Subway tunnel deformation automatic monitoring method and system

Abstract

The invention relates to the technical field of subway tunnel monitoring, and particularly discloses a subway tunnel deformation automatic monitoring method and system, and the method comprises the steps: building a tunnel model according to building data and visual information; based on a preset frequency broadcast data acquisition instruction, receiving tunnel data containing position and time acquired by a pre-installed range finder; when any range finder receives a data acquisition instruction, acquiring data based on an independent application probability; the application probability is obtained after the range finder performs local processing on the monitoring data; updating and displaying the tunnel model according to the tunnel data containing the position and the time; according to the invention, the local identification module is installed on the range finder, the data uploading frequency is determined by the local identification module, an intermittent data uploading architecture is provided, a real-time process is converted into a timing process, and the resource consumption is greatly reduced on the basis of ensuring the data validity as much as possible.

Description

Technical Field

[0001] The present invention relates to the technical field of subway tunnel monitoring, and specifically to an automatic monitoring method and system for subway tunnel deformation. Background Technique

[0002] As an important part of the urban underground transportation system, the stability and safety of subway tunnels are of crucial importance. During the construction and operation of subways, due to factors such as geological conditions, construction techniques, and changes in the surrounding environment, tunnels may undergo varying degrees of deformation. To ensure the structural safety and operation safety of subway tunnels, real-time and accurate deformation monitoring is particularly important. With the progress of sensor technology, automatic control technology, and data analysis methods, subway tunnel deformation monitoring has shifted from traditional manual detection to an automatic and intelligent monitoring system.

[0003] Basically, intelligent monitoring systems all require rangefinders. There are many types of rangefinders, which can obtain distances with different accuracies and then calculate the deformation situation. The existing calculation process is generally completed by a unified computer device. The rangefinders need to upload data in real time, and then the computer device performs statistical processing. In this process, the real-time upload of data will consume a large amount of data processing resources. How to reduce this consumption is the technical problem that the technical solution of the present invention aims to solve. Summary of the Invention

[0004] The purpose of the present invention is to provide an automatic monitoring method and system for subway tunnel deformation to solve the problems raised in the above background technique.

[0005] To achieve the above purpose, the present invention provides the following technical solutions: An automatic monitoring method and system for subway tunnel deformation, the method includes: Obtain the construction data of the subway tunnel, obtain the visual information of the subway tunnel, and create a tunnel model based on the construction data and visual information; Broadcast data acquisition instructions based on a preset frequency, and receive tunnel data containing position and time obtained by pre-installed rangefinders; when any rangefinder receives a data acquisition instruction, obtain data based on an independent application probability; the application probability is obtained after the rangefinder locally processes the monitoring data; Update and display the tunnel model according to the tunnel data containing position and time; Calculate the data upload frequency of each rangefinder within a preset time range according to the tunnel data containing position and time, mark the abnormal areas in the tunnel model according to the data upload frequency, and enhance the display of the marked abnormal areas.

[0006] Further, the steps of obtaining the construction data of the subway tunnel, obtaining the visual information of the subway tunnel, and creating a tunnel model based on the construction data and the visual information include: Obtain the BIM model of the subway tunnel as the basic model; Determine the visual acquisition parameters according to the basic model; the visual acquisition parameters are a parameter group, and a parameter group includes an acquisition position, an acquisition direction, and an acquisition wide angle. One parameter group corresponds to one acquisition area, and the union of the acquisition areas is not less than the inner surface of the basic model; Obtain visual information based on the visual acquisition parameters and identify the visual information; Fill the recognition result into the acquisition area corresponding to the visual acquisition parameter; the recognition result at least includes the object recognition result.

[0007] Further, the steps of broadcasting a data acquisition instruction based on a preset frequency, and receiving the tunnel data containing the position and time obtained by a pre-installed rangefinder include: Receive the time interval input by the management party, and broadcast a data acquisition instruction to all pre-installed rangefinders every time the time interval elapses; Receive the tunnel data containing the position and time fed back by the rangefinder; Among them, when any rangefinder receives a data acquisition instruction, it judges whether to apply the data acquisition instruction based on the application probability; the determination process of the application probability is: Receive the retrospective time preset by the management party, obtain the monitoring data in real time, calculate the mean value and standard deviation of the monitoring data within the retrospective time, calculate the difference between the latest monitoring data and the mean value, and jointly determine the application probability by combining the difference and the standard deviation.

[0008] Further, the steps of updating and displaying the tunnel model according to the tunnel data containing the position and time include: Select the latest tunnel data at each position according to the time; Query the coordinates of the rangefinder corresponding to the latest tunnel data; Locate the correction point in the tunnel model according to the coordinates and the position of the tunnel data; Update the coordinates of the correction point according to the tunnel data; among them, the update process is a fitting process; When the coordinates of a certain correction point are updated, refresh and display the tunnel model.

[0009] Further, the steps of calculating the data upload frequency of each rangefinder within a preset time range according to the tunnel data containing the position and time, marking the abnormal area in the tunnel model according to the data upload frequency, and enhancing the display of the marked abnormal area include: Receive the time range input by the management party; Classify the tunnel data according to the source label of the tunnel data, and sort it according to its time to obtain a data sequence; wherein, the source label is used to characterize which rangefinder uploads the tunnel data and is inserted when the rangefinder uploads the data. Taking the current moment as the starting point, obtain the data in the time range of the data sequence in reverse order, and calculate the data upload frequency according to the number of obtained data. Compare the data upload frequency with a preset frequency threshold. When the data upload frequency reaches the preset frequency threshold, read the positions corresponding to the data in the time range. Mark the read positions as abnormal positions, count the abnormal positions to obtain an abnormal area, and perform enhanced display on the marked abnormal area.

[0010] Furthermore, the rangefinder includes a fixed rangefinder and a mobile rangefinder. Any rangefinder is arranged on a base containing a steering component, and the steering component is used to adjust the central orientation of the rangefinder in the tunnel cross-section.

[0011] Furthermore, the method further includes: Regularly obtain images according to the visual detector installed on the top of the subway, and verify the accuracy of the tunnel model according to the images; the verification method is: When obtaining the image, synchronously record the acquisition time, acquisition position, and acquisition direction, intercept the simulated image in the tunnel model according to the acquisition position and acquisition direction, compare the model image with the obtained image, and verify the accuracy of the tunnel model according to the comparison result; use the acquisition time as the label of the accuracy.

[0012] The technical solution of the present invention also provides a subway tunnel deformation automatic monitoring system, and the system includes: A tunnel model creation module, which is used to obtain the construction data of the subway tunnel, obtain the visual information of the subway tunnel, and create a tunnel model according to the construction data and visual information; A tunnel data acquisition module, which is used to broadcast a data acquisition instruction based on a preset frequency, and receive the tunnel data containing the position and time obtained by the pre-installed rangefinder; when any rangefinder receives the data acquisition instruction, it obtains the data based on an independent application probability; the application probability is obtained after the rangefinder locally processes the monitoring data; A tunnel model update module, which is used to update and display the tunnel model according to the tunnel data containing the position and time; An abnormal area display module, which is used to calculate the data upload frequency of each rangefinder within a preset time range according to the tunnel data containing the position and time, mark the abnormal area in the tunnel model according to the data upload frequency, and perform enhanced display on the marked abnormal area.

[0013] Furthermore, the tunnel model creation module includes: A basic model creation unit for obtaining a BIM model of a subway tunnel as a basic model; A collection parameter determination unit for determining visual collection parameters according to the basic model; the visual collection parameters are a parameter group, and a parameter group includes a collection position, a collection direction, and a collection wide angle. One parameter group corresponds to one collection area, and the union of the collection areas is not less than the inner surface of the basic model; A visual information recognition unit for obtaining visual information based on the visual collection parameters and recognizing the visual information; An identification result filling unit for filling the identification result to the collection area corresponding to the visual collection parameters; the identification result at least includes an object recognition result.

[0014] Further, the tunnel data acquisition module includes: An instruction broadcasting unit for receiving the time interval input by the management party and broadcasting a data acquisition instruction to all pre-installed rangefinders every time the time interval elapses; A data receiving unit for receiving the tunnel data containing the position and time fed back by the rangefinder; Wherein, when any rangefinder receives the data acquisition instruction, it judges whether to apply the data acquisition instruction based on the application probability; the determination process of the application probability is as follows: Receiving the retrospective time preset by the management party, obtaining the monitoring data in real time, calculating the mean value and standard deviation of the monitoring data within the retrospective time, calculating the difference between the latest monitoring data and the mean value, and jointly determining the application probability by combining the difference and the standard deviation.

[0015] Compared with the prior art, the beneficial effects of the present invention are: The present invention installs a local recognition module on the rangefinder, and the local recognition module determines the data upload frequency, providing an intermittent data upload architecture, converting the real-time process into a timing process, and greatly reducing the resource consumption on the basis of ensuring the data validity as much as possible. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention.

[0017] Figure 1 Shows the overall flowchart of the subway tunnel deformation automatic monitoring method.

[0018] Figure 2 Shows the structure diagram of the subway tunnel deformation automatic monitoring system. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0020] Figure 1 As the general flow block diagram of the subway tunnel deformation automatic monitoring method and system, in an embodiment of the present invention, a subway tunnel deformation automatic monitoring method includes: Step S100: Obtain the construction data of the subway tunnel, obtain the visual information of the subway tunnel, and create a tunnel model according to the construction data and the visual information; The subway tunnel itself is a kind of building, and construction data will be retained in the design stage. This application defaults that the management party has the permission to obtain the construction data (in fact, the execution entity of this method is the participant in the construction process, and the process of obtaining the construction data is to read the data in its own database, and the permission is inherently available); based on the obtaining permission, obtain the construction data of the subway tunnel, and then, obtain the visual information of the subway tunnel. The visual information is generally obtained by an unmanned vehicle with a moving function and a shooting function. The unmanned vehicle moves in the tunnel and continuously takes pictures to obtain images of each position in the subway tunnel; combining the construction data and the visual information, a tunnel model can be created.

[0021] Step S200: Broadcast a data acquisition instruction based on a preset frequency, and receive the tunnel data containing position and time obtained by a pre-installed rangefinder; when any rangefinder receives the data acquisition instruction, obtain data based on an independent application probability; the application probability is obtained after the rangefinder locally processes the monitoring data; Broadcast a data acquisition instruction based on a preset frequency. The meaning of broadcasting is to send the data acquisition instruction to all rangefinders. When the rangefinder receives the data acquisition instruction, it determines whether to execute based on an independent application probability. Suppose the application probability is 30%. When receiving the data acquisition instruction, generate a random number between 1 and 100. When the random number is between 0 and 30, it is regarded as execution, and other values are regarded as non-execution. That is, there is a 30% probability of executing the data acquisition instruction to obtain data once. When the rangefinder obtains data, it simultaneously obtains the position and time, and feeds back the data containing the position and time obtained to the execution entity of this method; the data obtained by the rangefinder is collectively referred to as tunnel data. Since the rangefinder obtains distance, the tunnel data in this application generally refers to distance.

[0022] Step S300: Update and display the tunnel model according to the tunnel data containing position and time; After receiving the tunnel data containing location and time, the created tunnel model can be updated, and the updated tunnel model can be displayed, enabling the observer to intuitively and real-time observe the tunnel state.

[0023] Step S400: Calculate the data upload frequency of each rangefinder within a preset time range according to the tunnel data containing location and time, mark the abnormal areas in the tunnel model according to the data upload frequency, and enhance the display of the marked abnormal areas; This application also performs an additional process on the tunnel data containing location and time. When each rangefinder uploads data, a source label will be inserted into the data, and the source label is used to represent which rangefinder uploads the data. When the execution entity of this method obtains the tunnel data containing location and time, the tunnel data is classified according to the source label to obtain the data sequence corresponding to each rangefinder. The actual frequency, called the data upload frequency, can be calculated according to the data in the data sequence. According to the data upload frequency, the working state of each rangefinder can be judged (the data upload frequency is related to the measured data of the rangefinder, as described in step S200), and then the abnormal area can be determined. After determining the abnormal area, the abnormal area is enhanced for display to improve its intuitiveness.

[0024] For the above process, further distinction and explanation are needed, specifically the differences between step S200 and step S400, which are described as follows: Suppose there is a rangefinder that works independently, obtains monitoring data in real time, and conducts independent local analysis to determine an application probability. The stronger the volatility of the monitoring data, the greater the application probability. The local working process of the rangefinder does not need to be reported to the execution entity of this method, and the execution entity of this method is unaware of it. However, the execution entity of this method will periodically send data acquisition instructions. When the rangefinder receives the data acquisition instructions, it determines whether to upload data based on the application probability. If it uploads, the execution entity of this method will obtain the data sent by the rangefinder. Therefore, the execution entity of this method can only intermittently obtain the data uploaded by the rangefinder. These data contain time information, and a frequency can be calculated based on the time information. The actual meaning of this frequency is that it is an approximate value of the application probability inversely deduced by the execution entity of this method based on the obtained data. And the application probability reflects the volatility of the monitoring data. Therefore, according to the magnitude of the frequency, the fluctuation amplitude at the position corresponding to the monitored data can be determined, thereby determining the abnormal area. In this process, between the execution entity of this method and the rangefinder, there is only a regular periodic data upload process, and there is no real-time upload process (including the application probability, which is not uploaded in real time either), greatly reducing the data transmission pressure. In fact, in some architectures, the rangefinder can actually upload the local recognition results, that is, directly mark the abnormal area and upload it to the execution entity of this method. This method is of course feasible, but it means that the data transmission module in the rangefinder needs to work in real time. Although it seems that the amount of data to be transmitted is not much, the number of rangefinders is extremely large. In the case of a huge number of rangefinders, the working pressure on the processing device corresponding to the execution entity of this method will be very high.

[0025] Regarding step S100, the steps of obtaining the construction data of the subway tunnel, obtaining the visual information of the subway tunnel, and creating a tunnel model based on the construction data and the visual information include: Obtain the BIM model of the subway tunnel as the basic model; Determine the visual acquisition parameters according to the basic model; the visual acquisition parameters are a parameter group. A parameter group includes an acquisition position, an acquisition direction, and an acquisition wide angle. A parameter group corresponds to an acquisition area, and the union of the acquisition areas is not less than the inner surface of the basic model; Obtain visual information based on the visual acquisition parameters and identify the visual information; Fill the recognition result into the acquisition area corresponding to the visual acquisition parameters; the recognition result at least includes the object recognition result.

[0026] The above content specifically defines the creation process of the tunnel model. The BIM model of the subway tunnel is known data. Obtain the BIM model of the subway tunnel as the basic model. Then, determine the visual acquisition parameters based on the basic model. The practical meaning of the visual acquisition parameters is where to obtain images in which direction and what the wide angle of the obtained images is. The condition to be met is that the obtained images need to completely cover the inner surface of the tunnel. Obtain visual information based on the visual acquisition parameters, identify the visual information, and fill the recognition result into the acquisition area corresponding to the visual acquisition parameters. This process can be understood as "decorating" each position in the basic model according to the visual information. The recognition result at least includes the object recognition result, that is, determine which objects are in the tunnel, and then insert the objects into the corresponding positions in the basic model according to the scale of the basic model.

[0027] It is worth mentioning that if the recognition accuracy is high, the details of the basic model can be made more abundant to obtain a more refined tunnel model. The specific refinement process can refer to existing three-dimensional modeling solutions, which will not be elaborated in this application.

[0028] Regarding step S200, the step of obtaining the tunnel data containing position and time acquired by the pre-installed rangefinder based on the broadcast data acquisition instruction includes: Receive the time interval input by the management party. Every time the time interval elapses, broadcast the data acquisition instruction to all pre-installed rangefinders; Receive the tunnel data containing position and time fed back by the rangefinder; The frequency of broadcasting the data acquisition instruction is input by the management party, and the management party is the tunnel management personnel. Receive the time interval input by the management party. Every time the time interval elapses, broadcast the data acquisition instruction to all pre-installed rangefinders, and receive the tunnel data containing position and time fed back by each rangefinder.

[0029] Among them, when any rangefinder receives the data acquisition instruction, it judges whether to apply the data acquisition instruction based on the application probability. The determination process of the application probability is as follows: Receive the retrospective time preset by the management party, obtain the monitoring data in real time, calculate the mean value and standard deviation of the monitoring data within the retrospective time, calculate the difference between the latest monitoring data and the mean value, and jointly determine the application probability by combining the difference and the standard deviation.

[0030] One way to determine the application probability is: ; where is the application probability, and are preset correction coefficients, is the absolute value of the difference, is the standard deviation; the specific description of the above determination method is as follows: the application probability is directly proportional to both the absolute value of the difference and the standard deviation, and the weights of the absolute value of the difference and the standard deviation are different. Further, the value range of the application probability is from zero to one.

[0031] Regarding step S300, the step of updating and displaying the tunnel model according to the tunnel data containing position and time includes: Select the latest tunnel data at each position according to the time; Query the coordinates of the rangefinder corresponding to the latest tunnel data; Locate the correction point in the tunnel model according to the coordinates and the position of the tunnel data; Update the coordinates of the correction point according to the tunnel data; wherein, the update process is a fitting process; When the coordinates of a certain correction point are updated, refresh and display the tunnel model.

[0032] In an example of the technical solution of the present invention, the update and display process of the tunnel model is specifically defined. The latest (the latest in time) tunnel data at each different position is selected according to the time, and it is determined which rangefinder it is sent by according to the source label in the tunnel data, and then the coordinates of the corresponding rangefinder are queried; the position of the tunnel data refers to a certain position in the subway tunnel, and the obtained tunnel data is the distance, which refers to the distance between the coordinates of the rangefinder and a certain position in the subway tunnel. Based on the scale of the tunnel model, the points corresponding to the coordinates of the rangefinder and the points corresponding to a certain position in the subway tunnel are located in the tunnel model, and the current distance is corrected based on the tunnel data. This process is the update process; there is a lot of tunnel data, and multiple points in the tunnel model will be updated. Each time it is updated, only a small area is updated, and it still needs to maintain the connection relationship with other points (keep the tunnel model without breakpoints). That is, the update process is a fitting process.

[0033] Regarding step S400, the step of calculating the data upload frequency of each rangefinder within a preset time range according to the tunnel data containing position and time, marking the abnormal area in the tunnel model according to the data upload frequency, and enhancing the display of the marked abnormal area includes: Receive the time range input by the management party; Classify the tunnel data according to the source label of the tunnel data and sort it according to its time to obtain a data sequence; wherein, the source label is used to represent which rangefinder uploads the tunnel data and is inserted when the rangefinder uploads the data; Taking the current moment as the starting point, obtain the data in the time range of the data sequence in reverse order, and calculate the data upload frequency according to the number of obtained data; Compare the data upload frequency with a preset frequency threshold. When the data upload frequency reaches the preset frequency threshold, read the positions corresponding to the data within the time range. Mark the read positions as abnormal positions, count the abnormal positions to obtain an abnormal area, and perform enhanced display on the marked abnormal area.

[0034] In an example of the technical solution of the present invention, receive the time range input by the management party. The time range can be one hour, half a day, or a longer time. For all tunnel data received, classify the tunnel data according to the source label of the tunnel data, and perform separate analysis on the tunnel data from the same source.

[0035] For each category of tunnel data (data obtained by the same rangefinder), sort it according to its time to obtain a data sequence. Starting from the current moment, obtain the data in the time range of the data sequence in reverse order. Divide the number of data by the time to obtain the data upload frequency. When the data upload frequency reaches the preset frequency threshold, it indicates that the average application probability of the corresponding rangefinder within the time range is very high (the application probability is calculated in real time, and the time range is relatively long. Within the time range, the rangefinder may determine multiple application probabilities in real time), indicating that the volatility of the data obtained by the rangefinder is relatively high. At this time, mark the positions of the tunnel data within the time range as abnormal positions. Finally, count the abnormal positions to obtain an abnormal area, and perform enhanced display on the marked abnormal area.

[0036] Among them, regarding the enhanced display process, the S value and V value in the HSV color value space can be determined according to the average application probability, where the H value is a preset value, such as 120, representing red. The S value and V value are used to adjust the degree of red. The S value and V value are both proportional to the average application probability. When the average application probability is greater than the preset peak value, both the S value and V value are 1, and the result of the enhanced display is pure red.

[0037] As a preferred embodiment of the technical solution of the present invention, the types of rangefinders are limited. The rangefinders include fixed rangefinders and mobile rangefinders. Any rangefinder is arranged on a base containing a steering component. The steering component is used to adjust the central orientation of the rangefinder in the tunnel cross-section. The practical significance of the above architecture is that when each rangefinder measures the distance, its ranging direction is parallel to the tunnel cross-section, and the specific angle is determined by the steering component. The base of the fixed rangefinder is fixed, and the base of the mobile rangefinder is movable; no matter which rangefinder measures the distance in which direction, the obtained tunnel data records the position, time, and source label.

[0038] As a preferred embodiment of the technical solution of the present invention, the method further includes: Timely acquire images according to a visual detector installed on the top of the subway, and verify the accuracy of the tunnel model based on the images; the verification method is as follows: When acquiring images, synchronously record the acquisition time, acquisition position, and acquisition direction. Intercept simulated images from the tunnel model according to the acquisition position and acquisition direction, compare the model images with the acquired images, and verify the accuracy of the tunnel model based on the comparison results; use the acquisition time as the label of the accuracy.

[0039] In an example of the technical solution of the present invention, a visual detector is installed on the subway to timely acquire images (generally images in the forward direction of the subway). When acquiring images, synchronously record the acquisition time, acquisition position, and acquisition direction. According to the acquisition position and acquisition direction, the front view angle can be determined in the tunnel model to obtain simulated images. Whether it is the actually acquired images or the model images, they actually contain the contours of the front tunnel. By comparing this contour (specifically the curvature at each point), the accuracy of the tunnel model can be verified; one verification process is only the verification process corresponding to the moment. Therefore, it is necessary to insert a time label into the accuracy. It is worth mentioning that since the acquisition position is recorded, a position label can also be inserted into the accuracy to facilitate subsequent problem tracing.

[0040] Figure 2 The structure diagram of the automatic monitoring system for subway tunnel deformation is shown. In a preferred embodiment of the technical solution of the present invention, an automatic monitoring system for subway tunnel deformation is further provided. The system 10 includes: A tunnel model creation module 11, which is used to obtain the construction data of the subway tunnel, obtain the visual information of the subway tunnel, and create a tunnel model according to the construction data and visual information; A tunnel data acquisition module 12, which is used to broadcast data acquisition instructions based on a preset frequency, and receive tunnel data containing position and time obtained by a pre-installed rangefinder; when any rangefinder receives a data acquisition instruction, it obtains data based on an independent application probability; the application probability is obtained after the rangefinder performs local processing on the monitoring data; A tunnel model update module 13, which is used to update and display the tunnel model according to the tunnel data containing position and time; An abnormal area display module 14, which is used to calculate the data upload frequency of each rangefinder within a preset time range according to the tunnel data containing position and time, mark the abnormal area in the tunnel model according to the data upload frequency, and perform enhanced display on the marked abnormal area.

[0041] Furthermore, the tunnel model creation module 11 includes: A basic model creation unit, which is used to obtain the BIM model of the subway tunnel as the basic model; An acquisition parameter determination unit for determining visual acquisition parameters according to the basic model; the visual acquisition parameters are a parameter group, and a parameter group includes an acquisition position, an acquisition direction, and an acquisition wide angle. One parameter group corresponds to one acquisition area, and the union of the acquisition areas is not less than the inner surface of the basic model. A visual information recognition unit for obtaining visual information based on the visual acquisition parameters and recognizing the visual information. An identification result filling unit for filling the identification result to the acquisition area corresponding to the visual acquisition parameters; the identification result at least includes an object recognition result.

[0042] Specifically, the tunnel data acquisition module 12 includes: An instruction broadcasting unit for receiving the time interval input by the management party and broadcasting a data acquisition instruction to all pre-installed rangefinders every time the time interval elapses. A data receiving unit for receiving the tunnel data containing the position and time fed back by the rangefinder. Wherein, when any rangefinder receives the data acquisition instruction, it determines whether to apply the data acquisition instruction based on the application probability; the determination process of the application probability is as follows: Receive the retrospective time preset by the management party, obtain the monitoring data in real time, calculate the mean and standard deviation of the monitoring data within the retrospective time, calculate the difference between the latest monitoring data and the mean, and jointly determine the application probability by combining the difference and the standard deviation.

[0043] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. A method for automatically monitoring deformation of a subway tunnel, characterized in that: The method comprises: Obtain architectural data of subway tunnels, obtain visual information of subway tunnels, and create tunnel models based on architectural data and visual information; Based on the preset frequency broadcast data acquisition instructions, receive the tunnel data containing the position and time acquired by the pre-installed distance meter; when any distance meter receives the data acquisition instruction, it acquires the data based on the independent application probability; the application probability is obtained by the distance meter after local processing of the monitoring data; Update and display the tunnel model based on tunnel data including position and time; The data upload frequency of each rangefinder within a preset time range is calculated based on the tunnel data containing position and time, and abnormal areas are marked in the tunnel model according to the data upload frequency, and the marked abnormal areas are enhanced and displayed.

2. The subway tunnel deformation automatic monitoring method according to claim 1 is characterized in that: The steps of obtaining the architectural data of the subway tunnel, obtaining the visual information of the subway tunnel, and creating a tunnel model according to the architectural data and the visual information include: Obtain the BIM model of the subway tunnel as the base model; Determine visual acquisition parameters according to the basic model; the visual acquisition parameters are parameter groups, one parameter group includes an acquisition position, an acquisition direction and an acquisition wide angle, one parameter group corresponds to an acquisition area, and the union of the acquisition areas is not less than the inner surface of the basic model; Acquire visual information based on visual acquisition parameters, and identify the visual information; Fill the recognition result into the acquisition area corresponding to the visual acquisition parameter; the recognition result at least includes the object recognition result.

3. The subway tunnel deformation automatic monitoring method according to claim 1 is characterized in that: The step of broadcasting a data acquisition instruction based on a preset frequency and receiving tunnel data containing position and time acquired by a pre-installed range finder comprises: receiving a time interval input by a management party, and broadcasting a data acquisition instruction to all pre-installed rangefinders every time the time interval passes; Receive tunnel data containing position and time fed back by the distance meter; When any rangefinder receives a data acquisition instruction, it determines whether to apply the data acquisition instruction based on the application probability; the determination process of the application probability is: The receiver receives the backtracking time set in advance by the management party, obtains the monitoring data in real time, calculates the mean and standard deviation of the monitoring data within the backtracking time, calculates the difference between the latest monitoring data and the mean, and determines the application probability by combining the difference and standard deviation.

4. The subway tunnel deformation automatic monitoring method according to claim 1, characterized in that: The step of updating and displaying the tunnel model according to the tunnel data including the position and time comprises: Select the latest tunnel data at each location according to time; Query the coordinates of the distance meter corresponding to the latest tunnel data; locating the correction point in the tunnel model according to the coordinates and the position of the tunnel data; updating the coordinates of the correction points according to the tunnel data; wherein the updating process is a fitting process; When the coordinates of a certain correction point are updated, the tunnel model is refreshed and displayed.

5. The subway tunnel deformation automatic monitoring method according to claim 4 is characterized in that: The step of calculating the data upload frequency of each rangefinder within a preset time range according to the tunnel data containing the position and time, marking the abnormal area in the tunnel model according to the data upload frequency, and enhancing the display of the marked abnormal area comprises: The time frame for receiving the management input; The tunnel data is classified according to the source tag of the tunnel data, and sorted according to its time to obtain a data sequence; wherein the source tag is used to indicate which distance meter the tunnel data is uploaded by, and is inserted when the distance meter uploads the data; Taking the current time as the starting point, obtain the data in the data sequence within the time range in reverse order, and calculate the data upload frequency based on the number of data obtained; The data upload frequency is compared with a preset frequency threshold, and when the data upload frequency reaches the preset frequency threshold, a position corresponding to the data within the time range is read; The read positions are marked as abnormal positions, the abnormal positions are counted, the abnormal areas are obtained, and the marked abnormal areas are enhanced for display.

6. The subway tunnel deformation automatic monitoring method according to claim 1, characterized in that: The distance meter includes a fixed distance meter and a mobile distance meter. Any distance meter is arranged on a base having a steering component, and the steering component is used to adjust the center direction of the distance meter in the tunnel section.

7. The subway tunnel deformation automatic monitoring method according to claim 1, characterized in that: The method further comprises: Images are acquired regularly by a visual detector installed on the top of the subway, and the accuracy of the tunnel model is verified based on the images; the verification method is: When acquiring images, the acquisition time, acquisition position and acquisition direction are recorded synchronously. A simulated image is captured from the tunnel model according to the acquisition position and acquisition direction. The model image and the acquired image are compared. The accuracy of the tunnel model is verified based on the comparison results. The acquisition time is used as a label for accuracy.

8. An automatic monitoring system for subway tunnel deformation, characterized in that: The system comprises: A tunnel model creation module is used to obtain the architectural data of the subway tunnel, obtain the visual information of the subway tunnel, and create a tunnel model based on the architectural data and the visual information; The tunnel data acquisition module is used to broadcast data acquisition instructions based on a preset frequency and receive tunnel data containing position and time acquired by a pre-installed distance meter; when any distance meter receives the data acquisition instruction, it acquires data based on independent application probability; the application probability is obtained by the distance meter after local processing of the monitoring data; A tunnel model updating module, used for updating and displaying the tunnel model according to tunnel data including position and time; The abnormal area display module is used to calculate the data upload frequency of each rangefinder within a preset time range based on the tunnel data containing position and time, mark the abnormal area in the tunnel model according to the data upload frequency, and enhance the display of the marked abnormal area.

9. The subway tunnel deformation automatic monitoring system according to claim 8, characterized in that: The tunnel model creation module includes: A basic model creation unit is used to obtain a BIM model of a subway tunnel as a basic model; An acquisition parameter determination unit, configured to determine visual acquisition parameters according to the basic model; the visual acquisition parameters are parameter groups, each parameter group includes an acquisition position, an acquisition direction, and an acquisition wide angle, each parameter group corresponds to an acquisition area, and the union of the acquisition areas is not less than the inner surface of the basic model; A visual information recognition unit, used to obtain visual information based on visual acquisition parameters and recognize the visual information; The recognition result filling unit is used to fill the recognition result into the collection area corresponding to the visual collection parameter; the recognition result at least includes the object recognition result.

10. The subway tunnel deformation automatic monitoring system according to claim 8, characterized in that: The tunnel data acquisition module includes: An instruction broadcasting unit, used for receiving a time interval input by a management party, and broadcasting a data acquisition instruction to all pre-installed rangefinders every time the time interval passes; A data receiving unit, used for receiving tunnel data containing position and time fed back by the rangefinder; When any rangefinder receives a data acquisition instruction, it determines whether to apply the data acquisition instruction based on the application probability; the determination process of the application probability is: The receiver receives the backtracking time set in advance by the management party, obtains the monitoring data in real time, calculates the mean and standard deviation of the monitoring data within the backtracking time, calculates the difference between the latest monitoring data and the mean, and determines the application probability by combining the difference and standard deviation.

Images