A mobile detection system for detecting the wetness of a tunnel surface

Abstract

The present application relates to a kind of mobile detection systems for detecting tunnel pavement wet slippery state, comprising: track, be arranged above tunnel pavement in the length direction of tunnel, length is substantially same with tunnel length;Mobile detection device is arranged on track and can move along track, while collecting the pavement wet slippery state data of tunnel pavement, and pavement wet slippery state data at least includes the detection data set formed by the pavement wet slippery coefficient value of different detection point position;And data processing unit, for obtaining the analysis result indicating the wet slippery state of tunnel pavement by executing clustering algorithm to the clustering analysis of detection data set.The mobile detection system of the present application can detect the pavement wet slippery state in tunnel in time and reliably, effectively avoid the interference of tunnel traffic flow on detection and the unreliability of fixed detection result, provide decision basis for objectively judging the pavement wet slippery state in tunnel and scientifically and effectively controlling the traffic flow in tunnel.

Description

[0001] This application is a divisional application of the invention patent application with application number 202210754849.2, application date June 30, 2022, entitled "A mobile detection system for detecting the slippery condition of tunnel pavement". Technical Field

[0002] This invention relates to the detection of slippery conditions on tunnel surfaces, and more particularly to a mobile detection system for detecting slippery conditions on tunnel surfaces. Background Technology

[0003] Compared to open roads, highway tunnels differ significantly in road surface conditions, lighting environment, and infrastructure. While highway tunnels are relatively enclosed environments, and the internal road surface is less affected by external weather changes, the tunnel entrances and exits are directly connected to the outside world and are susceptible to weather conditions. Especially in severe weather conditions such as freezing, rain, and snow, the road surface becomes highly slippery, resulting in a significant difference in slipperiness between the tunnel entrances / exits and the interior. Due to the change in lighting conditions, drivers are prone to experiencing "black hole effects" and "white hole effects" when entering and exiting tunnels, requiring time to adapt to the tunnel lighting environment. Consequently, drivers at tunnel entrances and exits have difficulty observing the road ahead. Furthermore, the dim lighting inside tunnels reduces visibility, further limiting the driver's ability to anticipate road conditions. In addition, as highway tunnels age, factors such as the surrounding geographical environment, weather conditions, structural design, and maintenance frequency contribute to water leakage, becoming one of the main problems affecting operating tunnels. Water leakage leading to road surface overflow and slipperiness is a major factor affecting vehicle safety and causing traffic accidents.

[0004] Extensive historical accident data and research have revealed that due to the harsh driving environment and relatively enclosed space of highway tunnels, drivers are not only forced to shorten their visibility distance under the influence of road alignment and lighting, but their psychological state is also prone to significant fluctuations. Especially when the road surface is slippery and the coefficient of friction is reduced, accidents such as rear-end collisions and collisions with tunnel walls are highly likely to occur. Moreover, once a traffic accident occurs in a tunnel, not only is rescue difficult and traffic management challenging, but the reduced visibility also makes secondary accidents highly likely, causing more severe congestion and greater losses.

[0005] Considering the aforementioned characteristics of the tunnel environment, limiting vehicle speed may help reduce the risk of accidents to some extent, but this will obviously lead to a decrease in the overall traffic capacity of the tunnel and sacrifice its traffic efficiency.

[0006] In order to balance the safety and efficiency of highway tunnels, it is necessary to conduct timely and reliable detection and evaluation of the slippery condition of the road surface inside the tunnel, so as to provide a basis for decision-making on objectively judging the road surface condition inside the tunnel and scientifically and effectively controlling traffic flow inside the tunnel.

[0007] There are generally two types of devices used to detect the slipperiness of road surfaces: one is a contact road surface condition detector, which is usually a vehicle-mounted device that measures the friction coefficient or slipperiness of the road surface while the vehicle is moving; the other is a non-contact road surface condition detector, which usually uses methods such as optical polarization, image recognition, and infrared spectroscopy, and is usually fixed above the road to detect specific locations on the road surface.

[0008] Fixed roadside inspection equipment can only detect a specific point or a very small area on the road surface. In practical applications, the detection results of a single point or area are usually used to represent the road surface slipperiness of a larger section of road. Obviously, this point-to-area detection result cannot accurately reflect the actual slipperiness of the tunnel road surface, thus leading to problems such as untimely detection of tunnel road surface or infrastructure defects, and over- or under-management of traffic flow. Therefore, manual inspections are still necessary to determine the precise location of road surface problems.

[0009] Currently, while vehicle-mounted mobile inspection equipment can continuously measure multiple points, the spacing between these points is relatively large, typically measuring 4-10 points within a 100-meter interval. This fails to accurately and comprehensively reflect the slipperiness of the tunnel surface. Furthermore, the vehicles carrying the sensors require manual driving, inevitably affecting other vehicles. Moreover, vehicle-mounted sensors are limited by road conditions and traffic flow, preventing continuous, cyclical measurements. Therefore, not only are the uses of vehicle-mounted sensors subject to numerous limitations, but the detected results still cannot accurately reflect the slipperiness of the tunnel surface and its changes, nor can they provide an accurate and real-time assessment of the slipperiness of the tunnel surface.

[0010] In summary, the existing methods for detecting the slippery condition of tunnel pavements are not very precise and cannot reflect the slippery condition of tunnel pavements in a timely and accurate manner. Furthermore, they cannot provide a reliable assessment of the slippery condition of tunnel pavements in both time and space.

[0011] Therefore, it is necessary to design an effective system and method for detecting the slippery condition of tunnel road surfaces, so as to detect the slippery condition of tunnel road surfaces in a timely and accurate manner, thereby providing a basis for decision-making on the scientific management of traffic flow in tunnels, ensuring tunnel traffic efficiency, and effectively ensuring vehicle traffic safety. Summary of the Invention

[0012] The purpose of this invention is to provide a mobile detection system for detecting the slippery condition of tunnel pavement, which can detect the slippery condition of tunnel pavement in a timely and accurate manner, thereby providing a basis for decision-making in the scientific management of traffic flow in tunnels.

[0013] To achieve the above objectives, the present invention provides a mobile detection system for detecting the slippery condition of tunnel pavement, the mobile detection system comprising:

[0014] The track is positioned above the tunnel surface along the length of the tunnel, and the length of the track is approximately the same as the length of the tunnel.

[0015] A mobile detection device is set on the track and can move along the track. The mobile detection device can collect road surface slippage status data of the tunnel road surface while moving. The road surface slippage status data includes at least a detection dataset composed of road surface slippage coefficient values ​​at different detection points.

[0016] The data processing unit is used to perform cluster analysis on the detection dataset provided by the mobile detection device by executing a clustering algorithm to obtain analysis results representing the slippery state of the tunnel road surface.

[0017] Preferably, the mobile detection device further includes a road surface slip coefficient detector, which is capable of detecting the road surface slip coefficient value at different locations on the tunnel road surface.

[0018] Preferably, the mobile detection system further includes a unit grid marking unit, which is used to divide the tunnel surface into several unit grids, and the detection dataset includes the unit grid dataset obtained by the mobile detection device by collecting the road surface wet and slippery state data corresponding to the unit grids.

[0019] Preferably, the data processing unit is capable of performing cluster analysis on the unit grid dataset to obtain analysis results representing the slippery state of the unit grid road surface.

[0020] Preferably, the unit grid marking unit includes road markings disposed on the tunnel surface, wherein the mobile detection device determines the range of each unit grid by detecting the road markings.

[0021] Preferably, the unit grid marking unit includes a positioning unit, which is used to determine the position of the moving detection device relative to the track, and the moving detection device determines the range of each unit grid by the position.

[0022] Preferably, the positioning unit includes positioning marks disposed on the track.

[0023] Preferably, the length of the unit grid is 80 to 120 meters, and the unit grid dataset includes 200 to 800 road surface slip coefficient values.

[0024] Preferably, the cell grid dataset is X{X1,X2,…X} i ,…X n}, where 1≤i≤n, the process of cluster analysis performed by the data processing unit on the cell grid dataset includes the following steps:

[0025] The number of cluster centroids K is randomly selected, where K is an integer, 1 ≤ K ≤ 10, and the randomized cluster centroids are C{C1, C2, ... C2}. j ,…C K}, where 1≤j≤K, C j Let C be the centroid of the j-th cluster, 0 ≤ C j ≤1;

[0026] Step A: Calculate each data sample X in the cell grid dataset X using formula (1). i To the cluster centroid C of each cluster j European distance,

[0027]

[0028] Compare each data sample X in turn i To each cluster centroid C j The Euclidean distance between each data sample X i Assign to the nearest cluster centroid C j From the clusters, we obtain K clusters {S1, S2, ... S}. j ,…S K}, where S j Let j represent the j-th cluster, which is the data set of the j-th cluster after re-clustering;

[0029] Step B: Recalculate the S values ​​for each cluster using formula (2). j The center of mass,

[0030]

[0031] Among them, C m Let S represent the centroid of the m-th cluster, 1 ≤ m ≤ K; m | represents the number of data samples in the m-th cluster; X d This represents the d-th object in the m-th cluster, where 1 ≤ d ≤ |S|. m |;

[0032] Step C: Repeat steps A and B until the centroids of the K clusters no longer change, and obtain the cluster analysis results for the current K value.

[0033] Preferably, the process of clustering analysis of the cell grid dataset by the data processing unit further includes a step of optimizing the K value:

[0034] Step 1: For data sample X i Calculate X i The average distance to all other elements in the same cluster is denoted as a. i ;

[0035] Step 2: Select another cluster b and calculate X. i Find the average distance to all elements in b, and iterate through all other clusters to find X. i The average distance to the nearest cluster from all other clusters is denoted as b. i ;

[0036] Step 3: Calculate element X using formula (3) i The profile coefficient,

[0037]

[0038] Step 4: Calculate the silhouette coefficients of all data samples X, and calculate the overall silhouette coefficient corresponding to the current K value using formula (4).

[0039]

[0040] Step 5: Adjust the value of K to any other integer between 2 and 10, repeat steps A to C, and calculate the overall profile coefficient corresponding to each K value using steps 1 to 4, where the maximum overall profile coefficient E is... k' The corresponding K = k' is the optimal K value;

[0041] Step 6: Use the clustering result corresponding to the optimal K value as the result of the clustering analysis.

[0042] The mobile detection system of this invention can detect the slippery condition of the road surface in tunnels in a timely and reliable manner, effectively avoiding the interference of tunnel traffic flow on the detection and the unreliability of fixed detection results. It provides a basis for objectively judging the slippery condition of the road surface in tunnels and for scientifically and effectively controlling the traffic flow in tunnels, effectively ensuring the safety of vehicle passage while also ensuring the efficiency of tunnel passage. Attached Figure Description

[0043] Figure 1 This is a schematic diagram of the layout of the track and the mobile detection equipment in a mobile detection system according to a preferred embodiment of the present invention. Detailed Implementation

[0044] In this invention, the term "slippery road surface" refers to a road surface that is wet, waterlogged, icy, or covered in snow due to weather or geographical conditions such as ice, rain, snow, or fog. Under these conditions, the road surface friction coefficient decreases, leading to difficulty in braking, increased braking distance, and reduced vehicle stability, which can easily cause serious traffic accidents. The road surface slippage coefficient is typically used to characterize the slippery road surface condition; it is a value between 0 and 1, with a smaller value indicating a more slippery surface.

[0045] The road surface wet skid coefficient can be measured using non-contact methods such as optical polarization and infrared spectroscopy. Based on the differences in optical properties of different areas of the road surface, the state of the road surface can be distinguished, such as dry, water accumulation, snow accumulation, and ice formation. This leads to an evaluation index representing the degree of road surface wet skid, which is used to characterize the anti-skid performance of the road surface and has the same significance as the coefficient of friction.

[0046] The inventors of this invention discovered that the road surface slip coefficient value obtained by detecting a single detection point or a very small detection area cannot accurately represent the slipperiness of the road surface inside a tunnel. To scientifically evaluate the slipperiness of a tunnel road surface, it is necessary to detect a sufficient number of points on the road surface and perform cluster analysis on the obtained slipperiness data. The centroid of the cluster with the largest number of samples in the analysis results represents the slipperiness of most detection points or areas and is most suitable for representing the slipperiness of the road surface inside a tunnel.

[0047] In embodiments of the present invention, the mobile detection device is positioned above the tunnel surface and can move in a controlled manner along the entire length of the tunnel, while simultaneously collecting data on the slipperiness of the tunnel surface. In some embodiments, a dedicated track is provided at the top of the tunnel along its length, allowing the mobile detection device to move back and forth between the two ends of the tunnel. Those skilled in the art will understand that the specific construction and layout of the track, the coordination between the mobile detection device and the track, and the driving method of the mobile detection device can all be implemented using currently known or future feasible technical means, as long as they meet the requirements of mobile detection in this invention.

[0048] Because the mobile detection equipment moves above the tunnel surface, it is not affected by oncoming vehicles. The speed of movement can be controlled according to the needs of detection. Therefore, it can detect the wet and slippery condition of the road surface at small intervals, and thus obtain the road surface wet and slippery coefficient value at the corresponding location on the road surface.

[0049] However, in reality, such detailed detection results at multiple points cannot directly help drivers, road management units, or personnel determine the impact of road surface slipperiness on driving safety. The inventors of this invention have discovered that: on the one hand, a high slipperiness coefficient value at a single detection point on the road surface does not necessarily pose a serious threat to driving safety; on the other hand, while averaging the slipperiness coefficient values ​​at multiple locations on the road can avoid the bias caused by accidental factors in single-point measurements and reflect the overall slipperiness of the road to some extent, such an average value cannot reflect local differences in road slipperiness and cannot accurately reflect the impact of slipperiness at different locations on passing vehicles.

[0050] In order to accurately and objectively reflect the slipperiness of the road, facilitate drivers' safe driving, and enable road management personnel to scientifically control traffic flow while taking into account both traffic safety and efficiency, the inventors divided the detection road segment into multiple unit grids. Based on the road surface slipperiness coefficient detection data of multiple points within the unit grid, the clustering algorithm described in detail below is used for analysis and processing to obtain the road surface slipperiness coefficient representing the slipperiness state of the unit grid.

[0051] Figure 1 This is a schematic diagram illustrating the layout of the track and the mobile detection equipment in a mobile detection system according to a preferred embodiment of the present invention. Figure 1 As shown, a track 11 is installed on the top of the tunnel. The length of the track 11 is approximately the same as the length of the tunnel. A mobile detection device 12 (including a non-contact road surface wet slip coefficient detector 13) is installed on the track 11. It can move back and forth along the track 11 at a certain speed and detect the road surface wet slip coefficient value at different locations on the road surface at certain intervals while moving.

[0052] The track 11 and the mobile detection device 12 are located in the space above the tunnel, so they will not affect the passage of vehicles in the tunnel. Moreover, since the mobile detection device 12 can move back and forth cyclically throughout the entire length of the tunnel, it can perform multiple tests on the wet and slippery condition of the road surface throughout the tunnel at very short time intervals, thereby achieving all-weather, full-coverage, and uninterrupted detection of the road surface condition of the highway tunnel.

[0053] exist Figure 1 In the embodiment shown, the tunnel is divided into several sections with a length of L = 100 meters (i.e., unit grid 14) along its length. The mobile detection device 12 continuously detects the road surface in each unit grid 14 at intervals of 0.25 meters along the length of the tunnel, thereby measuring 400 points in one unit grid 14 and obtaining 400 road surface slip coefficient values ​​that characterize the slippery state of the road surface at each point.

[0054] Those skilled in the art will understand that the sensor or detection device used to detect the road surface slip coefficient value in the mobile detection equipment, namely the road surface slip coefficient detector 13, is not limited to a specific type, but can be any type of non-contact sensor or detection device known in the art or available in the future, as long as it is suitable for installation in the mobile detection equipment 12 and can collect the required road surface slip coefficient value. In fact, existing non-contact road condition detection technologies are already mature and widely used, and can complete the detection of a single grid cell in a very short time.

[0055] Those skilled in the art will understand that, depending on the type of mobile detection equipment or the non-contact sensors or detection devices therein, or to meet different subsequent analysis requirements, the number, location, and detection order of detection points within each cell grid can vary. For example, the mobile detection equipment can scan and detect points on the detection path perpendicular to its direction of movement while moving along the track, or scan and detect points on the detection path parallel to its direction of movement, or detect points on the path in a random order.

[0056] In addition, if it is necessary to detect the slippery condition of different lanes separately, multiple tracks and multiple mobile detection devices can be set up in the space above the tunnel; or multiple mobile detection devices can be set up on one track; or multiple detection sensors of the same or different types can be set up in one mobile detection device.

[0057] In order to perform cluster analysis based on the collected road surface slippery state data, the mobile detection system of the present invention also includes a data processing unit, which performs a clustering algorithm on the detection dataset provided by the mobile detection device to obtain analysis results representing the slippery state of the tunnel road surface.

[0058] In some embodiments of the present invention, the data processing unit does not move with the mobile detection device, but is communicatively connected to the mobile detection device (preferably wirelessly) to receive road surface slippage data collected by the mobile detection device. This design can reduce the impact on the driving device and improve the motion performance of the moving parts in the mobile detection system. In such embodiments, the data processing unit can be implemented as part of the central processing unit / controller of the mobile detection system, or it can be implemented based on a separate processor.

[0059] In other embodiments, the data processing unit is integrated with the mobile detection device, enabling the two to transmit data via high-speed data connections or lines, which helps improve the transmission efficiency and reliability of data on the slippery road surface.

[0060] To analyze and evaluate the slipperiness of tunnel pavements using cell grids as the basic unit, the mobile detection device needs to determine which cell grid the detected point belongs to when collecting pavement slipperiness data. Therefore, in some embodiments of the present invention, the mobile detection system further includes cell grid marking units to divide the tunnel pavement into several cell grids. In other words, the pavement slipperiness data collected by the mobile detection device is divided into cell grid datasets corresponding to each cell grid.

[0061] In some embodiments of the present invention, the unit grid marking unit includes road surface markings disposed on the tunnel surface, for example... Figure 1 The road surface markings (15) can be identified by the mobile detection device, thereby determining the boundary between two adjacent cell grids. Based on this information, the mobile detection device can determine which cell grid the detected point belongs to, and then classify the collected road surface slipperiness data into the corresponding cell grid dataset.

[0062] Road markings on tunnel surfaces can be markers placed on the road surface, special coatings applied to the road surface, or other forms that can be identified by mobile detection equipment.

[0063] Besides directly determining the position of the detection point relative to the tunnel surface, the mobile detection device can also determine the cell grid to which the currently detected point belongs by determining its own position relative to the track. In some embodiments of the present invention, the cell grid marking unit includes a positioning unit for determining the position of the mobile detection device relative to the track. The mobile detection device further combines the positional relationship between the road surface slip coefficient detector and the detection point to map the position on the track to the detection point on the tunnel surface. Thus, by determining the position of the mobile detection device relative to the track, the cell grid to which the detection point belongs can be determined. The position information of the mobile detection device relative to the track can be obtained through its driving device, such as the number of rotations / angles of the drive motor. Similar to the road surface markings described above, the positioning unit may also include positioning marks set on the track, for example, markers set on the track.

[0064] Generally speaking, the size of the unit grid can be determined based on data such as the tunnel's design speed, the actual average speed of vehicles on the road, and the safe stopping sight distance of vehicles, so as to facilitate accurate perception of the slippery road surface and scientific management of traffic flow.

[0065] For example, in a long tunnel exceeding 1000 meters in length, the average vehicle speed is approximately 80 km / h. Under slippery road conditions, within the timeframe for driver reaction and braking, the vehicle will continue to travel approximately 80-120 meters. This demonstrates that slippery road conditions directly impact vehicle performance during braking. Therefore, dividing the road into grid units at such intervals facilitates a more scientific and effective evaluation of road slipperiness, meeting both driver reaction and braking needs, as well as the requirements for refined road maintenance and management.

[0066] In a preferred embodiment of the invention, the mobile detection device continuously detects the tunnel surface along the length of the tunnel at 0.25-meter intervals within each 100-meter-long cell grid, thereby measuring 400 points within one cell grid and obtaining 400 road surface slip coefficient values ​​accordingly. These slip coefficient values ​​can fully reflect the various possible slip conditions of the road surface within the cell grid.

[0067] Those skilled in the art should understand that the number of detection points within each cell grid is not limited to 400. The number of detection points within a cell grid typically depends on the needs of the clustering algorithm, which will be described in detail below. Generally speaking, if the number of points is too small, there will be less data suitable for the clustering algorithm, making it impossible to achieve the ideal clustering effect and potentially affecting the accuracy of the assessment of road surface slipperiness. On the other hand, if the detection points are too dense, data redundancy may occur, affecting the operating efficiency of the clustering algorithm and thus potentially affecting the efficiency of the detection. Typically, setting 200-800 detection points within each cell grid can balance detection accuracy and efficiency.

[0068] The inventors discovered that the difference in road surface slipperiness within a tunnel is not significant along the width direction. Therefore, sequentially arranging detection points along the length of a single lane can accurately reflect the road surface slipperiness. However, those skilled in the art should understand that the detection points within each grid cell are not limited to the tunnel's length direction but can be arranged along both the tunnel's length and width directions. In some preferred embodiments of the invention, the detection points are evenly distributed within the grid cells, which facilitates a more accurate reflection of the overall road surface slipperiness within the grid cell.

[0069] The road surface slipperiness data obtained through mobile detection equipment may include detection time, detection location, and the road surface slipperiness coefficient value at the detection point. In some preferred embodiments, the detection location can be simplified to the cell grid described at the detection point, such as the cell grid number. Further processing of the road surface slipperiness data belonging to the same cell grid can yield the road surface slipperiness coefficient for that cell grid.

[0070] During the process of mobile detection equipment detecting the slippery condition of the road surface, vehicles passing by at corresponding points will inevitably cause some interference to the detection, which may lead to inaccurate detection results for that point. However, since such detection results only account for a very small proportion of all detection results in the entire cell grid, they will not affect the judgment of the slippery condition of the entire cell grid. Moreover, on the one hand, the clustering algorithm, which will be described in detail below, can easily identify and eliminate the influence of these inaccurate data; on the other hand, since the mobile detection equipment repeatedly detects within the tunnel, the data affected by passing vehicles will also be corrected during the repeated detection process.

[0071] The following describes in detail, with reference to a preferred embodiment of the present invention, the process by which the data processing unit performs cluster analysis on the collected road surface slippery state data.

[0072] In the road surface wet slip condition data corresponding to each unit grid, the data from different detection points have both similarities and differences. By using cluster analysis, data with high sample similarity and small differences in the detection data can be grouped into one category.

[0073] If most of the road surface within a cell grid is in a slippery state, then that cell grid is necessarily slippery; that is, the slipperiness coefficient of the road surface at most points within the cell grid is closer to 0. By using a clustering algorithm to group these similar slippery road surface data together, the centroid of the cluster with the largest number of clustered samples represents the slippery state of most areas within the cell grid and can be used as a parameter characterizing the overall slippery state of the road surface within that cell grid.

[0074] In a preferred embodiment of the present invention, the K-means clustering algorithm is used to perform clustering operations on the road surface slipperiness state data of each cell grid. This algorithm is an iterative clustering algorithm that uses Euclidean distance as a similarity index to cluster discrete data into K clusters (classes), with the centroid of each cluster being the center point. By calculating the distance between samples and clusters and iterating repeatedly, the algorithm can cluster samples with high similarity and low difference into one cluster, resulting in high similarity among samples within a cluster and high difference between different clusters, ultimately obtaining the optimal centroid value.

[0075] After moving the detection device to detect n points in a cell grid, the detection dataset X of the road surface wet skid coefficient of that cell grid can be obtained, i.e., X = X1, X2, ... X i ,…X n}, where 1≤i≤n. Assume the initial value of K is k0, and the initial cluster centroids are C={C1,C2,…C j ,…C k0}, where 1≤j≤k0, C j Let K be the initial centroid of the j-th cluster, physically representing the coefficient of slippage. The initial K value can generally be randomly selected from an integer between 1 and 10, and the initial centroid value can generally be randomly selected from a value between 0 and 1. The choice of initial values ​​does not affect the final clustering result.

[0076] The following formula (1) can be used to calculate the value of each data sample X in the detection dataset X. i To the cluster centroid C of each cluster j European distance,

[0077]

[0078] Step A: Compare each data sample X sequentially. i To each cluster centroid C j The Euclidean distance between each data sample X i Assign to the nearest cluster centroid C j From the clusters, we obtain k0 clusters S1, S2, ... S j ,…S k0}, where S j This represents the j-th cluster, which physically means the data set of the j-th cluster after re-clustering.

[0079] Step B: Recalculate the S values ​​for each cluster using the following formula (2). j The center of mass,

[0080]

[0081] Among them, C m Denotes the centroid of the m-th cluster, 1≤m≤k0; |S m | represents the number of data samples in the m-th cluster; X d This represents the d-th object in the m-th cluster, where 1 ≤ d ≤ |S|. m |; that is, for those belonging to S m Calculate the average value of all objects in a cluster.

[0082] Step C: Repeat Step A and Step B until the centroids of the k0 clusters no longer change, that is, the clustering results of the road surface slippery state data of the cell grid when K=k0 are obtained.

[0083] Considering the uncertainty of the road surface's slippery state within the cell mesh, the K value can be further optimized to obtain more accurate results:

[0084] Optimizing the K-value can be achieved by comparing the overall silhouette coefficients corresponding to different numbers of clusters (different K-values) and selecting the number of clusters (K-value) corresponding to the maximum overall silhouette coefficient. That is, the optimal solution for the K-value is determined with the goal of maximizing the overall silhouette coefficient. The silhouette coefficient is a key indicator describing the differences between clusters, combining the cluster's cohesion and separation, and is used to evaluate the clustering effect. Its value is between -1 and 1, with a larger value indicating a better clustering effect.

[0085] In a preferred embodiment of the present invention, the optimization of the K value is performed through the following steps:

[0086] Step 1: For the i-th data sample X i Calculate X i The average distance to all other elements in the same cluster is denoted as a. i .

[0087] Step 2: Select another cluster b and calculate X. i Find X by traversing all other clusters and finding the average distance from all elements in b. i The average distance to the nearest cluster from all other clusters is denoted as b. i .

[0088] Step 3: Calculate element X using the following formula (3). i The profile coefficient,

[0089]

[0090] Step 4: Calculate the silhouette coefficients of all data samples X, and then calculate the overall silhouette coefficient of the current cluster (K=k0) using the following formula (4):

[0091]

[0092] Step 5: Adjust the value of K, for example, by taking an integer between 2 and 10. Repeat steps A to C to obtain the clustering results, and calculate the overall silhouette coefficient corresponding to each K value using steps 1 to 4, where the maximum overall silhouette coefficient E is... k' The corresponding K = k' is the optimal K value.

[0093] Finally, based on the results of the above cluster analysis, the road surface slip coefficient Sp of this cell grid was determined.

[0094] According to the value of k' (the optimal K value), determine the centroids of k' clusters and the number of samples contained in each cluster, and determine the centroid of the cluster with the largest number of samples as the road surface skid resistance coefficient Sp of the unit grid. The cluster with the largest number of aggregated samples can best reflect the overall skid state of the unit grid, and the road surface skid resistance coefficient value Sp corresponding to the centroid of this cluster is also most suitable for representing the overall road surface skid resistance coefficient of the grid unit.

[0095] In the aforementioned K-means clustering algorithm, the selection of K value is an important factor affecting the final calculation result. Using a fixed K value results in relatively low calculation load, but there may be certain deviations in the calculation of the road surface skid resistance coefficient of the unit grid. Through the K value optimization step, the selection of K value can be optimized according to the actual situation of the detection data in the unit grid, which is beneficial to improving the calculation accuracy of the road surface skid resistance coefficient of the unit grid.

[0096] The advantages of adopting the K-means clustering algorithm are that the data convergence speed is fast, which can meet the requirement of real-time detection of the skid state of tunnel road surfaces; moreover, the classified data is scalable, which can reflect the skid state of unit grids scientifically and truly as much as possible.

[0097] By performing cluster analysis on the detection data of numerous points in a unit grid, the distribution of the detected road surface skid resistance coefficient values can be scientifically judged, and then the overall road surface skid state of the unit grid can be accurately determined. The clustering method can not only effectively eliminate the influence of inaccurate point detection data caused by external interference, but also shield the influence of very small skid areas that do not harm driving safety on the overall skid resistance coefficient value of the unit grid.

[0098] Based on the road surface skid resistance coefficient of each unit grid in the tunnel, the road surface skid state can be divided into several grades, which serve as a basis for road traffic flow control and tunnel maintenance.

[0099] For example, three thresholds m1, m2, m3 can be set for the road surface skid resistance coefficient of a unit grid, where 0<m1<m2<m3<1, so that the road surface skid state is divided into four grades, namely:

[0100] Grade I (dry), Sp∈(m3,1);

[0101] Grade II (slightly slippery), Sp∈(m2,m3);

[0102] Grade III (relatively slippery), Sp∈(m1,m2);

[0103] Grade IV (very slippery), Sp∈(0,m1).

[0104] Those skilled in the art should understand that, depending on the subsequent application and the actual needs of tunnel traffic flow management, the road surface slippery condition can be divided into more or fewer levels; and the intervals between the various thresholds can be the same or different.

[0105] Based on an accurate assessment of the current slippery condition of the road surface inside the tunnel, road managers can effectively control traffic flow on the road, including speed control, lane control, or by issuing information prompts through variable message signs.

[0106] Those skilled in the art will understand that, as the mobile detection device moves, it can detect n cell grids at different locations within the tunnel, for example, in the order of 1, 2, ..., n. By comparing the detection results of cell grids at different locations, the change in the wet and slippery state of the tunnel pavement with location can be obtained, thus revealing the spatial variation law of the wet and slippery state of the pavement.

[0107] Furthermore, as the mobile detection equipment moves back and forth, it can cyclically detect n grid cells within the tunnel, for example, continuously in the order of 1, 2, ..., n, n, ..., 2, 1. In this way, each grid cell is detected once at specific time intervals. By comparing the detection results at different times, the change in the road surface slipperiness of that grid cell over time can be obtained, thus providing a basis for predicting the changing trend of the road surface slipperiness.

[0108] Based on reliable assessments of the spatiotemporal variation trends of slippery road surfaces within tunnels, road managers can develop more scientific plans for the maintenance of tunnel surfaces and infrastructure.

[0109] Based on the foregoing description in conjunction with the preferred embodiments of the present invention, the mobile detection system for detecting the slippery condition of tunnel pavement of the present invention can significantly improve the spatial resolution of the detection of the slippery condition of tunnel pavement, accurately detect the slippery condition of the pavement in the tunnel with a smaller unit grid as the basic evaluation unit; at the same time, it can also improve the temporal resolution of the detection of the slippery condition of tunnel pavement, effectively tracking the changes in the slippery condition of the pavement in the tunnel.

[0110] It should be understood that the embodiments described above can be adjusted within a reasonable range according to the specific application, and are not limited to the specific situations in the above embodiments. That is to say, those skilled in the art can make various changes and / or modifications to specific embodiments without departing from the concept of the present invention.

Claims

1. A non-contact mobile detection system for detecting the slippery condition of tunnel pavement, the mobile detection system comprising: The track is set in the space above the tunnel surface along the length of the tunnel, and the length of the track is approximately the same as the length of the tunnel. A mobile detection device is set on the track and can move back and forth along the track. The mobile detection device can collect road surface slippery state data of the tunnel road surface while moving. The road surface slippery state data includes at least a detection dataset consisting of detection time, detection location and road surface slippery coefficient value corresponding to multiple different detection points. The data processing unit is used to perform cluster analysis on the detection dataset provided by the mobile detection device by executing a clustering algorithm. The clustering algorithm is used to cluster similar road surface slippery state data together, and the centroid of the cluster with the largest number of clustered samples is used as a parameter to characterize the slippery state of the tunnel road surface, so as to obtain the analysis results representing the slippery state of the tunnel road surface. as well as The unit grid marking unit is used to divide the tunnel surface into several unit grids, and the detection dataset includes the unit grid dataset obtained by the mobile detection device by collecting the road surface wet and slippery state data corresponding to the unit grids.

2. The motion detection system according to claim 1, wherein, The mobile detection device further includes a road surface slip coefficient detector, which can detect the road surface slip coefficient value at different locations on the tunnel road surface.

3. The motion detection system according to claim 1, wherein, The data processing unit can perform cluster analysis on the unit grid dataset to obtain analysis results representing the slippery state of the road surface of the unit grid.

4. The motion detection system according to claim 1, wherein, The unit grid marking unit includes road markings set on the tunnel surface, wherein the mobile detection device determines the range of each unit grid by detecting the road markings.

5. The motion detection system according to claim 1, wherein, The unit grid marking unit includes a positioning unit, which is used to determine the position of the mobile detection device relative to the track, and the mobile detection device determines the range of each unit grid based on the position.

6. The motion detection system according to claim 5, wherein, The positioning unit includes positioning marks set on the track.

7. The motion detection system according to claim 1, wherein, The unit grid has a length of 80 to 120 meters, and the unit grid dataset includes 200 to 800 road surface slip coefficient values.

8. The motion detection system according to claim 3, wherein, The cell grid dataset is Where 1≤i≤n, the process of cluster analysis performed by the data processing unit on the cell grid dataset includes the following steps: The number of cluster centroids K is randomly selected, where K is an integer, 1 ≤ K ≤ 10. Where 1≤j≤K, C j Let C be the centroid of the j-th cluster, 0 ≤ C j ≤1; Step A: Calculate each data sample X in the cell grid dataset X using formula (1). i To the cluster centroid C of each cluster j European distance, （1） Compare each data sample X in turn i To each cluster centroid C j The Euclidean distance between each data sample X i Assign to the nearest cluster centroid C j From the clusters, we obtain K clusters. , among which, S j Let j represent the j-th cluster, which is the data set of the j-th cluster after re-clustering; Step B: Recalculate the S values ​​for each cluster using formula (2). j The center of mass, （2） Among them, C m Denotes the centroid of the m-th cluster, 1≤m≤K; |S m | represents the number of data samples in the m-th cluster; X d This represents the d-th object in the m-th cluster, where 1 ≤ d ≤ |S|. m |; Step C: Repeat steps A and B until the centroids of the K clusters no longer change, and obtain the cluster analysis results for the current K value.

9. The motion detection system according to claim 8, wherein, The process of clustering analysis of the cell grid dataset by the data processing unit further includes the step of optimizing the K value: Step 1: For data sample X i Calculate X i The average distance to all other elements in the same cluster is denoted as a. i ; Step 2: Select another cluster b and calculate X. i Find the average distance to all elements in b, and iterate through all other clusters to find X. i The average distance to the nearest cluster from all other clusters is denoted as b. i ; Step 3: Calculate element X using formula (3) i The profile coefficient, （3） Step 4: Calculate the silhouette coefficients of all data samples X, and calculate the overall silhouette coefficient corresponding to the current K value using formula (4). （4） Step 5: Adjust the value of K to any other integer between 2 and 10, repeat steps A to C, and calculate the overall profile coefficient corresponding to each K value using steps 1 to 4, where the largest overall profile coefficient is... The corresponding K=k' is the optimal K value; Step 6: Use the clustering result corresponding to the optimal K value as the result of the clustering analysis.

Images