the integrity of the accident data in the step 11.
And step 12, respectively matching the target import and export traffic flow data within n minutes before the accident occurs from the import and export traffic flow data according to each accident in the accident data, and determining weather data of the area where the target tunnel is located within n minutes before the accident occurs.
Wherein n is an integer, and n is more than or equal to 5 and less than or equal to 15. It should be noted that, since traffic flow monitoring is generally performed at intervals of 5 minutes, n may be generally 5, 10 or 15.
In some embodiments of the present application, the target traffic flow data is a part of the traffic flow data of the import and export in step 11, specifically, the traffic flow data of the import and export within n minutes before the accident occurs. Specifically, the import and export traffic flow data in n minutes before the accident happens can be matched from the import and export traffic flow data obtained in the step 11 according to the accident occurrence time in the recorded data.
In some embodiments of the present application, weather data of the area where the target tunnel is located within n minutes before the accident occurs may be obtained from related websites of a weather department, where the weather data may be weather data of a sunny day, a cloudy day, a rainy day, a snowy day, and the like. Specifically, according to the time and place of accident occurrence in the recorded data, the weather data of the area where the target tunnel is located within n minutes before the accident occurrence can be searched.
And 13, respectively carrying out fusion processing on the traffic flow data of the target import and export corresponding to the accident and the weather data aiming at each accident to obtain accident fusion data of the accident, and obtaining comparison data of the accident fusion data.
In some embodiments of the present application, after determining the traffic flow data and the weather data of the target import and export corresponding to the accident, the traffic flow data and the weather data of the target import and export corresponding to the accident may be fused according to the time and place of the accident, so as to obtain the accident fusion data, thereby facilitating determination of the comparison data, enriching the subsequent experimental data set, and further helping to subsequently promote the training accuracy of the real-time risk prediction model of the tunnel accident.
The method comprises the steps of carrying out fusion processing on traffic flow data of a target import and export corresponding to an accident and weather data, wherein the obtained accident fusion data comprises the following steps: inlet flow, inlet average occupancy, inlet average vehicle speed, outlet flow, outlet average occupancy, outlet average vehicle speed, inlet-outlet flow difference (i.e., the difference between inlet flow and outlet flow), inlet-outlet occupancy difference (i.e., the difference between inlet average occupancy and outlet average occupancy), inlet-outlet speed difference (i.e., the difference between inlet average vehicle speed and outlet average vehicle speed), and weather data.
In some embodiments of the present application, control data for accident fusion data may be obtained by case control methods. Specifically, the control data may be obtained by: firstly, acquiring import and export traffic flow data of a target tunnel at preset relevant time by using a case comparison method, and acquiring weather data of an area where the target tunnel is located at the preset relevant time; and then carrying out fusion processing on import and export traffic flow data and weather data obtained by using a case comparison method, and taking the data after fusion processing as comparison data of accident fusion data.
It should be noted that, the types of data included in the comparison data and the accident fusion data are the same, and only the corresponding times of the data included in the comparison data and the accident fusion data are different. That is, the control data includes an inlet flow rate, an inlet average occupancy, an inlet average vehicle speed, an outlet flow rate, an outlet average occupancy, an outlet average vehicle speed, an inlet-outlet flow rate difference (i.e., a difference between the inlet flow rate and the outlet flow rate), an inlet-outlet occupancy difference (i.e., a difference between the inlet average occupancy and the outlet average occupancy), an inlet-outlet speed difference (i.e., a difference between the inlet average vehicle speed and the outlet average vehicle speed) of the target tunnel at a preset correlation time, and corresponding weather data.
Wherein the preset correlation time is correlated with the occurrence time of the accident. Generally, the data of the accident place, the first 7 days, 14 days, the last 7 days and 14 days of the period can be selected as the control data.
For example, assuming that the accident occurred at a time of 2018, 1, 9:03 am and the place is an a tunnel, data (including import and export traffic flow data and weather data) of 9:00 am on 2017, 12, 18, 12, 25, and 2018, 1, 8, 15, and 15 are extracted as control data.
In some possible embodiments of the present application, after determining the target import-export traffic flow data and the weather data corresponding to the accident, the record data of the accident and the target import-export traffic flow data and the weather data corresponding to the accident may be fused. That is, the accident fusion data further includes record data.
If the accident fusion data includes recording data, the acquired comparison data also includes recording data of the accident.
And step 14, taking accident fusion data and comparison data corresponding to all accidents in the accident data as an experimental data set.
In some embodiments of the present application, data may be fused according to the time and place of occurrence of the incident, and the incident fusion data and the control data may be combined into an experimental data set.
And 15, determining accident premonitory features affecting the tunnel accident risk based on the experimental data set.
In some embodiments of the present application, accident precursors that have a significant impact on the risk of a tunnel accident may be selected by a Spearman (Spearman) correlation coefficient and a conditional Logistic regression model, thereby facilitating subsequent real-time, accurate prediction of the risk of a tunnel accident.
It should be noted that, because the tunnel accident risk is presumed to be related to the import and export traffic characteristics and the weather conditions according to the real-time risk related study of the expressway accident and the semi-closed characteristic of the tunnel, the accident precursor characteristics are determined based on the experimental data set, so that the accuracy of the accident precursor characteristics can be improved, and the accuracy of the accident risk prediction can be improved.
And step 16, training a tunnel accident real-time risk prediction model based on the experimental data set by taking the accident precursor characteristics as independent variables and taking whether the accident occurs as dependent variables, so as to obtain the trained tunnel accident real-time risk prediction model.
In some embodiments of the present application, the above-mentioned experimental data set may be divided into training set data and test set data, and then the real-time risk prediction model of the tunnel accident is trained by using the training set data, and the real-time risk prediction model of the tunnel accident is tested by using the test set data, so as to obtain the real-time risk prediction model of the tunnel accident after training.
And step 17, collecting import and export traffic flow data of the target tunnel and weather data of the area where the target tunnel is located every n minutes.
The import and export traffic flow data collected each time are import and export traffic flow data (the import and export traffic flow data comprise import flow, import average occupancy, import average speed, export flow, export average occupancy and export average speed) in n minutes before the collection time, and the weather data collected each time are weather data (the weather data can be weather data of sunny days, cloudy days, rainy days, snowy days and the like) in n minutes before the collection time.
And 18, extracting accident pre-symptom characteristic data from the acquired import and export traffic flow data and weather data according to independent variables of the tunnel accident real-time risk prediction model aiming at the import and export traffic flow data and the weather data acquired each time, and predicting the tunnel accident risk based on the accident pre-symptom characteristic data and the trained tunnel accident real-time risk prediction model.
In some embodiments of the present application, the tunnel accident real-time risk prediction model may be a commonly used decision function based on a support vector machine. Specifically, the expression of the decision function may be:
Wherein f (x) represents a dependent variable, i.e. whether an accident has occurred,b for supporting vectors * For the bias amount +.>And b * Can be calculated from the karuss-Coulomb-Take (Karush-Kuhn-Tucker) condition, K is a kernel function, x i For the data of the accident pre-sign feature of the ith sample in the training set data, x is the data of the accident pre-sign feature of the tunnel to be predicted (i.e. the accident pre-sign feature data in step 18), y i E, gamma= { -1,1} is the output eigenvalue of whether the accident happens, and n is the number of samples in the training set data.
It is worth mentioning that, by analyzing accident data, import and export traffic flow data and related weather data of the tunnel in a preset historical time period, the method provided by the embodiment of the application obtains import and export traffic flow data and weather data in n minutes before the accident occurs, and takes the import and export traffic flow data and the weather data corresponding to each accident as accident fusion data of the accident; then, aiming at each accident of the tunnel in a preset historical time period, acquiring comparison data corresponding to accident fusion data of the accident, and taking the accident fusion data and the comparison data corresponding to all the accidents in the preset historical time period as an experimental data set; analyzing the experimental data set, determining accident pre-symptom characteristics which have obvious influence on tunnel accident risk, and training a tunnel accident real-time risk prediction model based on the experimental data set by taking the accident pre-symptom characteristics as independent variables and whether an accident occurs as dependent variables to obtain a trained tunnel accident real-time risk prediction model; finally, based on the import and export traffic flow data and the weather data which are collected in real time and the trained tunnel accident real-time risk prediction model, whether the tunnel has traffic accidents or not is predicted in real time, the real-time prediction of the expressway tunnel accident risk is realized, and references are provided for tunnel accident preventive measures (such as measures of flow, vehicle speed control and the like) so as to intervene in advance and improve the driving safety of vehicles in the tunnel.
The implementation of step 15 is described below with reference to specific embodiments.
In some embodiments of the present application, the step 15, a specific implementation of determining the accident precursor features affecting the risk of the tunnel accident based on the experimental data set, includes the following steps:
step one, respectively defining a variable for each type of data in the experimental data set, and taking the type of data as the variable data.
The experimental data set comprises ten data of inlet flow, inlet average occupancy, inlet average speed, outlet flow, outlet average occupancy, outlet average speed, inlet-outlet flow difference, inlet-outlet occupancy difference, inlet-outlet speed difference and weather data. In some embodiments of the present application, a variable is defined for each of the ten types of data, and the data is used as data of the corresponding variable. Here, the inlet flow is exemplified, and assuming that the variable defined for the inlet flow is t, the data of all inlet flows in the experimental data set are the values of the variable t.
And step two, calculating a correlation value among the defined variables by using the spearman correlation coefficient.
In some embodiments of the present application, for any two variables defined, the correlation value of the two variables may be calculated using the spearman correlation coefficient in combination with the data of the two variables.
Wherein, the expression of the spearman correlation coefficient is as follows:s represents the calculated correlation value, n represents the number of observations (i.e. the total number of data contained in the accident fusion data and the control data), d i Representing the difference between the positions of the paired variables after the corresponding two variables are respectively ordered. Note that, since the spearman correlation coefficient is a common correlation analysis method, the principle of the spearman correlation coefficient is not repeated here.
And thirdly, selecting a target variable from the defined variables according to the calculated correlation value.
In some embodiments of the present application, in order to reject features with strong correlation and improve the accuracy of the accident precursor features, it is necessary to delete features with weak correlation with the occurrence of the accident after calculating the correlation value between every two variables.
Specifically, after calculating the correlation value (i.e., the spearman correlation coefficient value) between any two variables, if the correlation value greater than the preset correlation value (e.g., 0.7) exists in the calculated correlation value, calculating the correlation coefficients (i.e., the spearman correlation coefficient value) between the two variables corresponding to the correlation value and the occurrence of the accident or not respectively, deleting the variable corresponding to the smaller one of the calculated correlation coefficients, and then taking the other variables except the deleted variable in all the defined variables as target variables.
For example, if the correlation value between the inlet flow rate and the outlet flow rate is 0.85, where the correlation coefficient between the inlet flow rate and the accident factor (i.e. whether the accident occurs) is 0.45, and the correlation coefficient between the outlet flow rate and the accident factor (i.e. whether the accident occurs) is 0.3, the variable corresponding to the outlet flow rate is deleted, and the variable corresponding to the inlet flow rate is reserved.
In some embodiments of the present application, the correlation coefficient between the above-mentioned variables and whether an accident occurs or not may also be calculated by a spearman correlation coefficient. It will be appreciated that in order to calculate the correlation coefficient between the variable and the occurrence of an accident, a variable may be defined for the occurrence of an accident (the value of the variable is 0 or 1,0 indicates that no accident has occurred, 1 indicates that an accident has occurred) in the actual processing, wherein the value of the variable in the accident fusion data is 1, and the value of the variable in the comparison data is 1 or 0.
And step four, calculating the influence value of each target variable on the tunnel accident risk by using a conditional Logistic regression model.
And fifthly, determining accident pre-characterization affecting the tunnel accident risk according to the calculated influence value.
In some embodiments of the present application, a target variable with an impact value less than or equal to a preset impact value (e.g., 0.05) and a target variable corresponding to weather data may be used as an accident precursor feature that affects the risk of a tunnel accident.
In the actual prediction process, after import and export traffic flow data and weather data of an area where a target tunnel is located are acquired each time, the import and export traffic flow data and the weather data are required to be analyzed, data corresponding to each accident precursor feature (namely, accident precursor feature data) is extracted, and then a trained tunnel accident real-time risk prediction model is input based on the extracted accident precursor feature data to perform tunnel accident risk prediction.
The determination of the characteristics of an accident precursor is illustrated in a specific example.
In this example, 187 tunnel traffic accidents in 15 tunnels in california in 2018 are collected first, part of information is deleted, misjudgment is carried out, 180 pieces of effective accident data are obtained in total, meanwhile, import and export traffic flow data of 15 tunnels in 2018 and weather data of an area where 15 tunnels in 2018 are located are collected (for example, weather of Ma Linjun in 1 month in 2018 is sunny); then screening 15 pieces of effective accident data of the tunnel A from 180 pieces of effective accident data, taking the 15 pieces of effective accident data as the accident data of the tunnel A, respectively aiming at each accident in the 15 pieces of effective accident data, inquiring and matching the import and export traffic flow data and the weather data within n minutes (the value of n is 5 here) before the accident occurs, and obtaining an experimental data set of the tunnel A based on the matched import and export traffic flow data and the weather data; each type of data in the experimental dataset was then defined as a variable, the descriptive statistics of which are shown in tables 1 and 2. In the actual processing process, the variable corresponding to the weather data may be one, and here, for the description of the statistical condition, the clear day, the cloudy day, the rainy day and the snowy day are separately described.
| Variable(s) | Mean value of | Standard deviation of | Minimum value | Maximum value |
| Inlet flow rate | 313.77 | 160.67 | 0.00 | 905.00 |
| Average occupancy of inlet | 0.09 | 0.09 | 0.00 | 0.62 |
| Average inlet velocity | 59.31 | 11.59 | 10.00 | 73.92 |
| Outlet flow rate | 315.03 | 159.84 | 0.00 | 810.00 |
| Average occupancy of outlet | 0.09 | 0.09 | 0.00 | 0.59 |
| Average velocity of outlet | 59.16 | 11.79 | 5.89 | 73.20 |
| Inlet-outlet flow difference | 72.68 | 92.91 | 0.00 | 627.00 |
| Poor occupancy of inlet and outlet | 0.04 | 0.07 | 0.00 | 0.47 |
| Speed difference between inlet and outlet | 5.23 | 7.36 | 0.00 | 57.80 |
TABLE 1
| Variable(s) | No accident (Unit: personal) | Accident (Unit: personal) | Total (Unit: personal) |
| Sunny day | 558 | 69 | 627 |
| Cloudy day | 76 | 56 | 132 |
| Rain day | 61 | 49 | 110 |
| Snow day | 25 | 6 | 31 |
| Totals to | 720 | 180 | 900 |
TABLE 2
After the variables are defined, the spearman correlation coefficient value between each two variables is calculated using the spearman correlation coefficients, and the spearman correlation coefficient value between each defined variable and whether the accident occurs or not is calculated. Wherein the calculated spearman correlation coefficient values are shown in table 3.
TABLE 3 Table 3
Combining the screening principle of the calculated spearman correlation coefficient value and the target variable, and selecting an inlet average speed, an outlet average occupancy, an outlet average speed, an inlet-outlet flow difference, an inlet-outlet occupancy difference, an inlet-outlet speed difference and weather as the target variable; and finally, calculating an influence value of each target variable on the tunnel accident risk by using a conditional Logistic regression model, and taking the target variable (here, the average inlet speed, the average outlet occupancy, the inlet-outlet flow difference and the inlet-outlet occupancy) with the influence value smaller than or equal to a preset influence value (here, the preset influence value is 0.05) and the target variable corresponding to the weather data as the accident precursor characteristics for influencing the tunnel accident risk. The influence value calculated by using the conditional Logistic regression model is shown in table 4, estimate represents the correlation strength between the target variable and the tunnel accident risk, and Pr (> |z|) represents the influence value of the target variable on the tunnel accident risk. Note that "-" in tables 1 to 4 indicates that this item does not exist.
| Target variable | Estimate | Pr(>|z|) |
| Average inlet speed | 0.28 | 0.15 |
| Average occupancy of outlet | -0.21 | 0.49 |
| Average exit vehicle speed | -0.87 | 0.00 |
| Inlet-outlet flow difference | -0.36 | 0.13 |
| Poor occupancy of inlet and outlet | -0.74 | 0.05 |
| Speed difference between inlet and outlet | 0.76 | 0.00 |
| Snow day | 0.45 | 0.47 |
| Cloudy day | 2.41 | 0.00 |
| Rain day | 1.77 | 0.00 |
| Sunny day | - | - |
TABLE 4 Table 4
The effect of the tunnel accident real-time risk prediction model is exemplarily described below with reference to specific test results.
The real-time risk prediction model of the tunnel accident is tested by using the test set data, the obtained test results are shown in table 5, and the ROC curve is shown in fig. 2. The F1 score is an index used for measuring the accuracy of the two classification models in statistics, and combines the accuracy and recall of the classification models, and the ROC curve is a receiver operation characteristic curve. Note that "-" in table 5 indicates that this item does not exist.
| Prediction accuracy | Recall ratio | F1 fraction | Support degree | |
| No accident | 0.91 | 0.99 | 0.94 | 215 |
| Has an accident | 0.92 | 0.60 | 0.73 | 55 |
| Accuracy rate of | - | - | 0.91 | 270 |
| Macro averaging | 0.91 | 0.79 | 0.83 | 270 |
| Weighted average | 0.91 | 0.91 | 0.90 | 270 |
TABLE 5
As can be seen from table 5, the total accuracy of the real-time risk prediction model of the tunnel accident is about 91%, which indicates that the prediction accuracy of the real-time risk prediction model of the tunnel accident is high; as can be seen from fig. 2, the AUC value (AUC value refers to the area under the ROC curve) is 0.97, which is close to 1, indicating that the real-time risk prediction model of tunnel accident is high in authenticity.
The expressway tunnel accident real-time risk prediction device provided by the application is described in an exemplary manner with reference to specific embodiments.
As shown in fig. 3, an embodiment of the present application provides a real-time risk prediction apparatus for an expressway tunnel accident, and the real-time risk prediction apparatus 300 for an expressway tunnel accident includes:
a first obtaining module 301, configured to obtain accident data and import-export traffic flow data of a target tunnel in a preset historical time period;
the data matching module 302 is configured to match, for each accident in the accident data, target import-export traffic flow data within n minutes before the accident occurs from the import-export traffic flow data, and determine weather data of an area where the target tunnel is located within n minutes before the accident occurs; n is an integer, and n is more than or equal to 5 and less than or equal to 15;
the second obtaining module 303 is configured to perform fusion processing on the traffic flow data of the target import and export corresponding to the accident and the weather data for each accident, obtain accident fusion data of the accident, and obtain comparison data of the accident fusion data;
the first determining module 304 is configured to use accident fusion data and comparison data corresponding to all accidents in the accident data as an experimental data set;
A second determining module 305 for determining, based on the experimental dataset, accident precursors characteristic affecting the risk of tunnel accidents;
the model training module 306 is configured to train the real-time risk prediction model of the tunnel accident based on the experimental data set, with the accident precursor feature as an independent variable, and whether the accident occurs as an independent variable, to obtain a trained real-time risk prediction model of the tunnel accident;
the data acquisition module 307 is configured to acquire import and export traffic flow data of the target tunnel and weather data of an area where the target tunnel is located every n minutes; the import and export traffic flow data collected each time are the import and export traffic flow data in n minutes before the collection time, and the weather data collected each time are the weather data in n minutes before the collection time;
the risk prediction module 308 is configured to extract, for each acquired import and export traffic flow data and weather data, accident pre-symptom feature data from the acquired import and export traffic flow data and weather data according to an argument of the tunnel accident real-time risk prediction model, and predict a tunnel accident risk based on the accident pre-symptom feature data and the trained tunnel accident real-time risk prediction model.
It should be noted that, because the content of information interaction and execution process between the above devices/units is based on the same concept as the method embodiment of the present application, specific functions and technical effects thereof may be referred to in the method embodiment section, and will not be described herein again.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working process of the units and modules in the above system may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.
As shown in fig. 4, an embodiment of the present application provides a terminal device, as shown in fig. 4, a terminal device D10 of the embodiment includes: at least one processor D100 (only one processor is shown in fig. 4), a memory D101 and a computer program D102 stored in the memory D101 and executable on the at least one processor D100, the processor D100 implementing the steps in any of the various method embodiments described above when executing the computer program D102.
Specifically, when the processor D100 executes the computer program D102, accident data, import and export traffic flow data and related weather data of the tunnel in a preset historical time period are analyzed to obtain import and export traffic flow data and weather data corresponding to each accident occurring in the tunnel in the preset historical time period, and the import and export traffic flow data and the weather data corresponding to each accident are used as accident fusion data of the accident; then, aiming at each accident of the tunnel in a preset historical time period, acquiring comparison data corresponding to accident fusion data of the accident, and taking the accident fusion data and the comparison data corresponding to all the accidents in the preset historical time period as an experimental data set; analyzing the experimental data set, determining accident pre-symptom characteristics which have obvious influence on tunnel accident risk, and training a tunnel accident real-time risk prediction model based on the experimental data set by taking the accident pre-symptom characteristics as independent variables and whether an accident occurs as dependent variables to obtain a trained tunnel accident real-time risk prediction model; finally, the tunnel accident risk is predicted in real time based on the import and export traffic flow data, the weather data and the trained tunnel accident real-time risk prediction model which are acquired in real time, so that the real-time prediction of the expressway tunnel accident risk is realized, and further, a reference is provided for tunnel accident prevention measures, so that the driving safety of vehicles in a tunnel is improved by intervention in advance.
The processor D100 may be a central processing unit (CPU, central Processing Unit), the processor D100 may also be other general purpose processors, digital signal processors (DSP, digital Signal Processor), application specific integrated circuits (ASIC, application Specific Integrated Circuit), off-the-shelf programmable gate arrays (FPGA, field-Programmable Gate Array) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory D101 may in some embodiments be an internal storage unit of the terminal device D10, for example a hard disk or a memory of the terminal device D10. The memory D101 may also be an external storage device of the terminal device D10 in other embodiments, for example, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the terminal device D10. Further, the memory D101 may also include both an internal storage unit and an external storage device of the terminal device D10. The memory D101 is used for storing an operating system, an application program, a boot loader (BootLoader), data, other programs, etc., such as program codes of the computer program. The memory D101 may also be used to temporarily store data that has been output or is to be output.
It should be noted that, because the content of information interaction and execution process between the above devices/units is based on the same concept as the method embodiment of the present application, specific functions and technical effects thereof may be referred to in the method embodiment section, and will not be described herein again.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working process of the units and modules in the above system may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.
Embodiments of the present application also provide a computer readable storage medium storing a computer program which, when executed by a processor, implements steps that may implement the various method embodiments described above.
The present embodiments provide a computer program product which, when run on a terminal device, causes the terminal device to perform steps that enable the respective method embodiments described above to be implemented.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present application implements all or part of the flow of the method of the above embodiments, and may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, where the computer program, when executed by a processor, may implement the steps of each of the method embodiments described above. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include at least: any entity or device capable of carrying computer program code to the highway tunnel accident real-time risk prediction apparatus/terminal equipment, recording medium, computer Memory, read-Only Memory (ROM), random access Memory (RAM, random Access Memory), electrical carrier signals, telecommunications signals, and software distribution media. Such as a U-disk, removable hard disk, magnetic or optical disk, etc. In some jurisdictions, computer readable media may not be electrical carrier signals and telecommunications signals in accordance with legislation and patent practice.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus/network device and method may be implemented in other manners. For example, the apparatus/network device embodiments described above are merely illustrative, e.g., the division of the modules or units is merely a logical functional division, and there may be additional divisions in actual implementation, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection via interfaces, devices or units, which may be in electrical, mechanical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
The above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.
Claims (8)
1. The real-time risk prediction method for the expressway tunnel accident is characterized by comprising the following steps of:
acquiring accident data and import-export traffic flow data of a target tunnel in a preset historical time period;
respectively matching target import and export traffic flow data within n minutes before the accident occurs from the import and export traffic flow data aiming at each accident in the accident data, and determining weather data of an area where the target tunnel is located within n minutes before the accident occurs; n is an integer, and ；
Respectively carrying out fusion processing on the traffic flow data of the target import and export corresponding to each accident and the weather data according to each accident to obtain accident fusion data of the accident, and obtaining comparison data of the accident fusion data;
taking accident fusion data and comparison data corresponding to all accidents in the accident data as an experimental data set;
determining accident precursors characteristic affecting tunnel accident risk based on the experimental data set;
based on the experimental data set, training a tunnel accident real-time risk prediction model by taking the accident pre-symptom characteristic as an independent variable and taking whether an accident occurs as an independent variable, so as to obtain a trained tunnel accident real-time risk prediction model;
collecting import and export traffic flow data of the target tunnel every n minutes and weather data of an area where the target tunnel is located; the import and export traffic flow data collected each time are the import and export traffic flow data in n minutes before the collection time, and the weather data collected each time are the weather data in n minutes before the collection time;
aiming at import and export traffic flow data and weather data which are collected each time, according to independent variables of the tunnel accident real-time risk prediction model, accident pre-symptom characteristic data are extracted from the collected import and export traffic flow data and weather data, and tunnel accident risk is predicted based on the accident pre-symptom characteristic data and the trained tunnel accident real-time risk prediction model;
Wherein the determining, based on the experimental dataset, an accident pre-characterization that affects a risk of a tunnel accident comprises:
defining a variable for each type of data in the experimental data set, and taking the type of data as the variable data;
calculating a correlation value between the defined variables using the spearman correlation coefficient;
selecting a target variable from the defined variables according to the calculated correlation value;
calculating the influence value of each target variable on the tunnel accident risk by using a conditional Logistic regression model;
and determining accident premonition features influencing the tunnel accident risk according to the calculated influence values.
2. The method of claim 1, wherein selecting the target variable from the defined variables based on the calculated correlation value comprises:
if the correlation value greater than the preset correlation value exists in the calculated correlation values, respectively calculating correlation coefficients between two variables corresponding to the correlation values and whether the accident occurs or not, and deleting the variable corresponding to the smaller correlation coefficient;
and taking other variables except the deleted variable in all the defined variables as target variables.
3. The method according to claim 1, wherein said determining accident precursors characteristic affecting the risk of tunnel accidents based on the calculated impact values comprises:
and taking the target variable with the influence value smaller than or equal to the preset influence value and the target variable corresponding to the weather data as the accident pre-symptom characteristic for influencing the tunnel accident risk.
4. The method of claim 1, wherein the ingress and egress traffic flow data comprises: inlet flow, inlet average occupancy, inlet average vehicle speed, outlet flow, outlet average occupancy, and outlet average vehicle speed.
5. The method of claim 1, wherein the obtaining control data for the accident fusion data comprises:
and obtaining control data of the accident fusion data by using a case control method.
6. The utility model provides a highway tunnel accident real-time risk prediction device which characterized in that includes:
the first acquisition module is used for acquiring accident data and import-export traffic flow data of the target tunnel in a preset historical time period;
the data matching module is used for matching each accident in the accident data from the import and export traffic flow data within n minutes before the accident happens The method comprises the steps of (1) determining weather data of an area where a target tunnel is located within n minutes before the accident occurs according to target import-export traffic flow data of the target tunnel; n is an integer, and；
the second acquisition module is used for respectively carrying out fusion processing on the traffic flow data of the target import and export corresponding to each accident and the weather data according to each accident to obtain accident fusion data of the accidents and acquiring comparison data of the accident fusion data;
the first determining module is used for taking accident fusion data and comparison data corresponding to all accidents in the accident data as an experimental data set;
a second determining module for determining, based on the experimental dataset, accident precursors characteristic affecting a risk of a tunnel accident;
the model training module is used for training a tunnel accident real-time risk prediction model based on the experimental data set by taking the accident precursor characteristics as independent variables and whether the accident occurs as dependent variables, so as to obtain a trained tunnel accident real-time risk prediction model;
the data acquisition module is used for acquiring import and export traffic flow data of the target tunnel and weather data of an area where the target tunnel is located every n minutes; the import and export traffic flow data collected each time are the import and export traffic flow data in n minutes before the collection time, and the weather data collected each time are the weather data in n minutes before the collection time;
The risk prediction module is used for extracting accident pre-symptom characteristic data from the acquired import and export traffic flow data and weather data according to independent variables of the tunnel accident real-time risk prediction model aiming at the acquired import and export traffic flow data and weather data each time, and predicting tunnel accident risk based on the accident pre-symptom characteristic data and the trained tunnel accident real-time risk prediction model;
the second determining module is specifically configured to execute the following steps:
defining a variable for each type of data in the experimental data set, and taking the type of data as the variable data;
calculating a correlation value between the defined variables using the spearman correlation coefficient;
selecting a target variable from the defined variables according to the calculated correlation value;
calculating the influence value of each target variable on the tunnel accident risk by using a conditional Logistic regression model;
and determining accident premonition features influencing the tunnel accident risk according to the calculated influence values.
7. Terminal device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the method for real-time risk prediction of an expressway tunnel accident according to any one of claims 1 to 5 when executing the computer program.
8. A computer readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the highway tunnel accident real-time risk prediction method according to any one of claims 1 to 5.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211170362.6A CN115565373B (en) | 2022-09-22 | 2022-09-22 | Expressway tunnel accident real-time risk prediction method, device, equipment and medium |
| PCT/CN2023/087326 WO2024060588A1 (en) | 2022-09-22 | 2023-04-10 | Expressway tunnel accident real-time risk prediction method and apparatus, device, and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211170362.6A CN115565373B (en) | 2022-09-22 | 2022-09-22 | Expressway tunnel accident real-time risk prediction method, device, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115565373A CN115565373A (en) | 2023-01-03 |
| CN115565373B true CN115565373B (en) | 2024-04-05 |
Family
ID=84743550
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211170362.6A Active CN115565373B (en) | 2022-09-22 | 2022-09-22 | Expressway tunnel accident real-time risk prediction method, device, equipment and medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115565373B (en) |
| WO (1) | WO2024060588A1 (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115565373B (en) * | 2022-09-22 | 2024-04-05 | 中南大学 | Expressway tunnel accident real-time risk prediction method, device, equipment and medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20170065898A (en) * | 2015-12-04 | 2017-06-14 | 한국교통연구원 | Method for predicting possibility of a traffic accident occurrence on road and device for the same |
| KR20180078029A (en) * | 2016-12-29 | 2018-07-09 | (주) 더아이엠씨 | Analysis Method for Risk of Traffic Accident and Storage Medium Having the Same |
| CN111126868A (en) * | 2019-12-30 | 2020-05-08 | 中南大学 | Road traffic accident occurrence risk determination method and system |
| CN112419709A (en) * | 2020-10-16 | 2021-02-26 | 同济大学 | Expressway accident risk real-time prediction method based on road section heterogeneity |
| CN113095584A (en) * | 2021-04-23 | 2021-07-09 | 中南大学 | Intersection safety level short-time prediction method, system, terminal and readable storage medium based on traffic flow characteristics |
| CN113269960A (en) * | 2021-05-17 | 2021-08-17 | 郑州航空工业管理学院 | Method for analyzing accident risk of highway tunnel group traffic |
| CN113744526A (en) * | 2021-08-25 | 2021-12-03 | 江苏大学 | Expressway risk prediction method based on LSTM and BF |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103198713B (en) * | 2013-03-21 | 2016-01-06 | 东南大学 | Based on the vehicle regulate and control method of the minimizing traffic hazard of traffic data and weather data |
| KR20210032758A (en) * | 2019-09-17 | 2021-03-25 | 주식회사 퀀텀게이트 | System and method for providing traffic safty based on traffic flow information in a tunnel |
| JP2021182189A (en) * | 2020-05-18 | 2021-11-25 | 株式会社オリエンタルコンサルタンツ | Accident prediction method, computer program, accident prediction device, and learning model generation method |
| CN112101759A (en) * | 2020-09-03 | 2020-12-18 | 交通运输部科学研究院 | Method and device for constructing risk assessment model and assessing risk of expressway tunnel |
| CN112149922A (en) * | 2020-11-03 | 2020-12-29 | 南京信息职业技术学院 | Method for predicting severity of accident in exit and entrance area of down-link of highway tunnel |
| CN112990545B (en) * | 2021-02-08 | 2022-11-18 | 东南大学 | Traffic safety state prediction method for expressway intersection area |
| CN114970943B (en) * | 2022-03-29 | 2023-04-07 | 浙江省交通投资集团有限公司智慧交通研究分公司 | Expressway accident type and severity prediction method |
| CN115565373B (en) * | 2022-09-22 | 2024-04-05 | 中南大学 | Expressway tunnel accident real-time risk prediction method, device, equipment and medium |
-
2022
- 2022-09-22 CN CN202211170362.6A patent/CN115565373B/en active Active
-
2023
- 2023-04-10 WO PCT/CN2023/087326 patent/WO2024060588A1/en unknown
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20170065898A (en) * | 2015-12-04 | 2017-06-14 | 한국교통연구원 | Method for predicting possibility of a traffic accident occurrence on road and device for the same |
| KR20180078029A (en) * | 2016-12-29 | 2018-07-09 | (주) 더아이엠씨 | Analysis Method for Risk of Traffic Accident and Storage Medium Having the Same |
| CN111126868A (en) * | 2019-12-30 | 2020-05-08 | 中南大学 | Road traffic accident occurrence risk determination method and system |
| CN112419709A (en) * | 2020-10-16 | 2021-02-26 | 同济大学 | Expressway accident risk real-time prediction method based on road section heterogeneity |
| CN113095584A (en) * | 2021-04-23 | 2021-07-09 | 中南大学 | Intersection safety level short-time prediction method, system, terminal and readable storage medium based on traffic flow characteristics |
| CN113269960A (en) * | 2021-05-17 | 2021-08-17 | 郑州航空工业管理学院 | Method for analyzing accident risk of highway tunnel group traffic |
| CN113744526A (en) * | 2021-08-25 | 2021-12-03 | 江苏大学 | Expressway risk prediction method based on LSTM and BF |
Non-Patent Citations (2)
| Title |
|---|
| Risk analysis for severe traffic accidents in long road tunnels;Konstantinos Gkoumas et al.;《Int. J. Forensic Engineering》;20161231;第106-126页 * |
| 基于Hankel-DMD的城市交通事故风险时空预测;金杰灵 等;《中国安全生产科学技术》;20220831;第18卷(第8期);第18-23页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115565373A (en) | 2023-01-03 |
| WO2024060588A1 (en) | 2024-03-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yang et al. | A Bayesian dynamic updating approach for urban expressway real-time crash risk evaluation | |
| CN110866677B (en) | Driver relative risk evaluation method based on benchmark analysis | |
| CN111462488B (en) | Intersection safety risk assessment method based on deep convolutional neural network and intersection behavior characteristic model | |
| Theofilatos et al. | Impact of real-time traffic characteristics on crash occurrence: Preliminary results of the case of rare events | |
| CN108847022B (en) | Abnormal value detection method of microwave traffic data acquisition equipment | |
| CN103150900A (en) | Traffic jam event automatic detecting method based on videos | |
| CN108764375B (en) | Highway goods stock transprovincially matching process and device | |
| Jonsson | Classification of road conditions: From camera images and weather data | |
| CN110304068B (en) | Method, device, equipment and storage medium for collecting automobile driving environment information | |
| CN112634614B (en) | Long downhill traffic incident real-time detection method, device and storage medium | |
| Das et al. | Association of reduced visibility with crash outcomes | |
| CN115565373B (en) | Expressway tunnel accident real-time risk prediction method, device, equipment and medium | |
| Lestyan et al. | Extracting vehicle sensor signals from CAN logs for driver re-identification | |
| CN110562261B (en) | Method for detecting risk level of driver based on Markov model | |
| CN114076631A (en) | Overload vehicle identification method, system and equipment | |
| CN115080638B (en) | Multi-source data fusion analysis method for microscopic simulation, electronic equipment and storage medium | |
| CN109598931A (en) | Group based on traffic safety risk divides and difference analysis method and system | |
| CN106910334B (en) | Method and device for predicting road section conditions based on big data | |
| Paul et al. | Prediction of road accident and severity of Bangladesh applying machine learning techniques | |
| Bitar et al. | A probabilistic approach to improve the accuracy of axle-based automatic vehicle classifiers | |
| Wang et al. | Real-time safety analysis for expressways considering the heterogeneity of different segment types | |
| CN113255580A (en) | Method and device for identifying sprinkled objects and vehicle sprinkling and leaking | |
| CN110705628B (en) | Method for detecting risk level of driver based on hidden Markov model | |
| CN114756420A (en) | Fault prediction method and related device | |
| CN113192340B (en) | Method, device, equipment and storage medium for identifying highway construction vehicles |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |