Road discontinuity state warning method

Abstract

The application discloses a highway discontinuous state early warning method, which comprises the following steps: collecting road surface state data of corresponding road surfaces through multiple road surface data collection devices arranged at intervals on the highway, and sending the road surface state data to a data processing device for processing to obtain a first processing result; since the data processing device is arranged at the front end, the road surface state data can be processed in real time, rapid reaction to abnormal data can be realized, the data processing device can determine a first risk level based on the first processing result, and the first risk level can be sent to a decision device when the first risk level is greater than a risk threshold, so that the abnormal situation can be responded in time. In addition, the decision device can also divide early warning levels according to the first risk level, and select a target execution device suitable for the current risk scene from multiple execution devices according to different early warning levels to carry out hierarchical early warning, so that accurate scheduling and optimized configuration of risk response resources are realized, and rapid identification and early warning of the road abnormal state are realized.

Description

Technical Field

[0001] This disclosure generally relates to the field of intelligent transportation technology, and specifically to a method for early warning of discontinuous highway conditions. Background Technology

[0002] At present, disasters caused by extreme weather are becoming increasingly frequent, bringing significant impacts to many industries, especially land transportation within the transportation sector. Road and rail transport, as crucial components of the transportation industry, are characterized by long distances, complex and variable geological conditions, and numerous structural features, making them highly susceptible to accidents such as roadbed collapses and bridge washouts triggered by extreme weather, leading to disruptions in transportation routes and threatening the safety of drivers and passengers.

[0003] Traditional methods for early warning of these accidents usually rely on fixed cameras and manual patrols, but these methods have problems such as response delays and low road network coverage when facing emergencies. Therefore, there is an urgent need to propose a new method for monitoring land transportation to solve these problems. Summary of the Invention

[0004] This application provides a method for early warning of discontinuous road conditions, which can achieve rapid identification and early warning of abnormal road conditions.

[0005] This application presents a method for early warning of discontinuous highway conditions. The method is applied to an early warning system, which includes data acquisition equipment, data processing equipment, decision-making equipment, and execution equipment. The data acquisition equipment includes multiple road surface data acquisition devices, which are set at adaptive intervals based on the curvature of the highway. The method includes: The data processing device receives road surface condition data collected by the road surface data acquisition device and processes the road surface condition data to obtain a first processing result. The data processing device determines a first risk level based on the first processing result, and sends the first risk level to the decision-making device if the first risk level is greater than the risk threshold. The decision-making device classifies the early warning level according to the first risk level, and determines the first target execution device according to the early warning level; The decision-making device sends a warning instruction to the first target execution device, the warning instruction being used to instruct the target execution device to perform a warning operation.

[0006] In an optional embodiment, the road surface condition data carries a first identifier for marking the road surface data acquisition device, characterized in that the step of processing the road surface condition data to obtain a first processing result includes: the data processing device matching the first identifier of the road surface data acquisition device with a first correspondence table to obtain the physical coordinates of the road surface data acquisition device, wherein the second correspondence table includes a plurality of second identifiers of road surface data acquisition devices and physical coordinates corresponding to the second identifier of each road surface data acquisition device; The data processing device retrieves historical status data based on the physical coordinates of the road surface data acquisition device, and determines the first processing result based on the road surface status data and the historical status data.

[0007] In an optional embodiment, the road surface condition data includes vertical displacement data, and the historical condition data is the historical vertical displacement data collected at the previous moment of the vertical displacement data. The step of determining the first processing result based on the road surface condition data and the historical image data includes: subtracting the vertical displacement data from the historical vertical displacement data to obtain the vertical displacement difference, and obtaining the vertical displacement change rate by comparing the vertical displacement difference with the difference between adjacent time windows. The vertical displacement change rate is compared with the change rate threshold to obtain a comparison result, and the comparison result is used as the first processing result.

[0008] In an optional embodiment, the road surface condition data includes horizontal displacement data, and the historical condition data is historical horizontal displacement data collected at the previous moment. Determining the first processing result based on the road surface condition data and the historical image data includes: The displacement offset is determined by baseline calculation method based on the horizontal displacement data and the historical horizontal displacement data. The displacement offset is compared with the standard deviation to obtain a comparison result, and the comparison result is used as the first processing result.

[0009] In one optional embodiment, the road surface condition data includes displacement data within a monitoring period, and the historical condition data is historical displacement data. Determining the first processing result based on the road surface condition data and the historical image data includes: Each displacement data is subtracted from the corresponding historical displacement data to obtain multiple displacement differences, and the multiple displacement differences are summed to obtain the cumulative displacement. The displacement rate is determined based on the displacement data and the time of acquisition of the displacement data. The cumulative displacement and the displacement rate are used as the first processing result.

[0010] In an optional embodiment, the road surface condition data further includes geological parameters and traffic load, and the data processing device determines the risk level based on the first processing result, including: The data processing device determines the risk level based on the sum of the product of the displacement rate and the first parameter, the product of the cumulative displacement and the second parameter, the product of the geological parameter and the third parameter, and the product of the traffic load and the fourth parameter.

[0011] In an optional embodiment, the data acquisition device further includes an image acquisition device installed on a target road segment in the highway, wherein the target road segment is a road segment with a driving risk greater than a preset risk, and the method further includes: For the target road segment, if the data processing device determines that the first risk level is less than the risk threshold, it acquires the image data acquired by the image acquisition device and compares the image data with historical image data to obtain a second processing result. If the second processing result is that there are target objects in the image data that are inconsistent with the historical image data, and the number of target objects is greater than the number threshold, then an early warning message is generated, and the early warning message carries a second risk level. The second risk level is sent to the decision-making device.

[0012] In an optional embodiment, the image data carries a second identifier for marking the image acquisition device, and the method further includes: The data processing device matches the second identifier of the target image set device with the second correspondence table to obtain the physical coordinates of the target image set device. The first correspondence table includes the second identifiers of multiple image acquisition devices and the physical coordinates corresponding to the second identifier of each image acquisition device. The data processing device retrieves the historical image data based on the physical coordinates of the target image set device.

[0013] In an optional embodiment, the method further includes: If the processing device does not receive data from the data acquisition device during the monitoring period, it determines the target data acquisition device adjacent to the data acquisition device based on the unique identifier of the data acquisition device, and sends a test command to the data acquisition device. After receiving the test instruction, the target data acquisition device sends a first test message to the data acquisition device. If the target data acquisition device does not receive a response message based on the first test message within a preset time period, it sends an abnormal message to the data processing device. The data processing device generates a risk message based on the abnormal message and reports the risk message to the traffic management center.

[0014] In one optional embodiment, the early warning system further includes a power supply device for supplying power to the data acquisition device, the data processing device, and the execution device.

[0015] This application provides a method for early warning of discontinuous road conditions. Considering that current traffic warning methods often rely on fixed cameras and manual patrols, which result in response delays and low road network coverage when facing emergencies, this application addresses this issue by periodically installing multiple road surface data acquisition devices along the highway. Each device collects road surface condition data for its corresponding surface and sends it to a data processing device with which it communicates for processing to obtain a first processing result. Since the data processing device is located at the front end, it can process the road surface condition data collected by the acquisition devices in real time, enabling rapid response to abnormal data. Furthermore, the data processing device determines a first risk level based on the first processing result and sends this first risk level to a decision-making device if it exceeds a risk threshold, ensuring immediate response to abnormal situations. In addition, the decision-making device can classify warning levels based on the first risk level and select the appropriate target execution device from multiple execution devices for tiered warning based on different warning levels. This achieves precise scheduling and optimized allocation of risk response resources, thereby enabling rapid identification and early warning of abnormal road conditions. Attached Figure Description

[0016] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 An application scenario diagram of a highway discontinuous state early warning method provided in this application; Figure 2 A flowchart of the steps of a method for early warning of discontinuous highway conditions provided in this application; Figure 3 A flowchart illustrating the steps of another method for early warning of discontinuous highway conditions provided in this application; Figure 4 A flowchart illustrating the steps of another method for early warning of discontinuous highway conditions provided in this application; Figure 5 A flowchart illustrating the steps of another method for early warning of discontinuous highway conditions provided in this application; Figure 6 A flowchart illustrating the steps of another method for early warning of discontinuous highway conditions provided in this application; Figure 7A flowchart illustrating the steps of another method for early warning of discontinuous highway conditions provided in this application; Figure 8 A flowchart illustrating the steps of another method for early warning of discontinuous highway conditions provided in this application. Detailed Implementation

[0017] The present application will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings.

[0018] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0019] Please refer to Figure 1 , Figure 1 This diagram illustrates an application scenario of the highway discontinuous state early warning method provided in this application. The application scenario includes an early warning system comprising a data acquisition device 101, a data processing device 102, an execution device 103, and a decision-making device 104, all spaced apart along the highway. The data acquisition device 101 is communicatively connected to the data processing device 102, and both the data processing device 102 and the execution device 103 are communicatively connected to the decision-making device 104. The data acquisition device 101 may include, for example, a road surface data acquisition device and an image acquisition device. The road surface data acquisition device may be, for example, a vibration sensor, a displacement sensor, a tilt sensor, a weather sensor, or radar. The image acquisition device may be, for example, a camera. The data processing device 102 may be, for example, a microcontroller, a processing chip, or a BeiDou integrated machine. The execution device 103 may be, for example, an audible and visual alarm or an electronic sign. The decision-making device 104 may be, for example, a cloud platform, a server, or a server cluster. It is understood that the above-mentioned early warning system also includes power supply equipment (not shown in the figure), which is used to supply power to the data acquisition device 101, the data processing device 102 and the execution device 103.

[0020] The road surface data acquisition device transmits the collected road surface condition data (vertical displacement, horizontal displacement, soil moisture, etc.) to the data processing device 102 via a network. The data processing device 102 processes the road surface condition data (filtering, normalization, cleaning, subtraction, comparison, etc.) to obtain a first processing result, and determines a first risk level (Level 1, Level 2, Level 3, etc.) based on the first processing result. When the data processing device 102 determines that the first risk level is greater than the risk threshold, it generates an abnormal message and sends the abnormal message carrying the first risk level to the decision-making device 104. After receiving the abnormal message, the decision-making device 104 parses the abnormal message, classifies the warning level according to the obtained first risk level, and determines the target execution device from multiple execution devices 103 according to the warning level. It then sends a warning command to the target execution device to instruct it to perform the corresponding warning operation, thereby realizing the rapid identification and warning of abnormal road conditions.

[0021] The following description uses the application of the highway discontinuous state early warning method provided in this application to the aforementioned early warning system as an example to illustrate the highway discontinuous state early warning method.

[0022] like Figure 2 As shown, Figure 2 A flowchart of a method for early warning of discontinuous highway conditions provided in this application is shown. The method includes: Step S20: The data processing device receives the road surface status data collected by the road surface data acquisition device and processes the road surface status data to obtain the first processing result. The road surface data acquisition device can be any device installed along the highway, and the data processing equipment can be any device that communicates with the road surface data acquisition device. Alternatively, multiple road surface data acquisition devices can share a single data processing device. This means that the data processing device can receive and process data from multiple road surface acquisition devices, eliminating the need for a separate data processing device for each device, thus saving resources and reducing costs.

[0023] If multiple road surface data acquisition devices share a single data processing device, the road surface data acquisition device can encapsulate a unique identifier that can identify itself along with the road surface status data and send it to the data processing device. This allows the data processing device to process the road surface status data carrying the unique identifier separately, thus avoiding data confusion.

[0024] As mentioned above, when the road surface data acquisition device is a vertical displacement sensor, the collected road surface condition data is vertical displacement; when the road surface data acquisition device is a horizontal displacement sensor, the collected road surface condition data is horizontal displacement; and when the road surface data acquisition device is a meteorological sensor, the collected road surface condition data is soil moisture, etc. It is understood that the types of road surface data acquisition devices installed at intervals on a highway can be one or more. For example, point A on the highway is simultaneously equipped with a vertical displacement sensor, a horizontal displacement sensor, and a meteorological sensor. Therefore, when multiple types of road surface data acquisition devices are installed, the data processing equipment can receive multiple different road surface condition data for the same location, which will not be elaborated here. Traditional early warning systems often rely on a single piece of data to directly trigger an alarm (e.g., an alarm is triggered when vertical displacement exceeds a threshold), while the data processing equipment in this application can issue early warnings based on multi-source data, improving the accuracy of risk assessment.

[0025] After receiving road surface status data from the road surface data acquisition device, the data processing equipment enters the data processing stage. During this stage, the data processing equipment can perform operations on the road surface status data, such as the following: 1. Data cleaning and standardization: Cleaning road condition data removes noise and identifies anomalies, providing accurate data for subsequent early warning systems. Standardizing road condition data unifies the format of data from different types of devices, facilitating subsequent processing by data processing equipment and improving processing efficiency.

[0026] 2. Perform feature extraction processing on road surface condition data. For example, input the road surface condition data into machine vision models, time series analysis models, etc., to extract key features, thereby reducing the amount of data processing and further improving data processing efficiency.

[0027] 3. Generate the first processing result based on preset rules or lightweight models (such as threshold judgment, cluster analysis). For example, compare the vertical displacement data with historical vertical displacement data to obtain the comparison result.

[0028] The above is merely an illustrative description of the method for processing road surface condition data. The data processing device may also use other adaptive methods to process road surface condition data, and this application does not limit these methods.

[0029] It is understandable that, since road condition data includes various types of data, the first processing result can be a comprehensive processing result for different types of data, or a classification result for each type of data; this application does not limit this. When the first processing result is a comprehensive processing result for different types of data, the first processing result can be a risk value, a probability value, etc.

[0030] Road surface condition data is collected by a road surface data acquisition device and processed by a data processing device to obtain a first processing result. This is to determine whether the road section has been affected by a natural disaster and to take appropriate remedial measures accordingly. The following steps, S30-S50, explain how to determine whether the road section has been affected by a natural disaster.

[0031] Step S30: The data processing device determines a first risk level based on the first processing result, and generates an abnormal message if the first risk level is greater than the risk threshold, and sends the abnormal message to the decision-making device. The abnormal message carries the first risk level. As mentioned above, the data processing equipment can process road surface condition data using various methods. Therefore, the first processing result can be data that has undergone data cleaning and standardization; it can also be feature data after feature extraction; it can be a judgment result after threshold judgment; or it can be a predicted risk value, etc. For example, the first processing result is that the vertical displacement data is greater than the historical vertical displacement data.

[0032] The data processing equipment may determine the first risk level based on the first processing result in the following ways: 1. The data processing equipment may store correspondence information for different types of data. This correspondence information includes a first processing result and the risk level corresponding to the first processing result. Therefore, after the data processing equipment processes the road condition data to obtain a first processing result, it can match the first processing result with the correspondence information to obtain the first risk level. This method of determining the risk level through established industry standards is simple and can quickly obtain the first risk level result, thereby improving the efficiency of early warning.

[0033] 2. The first processing result is converted into a risk value based on the risk value calculation method, and then matched with the risk value and risk level correspondence information table to obtain the corresponding risk level. For example, the data processing device may multiply the vertical displacement data by the first weight, multiply the horizontal displacement data by the second weight, multiply the meteorological data by the third weight, and then add the three products to obtain the corresponding risk value.

[0034] The corresponding relationship information table is as follows: Risk value Risk level 0-30 Blue 31-60 Yellow 61-80 Orange 81-100 Red Understandably, if the first risk level is blue, it indicates low risk; if it is yellow, it indicates some risk, but not much risk; if it is orange, it indicates high risk; and if it is red, it indicates the highest risk.

[0035] This application differentiates different risks by determining their risk levels, making subsequent early warnings more targeted and the early warning actions implemented more suitable for the current environment.

[0036] Understandably, to conserve resources, not all first-risk levels obtained by data processing equipment are typically reported to decision-making equipment; instead, reports are selective. This application sets the result of comparing the first-risk level with a preset risk threshold as the standard for selective reporting, reporting only when the comparison result shows that the first-risk level is greater than the risk threshold.

[0037] It's important to note here that the risk threshold can be a limit set based on historical data, human experience, etc., used to define the conditions for reporting to the decision-making equipment and the triggering conditions for generating abnormal messages. For example, the risk threshold could be yellow, meaning that when the first risk level is higher than or equal to yellow, a report will be sent to the decision-making equipment.

[0038] Abnormal messages are used to indicate that there is a risk in the current road section. When generating abnormal messages, the data processing equipment will encapsulate the determined risk level in the abnormal message so that the decision-making equipment can make targeted decisions, so that the warning is more adapted to the current risk, and avoids the situation where the warning is too weak to alert pedestrians, or too strong to cause pedestrian panic and secondary safety accidents.

[0039] Step S40: The decision-making device classifies the warning level according to the first risk level in the abnormal message, and determines the target execution device from multiple execution devices according to the warning level; When the decision-making device receives an abnormal message from the data processing device, it will analyze the abnormal message to obtain the first risk level, and then determine the warning level based on the first risk level.

[0040] Decision-making equipment could, for example, compare a first risk level with a classification threshold and determine the warning level based on the comparison result.

[0041] For example, when the decision-making device determines that the first risk level is orange, the grading threshold is yellow, and the comparison result shows that the first risk level exceeds the grading threshold by 30%, then the warning level is determined to be level two.

[0042] The decision-making equipment can also determine the warning level directly based on pre-stored correspondence information, such as: Level 1 Risk Warning Blue Level 4 Yellow Level 3 Orange Level 2 Red Level 1 Understandably, after receiving an abnormal message from the data processing device, the decision-making device can directly match the parsed first risk level with the aforementioned corresponding information to obtain the warning level. This classification method does not require a complex calculation process and can quickly classify the warning level, further improving the warning efficiency.

[0043] Execution devices include, for example, laser warning posts, variable message signs, directional acoustic devices, and intelligent road markings. Each execution device is paired with a road surface data acquisition device; therefore, execution devices are installed at every location along the highway where road surface data acquisition devices are located. Furthermore, at least two types of execution devices are included, allowing the decision-making equipment to select the appropriate target execution device to perform the corresponding warning operation based on different warning levels.

[0044] The decision-making device may also store strategies for selecting targets to execute based on the warning level. For example, the decisions within the decision-making device may include the following: When the warning level is Level 1, the three patterns of the laser warning post are displayed in a loop, a prompt message is displayed on the variable message sign, the directional sound wave device is activated to broadcast a danger voice, the intelligent road markings provide dynamic guidance, the vehicle OBU broadcasts, and the navigation APP pushes information. When the warning level is level 2, the two patterns of the laser warning post are displayed in a loop, the directional sound wave device is activated to broadcast danger voice warnings, the intelligent road markings provide dynamic guidance, the vehicle OBU broadcasts, and the navigation APP pushes information. When the warning level is level three, the directional sound wave device is activated to broadcast danger voice messages, and the intelligent road markings provide dynamic guidance, vehicle OBU broadcast, and navigation APP push. When the warning level is level four, dynamic guidance is provided through intelligent road markings, vehicle OBU broadcasts, and navigation APP push notifications.

[0045] This application sets up different execution devices for different warning levels, making the warnings more targeted.

[0046] In step S50, the decision-making device sends a warning instruction to the target execution device, which instructs the target execution device to perform a warning operation.

[0047] The number of target execution devices can be one or more, depending on the warning level. When there are multiple target execution devices, the decision-making device can send warning commands to multiple target execution devices simultaneously to instruct them to perform warning operations.

[0048] For example, if the target device is a laser warning post, the warning operation is to display a pattern; if the target device is a variable message sign, the warning operation is to display a prompt message; if the target device is a directional sound wave device, the warning operation is to broadcast a warning of danger, etc. The warning operation is different for different devices, which will not be elaborated here.

[0049] In an optional embodiment, such as Figure 3 As shown, Figure 3 An optional method embodiment for processing road surface condition data using the data processing device provided in this application includes the following steps: Step S301: The data processing device matches the first identifier of the road data acquisition device with the first correspondence table to obtain the physical coordinates of the road data acquisition device. The second correspondence table includes the first identifiers of multiple road data acquisition devices and the physical coordinates corresponding to the first identifier of each road data acquisition device. As mentioned above, the road surface data acquisition device includes multiple devices, which are based on the curvature adaptive interval device of the highway. Since the data processing device can receive data sent by multiple road surface data acquisition devices, each road surface data acquisition device can encapsulate its unique identifier (first identifier) ​​in the road surface status data when sending the road surface status data. This facilitates the data processing device to distinguish between them and to identify the physical coordinates of the road surface data acquisition device that sent the road surface status data.

[0050] The first correspondence table is pre-set in the storage space of the data processing device. It includes the first identifier of multiple road surface acquisition devices and the physical coordinates corresponding to the first identifier of each road surface acquisition device. When the data processing device receives road surface status data, it parses the road surface status data to obtain the first identifier of the road surface data acquisition device, and then matches it with the first correspondence table to quickly obtain the physical coordinates of the road surface data acquisition device.

[0051] The purpose of determining the physical coordinates is to retrieve the historical status data corresponding to the physical coordinates of the road data acquisition device. This is because the data processing equipment can store historical status data according to the coordinates of each road segment.

[0052] Optionally, the decision-making device maps the first identifier of each road data acquisition device to the physical coordinates of each road data acquisition device using Kalman filtering, and generates the first mapping table.

[0053] This application employs Kalman filtering for road surface data acquisition device location estimation, eliminating GPS positioning drift through a prediction-correction mechanism. Dynamic correction via Kalman filtering effectively eliminates multipath interference in highway scenarios, ensuring accurate correspondence between the road surface data acquisition device location and the road segment topology.

[0054] S302, the data processing equipment retrieves historical status data based on the physical coordinates of the road surface data acquisition device, and determines the first processing result based on the road surface status data and the historical status data.

[0055] In this process, after the data processing equipment retrieves historical status data based on the physical coordinates of the road surface data acquisition device, it can determine a first processing result based on the road surface status data and the historical status data. This determination method may include, for example, the following: The road surface condition data is compared with historical condition data to obtain results such as consistency, consistency rate of 10%, consistency rate of 30%, and consistency rate of 50%, and the result is used as the first processing result. Alternatively, the road surface condition data can be compared with the average value of historical condition data to obtain the deviation of the road surface condition data, such as deviation of 40%, 25%, 10%, or 15%, and this deviation result can be used as the first processing result.

[0056] Data processing equipment has other methods for determining the first processing result, which will not be elaborated here.

[0057] This application determines the first processing result by comparing road surface condition data with historical condition data. Since historical condition data is readily available and highly reliable, it can provide a reliable basis for analyzing road surface condition data and improve the accuracy of early warning.

[0058] In an optional method embodiment, if the road surface condition data includes vertical displacement data, then the historical condition data is the historical vertical displacement data at the time before the vertical displacement data was collected. Based on this data, this application provides an optional method embodiment for determining a first processing result based on road surface condition data and historical condition data, such as... Figure 4 As shown, an embodiment of this method includes the following steps: Step S401: Subtract the vertical displacement data from the historical vertical displacement data to obtain the vertical displacement difference, and obtain the vertical displacement change rate by comparing the vertical displacement difference with the difference between adjacent time windows. Vertical displacement data refers to the positional change of a road surface along the direction of gravity, including surface subsidence, building uplift, or vertical deformation of structures. Vertical displacement data can be obtained by displacement sensors that capture changes in vertical distance in real time.

[0059] The historical vertical displacement data from the previous moment is obtained from the memory address of the data processing device. By subtracting the historical vertical displacement data from the current vertical displacement data, the amount of calculation can be reduced, and the efficiency of early warning can be improved.

[0060] By calculating the rate of change of vertical displacement in real time, the degree of damage to highway structures can be accurately quantified, and the reinforcement effect can be quantitatively assessed during remediation. It can also achieve a technological leap from static monitoring to dynamic early warning.

[0061] Step S402: Compare the vertical displacement change rate with the change rate threshold to obtain the comparison result, and use the comparison result as the first processing result.

[0062] The rate of change threshold can be a value set based on historical data, experiments, human experience, etc., to provide a limit for measuring the degree of vertical change.

[0063] By comparing the rate of change of vertical displacement with a rate of change threshold, abnormal settlement or uplift exceeding the rate of change threshold can be quickly identified, thereby obtaining the processing result of whether it is abnormal.

[0064] The first processing result includes: the rate of change of vertical displacement is greater than or equal to the rate of change threshold, or the rate of change of vertical displacement is less than the rate of change threshold.

[0065] Furthermore, the data processing device can determine the first risk level as orange or red when the first processing result is that the vertical displacement change rate is greater than or equal to the change rate threshold; and determine the first risk level as blue when the first processing result is that the vertical displacement change rate is less than the change rate threshold.

[0066] In an optional embodiment of the method, if the road surface condition data includes horizontal displacement data, then the historical condition data is the historical horizontal displacement data at the time before the horizontal displacement data was collected. Based on this data, this application provides an optional method embodiment for determining a first processing result based on road surface condition data and historical condition data, such as... Figure 5 As shown, an embodiment of this method includes the following steps: Step S501: Determine the displacement offset based on the horizontal displacement data and historical horizontal displacement data using the baseline calculation method; The difference between horizontal and vertical displacement data lies in the direction of horizontal displacement, which is orthogonal to the direction of gravity. It assesses the lateral slippage of the highway and the lateral deformation of the structure. Horizontal displacement data can be acquired using equipment such as GNSS receivers and total stations.

[0067] The baseline calculation method is based on establishing a baseline using a control network coordinate system, and then calculating the lateral offset of the current point relative to the baseline using coordinate methods. It employs the least squares method to eliminate observation errors.

[0068] Step S502: Compare the displacement offset with the standard deviation to obtain the comparison result, and use the comparison result as the first processing result.

[0069] The standard deviation can be calculated from historical data and reflects the statistical fluctuation range of normal structural deformation.

[0070] The first processing result includes either the displacement offset exceeding the standard deviation or the displacement offset not exceeding the standard deviation. Therefore, the data processing equipment can determine the first risk level as orange when the first processing result is that the displacement offset exceeds the standard deviation, and determine the first risk level as blue when the first processing result is that the displacement offset does not exceed the standard deviation.

[0071] This application determines the first processing result through a dynamic standard deviation threshold mechanism, which can adapt to different geological conditions.

[0072] In another optional embodiment, the road surface condition data may further include displacement data within a detection cycle. This displacement data may be vertical displacement data, horizontal displacement data, or both vertical and horizontal displacement data; this application does not impose any limitations on this. Correspondingly, historical condition data may be historical vertical displacement data, historical horizontal displacement data, or historical vertical displacement data and historical horizontal displacement data.

[0073] So, based on Figure 6 The data processing device determines the first processing result based on the road surface condition data and the historical image data, including: Step S601: Subtract each displacement data from the corresponding historical displacement data to obtain multiple displacement differences, and sum the multiple displacement differences to obtain the cumulative displacement. Among them, historical displacement data can be the corresponding historical benchmark values, such as the average displacement during the stable period of a highway structure.

[0074] The cumulative displacement can be the total displacement of the same monitored location within a monitoring period. This monitoring period can be one month, one week, three months, etc.

[0075] Step S602: Determine the displacement rate based on each displacement data and the time taken to collect each displacement data. This application calculates the instantaneous velocity using the time difference Δt between two adjacent monitoring data points and the displacement change ΔD: v = ΔD / Δt, where v is the instantaneous displacement velocity. This allows for the acquisition of multiple instantaneous displacement velocities within a monitoring cycle.

[0076] The displacement rate within a monitoring cycle can be obtained by comparing the sum of all displacement data within a monitoring cycle with the monitoring time difference. This application does not limit this.

[0077] Step S603: The cumulative displacement and displacement rate are taken as the first processing results.

[0078] This application uses cumulative displacement to reflect long-term deformation trends and displacement rate to identify sudden deformation risks, using dual data as a discrimination mechanism to improve the accuracy of early warning.

[0079] Understandably, the data processing device can determine the first risk level based on the specific values ​​of the cumulative displacement and displacement rate. For example, it can determine the first risk level based on the stored correspondence information, which will not be elaborated here.

[0080] Optionally, the data processing device may also determine the first risk level based on the sum of the product of displacement rate and a first parameter, the product of cumulative displacement and a second parameter, the product of geological parameters and a third parameter, and the product of traffic load and a fourth parameter.

[0081] The formula is: R = α*V + β*D + γ*G + δ*T Where V is the displacement rate, D is the cumulative displacement, G is the geological parameter, and T is the traffic load. α is the first parameter, β is the second parameter, γ is the third parameter, and δ is the fourth parameter; α, β, γ, and δ are all adjustable weights, which can be dynamically adjusted based on historical accident data and real-time monitoring data. This application, through multi-parameter coupled analysis, can distinguish between short-term deformation caused by traffic load and long-term deformation caused by geological problems, thereby improving the accuracy of early warning.

[0082] In addition to multiple road surface data acquisition devices with adaptive curvature intervals based on highways, the data acquisition equipment of this application also includes image acquisition devices (such as cameras) installed on road sections where the driving risk is greater than the preset risk, in order to enhance risk monitoring of road sections where the driving risk is greater than the preset risk.

[0083] The following is based on Figure 7 The method for issuing an early warning when adding an image acquisition device is explained, including the following steps: Step S701: For the target road segment, if the data processing device determines that the first risk level is less than the risk threshold, then the image data collected by the image acquisition device is acquired, and the image data is compared with the historical image data to obtain the second processing result. The target road segment is defined as a segment where the driving risk is greater than the preset risk, which can be set based on historical accidents, historical data, etc. Therefore, the number of image acquisition devices will be less than that of road surface data acquisition devices, because road surface data acquisition devices are laid along the entire route, while image acquisition devices are only laid along the target road segment.

[0084] When the data processing equipment receives road surface condition data collected by the road surface data acquisition device installed on the target road section, and determines that the first risk level is less than the risk threshold based on the road surface condition data, the image acquisition device will be activated and image data collected by the image acquisition device within the acquisition range will be obtained.

[0085] Historical image data can be images of a target road segment stored in a data processing device. This application can use a feature point matching algorithm to identify objects that have been added or removed from the image data compared to the historical image data.

[0086] The second processing result could be, for example, the similarity between the image data and historical image data, or the number of objects in the image data that are inconsistent with the historical image data.

[0087] Step S702: If the second processing result is that there are target objects in the image data that are inconsistent with the historical image data, and the number of target objects is greater than the number threshold, then a warning message is generated, and the warning message carries a second risk level. In this application, a second processing result is obtained by comparing inconsistent target objects in image data with historical image data, and a second risk level is determined based on the second processing result.

[0088] The quantity threshold can be determined based on historical data, historical accident rates, etc., and is not limited here. For example, it could be 5.

[0089] For example, the data processing device may pre-store corresponding relationship information for determining the second risk level. The corresponding relationship information is as follows: Target quantity, second risk level Level 3-5 (Level 4) Levels 6-8 Level 8-10 Level 10 and above In addition, this application can further determine a second risk level based on the size of the target object, thereby enhancing the accuracy of the early warning. This technology can be achieved through corresponding relationship information, which will not be elaborated here.

[0090] Step S703: Send the warning information to the decision-making device so that the decision-making device can classify the warning level according to the second risk level.

[0091] The data processing equipment further determines whether there is a risk in the target road segment based on the images collected by the image acquisition equipment. It can trigger the generation of early warning information when the number of target objects exceeds a certain threshold, and send this information to the decision-making equipment. The decision-making equipment then reclassifies the warning level based on the second risk level indicated in the early warning information. This dual-verification mechanism strengthens the monitoring of risks in the target road segment and improves its safety.

[0092] It should be noted here that the data processing device can retrieve historical image data using the same method as retrieving historical status data, as detailed below, and will not be elaborated upon here: The data processing device matches the second identifier of the target image set device with the second correspondence table to obtain the physical coordinates of the target image set device. The second correspondence table includes the second identifiers of multiple image acquisition devices and the physical coordinates corresponding to the second identifier of each image acquisition device. The data processing equipment retrieves historical image data based on the physical coordinates of the target image set device.

[0093] Optionally, the decision-making device maps the first identifier of each image acquisition device to the physical coordinates of each image acquisition device using Kalman filtering, and generates a second mapping table.

[0094] This application employs Kalman filtering for image acquisition device location estimation and eliminates GPS positioning drift through a prediction-correction mechanism. Dynamic correction via Kalman filtering effectively eliminates multipath interference in road surface scenarios, ensuring accurate correspondence between the image acquisition device location and the road segment topology.

[0095] In another alternative embodiment, the data processing device may also perform risk warning according to the following method, such as Figure 8 As shown, it includes the following steps: Step S801: If the data processing device does not receive data sent by the data acquisition device within the monitoring period, the target data acquisition device adjacent to the data acquisition device is determined according to the unique identifier of the data acquisition device, and a test command is sent to the data acquisition device. In this application, the use of adjacent device-assisted verification prevents the occurrence of reporting link interruptions, thereby avoiding data processing devices from mistakenly classifying risky locations as risk-free locations.

[0096] The data acquisition device can be either the aforementioned road surface data acquisition device or an image acquisition device; no limitation is made here. The monitoring cycle can be one week, two days, two weeks, etc.

[0097] The unique identifier for each data acquisition device is either the first identifier of the road data acquisition device or the second identifier of the image acquisition device. Since each data acquisition device has an identifier that distinguishes it from other devices, and the data acquisition devices store their coordinates, the unique identifier of each device allows for the identification of adjacent target data acquisition devices.

[0098] In step S802, after receiving the test instruction, the target data acquisition device sends a first test message to the data acquisition device. If the target data acquisition device does not receive a response message based on the first test message within a preset time period, it sends an abnormal message to the data processing device. In step S803, the data processing device generates a risk message based on the abnormal message and reports the risk message to the traffic management center.

[0099] The interaction sequence is as follows: Data processing device -> Target device: Send test commands (e.g., TCP port 502) Target data acquisition device >> Data acquisition device: Send, for example, ICMPv6 test packets Note regarding the data acquisition device: Response timeout (default 3s) Target data acquisition device >> data processing device: Report risk message (SNMP Trap).

[0100] By verifying in collaboration with adjacent devices, it is possible to effectively distinguish between two scenarios: network congestion (temporary interruption) and equipment damage (permanent offline), so as to carry out emergency handling in a timely manner and avoid interruption of risk warning monitoring.

[0101] This application provides a method for early warning of discontinuous road conditions. Considering that current traffic warning methods often rely on fixed cameras and manual patrols, which result in response delays and low road network coverage when facing emergencies, this application addresses this issue by periodically installing multiple road surface data acquisition devices along the highway. Each device collects road surface condition data for its corresponding surface and sends it to a data processing device with which it communicates for processing to obtain a first processing result. Since the data processing device is located at the front end, it can process the road surface condition data collected by the acquisition devices in real time, enabling rapid response to abnormal data. Furthermore, the data processing device determines a first risk level based on the first processing result and sends this first risk level to a decision-making device if it exceeds a risk threshold, ensuring immediate response to abnormal situations. In addition, the decision-making device can classify warning levels based on the first risk level and select appropriate target execution devices from multiple execution devices for tiered warning based on different warning levels. This achieves precise scheduling and optimized allocation of risk response resources, thereby enabling rapid identification and early warning of abnormal road conditions. It should be noted that although the operations of the method of the present invention are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all of the operations shown must be performed to achieve the desired result. On the contrary, the steps depicted in the flowchart may be performed in a different order.

[0102] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the inventive concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this application.

Claims

1. A method for early warning of discontinuous highway conditions, the method being applied to an early warning system, the early warning system comprising a data acquisition device, multiple data processing devices, multiple decision-making devices, and multiple execution devices, the data acquisition device comprising multiple road surface data acquisition devices and image acquisition devices disposed on a target road segment in the highway, the target road segment being a road segment with a driving risk greater than a preset risk, the multiple road surface data acquisition devices being set at adaptive intervals based on the curvature of the highway, each of the data processing devices being configured corresponding to at least one of the road surface data acquisition devices, and each execution device being configured corresponding to each of the road surface data acquisition devices, the method comprising: The data processing device receives road surface condition data collected by the road surface data acquisition device and processes the road surface condition data to obtain a first processing result. The data processing device determines a first risk level based on the first processing result, and generates an abnormal message if the first risk level is greater than a risk threshold, and sends the abnormal message to the decision-making device, wherein the abnormal message carries the first risk level. The decision-making device classifies the warning level according to the first risk level in the abnormal message, and determines the target execution device from multiple execution devices according to the warning level; The decision-making device sends an early warning command to the target execution device, the early warning command being used to instruct the target execution device to perform an early warning operation; The method further includes: For the target road segment, if the data processing device determines that the first risk level is less than the risk threshold, it acquires the image data acquired by the image acquisition device and compares the image data with historical image data to obtain a second processing result. If the second processing result is that there are target objects in the image data that are inconsistent with the historical image data, and the number of target objects is greater than the number threshold, then an early warning message is generated, and the early warning message carries a second risk level. The warning information is sent to the decision-making device, so that the decision-making device classifies the warning level according to the second risk level; The image data carries a second identifier for marking the image acquisition device, and the method further includes: The data processing device matches the second identifier of the target image set device with the second correspondence table to obtain the physical coordinates of the target image set device. The second correspondence table includes the second identifiers of multiple image acquisition devices and the physical coordinates corresponding to the second identifier of each image acquisition device. The data processing device retrieves the historical image data based on the physical coordinates of the target image set device. If the data processing device does not receive data sent by the data acquisition device during the monitoring period, it determines the target data acquisition device adjacent to the data acquisition device based on the unique identifier of the data acquisition device, and sends a test command to the data acquisition device. After receiving the test instruction, the target data acquisition device sends a first test message to the data acquisition device. If the target data acquisition device does not receive a response message based on the first test message within a preset time period, it sends an abnormal message to the data processing device. The data processing device generates a risk message based on the abnormal message and reports the risk message to the traffic management center.

2. The method according to claim 1, wherein the road surface condition data carries a first identifier for marking the road surface data acquisition device, characterized in that, The process of processing the road surface condition data to obtain a first processing result includes: The data processing device matches the first identifier of the road data acquisition device with the first correspondence table to obtain the physical coordinates of the road data acquisition device. The first correspondence table includes the first identifiers of multiple road data acquisition devices and the physical coordinates corresponding to the first identifier of each road data acquisition device. The data processing device retrieves historical status data based on the physical coordinates of the road surface data acquisition device, and determines the first processing result based on the road surface status data and the historical status data.

3. The method according to claim 2, wherein the road surface state data includes vertical displacement data, and the historical state data is the historical vertical displacement data at the previous moment before the vertical displacement data was collected, characterized in that... Determining the first processing result based on the road surface condition data and the historical condition data includes: The vertical displacement difference is obtained by subtracting the vertical displacement data from the historical vertical displacement data, and the vertical displacement change rate is obtained by comparing the vertical displacement difference with the difference between adjacent time windows. The vertical displacement change rate is compared with the change rate threshold to obtain a comparison result, and the comparison result is used as the first processing result.

4. The method according to claim 3, wherein the road surface state data includes horizontal displacement data, and the historical state data is the historical horizontal displacement data at the previous moment before the horizontal displacement data was collected, characterized in that, Determining the first processing result based on the road surface condition data and the historical condition data includes: The displacement offset is determined by baseline calculation method based on the horizontal displacement data and the historical horizontal displacement data. The displacement offset is compared with the standard deviation to obtain a comparison result, which is then used as the first processing result.

5. The method according to claim 3, wherein the road surface condition data includes displacement data within a monitoring period, and the historical condition data is historical displacement data, characterized in that, Determining the first processing result based on the road surface condition data and the historical condition data includes: Each displacement data is subtracted from the corresponding historical displacement data to obtain multiple displacement differences, and the multiple displacement differences are summed to obtain the cumulative displacement. The displacement rate is determined based on the displacement data and the time of acquisition of the displacement data. The cumulative displacement and the displacement rate are used as the first processing result.

6. The method according to claim 5, wherein the road surface condition data further includes geological parameters and traffic load, characterized in that, The data processing device determines a first risk level based on the first processing result, including: The data processing device determines the first risk level based on the sum of the product of the displacement rate and the first parameter, the product of the cumulative displacement and the second parameter, the product of the geological parameter and the third parameter, and the product of the traffic load and the fourth parameter.

7. The method according to claim 1, characterized in that, The early warning system also includes a power supply device, which is used to power the data acquisition device and the data processing device. Power is supplied to the processing device and the execution device.

Images