Road surface hidden danger detection method and system for highway network operation guarantee platform

Abstract

The invention relates to the technical field of pavement hidden danger detection, in particular to a pavement hidden danger detection method and system for a highway network operation guarantee platform, and the method comprises the steps: obtaining the dimension data of each target road section on a highway network to be detected under each preset monitoring dimension at each preset collection moment; determining a data fluctuation change factor of each target road section under each preset monitoring dimension at each preset acquisition moment; determining a dimension change stability performance index and a hidden danger influence characteristic index corresponding to each target road section; and screening out a target similar road section corresponding to each target road section from all the target road sections, and carrying out road surface hidden danger detection based on the difference between each target road section and the hidden danger influence characteristic index corresponding to the target similar road section. By analyzing the dimension data of different road sections under different preset monitoring dimensions at different moments, the road surface hidden danger detection is realized, and the road surface hidden danger detection efficiency is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of road surface hidden danger detection, and particularly relates to a road surface hidden danger detection method and system for a highway network operation guarantee platform. BACKGROUND

[0002] With the rapid development of the transportation industry, the mileage of highways gradually increases. In order to ensure the safety and smoothness of highways, it is often necessary to periodically detect road surface hidden dangers of highways, and highway detection is mainly carried out by manual detection.

[0003] However, when the manual detection method is used to detect road surface hidden dangers of highways, the following technical problems often exist: Since the cost of manual detection is high, the period of road surface hidden danger detection using the manual detection method is often long, which leads to difficulty in timely road surface hidden danger detection, and further leads to poor road surface hidden danger detection efficiency. In addition, the detection result of road surface hidden danger detection using the manual detection method is often affected by subjective factors, which may lead to poor accuracy of road surface hidden danger detection. SUMMARY

[0004] In order to solve the technical problem of poor road surface hidden danger detection efficiency, the present application provides a road surface hidden danger detection method and system for a highway network operation guarantee platform.

[0005] In a first aspect, the present application provides a road surface hidden danger detection method for a highway network operation guarantee platform, which comprises: obtaining dimension data of each target road section on the highway network to be detected in each preset collection time under each preset monitoring dimension, wherein the latest preset collection time is denoted as the current collection time; determining a data fluctuation change factor of each target road section in each preset collection time under each preset monitoring dimension according to the dimension data of each target road section in each preset collection time and the preset collection time before it under the same preset monitoring dimension; determining a dimension change stability performance index corresponding to each target road section according to the number of preset monitoring dimensions and the data fluctuation change factors of each target road section under different preset monitoring dimensions at the current collection time and the preset collection time before it; determining a hidden danger influence feature index corresponding to each target road section according to the difference between the data fluctuation change factors of each target road section under the preset monitoring dimension at the current collection time and the preset collection time before it, and the dimension change stability performance index corresponding to each target road section; Screening a target similar road section corresponding to each target road section from all target road sections, and detecting a road surface hidden danger based on a difference between a hidden danger influence characteristic index corresponding to each target road section and a target similar road section thereof.

[0006] In combination with the first aspect, in a possible implementation manner, the determining, according to the dimension data of each target road section under the same preset monitoring dimension at each preset collection time and a preset collection time before the preset collection time, of a data fluctuation change factor of each target road section under each preset monitoring dimension at each preset collection time, includes: An arbitrary target road section is determined as a marker road section, an arbitrary preset collection time is determined as a marker time, and an arbitrary preset monitoring dimension is determined as a marker monitoring dimension; A mean value of the dimension data of the marker road section under the marker monitoring dimension at all preset collection times before the marker time is determined as reference representative data of the marker road section under the marker monitoring dimension at the marker time; A difference between the dimension data of the marker road section under the marker monitoring dimension at the marker time and the reference representative data is normalized to obtain a data fluctuation change factor of the marker road section under the marker monitoring dimension at the marker time.

[0007] In combination with the first aspect, in a possible implementation manner, the determining, according to the number of preset monitoring dimensions and the data fluctuation change factors of each target road section under different preset monitoring dimensions at a current collection time and preset collection times before the current collection time, of a dimension change stability performance index corresponding to each target road section, includes: A mean value of the data fluctuation change factors of each target road section under the same preset monitoring dimension at all preset collection times before the current collection time is determined as a historical fluctuation representative factor of each target road section under each preset monitoring dimension at the current collection time; A monitoring feature representative factor of each target road section under each preset monitoring dimension at the current collection time is determined according to the data fluctuation change factor and the historical fluctuation representative factor of each target road section under each preset monitoring dimension at the current collection time; A dimension feature fluctuation factor corresponding to each target road section is determined according to the monitoring feature representative factors of each target road section under different preset monitoring dimensions at the current collection time; A dimension change stability performance index corresponding to each target road section is determined according to the number of preset monitoring dimensions and the dimension feature fluctuation factor corresponding to each target road section.

[0008] In a possible implementation manner of the first aspect, the method further includes: determining, according to the monitoring feature representative factor of each target road section under each preset monitoring dimension at the current collection time, a dimension feature fluctuation factor corresponding to each target road section. The variance of the monitoring feature representative factor of each target road section under all preset monitoring dimensions at the current collection time is determined as the dimension feature fluctuation factor corresponding to each target road section.

[0009] In a possible implementation manner of the first aspect, the method further includes: determining, according to the number of preset monitoring dimensions and the dimension feature fluctuation factor corresponding to each target road section, a dimension change stability performance index corresponding to each target road section. The dimension feature fluctuation factor corresponding to each target road section is determined according to the dimension feature fluctuation factor corresponding to each target road section, wherein the dimension feature fluctuation factor and the initial stability factor are in a negative correlation relationship. The product of the number of preset monitoring dimensions and the initial stability factor corresponding to each target road section is normalized to obtain the dimension change stability performance index corresponding to each target road section.

[0010] In a possible implementation manner of the first aspect, the method further includes: determining, according to the difference between the data fluctuation change factor of each target road section under the preset monitoring dimension at the current collection time and the previous preset collection time and the dimension change stability performance index corresponding to each target road section, a hidden danger influence feature index corresponding to each target road section. The mean value of the data fluctuation change factor of each target road section under all preset monitoring dimensions at the current collection time is determined as a current overall fluctuation index corresponding to each target road section. The mean value of the data fluctuation change factor of each target road section under all preset monitoring dimensions at the previous preset collection time of the current collection time is determined as a reference overall fluctuation index corresponding to each target road section. The hidden danger influence feature index corresponding to each target road section is determined according to the dimension change stability performance index corresponding to each target road section, the current overall fluctuation index, and the reference overall fluctuation index.

[0011] In a possible implementation manner of the first aspect, the method further includes: determining, according to the dimension change stability performance index corresponding to each target road section, the current overall fluctuation index, and the reference overall fluctuation index, the hidden danger influence feature index corresponding to each target road section. The hidden danger influence feature index corresponding to each target road section is determined according to the dimension change stability performance index corresponding to each target road section, the time length between the current collection time and the previous preset collection time, and the difference between the current overall fluctuation index and the reference overall fluctuation index corresponding to each target road section.

[0012] In a possible implementation of the first aspect, the filtering, from all target road segments, of a target similar road segment corresponding to each target road segment comprises: determining any one target road segment as a marker road segment, and filtering, from all target road segments, a target road segment having a same material thickness as the marker road segment to form a reference road segment set corresponding to the marker road segment; filtering, from the reference road segment set corresponding to the marker road segment, a target road segment having a distance less than a preset distance threshold to the marker road segment as a target similar road segment corresponding to the marker road segment.

[0013] In a possible implementation of the first aspect, the road surface hidden danger detection based on a difference between the hidden danger influence feature index corresponding to each target road segment and the target similar road segment thereof comprises: determining a target anomaly index corresponding to each target road segment according to a difference between the hidden danger influence feature index corresponding to each target road segment and the hidden danger influence feature index corresponding to the target similar road segment thereof; if the target anomaly index corresponding to the target road segment is greater than a preset anomaly threshold, determining that the target road segment has a greater road surface hidden danger.

[0014] In a second aspect, the present application provides a road surface hidden danger detection system for a highway road network operation guarantee platform, comprising a processor and a memory, wherein the processor is configured to process instructions stored in the memory to implement the road surface hidden danger detection method for the highway road network operation guarantee platform, and specifically, the system comprises: a dimension data acquisition module configured to acquire dimension data of each target road segment in each preset monitoring dimension at each preset acquisition time in a to-be-detected highway road network; a data fluctuation change factor determination module configured to determine a data fluctuation change factor of each target road segment in each preset monitoring dimension at each preset acquisition time according to dimension data of each target road segment in the same preset monitoring dimension at each preset acquisition time and a preset acquisition time before the preset acquisition time; a dimension change stability performance index determination module configured to determine a dimension change stability performance index corresponding to each target road segment according to a number of preset monitoring dimensions and data fluctuation change factors of each target road segment in different preset monitoring dimensions at a current acquisition time and a preset acquisition time before the current acquisition time; a hidden danger influence feature index determination module configured to determine a hidden danger influence feature index corresponding to each target road segment according to a difference between data fluctuation change factors of each target road segment in a preset monitoring dimension at a current acquisition time and a preset acquisition time before the current acquisition time, and the dimension change stability performance index corresponding to each target road segment. The screening and road surface hidden danger detection module is configured to screen a target similar road section corresponding to each target road section from all target road sections, and perform road surface hidden danger detection based on a difference between a hidden danger influence characteristic index corresponding to each target road section and its target similar road section.

[0015] In a third aspect, a server is provided, comprising a memory and a processor. The memory is configured to store executable program code, and the processor is configured to invoke and run the executable program code from the memory, so that the device executes the method in the first aspect or any possible implementation manner of the first aspect.

[0016] In a fourth aspect, a computer program product is provided, which comprises computer program code. When the computer program code is run on a computer, the computer program code causes the computer to execute the method in the first aspect or any possible implementation manner of the first aspect.

[0017] In a fifth aspect, a computer readable storage medium is provided, which stores computer program code. When the computer program code is run on a computer, the computer program code causes the computer to execute the method in the first aspect or any possible implementation manner of the first aspect.

[0018] The present application has the following beneficial effects: The road surface hidden danger detection method for the expressway road network operation guarantee platform provided by the present application objectively quantifies data fluctuation change factors, dimension change stability performance indexes and hidden danger influence characteristic indexes by analyzing dimension data of different road sections under different preset monitoring dimensions at different times, reduces the influence of artificial subjective factors to a certain extent, improves the accuracy of road surface hidden danger detection, realizes road surface hidden danger detection through real-time collected dimension data, reduces the cycle length of road surface hidden danger detection to a certain extent, and improves the efficiency of road surface hidden danger detection. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the drawings needed in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0020] Figure 1 A flowchart of a road surface hidden danger detection method for an expressway road network operation guarantee platform of the present application; Figure 2 A composition structure schematic diagram of a road surface hidden danger detection system for an expressway road network operation guarantee platform of the present application; Figure 3 Figure 1 is a schematic diagram of a computer device according to the present application. DETAILED DESCRIPTION

[0021] In order to further clarify the technical means and effects taken by the present application to achieve the predetermined object of the application, the specific embodiments, structures, features and effects of the technical solutions proposed according to the present application are described in detail below in combination with the drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs.

[0023] With the increasing expansion of the highway network, its operation and management is facing unprecedented challenges. The traditional way of road patrol by flooding has often been difficult to meet the efficient and accurate safety hazard investigation and special event disposal needs. The "Internet of Things +" mode takes the Internet of Things technology as the core, through intelligent sensing, data transmission, information processing and decision support, etc. Links, to realize the effective operation and management of highway network guarantee. For potential safety hazards such as water damage under highway bridges and high slope hollowing, the road environment change monitoring device under development uses Internet of Things technology to realize real-time monitoring and early warning of these key areas. By arranging sensors, the device can capture environmental change data and transmit it to the monitoring platform in real time through the Internet of Things network.

[0024] In the process of highway network operation analysis, first of all, the deployment of edge computing devices and the acquisition of sensing information are needed. Select the appropriate edge computing device, such as industrial computer, embedded system, these devices have enough computing power to process complex models and real-time data. The highway network is equipped with a variety of sensors to collect environmental information in real time. Cameras are used to capture images, perform visual recognition and object detection; laser radar provides detailed three-dimensional spatial data to help identify the shape and precise position of objects. These sensor data are processed and preliminarily fused by edge computing devices to reduce data transmission delay.

[0025] In the process of digital modeling of the highway network, the Beidou high-precision positioning system is used to collect the coordinates of the whole line pile number, ensuring that the positioning accuracy reaches ± 5 cm. At the same time, record key parameters including design speed, number of lanes, slope angle, etc. Merge the nearly 5 years of maintenance records and traffic accident reports, and clean and standardize these historical data, including unified time format, location identification, etc.

[0026] Corresponding to different types of road surface hidden danger information, different monitoring equipment is used to realize, including: using laser profilograph to detect the flatness of the road surface, calculating the international roughness index (IRI value) to evaluate the road surface comfort and safety; using geological radar to scan the roadbed, the detection depth reaches 3 meters, to identify potential cavities or other structural problems; using unmanned aerial vehicle to take pictures of the slope, the resolution reaches 0.5m / px, and the stability of the slope and the potential landslide risk are evaluated through image analysis.

[0027] In the road network segmentation marking process, reasonable segmentation principles are determined according to pile number, lane number, design speed, etc., and specific segmentation marks are implemented in the GIS database. Each section should contain pile number range, lane number, design speed, slope angle, maintenance record and accident record, etc.

[0028] The data of segmentation marking is displayed on the map through GIS visualization tool, ensuring that decision makers can intuitively view the specific parameters and historical records of each section. These data analysis results will provide strong support for maintenance decision, traffic safety hidden danger evaluation and real-time monitoring, thus effectively improving the operation management level and safety of the highway.

[0029] The management and maintenance of highway network is a complex and systematic project, which is affected by multiple factors, among which the information updating method of geological characteristics and road surface patrol operation has a significant impact on the implementation of road surface hidden danger detection by Internet of Things devices set in the actual highway network. The identification and evaluation of road surface hidden dangers rely on the integration and analysis of multiple types of data, which requires full consideration of geological characteristics and patrol performance to achieve precise analysis. Specifically, first, data from different sources need to be collected and integrated, including geological survey data, soil type, groundwater level, weather conditions, road disease records, patrol reports, and real-time data obtained by modern detection technology, etc., and the potential impact of geological characteristics on road surface hidden dangers should be given priority. Patrol performance data provides real-time conditions of road diseases. These data usually include the type, number and distribution of diseases such as road surface cracks, potholes and settlement. Through regular patrol and high-precision detection technology such as laser scanning, unmanned aerial photography, etc., hidden dangers can be found and relevant information recorded, realizing dynamic updating of data.

[0030] Since the geological features have a direct impact on the segmentation characteristics and maintenance strategies of the expressway, the main performance is that in the corresponding expressway network section, different soil types such as clay, sand or rock and their bearing capacity differences will cause some sections to be more prone to diseases such as settlement and cracks. And the change of groundwater level often affects the stability of the roadbed, especially in the rainy season, high water level may cause soil softening, increase the risk of subsidence and landslide. Therefore, the main performance is the stability performance of the occurrence type of the road surface hidden danger, that is, the segmentation monitoring data of the corresponding expressway network has obvious road section type correlation. Therefore, when segmenting the expressway, these geological features must be fully considered in order to develop targeted maintenance programs. At the same time, the terrain and slope also have an impact on the slope stability, and the areas with larger slope are more prone to landslides or mudslides, which need to be specially marked and monitored when segmenting.

[0031] Reference Figure 1 , shows the flow of some embodiments of a road surface hidden danger detection method for an expressway network operation guarantee platform of the application. The road surface hidden danger detection method for the expressway network operation guarantee platform, comprising the following steps: Step S1, obtaining the dimension data of each target road section in each preset monitoring dimension at each preset collection time on the expressway network to be detected.

[0032] The to-be-detected highway network can be a highway network to be detected for road surface hidden danger. The highway network can be an interconnected highway network system mainly composed of expressways. The target section can be a section obtained by pre-dividing an expressway included in the to-be-detected highway network. The length corresponding to the target section can be 100 meters. In actual situations, a single expressway is often relatively long, and in order to facilitate accurate monitoring or maintenance, the single expressway is often further segmented, and the segmented section can be referred to as the target section. The preset collection time point can be a data collection time point set in advance. The time length between adjacent preset collection time points can be 1 day. The latest preset collection time point can be referred to as the current collection time point. The preset monitoring dimension can be a dimension related to a road surface hidden danger set in advance. For example, the preset monitoring dimension can be, but is not limited to, a flatness dimension, an average temperature dimension, an average humidity dimension, a material elastic modulus dimension, and a Poisson's ratio dimension. The dimension data under the preset monitoring dimension can be a normalized value of the preset monitoring dimension value. For example, the dimension data of a target section under the flatness dimension at a preset collection time point can be a normalized value of the flatness of the target section collected at the preset collection time point. The method for obtaining the dimension data of a target section under the average temperature dimension at a preset collection time point can be: taking the preset collection time point as a temporary time point; constructing a temporary time period with the temporary time point as an ending time point, wherein the time length corresponding to the temporary time period can be 1 day; every 1 minute in the temporary time period, collecting the temperature at the target section, and taking the normalized value of the average of all temperatures collected at the target section in the temporary time period as the dimension data of the target section under the average temperature dimension at the preset collection time point. The dimension data under different preset monitoring dimensions can be collected by corresponding sensors. For example, the temperature collected when obtaining the dimension data under the average temperature dimension can be collected by a temperature sensor.

[0033] It should be noted that the highway network is often operated and guaranteed by a highway network operation guarantee platform. The highway network operation guarantee platform is a digital management system based on cloud computing, big data, artificial intelligence, etc., aiming to realize all-weather monitoring, risk early warning and collaborative scheduling of the highway network operation state, and ensure safe and efficient traffic of the highway network.

[0034] Step S2, according to the dimension data of each target section under the same preset monitoring dimension at each preset collection time point and the preset collection time point before each preset collection time point, determining the data fluctuation change factor of each target section under each preset monitoring dimension at each preset collection time point.

[0035] As an example, the present step can include the following steps: In a first step, any one target road section is determined as a marker road section, any one preset collection time is determined as a marker time, and any one preset monitoring dimension is determined as a marker monitoring dimension.

[0036] In a second step, an average of dimension data of the marker road section under the marker monitoring dimension at all preset collection times before the marker time is determined as reference representative data of the marker road section under the marker monitoring dimension at the marker time.

[0037] In a third step, a difference between the dimension data of the marker road section under the marker monitoring dimension at the marker time and the reference representative data is normalized to obtain a data fluctuation change factor of the marker road section under the marker monitoring dimension at the marker time.

[0038] For example, a formula corresponding to the data fluctuation change factor of the target road section under the different preset monitoring dimensions at the different preset collection times can be: ; ; wherein, is the data fluctuation change factor of the i th target road section under the k th preset monitoring dimension at the j th preset collection time. i is the serial number of the target road section. j is the serial number of the preset collection time. k is the serial number of the preset monitoring dimension. is a normalization function. is the dimension data of the i th target road section under the k th preset monitoring dimension at the j th preset collection time. is the reference representative data of the i th target road section under the k th preset monitoring dimension at the j th preset collection time. a is the serial number of the j th preset collection time and the preset collection times before the j th preset collection time. is the dimension data of the i th target road section under the k th preset monitoring dimension at the a th preset collection time.

[0039] It should be noted that, can represent the data deviation of the i th target road section under the k th preset monitoring dimension at the j th preset collection time. The greater the value, the more likely the dimension data of the i th target road section under the k th preset monitoring dimension at the j th preset collection time deviates from the historical average level.

[0040] In step S3, according to the number of preset monitoring dimensions and the data fluctuation change factors of each target road section under different preset monitoring dimensions at the current collection time and the preset collection times before the current collection time, a dimension change stability performance index corresponding to each target road section is determined.

[0041] As an example, the step can include the following steps: Firstly, the mean value of the data fluctuation change factor of each target road section under the same preset monitoring dimension at all preset collection time points before the current collection time point is determined as the historical fluctuation representative factor of each target road section under each preset monitoring dimension at the current collection time point.

[0042] For example, the formula corresponding to the determination of the historical fluctuation representative factor of the target road section under different preset monitoring dimensions at the current collection time point can be: ; Wherein, is the historical fluctuation representative factor of the ith target road section under the kth preset monitoring dimension at the current collection time point. i is the serial number of the target road section. k is the serial number of the preset monitoring dimension. n is the number of preset collection time points, which is equal to the serial number of the current collection time point. j is the serial number of the preset collection time point. is the data fluctuation change factor of the ith target road section under the kth preset monitoring dimension at the jth preset collection time point.

[0043] It should be noted that when is larger, it often means that the dimension data of the ith target road section under the kth preset monitoring dimension at the jth preset collection time point is more likely to deviate from the historical average level. Therefore, can represent the data deviation of the ith target road section under the kth preset monitoring dimension at the historical collection time point. When the value is larger, it often means that the dimension data of the ith target road section under the kth preset monitoring dimension at the historical collection time point is relatively larger, and it often means that the dimension data of the ith target road section under the kth preset monitoring dimension at the historical collection time point is more likely to deviate from the corresponding average level.

[0044] Secondly, according to the data fluctuation change factor and the historical fluctuation representative factor of each target road section under each preset monitoring dimension at the current collection time point, the monitoring feature representative factor of each target road section under each preset monitoring dimension at the current collection time point is determined.

[0045] For example, the formula corresponding to the determination of the monitoring feature representative factor of the target road section under different preset monitoring dimensions at the current collection time point can be: ; Wherein, is the monitoring feature representative factor of the ith target road section under the kth preset monitoring dimension at the current collection time point. i is the serial number of the target road section. k is the serial number of the preset monitoring dimension. n is the number of preset collection time points, which is equal to the serial number of the current collection time point. is a data fluctuation change factor of the ith target road section under the kth preset monitoring dimension at the nth preset collection time, that is, a data fluctuation change factor of the ith target road section under the kth preset monitoring dimension at the current collection time. is a historical fluctuation representative factor of the ith target road section under the kth preset monitoring dimension at the current collection time. is a preset factor greater than 0, mainly used to prevent the denominator from being 0, which can be 0.0001.

[0046] It should be noted that, can represent the data deviation of the ith target road section under the kth preset monitoring dimension at the current collection time. can represent the data deviation of the ith target road section under the kth preset monitoring dimension at the historical collection time. Therefore, can represent the relative data deviation of the ith target road section under the kth preset monitoring dimension at the current collection time, and to some extent, can represent the kth preset monitoring dimension feature of the ith target road section at the current collection time.

[0047] Thirdly, according to the monitoring feature representative factor of each target road section under different preset monitoring dimensions at the current collection time, the dimension feature fluctuation factor corresponding to each target road section is determined.

[0048] For example, the variance of the monitoring feature representative factor of each target road section under all preset monitoring dimensions at the current collection time can be determined as the dimension feature fluctuation factor corresponding to each target road section.

[0049] Fourthly, according to the number of preset monitoring dimensions and the dimension feature fluctuation factor corresponding to each target road section, the dimension change stability performance index corresponding to each target road section is determined, which can include the following sub-steps: Firstly, according to the dimension feature fluctuation factor corresponding to each target road section, the initial stability factor corresponding to each target road section is determined.

[0050] Wherein, the dimension feature fluctuation factor can be in a negative correlation relationship with the initial stability factor.

[0051] For example, the formula for determining the initial stability factor corresponding to the target road section can be: ; Wherein, is the initial stability factor corresponding to the ith target road section. i is the serial number of the target road section. is an exponential function with a natural constant as the base. is the variance of the monitoring feature representative factor of the ith target road section under all preset monitoring dimensions at the current collection time.

[0052] It should be noted that, can represent the distribution of different preset monitoring dimension features of the ith target road section at the current collection time. The greater the value, the more likely it is that the different preset monitoring dimension features of the ith target road section at the current collection time are uniformly distributed.

[0053] Secondly, the product of the number of preset monitoring dimensions and the initial stability factor corresponding to each target road section is normalized to obtain a dimension change stability performance index corresponding to each target road section.

[0054] For example, the formula corresponding to the dimension change stability performance index of the target road section can be: ; Among them, is the dimension change stability performance index corresponding to the ith target road section. i is the serial number of the target road section. is a normalization function. N is the number of preset monitoring dimensions. is the initial stability factor corresponding to the ith target road section.

[0055] It should be noted that, can represent the distribution of different preset monitoring dimension features of the ith target road section at the current collection time. The greater the value, the more likely it is that the different preset monitoring dimension features of the ith target road section at the current collection time are uniformly distributed. When N is larger, it means that more preset monitoring dimensions are considered when detecting road hazards, and it means that the factors considered when detecting road hazards are relatively more comprehensive. can relatively accurately represent the road feature of the ith target road section at the current collection time.

[0056] Step S4, according to the difference between the data fluctuation change factor of each target road section under the preset monitoring dimension at the current collection time and the previous preset collection time, and the dimension change stability performance index corresponding to each target road section, determine the hidden danger influence feature index corresponding to each target road section.

[0057] As an example, this step can include the following steps: Firstly, the mean value of the data fluctuation change factor of each target road section under all preset monitoring dimensions at the current collection time is determined as the current overall fluctuation index corresponding to each target road section.

[0058] Secondly, the mean value of the data fluctuation change factors of all the preset monitoring dimensions of each target road section at a preset monitoring time before the current monitoring time is determined as the reference overall fluctuation index corresponding to each target road section.

[0059] Thirdly, the hidden danger influence characteristic index corresponding to each target road section is determined according to the dimension change stability performance index corresponding to each target road section, the current overall fluctuation index and the reference overall fluctuation index.

[0060] For example, the hidden danger influence characteristic index corresponding to each target road section can be determined according to the dimension change stability performance index corresponding to each target road section, the time length between the current monitoring time and the preset monitoring time before the current monitoring time, and the difference between the current overall fluctuation index and the reference overall fluctuation index corresponding to each target road section.

[0061] For example, the formula for determining the hidden danger influence characteristic index corresponding to each target road section can be as follows: ; Wherein, is the hidden danger influence characteristic index corresponding to the ith target road section. i is the serial number of the target road section. is a normalization function. is the dimension change stability performance index corresponding to the ith target road section. t is the time length between the current monitoring time and the preset monitoring time before the current monitoring time. is an absolute value function. is the current overall fluctuation index corresponding to the ith target road section, that is, the mean value of the data fluctuation change factors of all the preset monitoring dimensions of the ith target road section at the current monitoring time. is the reference overall fluctuation index corresponding to the ith target road section, that is, the mean value of the data fluctuation change factors of all the preset monitoring dimensions of the ith target road section at the preset monitoring time before the current monitoring time. is a preset factor greater than 0, mainly used to prevent the denominator from being 0, which can be 0.0001.

[0062] It should be noted that, can relatively accurately represent the road surface feature situation of the ith target road section at the current monitoring time. When t is smaller, it means that the time length between the current monitoring time and the preset monitoring time before the current monitoring time is smaller, which means that the data collected at the preset monitoring time before the current monitoring time is more valuable. When is smaller, it means that the dimension data fluctuation situation of the ith target road section between the current monitoring time and the preset monitoring time before the current monitoring time is more similar. Therefore, The road surface state change feature of the ith target road section at the current collection time can be characterized to some extent, so that the road surface hidden danger influence feature can be characterized.

[0063] Step S5: screening out the target similar road section corresponding to each target road section from all target road sections, and performing road surface hidden danger detection based on the difference between the hidden danger influence feature index corresponding to each target road section and the target similar road section thereof.

[0064] As an example, the present step can include the following steps: Firstly, screening out the target similar road section corresponding to each target road section from all target road sections can include the following sub-steps: First sub-step: determining any one target road section as a marker road section, and screening out the target road sections with the same material thickness as the marker road section from all target road sections to form a reference road section set corresponding to the marker road section.

[0065] The material thickness of the target road sections in the reference road section set corresponding to the marker road section can be the same as the material thickness of the marker road section.

[0066] Second sub-step: screening out the target road sections with a distance less than a preset distance threshold from the marker road section from the reference road section set corresponding to the marker road section as the target similar road section corresponding to the marker road section.

[0067] The distance between two road sections can be equal to the distance between the center points of the two road sections. The preset distance threshold can be a preset threshold, which can be 500 meters.

[0068] Secondly, according to the difference between the hidden danger influence feature index corresponding to each target road section and the hidden danger influence feature index corresponding to the target similar road section thereof, determining the target abnormality index corresponding to each target road section.

[0069] For example, the formula for determining the target abnormality index corresponding to the target road section can be: ; Wherein, is the target abnormality index corresponding to the ith target road section. i is the serial number of the target road section. is an exponential function with a natural constant as the base. is the number of target similar road sections corresponding to the ith target road section. b is the serial number of the target similar road section corresponding to the ith target road section. is an absolute value function. is the hidden danger influence feature index corresponding to the ith target road section. is the hidden danger influence feature index corresponding to the bth target similar road section corresponding to the ith target road section.

[0070] It should be noted that in actual situations, the road surface of most sections of the expressway is often normal, and the abnormal sections with road surface hidden dangers are usually a minority. Therefore, the road surface hidden danger of the target section can be judged by comparing the differences between the target section and the similar sections. The smaller the value is, the more similar the road surface state change characteristics between the i-th target section and the b-th target similar section at the current collection time are. Therefore, when the value is larger, the more similar the road surface state change characteristics between the i-th target section and the target similar section at the current collection time are, and the relatively smaller the road surface hidden danger risk of the i-th target section is.

[0071] Thirdly, if the target abnormal index corresponding to the target section is greater than a preset abnormal threshold, it is determined that the target section has a larger road surface hidden danger.

[0072] The preset abnormal threshold can be a preset threshold, which can be 0.6.

[0073] Optionally, when the target abnormal index corresponding to the target section is larger, it means that the target section is more likely to have an abnormality. At this time, the sampling frequency of the monitoring data can be increased in the monitoring process of the road surface condition of the target section, so as to facilitate the analysis of the road surface condition of the target section by the staff.

[0074] Optionally, the target abnormal index corresponding to the target section can be corrected by using multiple existing indexes representing road surface hidden dangers to obtain a final index that can better represent road surface hidden dangers. The existing indexes representing road surface hidden dangers can be, but are not limited to, rut depth and deflection value. The larger the rut depth is, the larger the depth is, the track belt depression leads to the increase of water accumulation risk, the extension of vehicle braking distance and the decrease of directional stability. The larger the deflection value is, the less the road surface structure stiffness is, and the more likely the structure is damaged by cracks, subsidence and other structural damages under long-term load.

[0075] For example, the rut depth and the deflection value of the target section at the current collection time can be collected, denoted as the current rut depth and the current deflection value, and the multiplication value of the target abnormal index corresponding to the target section, the current rut depth and the current deflection value is normalized to obtain a corrected abnormal index as a final index that can better represent road surface hidden dangers.

[0076] With reference to Figure 2 Based on the same inventive concept as the above method embodiment, the present application provides a road surface hidden danger detection system for a high-speed road network operation guarantee platform, which comprises a processor and a memory. The processor is used to process instructions stored in the memory to realize the steps of a road surface hidden danger detection method for a high-speed road network operation guarantee platform, which can specifically include: ​The dimension data acquisition module 201 is configured to acquire dimension data of each target road section on the expressway network under each preset monitoring dimension at each preset collection time. The data fluctuation change factor determination module 202 is configured to determine a data fluctuation change factor of each target road section under each preset monitoring dimension at each preset collection time according to the dimension data of each target road section under the same preset monitoring dimension at each preset collection time and the preset collection time before the preset collection time. The dimension change stability performance index determination module 203 is configured to determine a dimension change stability performance index corresponding to each target road section according to the number of preset monitoring dimensions and the data fluctuation change factors of each target road section under different preset monitoring dimensions at the current collection time and the preset collection time before the current collection time. The hidden danger influence characteristic index determination module 204 is configured to determine a hidden danger influence characteristic index corresponding to each target road section according to the difference between the data fluctuation change factors of each target road section under the preset monitoring dimension at the current collection time and the preset collection time before the current collection time, and the dimension change stability performance index corresponding to each target road section. The screening and road surface hidden danger detection module 205 is configured to screen a target similar road section corresponding to each target road section from all target road sections, and perform road surface hidden danger detection based on the difference between the hidden danger influence characteristic indexes corresponding to each target road section and the target similar road section thereof.

[0077] Figure 3 is a structural schematic diagram of a computer device provided by an embodiment of the present application. As shown in the example, Figure 3 the computer device 300 includes a memory 301, a processor 302, and a computer program 303 stored in the memory 301 and running on the processor 302, wherein the processor 302 executes the computer program 303, so that the computer device can execute any one of the road surface hidden danger detection methods for the expressway network operation guarantee platform introduced above.

[0078] Based on the same inventive concept as the above method embodiment, the present application provides a server including a memory and a processor. The memory is configured to store executable program code, and the processor is configured to call and run the executable program code from the memory, so that the device executes any one of the road surface hidden danger detection methods for the expressway network operation guarantee platform described above.

[0079] Based on the same inventive concept as the above method embodiment, the present application provides a computer program product, which includes computer program code. When the computer program code runs on a computer, it makes the computer execute any one of the road surface hidden danger detection methods for the expressway network operation guarantee platform described above.

[0080] Based on the same inventive concept as the above method embodiments, the present application provides a computer readable storage medium storing computer program code, which, when executed on a computer, causes the computer to perform any one of the above-mentioned road surface hidden danger detection methods for a highway network operation guarantee platform.

[0081] In summary, the present application quantifies the data fluctuation change factor, dimension change stability performance index and hidden danger influence characteristic index relatively objectively by analyzing the dimension data of different road sections under different preset monitoring dimensions at different times, to a certain extent, reduces the influence of artificial subjective factors, thereby improving the accuracy of road surface hidden danger detection, and realizes road surface hidden danger detection through real-time collected dimension data, to a certain extent, reduces the cycle length of road surface hidden danger detection, thereby improving the efficiency of road surface hidden danger detection.

[0082] The above embodiments are only used to illustrate the technical solutions of the present application, but not limit it; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A road surface hidden danger detection method for a highway network operation guarantee platform, characterized in that: The following steps are involved: Obtain dimensional data for each preset monitoring dimension at each preset collection time for each target section on the highway network to be inspected, where the latest preset collection time is recorded as the current collection time; Determine the data fluctuation change factor of each target road section at each preset monitoring dimension at each preset collection time based on the dimensional data of each target road section at the same preset monitoring dimension at each preset collection time and the preset collection time before that; Determine the dimension change stability performance index corresponding to each target road section based on the number of preset monitoring dimensions and the data fluctuation change factor of each target road section under different preset monitoring dimensions at the current collection time and the preset collection time before; Determine the hidden danger impact characteristic index corresponding to each target road section based on the difference between the data fluctuation change factor under the preset monitoring dimension at the current collection time and the previous preset collection time, as well as the dimension change stability performance index corresponding to each target road section; Target similar road sections corresponding to each target road section are screened out from all target road sections, and road hazard detection is performed based on the difference between the hazard impact characteristic indicators corresponding to each target road section and its target similar road sections.

2. A road surface hidden danger detection method for a highway network operation guarantee platform according to claim 1, characterized in that: The step of determining the data fluctuation change factor of each target road section at each preset monitoring dimension at each preset collection time based on the dimensional data of each target road section at the same preset monitoring dimension at each preset collection time and the preset collection time before the preset collection time includes: Determine any target road section as a marked road section, any preset collection time as a marked time, and any preset monitoring dimension as a marked monitoring dimension; Determine the mean of the dimension data of the marked road section under the marked monitoring dimension at all preset collection moments before the marking moment as the reference representative data of the marked road section under the marked monitoring dimension at the marking moment; The difference between the dimensional data of the marked section in the marked monitoring dimension at the marking moment and the reference representative data is normalized to obtain a data fluctuation change factor of the marked section in the marked monitoring dimension at the marking moment.

3. The method for detecting road hazards for a highway network operation assurance platform according to claim 1, characterized in that: Determining the dimension change stability performance index corresponding to each target road section based on the number of preset monitoring dimensions and the data fluctuation change factor of each target road section under different preset monitoring dimensions at the current collection time and the preset collection time before the current collection time includes: The average of the data fluctuation change factors of each target road section under the same preset monitoring dimension at all preset collection moments before the current collection moment is determined as the historical fluctuation representative factor of each target road section under each preset monitoring dimension at the current collection moment; Determine the monitoring feature representative factor of each target road section under each preset monitoring dimension at the current collection time based on the data fluctuation change factor and historical fluctuation representative factor of each target road section under each preset monitoring dimension at the current collection time; Determine the dimensional feature fluctuation factor corresponding to each target road section based on the monitoring feature representative factors of each target road section under different preset monitoring dimensions at the current collection time; According to the number of preset monitoring dimensions and the dimension characteristic fluctuation factor corresponding to each target section, the dimension change stability performance index corresponding to each target section is determined.

4. A road surface hidden danger detection method for a highway network operation guarantee platform according to claim 3, characterized in that: The determining of the dimensional feature fluctuation factor corresponding to each target road section according to the monitoring feature representative factors of each target road section under different preset monitoring dimensions at the current collection moment includes: The variance of the monitoring feature representative factors of each target road section under all preset monitoring dimensions at the current collection moment is determined as the dimensional feature fluctuation factor corresponding to each target road section.

5. The method for detecting road hazards for a highway network operation assurance platform according to claim 3, characterized in that: Determining the dimension change stability performance index corresponding to each target road section based on the number of preset monitoring dimensions and the dimension characteristic fluctuation factor corresponding to each target road section includes: According to the dimensional feature fluctuation factor corresponding to each target road section, the initial stability factor corresponding to each target road section is determined, wherein the dimensional feature fluctuation factor is negatively correlated with the initial stability factor; The product of the number of preset monitoring dimensions and the initial stability factor corresponding to each target section is normalized to obtain the dimension change stability performance index corresponding to each target section.

6. The method for detecting road hazards for a highway network operation assurance platform according to claim 1, characterized in that: The method of determining the hidden danger impact characteristic index corresponding to each target road section based on the difference between the data fluctuation change factor under the preset monitoring dimension at the current collection moment and the previous preset collection moment, and the dimension change stability performance index corresponding to each target road section, includes: The average of the data fluctuation change factors of all preset monitoring dimensions for each target road section at the current collection time is determined as the current overall fluctuation index corresponding to each target road section; The average of the data fluctuation change factors of all preset monitoring dimensions at the preset collection time before the current collection time for each target road section is determined as the reference overall fluctuation index corresponding to each target road section; According to the dimensional change stability performance index, current overall fluctuation index and reference overall fluctuation index corresponding to each target road section, the hidden danger impact characteristic index corresponding to each target road section is determined.

7. A road surface hidden danger detection method for a highway network operation guarantee platform according to claim 6, characterized in that: The hidden danger impact characteristic index corresponding to each target road section is determined based on the dimensional change stability performance index, the current overall fluctuation index, and the reference overall fluctuation index corresponding to each target road section, including: The hidden danger impact characteristic index corresponding to each target road section is determined based on the dimensional change stability performance index corresponding to each target road section, the time between the current collection moment and its previous preset collection moment, and the difference between the current overall fluctuation index corresponding to each target road section and the reference overall fluctuation index.

8. The method for detecting road hazards for a highway network operation assurance platform according to claim 1, characterized in that: The step of selecting target similar road segments corresponding to each target road segment from all target road segments includes: Determine any target road section as a marked road section, and select target road sections with the same material thickness as the marked road section from all target road sections to form a reference road section set corresponding to the marked road section; A target road segment whose distance to the marked road segment is less than a preset distance threshold is screened out from the reference road segment set corresponding to the marked road segment as the target similar road segment corresponding to the marked road segment.

9. The method for detecting road hazards for a highway network operation assurance platform according to claim 1, characterized in that: The road surface hidden danger detection based on the difference between the hidden danger impact characteristic indicators corresponding to each target road section and its target similar road sections includes: Determine the target abnormality index corresponding to each target road section based on the difference between the hidden danger impact characteristic index corresponding to each target road section and the hidden danger impact characteristic index corresponding to similar target road sections; If the target abnormality index corresponding to the target road section is greater than the preset abnormality threshold, it is determined that there are major road hazards in the target road section.

10. A road surface hidden danger detection system for a highway network operation guarantee platform, characterized in that: It comprises a processor and a memory, wherein the processor is used to process instructions stored in the memory to implement a road surface hazard detection method for a highway network operation assurance platform as described in any one of claims 1 to 9.

Images