An array-type water curtain projection device and method for tunnel entrances

Abstract

This application relates to the field of water curtain projection technology, specifically to an array-type tunnel entrance water curtain projection device and method. The method includes: acquiring the tunnel entrance wind speed, the water supply pressure of the tunnel entrance water curtain, and a water curtain point cloud dataset; obtaining water droplet splashing characteristic values ​​for each point cloud data point based on the local outlier rate of the point cloud data in the water curtain point cloud dataset, and obtaining the water curtain deviation degree at each acquisition time based on the abnormal deviation and average level of the water droplet splashing characteristic values ​​of all point cloud data at each acquisition time; obtaining the water curtain interference degree at each acquisition time based on the distribution trends of the tunnel entrance wind speed and water curtain deviation degree, and obtaining the desired water supply pressure for the tunnel entrance water curtain based on the changes in the water curtain interference degree and the water supply pressure; and using a PID controller to control and adjust the water supply pressure during the tunnel entrance water curtain projection process. This application can improve the stability of tunnel entrance water curtain projection.

Description

Technical Field

[0001] This application relates to the field of water curtain projection technology, specifically to an array-type tunnel entrance water curtain projection device and method. Background Technology

[0002] Highway tunnels, with their semi-concealed and near-enclosed structural characteristics, severely limit drivers' visibility and offer limited space for maneuver. The consequences of emergencies in highway tunnels are far greater than on ordinary roads. Therefore, to improve the safety of highway tunnel operations, water curtain projection devices are increasingly being installed at tunnel entrances. In the event of a traffic accident, the water curtain projection at the tunnel entrance serves as a warning to vehicles to stay away from the lane, thus preventing serious injuries and property damage.

[0003] Currently, the water supply pressure of the water curtain at the tunnel entrance is generally controlled and regulated by the wind speed at the tunnel entrance to improve its stability and ensure that the water curtain projection clearly displays traffic instructions. However, because the stability of the water curtain at the tunnel entrance is adversely affected by the wind speed, it is prone to deviation or even breakage. Existing technology has not fully explored the characteristic changes in the stability of the water curtain affected by the wind speed, resulting in poor accuracy in controlling and regulating the water supply pressure of the water curtain, which affects the stability of the water curtain at the highway tunnel entrance and the clarity of the water curtain projection. Summary of the Invention

[0004] To address the aforementioned technical problems, the purpose of this application is to provide an array-type tunnel entrance water curtain projection device and method, the specific technical solution of which is as follows:

[0005] This application provides an array-type tunnel entrance water curtain projection method, including the following steps:

[0006] Acquire the wind speed at the tunnel entrance, the water supply pressure of the water curtain at the tunnel entrance, and the point cloud dataset of the water curtain projection.

[0007] By analyzing the local outlier degree of the point cloud data in the water curtain point cloud dataset, the water droplet splashing characteristics of the water curtain at the tunnel entrance are obtained to acquire the water droplet splashing characteristic values ​​of each point cloud data. Based on the abnormal deviation and average level of the water droplet splashing characteristic values ​​of all point cloud data at each acquisition time, the water curtain deviation degree at each acquisition time is obtained.

[0008] The water curtain interference degree at each acquisition time is obtained by measuring the distribution trend of wind speed and water curtain deviation at the tunnel entrance. The expected water supply pressure of the water curtain at the tunnel entrance is obtained by measuring the change of water curtain interference degree and water supply pressure. The water supply pressure during the water curtain projection process at the tunnel entrance is controlled and regulated by a PID controller.

[0009] Preferably, the process of obtaining the water droplet splash feature values ​​of the point cloud data is as follows: In the formula, Let be the water droplet splash feature value of the i-th point cloud data. Let represent the degree of dispersion of the local density of all point cloud data within the neighborhood point cloud set corresponding to the i-th point cloud data. Let be the mean of the Euclidean distances between all point cloud data points in the neighborhood point cloud set corresponding to the i-th point cloud data point. Let be the local density of the i-th point cloud data. To avoid constants with a denominator of 0.

[0010] Preferably, the water curtain point cloud dataset at each acquisition time is used as the input of the density peak clustering algorithm to extract the local density of each point cloud data in the water curtain point cloud dataset and the neighborhood point cloud set of its truncation distance range.

[0011] Preferably, the process for obtaining the water curtain deviation at each acquisition time is as follows: In the formula, Let be the water curtain deviation at the t-th acquisition time. Let be the number of points in the anomaly point cloud set at the t-th acquisition time. Let be the number of point clouds in the water curtain point cloud dataset at time t. Let be the mean of the water droplet splash feature values ​​of all point cloud data in the water curtain point cloud dataset at the t-th acquisition time.

[0012] Preferably, the water droplet splash feature values ​​of all point cloud data in the water curtain point cloud dataset at each acquisition time are thresholded, and the point cloud data corresponding to the water droplet splash feature values ​​that are higher than the segmentation threshold are used to form the abnormal point cloud set at each acquisition time.

[0013] Preferably, the process for obtaining the degree of interference with the water curtain at each acquisition time is as follows: In the formula, Let be the degree of interference with the water curtain at the t-th acquisition time. For normalization function, Let be the mean of the fitted slopes of the wind speed sequence and the water curtain deviation sequence at the t-th acquisition time. It is an exponential function with the natural constant as its base. and , respectively, are the fitting slopes of the wind speed sequence and the water curtain deviation sequence at the t-th acquisition time.

[0014] Preferably, the multiple acquisition times that are closest to the time interval of each acquisition time are taken as the nearest neighbor acquisition times of each acquisition time.

[0015] Preferably, the wind speed and water curtain deviation at the tunnel entrance at each acquisition time and its multiple neighboring acquisition times are arranged in chronological order, and the arranged sequences are normalized to obtain the wind speed sequence and water curtain deviation sequence at each acquisition time. The fitting slope of the wind speed sequence and water curtain deviation sequence is then extracted by fitting.

[0016] Preferably, the process for obtaining the desired water supply pressure of the tunnel entrance water curtain is as follows: In the formula, The desired water supply pressure at the current sampling time. The water supply pressure at the current sampling time. and These represent the interference levels of the water curtain at the current acquisition time and the previous acquisition time, respectively.

[0017] This application also provides an array-type tunnel entrance water curtain projection device, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any of the above-described array-type tunnel entrance water curtain projection methods.

[0018] As can be seen from the above, the array-type tunnel entrance water curtain projection device and method provided in this application have at least the following beneficial effects:

[0019] This application uses water curtain point cloud data to accurately measure the characteristics of water droplet splashing caused by adverse wind speed at the tunnel entrance. It also uses the size of the water droplet splash to accurately measure the degree of deviation of the water curtain when affected by wind speed at the tunnel entrance. This allows for a clearer display of the degree to which the real-time state of the water curtain at the tunnel entrance deviates from its normal state, which is beneficial for improving the stability of the water curtain at the highway tunnel entrance and the clarity of the water curtain projection.

[0020] Meanwhile, this application accurately measures the degree of interference of the tunnel entrance water curtain with the tunnel entrance wind speed by the change of the deviation between the tunnel entrance wind speed and the water curtain. It clearly shows the degree of adverse interference of the tunnel entrance water curtain with the tunnel entrance wind speed at different times, which is conducive to the accurate control and adjustment of the water supply pressure of the tunnel entrance water curtain in the future, and improves the quality of the formation of the tunnel entrance water curtain and its wind resistance.

[0021] This application fully explores the characteristic changes of the stability of the water curtain at the tunnel entrance affected by the wind speed at the tunnel entrance, and accurately calculates the expected water supply pressure of the water curtain at the tunnel entrance in real time by using the characteristic changes of the water curtain at the tunnel entrance affected by the wind speed at the tunnel entrance. The application also uses a fuzzy adaptive PID control method to accurately control and regulate the water supply pressure of the water curtain at the tunnel entrance, thereby avoiding the problem of serious deviation or even rupture of the water curtain at the highway tunnel entrance due to the influence of wind. Attached Figure Description

[0022] To more clearly illustrate the technical solutions and advantages in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 A flowchart of the steps of an array-type tunnel entrance water curtain projection method provided in this application;

[0024] Figure 2 A block diagram of an array-type tunnel entrance water curtain projection device provided in an embodiment of this application. Detailed Implementation

[0025] To further illustrate the technical means and effects adopted by this application to achieve the intended purpose of the invention, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of an array-type tunnel entrance water curtain projection device and method proposed in this application. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0026] Unless otherwise specified and limited, terms such as “comprising,” “including,” or any other variations thereof are intended to cover a non-exclusive inclusion, such that a circuit structure, article, or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase “comprising one…” does not exclude the presence of other identical elements in the article or device that includes said element. Furthermore, the term “and / or” as used herein includes any and all combinations of one or more of the associated listed items. All technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.

[0027] The following description, in conjunction with the accompanying drawings, details the specific scheme of the array-type tunnel entrance water curtain projection device and method provided in this application.

[0028] Please see Figure 1 The diagram illustrates a flowchart of an array-type tunnel entrance water curtain projection method according to an embodiment of this application, including the following steps:

[0029] Step 1: Obtain the wind speed at the tunnel entrance, the water supply pressure of the water curtain at the tunnel entrance, and the point cloud dataset of the water curtain projection.

[0030] To improve the stability of water curtain projection at highway tunnel entrances and prevent severe deviations or even breakages caused by wind, it is necessary to fully explore the characteristic changes of water curtain affected by wind speed interference at tunnel entrances. This will allow for accurate control and adjustment of water curtain pressure, ensuring that the water curtain projection clearly displays traffic instructions.

[0031] When an accident occurs inside a highway tunnel, wind speed sensors and pressure sensors deployed at the tunnel entrance collect data on the wind speed and water supply pressure of the water curtain at the tunnel entrance. The sampling frequency for both sensors is 10Hz. Additionally, a 3D LiDAR device collects data on the water curtain point cloud dataset. This point cloud dataset is LiDAR point cloud data, generated by the 3D LiDAR device scanning the water curtain at a sampling frequency of 10Hz. Each point cloud data point contains 3D coordinate information, namely X, Y, and Z elements, denoted as (X, Y, Z). This 3D coordinate information is based on the LiDAR coordinate system. In the LiDAR coordinate system, facing the LiDAR, the positive half-axis of the X-axis is forward, the positive half-axis of the Z-axis is upward, and the positive half-axis of the Y-axis is to the right.

[0032] Thus, based on the above process in this embodiment, the wind speed at the tunnel entrance, the water supply pressure of the water curtain at the tunnel entrance, and the water curtain point cloud dataset can be obtained at each acquisition moment.

[0033] Step 2: By analyzing the local outlier degree of the point cloud data in the water curtain point cloud dataset, the water droplet splashing characteristics of the water curtain at the tunnel entrance are obtained to acquire the water droplet splashing characteristic values ​​of each point cloud data. Based on the abnormal deviation and average level of the water droplet splashing characteristic values ​​of all point cloud data at each acquisition time, the water curtain deviation degree at each acquisition time is obtained.

[0034] When the stability of the water curtain at the tunnel entrance is affected by the wind speed at the tunnel entrance, water droplets are likely to splash within the water curtain, causing outlier characteristics to appear in the point cloud data of the water curtain. The greater the outlier characteristics of the point cloud data, the more severe the adverse effects of the wind speed at the tunnel entrance on the stability of the water curtain.

[0035] Therefore, in order to analyze the adverse effects of wind speed at the tunnel entrance on the stability of the water curtain, the water curtain point cloud dataset at each acquisition time was used as the input to the Density Peaks Clustering (DPC) algorithm. The cutoff distance was selected as the preset cutoff distance when the number of point cloud data points within the average cutoff distance range of each point cloud data point accounted for 2% of the total number of point cloud data points. The local density of each point cloud data in the water curtain point cloud dataset and its neighborhood point cloud set within the cutoff distance range were obtained through the DPC density peaks clustering algorithm. The DPC density peaks clustering algorithm is a well-known technology, and the specific process will not be described in detail.

[0036] Based on the above analysis, the water droplet splashing characteristics of the water curtain at the tunnel entrance are analyzed by examining the degree of local outliers in the point cloud data of the water curtain point cloud dataset, and the water droplet splashing characteristic value of each point cloud data in the water curtain point cloud dataset is calculated: In the formula, Let be the water droplet splash feature value of the i-th point cloud data. Let represent the degree of dispersion of the local density of all point cloud data within the neighborhood point cloud set corresponding to the i-th point cloud data. Let be the mean of the Euclidean distances between all point cloud data points in the neighborhood point cloud set corresponding to the i-th point cloud data point. Let be the local density of the i-th point cloud data. To avoid constants with a denominator of 0, the value is taken within a small range (0.01, 0.1), which has a negligible impact on the calculation result. In this embodiment, the value is taken as 0.05.

[0037] The method for measuring the degree of dispersion can be variance, standard deviation, or coefficient of variation. In this embodiment, standard deviation is used to measure the degree of dispersion.

[0038] Based on the above process, it can be understood that the water droplet splash characteristic value reflects the size of the water droplet splash caused by the adverse influence of wind speed at the tunnel entrance. The larger the water droplet splash characteristic value, the more prominent the phenomenon of water droplet splash caused by the wind speed at the tunnel entrance. At this time, the water curtain is more likely to deviate or even break. In this case, the water supply pressure of the water curtain at the tunnel entrance should be appropriately increased to improve the quality of the water curtain formation and its wind resistance.

[0039] To more accurately measure the deviation of the water curtain at the tunnel entrance at different acquisition times, the water droplet splash feature values ​​of all point cloud data in the water curtain point cloud dataset at each acquisition time are used as the input of the maximum inter-class variance algorithm. The segmentation threshold is obtained through the maximum inter-class variance algorithm. The set of all point cloud data corresponding to the water droplet splash feature values ​​that are higher than the segmentation threshold is denoted as the abnormal point cloud set at each acquisition time. The maximum inter-class variance algorithm is a well-known technique, and the specific process will not be described in detail.

[0040] Generally, the larger the ratio of the number of points in the anomaly cloud set to the total number of points, the more water droplets are splashed due to the wind speed at the tunnel entrance. Furthermore, the higher the overall level of the water droplet splash characteristic value of all point cloud data, the higher the deviation of the water curtain formation at the tunnel entrance, which will affect the stability of the water curtain at the highway tunnel entrance and the clarity of the water curtain projection.

[0041] Based on the above analysis process, in this embodiment, the abnormal deviation of the water droplet splash feature value is analyzed according to the proportion of the point cloud data in the abnormal point cloud set at each acquisition time in the water curtain point cloud dataset. Combined with the average level of the water droplet splash feature value, the water curtain deviation at each acquisition time is calculated: In the formula, Let be the water curtain deviation at the t-th acquisition time. Let be the number of points in the anomaly point cloud set at the t-th acquisition time. Let be the number of point clouds in the water curtain point cloud dataset at time t. Let be the mean of the water droplet splash feature values ​​of all point cloud data in the water curtain point cloud dataset at the t-th acquisition time.

[0042] Among them, the water curtain deviation reflects the degree of deviation of the water curtain at the tunnel entrance when affected by the wind speed at the tunnel entrance. The greater the water curtain deviation, the deeper the deviation of the water curtain at the tunnel entrance from the normal state. At this time, there will be more water droplets splashing in the water curtain at the tunnel entrance. Therefore, the quality of the water curtain at the tunnel entrance is poor. The water supply pressure of the water curtain at the tunnel entrance should be controlled and adjusted in time to improve the quality of the water curtain formation and its wind resistance.

[0043] Step 3: Obtain the water curtain interference degree at each acquisition time based on the distribution trend of wind speed and water curtain deviation at the tunnel entrance, and obtain the expected water supply pressure of the water curtain at the tunnel entrance by the change of water curtain interference degree and water supply pressure. Use a PID controller to control and adjust the water supply pressure during the water curtain projection process at the tunnel entrance.

[0044] Furthermore, in order to analyze the degree of interference of the tunnel entrance water curtain with the tunnel entrance wind speed in a short period of time, preferably, in this embodiment, the L collection times with the closest time interval between each collection time are all taken as the nearest neighbor collection times of each collection time, where L is set to 100, and are used to analyze the stability characteristics of the tunnel entrance water curtain in a short period of 10 seconds.

[0045] Furthermore, the wind speed and water curtain deviation at the tunnel entrance at each acquisition time and its L nearest neighbor acquisition times are arranged in chronological order, and the arranged sequence is subjected to maximum value normalization to eliminate the dimensional effect between different parameters. After maximum value normalization, the wind speed sequence and water curtain deviation sequence at each acquisition time are obtained. Maximum value normalization is a well-known technique, and the specific process will not be described in detail.

[0046] Generally, if both the wind speed at the tunnel entrance and the deviation of the water curtain are continuously increasing, and the smaller the difference in the fitting slope between the two, the stronger the positive correlation between the wind speed at the tunnel entrance and the deviation of the water curtain. In this case, it can better reflect the sudden change in the stability of the water curtain at the tunnel entrance when it is affected by the wind speed at the tunnel entrance, resulting in poor stability of the water curtain at the tunnel entrance. It is necessary to increase the water supply pressure of the water curtain at the tunnel entrance in a timely manner to improve the quality of the water curtain formation and its wind resistance.

[0047] Therefore, the wind speed sequence and water curtain deviation sequence at each acquisition time are used as inputs to the least squares linear fitting algorithm. The fitting slopes of the wind speed sequence and water curtain deviation sequence are obtained by the least squares linear fitting algorithm. The least squares linear fitting algorithm is a well-known technique, and the specific process will not be described in detail.

[0048] Based on the above analysis, in this embodiment, the degree of interference with the water curtain at each data acquisition moment is calculated according to the changing trends of wind speed and water curtain deviation at the tunnel entrance: In the formula, Let be the degree of interference with the water curtain at the t-th acquisition time. For the normalization function, maximum value normalization is used in this embodiment. Let be the mean of the fitted slopes of the wind speed sequence and the water curtain deviation sequence at the t-th acquisition time. It is an exponential function with the natural constant as its base. and , respectively, are the fitting slopes of the wind speed sequence and the water curtain deviation sequence at the t-th acquisition time.

[0049] Understandably, the degree of interference with the water curtain reflects the extent to which the water curtain at the tunnel entrance is affected by the wind speed at the tunnel entrance. If the degree of interference increases, it indicates that the stability of the water curtain is worse. In this case, to improve the quality and wind resistance of the water curtain formation, the water supply pressure should be appropriately increased. Conversely, if the degree of interference decreases, it indicates that the stability of the water curtain is better. In this case, to reduce resource waste, the water supply pressure should be appropriately decreased.

[0050] Furthermore, in this embodiment, the expected water supply pressure at the current sampling time is calculated by combining the degree of change in the water curtain's disturbance level with the actual water supply pressure at the current sampling time: In the formula, The desired water supply pressure at the current sampling time. The water supply pressure at the current sampling time. and These represent the interference levels of the water curtain at the current acquisition time and the previous acquisition time, respectively.

[0051] Therefore, in this embodiment, the water supply pressure of the water curtain at the tunnel entrance is adjusted by the degree of interference from the wind speed at the tunnel entrance, thereby improving the quality and wind resistance of the water curtain formation and preventing serious deviation or even breakage of the water curtain at the tunnel entrance, thus ensuring the stability of the water curtain at the highway tunnel entrance and the clarity of the water curtain projection.

[0052] Furthermore, in this embodiment, in order to accurately control the water supply pressure of the tunnel entrance water curtain, preferably, the error between the desired water supply pressure and the actual water supply pressure, as well as the rate of change of the error, are obtained and transmitted to the fuzzy controller. The fuzzy controller adjusts the proportional parameter Kp, integral parameter Ki, and derivative parameter Kd of the PID controller through fuzzy control rules. The specific process is existing technology, and this embodiment does not impose any special restrictions on it. Then, the PID controller controls and regulates the water supply pressure of the tunnel entrance water curtain to achieve the regulation of the water supply pressure of the tunnel entrance water curtain. The calculation of the error between the desired water supply pressure and the actual water supply pressure, as well as the rate of change of the error, is a well-known technology. The control process of the fuzzy controller and the PID controller is existing technology known to those skilled in the art, and this embodiment does not impose any special restrictions on it. The specific process will not be described in detail.

[0053] Based on the same inventive concept as the above method, this application embodiment also provides an array-type tunnel entrance water curtain projection device, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any of the above-described array-type tunnel entrance water curtain projection methods.

[0054] Preferably, in this embodiment, the array-type tunnel entrance water curtain projection device further includes a water curtain projection data sensing unit, a water curtain projection generating unit, and a tunnel water curtain projection control unit. Specifically, the block diagram of the array-type tunnel entrance water curtain projection device is as follows: Figure 2As shown in the diagram, the water curtain projection data sensing unit is used to acquire the wind speed at the tunnel entrance, the water supply pressure of the water curtain at the tunnel entrance, and the water curtain point cloud dataset for the water curtain projection. The water curtain projection generating unit includes a water curtain array, a water pump, a water tank, and a projector, used to form a stable water curtain at the tunnel entrance and project the water curtain onto the water curtain formed at the tunnel entrance. The tunnel water curtain projection control unit is used to analyze the water droplet splashing characteristics of the water curtain at the tunnel entrance by analyzing the local outlier degree of the point cloud data in the water curtain point cloud dataset to obtain the water droplet splashing characteristic value of each point cloud data. Based on the abnormal deviation and average level of the water droplet splashing characteristic values ​​of all point cloud data at each acquisition time, the water curtain deviation degree at each acquisition time is obtained. Based on the distribution trend of the wind speed at the tunnel entrance and the water curtain deviation degree, the water curtain interference degree at each acquisition time is obtained. Based on the change of the water curtain interference degree and the water supply pressure, the expected water supply pressure of the water curtain at the tunnel entrance is obtained. The water supply pressure during the water curtain projection process at the tunnel entrance is controlled and regulated using a PID controller.

[0055] It is understood that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0056] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0057] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Any equivalent structural or procedural transformations made based on the description and drawings of this application, or direct or indirect applications in other related technical fields, are similarly included within the protection scope of this application.

Claims

1. An arrayed tunnel portal water curtain projection method, characterized by, The method comprises the following steps: acquiring the wind speed at the tunnel portal, the water curtain supply pressure at the tunnel portal, and a water curtain point cloud data set projected by the water curtain; analyzing the water droplet splashing characteristics of the water curtain at the tunnel portal according to the local outlier degree of the point cloud data in the water curtain point cloud data set to obtain water droplet splashing characteristic values of each point cloud data, and obtaining the water curtain deviation degree at each collection time according to the abnormal deviation and average level of the water droplet splashing characteristic values of all point cloud data at each collection time; obtaining the water curtain disturbance degree at each collection time according to the distribution change trend of the wind speed at the tunnel portal and the water curtain deviation degree, and obtaining the expected water curtain supply pressure at the tunnel portal through the change of the water curtain disturbance degree and the water supply pressure, and using a PID controller to control and adjust the water supply pressure during the projection of the water curtain at the tunnel portal.

2. The method of claim 1, wherein the array of tunnel portal water curtain projections is characterized by, The acquisition process of the water drop splashing feature value of the point cloud data is as follows: ; in the formula, is the water drop splashing feature value of the i th point cloud data, is the discrete degree of the local density of all point cloud data in the neighborhood point cloud set corresponding to the i th point cloud data, is the mean value of the Euclidean distance between all point cloud data in the neighborhood point cloud set corresponding to the i th point cloud data, is the local density of the i th point cloud data, is a constant to avoid the denominator taking the value of 0.

3. The method of claim 2, wherein the array of tunnel portal water curtain projections is generated by a plurality of water jets. The water curtain point cloud data set at each collection time is taken as the input of a density peak value clustering algorithm to extract the local density of each point cloud data in the water curtain point cloud data set and the neighborhood point cloud set in the range of the cut-off distance thereof.

4. The method of claim 1, wherein the array of tunnel portal water curtain projections is characterized by, The acquisition process of the water curtain deviation degree of each acquisition time is: ; in the formula, is the water curtain deviation degree of the tth acquisition time, is the number of point clouds in the point cloud set of the tth acquisition time, is the number of point clouds in the water curtain point cloud data set of the tth acquisition time, is the mean value of the droplet splash characteristic values of all point cloud data in the water curtain point cloud data set of the tth acquisition time.

5. The method of claim 4, wherein the array of tunnel portal water curtain projections is further defined as: The water droplet splashing characteristic values of all point cloud data in the water curtain point cloud data set at each collection time are subjected to threshold segmentation, and the point cloud data corresponding to the water droplet splashing characteristic values higher than the segmentation threshold are grouped into an abnormal point cloud set at each collection time.

6. The method of claim 1, wherein, The acquisition process of the water curtain disturbance degree at each collection time is: ; in the formula, is the water curtain disturbance degree at the tth collection time, is a normalization function, is the fitting slope mean value of the wind speed sequence and the water curtain deviation degree sequence at the tth collection time, is an exponential function with a natural constant as the base number, and are the fitting slopes of the wind speed sequence and the water curtain deviation degree sequence at the tth collection time, respectively.

7. The method of claim 6, wherein the array of tunnel portal water curtain projections is further defined as: The multiple collection times closest to each collection time in time interval are taken as the neighboring collection times of each collection time.

8. The method of claim 6, wherein the array of tunnel portal water curtain projections is characterized by, The wind speed at the tunnel portal and the water curtain deviation degree of each collection time and its multiple neighboring collection times are arranged in time sequence respectively, and the arranged sequences are subjected to normalization processing to obtain the wind speed sequence and the water curtain deviation degree sequence at each collection time, and the fitting slopes of the wind speed sequence and the water curtain deviation degree sequence are extracted through fitting.

9. The method of claim 1, wherein, The acquisition process of the expected water supply pressure of the tunnel portal water curtain is as follows: ; wherein, is the expected water supply pressure at the current acquisition time, is the water supply pressure at the current acquisition time, and are the water curtain disturbance degrees at the current acquisition time and the previous acquisition time, respectively.

10. An arrayed tunnel portal water curtain projection device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein, The processor implements the steps of the array tunnel portal water curtain projection method according to any one of claims 1-9 when executing the computer program.

Images