Rapid positioning method and system for underground pipe gallery leakage

Abstract

The present invention discloses a rapid positioning method and system for underground pipe gallery leakage, which belongs to the field of leakage monitoring, wherein the method includes: determining a target underground pipe gallery, performing regional division, and obtaining N monitoring areas; selecting monitoring points in the N monitoring areas respectively, and setting a leakage monitoring integrated device at each monitoring point; establishing a three-dimensional underground pipe gallery model of the target underground pipe gallery, and performing comparison between leakage monitoring results and leakage discrimination models; when the leakage discrimination result exceeds the preset leakage constraint in the leakage discrimination model, determining the leakage position based on the position positioning result; generating early warning information based on the leakage position and the three-dimensional underground pipe gallery model, and performing visual display. The present application solves the technical problems of inaccurate leakage position positioning and untimely discovery in the prior art, and achieves the technical effect of real-time monitoring of leakage and rapid and accurate locking of leakage position.

Description

Technical Field

[0001] The invention relates to the field of leakage monitoring, and in particular to a method and system for quickly locating leakage in an underground pipe gallery. Background Art

[0002] Underground pipe corridors centrally accommodate municipal pipelines such as electricity, communications, water supply and drainage, and heat, and are important infrastructure to ensure the operation of cities. However, underground pipe corridors have been in a complex underground environment for a long time, and leakage problems occur from time to time, seriously affecting the operation of cities. In the existing technology, underground pipe corridor leakage monitoring mainly relies on manual inspections and traditional instrument measurements. Manual inspections are inefficient and it is difficult to detect leakage problems in a timely manner; traditional instruments such as pressure gauges and listening rods have limited accuracy, and the positioning is often not accurate enough, and require a lot of manpower and material resources. Once a leakage occurs, it is difficult for maintenance personnel to quickly determine the specific location of the leakage, which brings great difficulties to the emergency repair work. Therefore, there are technical problems in the existing technology that the leakage location is inaccurate and the leakage is not discovered in time. Summary of the invention

[0003] The present application aims to solve the technical problems of inaccurate positioning and untimely discovery of leakage in the prior art by providing a method and system for quickly locating leakage in an underground pipe gallery.

[0004] In view of the above problems, the present application provides a method and system for quickly locating leakage in an underground pipe gallery.

[0005] The first aspect disclosed in the present application provides a rapid positioning method for underground pipeline corridor leakage, the method comprising: determining a target underground pipeline corridor, obtaining a plane distribution map of the target underground pipeline corridor, dividing the area based on the plane distribution map, and obtaining N monitoring areas; selecting monitoring points in the N monitoring areas according to the plane distribution map and the N monitoring areas, and setting a leakage monitoring integrated device at each monitoring point; establishing a three-dimensional underground pipeline corridor model of the target underground pipeline corridor, and using UWB wireless carrier communication technology to locate the position of the leakage monitoring integrated device, and integrating the position positioning result into the three-dimensional underground pipeline corridor model; performing leakage monitoring on the target underground pipeline corridor based on the leakage monitoring integrated device, and synchronously executing and comparing the leakage monitoring result with a leakage discrimination model, the leakage discrimination model having a preset leakage constraint; when the leakage judgment result exceeds the preset leakage constraint in the leakage discrimination model, determining the leakage location based on the position positioning result; generating early warning information based on the leakage location and the three-dimensional underground pipeline corridor model, and performing visual display.

[0006] Another aspect disclosed in the present application provides a rapid positioning system for underground pipe gallery leakage, the system comprising: a monitoring area acquisition module, used to determine the target underground pipe gallery, obtain the plane distribution map of the target underground pipe gallery, divide the area based on the plane distribution map, and obtain N monitoring areas; a monitoring point selection module, used to select monitoring points in the N monitoring areas according to the plane distribution map and the N monitoring areas, and set a leakage monitoring integrated device at each monitoring point; a three-dimensional model establishment module, used to establish a three-dimensional underground pipe gallery model of the target underground pipe gallery, and use UWB wireless carrier communication to establish a three-dimensional underground pipe gallery model of the target underground pipe gallery. The technology locates the position of the leakage monitoring integrated device and integrates the positioning result into the three-dimensional underground pipe gallery model; the leakage discrimination module is used to monitor the leakage of the target underground pipe gallery based on the leakage monitoring integrated device, and synchronously compare the leakage monitoring results with the leakage discrimination model, and the leakage discrimination model has a preset leakage constraint; the leakage position determination module is used to determine the leakage position based on the positioning result when the leakage judgment result exceeds the preset leakage constraint in the leakage discrimination model; the early warning information display module is used to generate early warning information based on the leakage position and the three-dimensional underground pipe gallery model for visual display.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] By determining the target underground corridor, obtaining the plane distribution map, dividing the area based on the distribution map, obtaining N monitoring areas, and realizing regional management of the target corridor, the foundation is laid for subsequent distributed monitoring; according to the plane distribution map and the N monitoring areas, monitoring points are selected in each monitoring area, and leakage monitoring integrated devices are set at each monitoring point to achieve full coverage monitoring of each monitoring area and improve monitoring efficiency and accuracy; a three-dimensional underground corridor model of the target underground corridor is established, and the position of the leakage monitoring integrated device is located using UWB wireless carrier communication technology, and the positioning results are integrated into the three-dimensional model to achieve high-precision positioning and three-dimensional spatial information management, which is convenient for the location of the leakage. Provide data support for accurate judgment; conduct leakage monitoring on the target pipe gallery based on the leakage monitoring integrated device, compare the monitoring results with the preset leakage discrimination model, realize real-time collection and intelligent discrimination of leakage monitoring data, and timely discover leakage problems; when the monitoring results exceed the preset leakage constraint of the leakage discrimination model, determine the leakage location based on the position positioning result, and realize rapid and accurate judgment of the leakage location; generate early warning information based on the leakage location and three-dimensional pipe gallery model, and perform visual display to realize intuitive leakage information presentation. The technical solution solves the technical problems of inaccurate leakage location positioning and untimely discovery in the prior art, and achieves the technical effect of real-time monitoring of leakage and rapid and accurate locking of leakage location.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A schematic flow chart of a method for quickly locating leakage in an underground pipe gallery is provided for an embodiment of the present application;

[0011] Figure 2 A structural schematic diagram of a system for quickly locating leakage in an underground pipe gallery is provided for an embodiment of the present application.

[0012] Explanation of the reference numerals: monitoring area acquisition module 11 , monitoring point selection module 12 , three-dimensional model establishment module 13 , leakage identification module 14 , leakage location determination module 15 , early warning information display module 16 . DETAILED DESCRIPTION

[0013] The overall idea of ​​the technical solution provided by this application is as follows:

[0014] The embodiments of the present application provide a method and system for quickly locating leakage in underground pipe corridors, and construct a solution for quickly locating leakage in underground pipe corridors through regional division and point monitoring, positioning technology and three-dimensional modeling, intelligent discrimination and visual early warning. Among them, regional division and distributed monitoring realize full coverage monitoring of the pipe corridor, improving monitoring efficiency; the integration of UWB positioning and three-dimensional pipe corridor model realizes high-precision spatial position expression, laying the foundation for leakage positioning; the introduction of leakage discrimination model realizes intelligent identification of leakage and timely early warning. The visual display of leakage information facilitates management personnel to intuitively perceive and quickly deal with it.

[0015] In short, the present application can monitor the leakage of underground pipe corridors in real time. Once leakage occurs, the leakage location can be determined quickly and accurately, and an early warning can be issued in a timely manner. Compared with the existing technology, the leakage location can be accurately located and the problem can be discovered in a timely manner, greatly improving the supervision efficiency and emergency response capabilities of underground pipe corridor leakage.

[0016] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically described below in conjunction with the drawings in the specification.

[0017] Embodiment 1

[0018] like Figure 1 As shown, the embodiment of the present application provides a method for quickly locating leakage in an underground pipe gallery, the method comprising:

[0019] Determine a target underground utility corridor, obtain a plane distribution map of the target underground utility corridor, perform area division based on the plane distribution map, and obtain N monitoring areas.

[0020] Furthermore, the area division is performed based on the plane distribution map to obtain N monitoring areas, including:

[0021] Set the complexity constraints and adaptive partitioning frame of the pipe gallery, and initialize the adaptive partitioning frame according to the plane distribution diagram;

[0022] Using an adaptive partitioning frame to slide on the plane distribution map to determine a first area to be divided;

[0023] Obtaining the first area corridor complexity of the first area to be divided, and adjusting the first area to be divided according to the first area corridor complexity and the corridor complexity constraint to obtain a first monitoring area;

[0024] The first monitoring area is added to the N monitoring areas.

[0025] Further, obtaining the first monitoring area includes:

[0026] Determine a partition frame adjustment step vector according to the complexity of the pipeline gallery in the first area and the complexity constraint of the pipeline gallery;

[0027] Adjusting the first area to be divided by changing the adaptive division frame based on the division frame adjustment step vector;

[0028] When the pipeline corridor complexity of the first area meets the pipeline corridor complexity constraint, the first area to be divided is determined as the first monitoring area.

[0029] In an embodiment of the present application, the target underground pipeline corridor refers to an underground pipeline corridor facility that needs to be monitored for leakage. The target underground pipeline corridor is composed of several pipeline corridor tunnel sections, including municipal pipelines such as electricity, communications, gas, water supply and drainage. After determining the target underground pipeline corridor, obtain a plan distribution map of the target underground pipeline corridor for subsequent monitoring area division. The plan distribution map is a plan projection map of the target underground pipeline corridor, which reflects the spatial layout and pipeline distribution inside the underground pipeline corridor. Through on-site survey and drawing, professional surveying and mapping personnel carry out pipeline detection and spatial measurement, use total stations, laser rangefinders and other equipment to collect data, and draw a plan distribution map.

[0030] After obtaining the plane distribution map, the area is divided based on the plane distribution map. First, the complexity constraint of the pipeline corridor and the adaptive partition frame are set. Among them, the complexity constraint of the pipeline corridor is a quantitative indicator reflecting the complexity of the internal structure of the pipeline corridor. It is obtained based on parameters such as the number of pipeline types, the frequency of pipeline crossing, and the density of pipelines. The complexity constraint of the pipeline corridor includes a lower limit value and an upper limit value, which respectively represent the minimum and maximum acceptable complexity. The greater the complexity, the more complex the structure of the pipeline corridor is, and the higher the monitoring density is required; the adaptive partition frame is a rectangular window used for the partition of the plane map. Its size is automatically adjusted according to the complexity constraint of the pipeline corridor and the total area of ​​the drawing. At the beginning of the partition, the adaptive partition frame is initialized to a given size and is located in the upper left corner of the plane distribution map. The initial size is set according to experience or converted according to the length and width ratio of the drawing. Then, the adaptive partition frame is used to slide on the plane distribution map to determine the first area to be divided. Specifically, the adaptive partition frame starts from the upper left corner of the plane distribution map and moves on the plane distribution map until it covers the entire drawing. During the sliding process, the area in the frame is a zone to be divided, that is, the first area to be divided. Subsequently, the first area to be divided is taken as the research object, and the pipeline information in the area is extracted. According to the extracted pipeline information, based on the number of pipeline types, pipeline crossing frequency, pipeline density and other parameters, a comprehensive index is obtained through weighted average, nonlinear combination and other mathematical models as the complexity of the pipeline corridor in the first area. For example, the number of different types of pipelines in the first area to be divided is counted separately, and the number of each type of pipeline is weighted and summed to obtain the complexity of pipeline types; then the number of pipeline intersections in the same area is counted to obtain the frequency of pipeline crossing; finally, the two indicators are dimensionless and weighted fused to obtain the complexity of the pipeline corridor in the first area.

[0031] Then, the lower limit of the corridor complexity constraint is recorded as the target complexity lower limit, and the upper limit is recorded as the target complexity upper limit, and the corridor complexity of the first area is compared with the target complexity lower limit and the target complexity upper limit of the corridor complexity constraint. When the corridor complexity of the first area is greater than the target complexity upper limit, the first area to be divided is reduced, and the partition frame adjustment step vector is determined according to the difference between the corridor complexity of the first area and the target complexity upper limit. When the corridor complexity of the first area is less than the target complexity lower limit, the first area to be divided is enlarged, and the partition frame adjustment step vector is determined according to the difference between the corridor complexity of the first area and the target complexity lower limit. Subsequently, the partition frame adjustment step vector is applied to the first area to be divided, and the first area to be divided is adjusted to obtain a new partition frame size, which is the adjusted first area to be divided. Next, it is judged again whether the corridor complexity of the adjusted first area meets the corridor complexity constraint. If it does, the adjusted first area to be divided is determined as the first monitoring area, otherwise it continues to be adjusted. Then, the divided first monitoring area is included in the N monitoring areas. Subsequently, the adaptive partitioning frame is moved to the boundary of the first monitoring area, and the remaining areas are further divided, and the obtained monitoring areas are added to the N monitoring areas one by one until the entire plane distribution map is covered. At this point, the monitoring partitioning of the entire target underground utility corridor is completed, and N monitoring areas are obtained.

[0032] According to the plan distribution map and the N monitoring areas, monitoring points are selected in the N monitoring areas respectively, and a leakage monitoring integrated device is set at each monitoring point;

[0033] Furthermore, the monitoring points are selected, including:

[0034] Cutting the plane distribution map according to the N monitoring areas to obtain N area plane maps;

[0035] A monitoring point selection network is constructed, the N regional plan views are sequentially input into the monitoring point selection network, and the monitoring points are output.

[0036] Furthermore, a monitoring point selection network is constructed, including:

[0037] Based on the underground pipe gallery big data, a regional plan map sample set is obtained, wherein the regional plan map sample set includes a plurality of regional plan map samples;

[0038] Marking monitoring points of the plurality of regional plan map samples to construct a monitoring point sample set;

[0039] Based on a convolutional neural network, a monitoring point selection network is obtained by taking the regional plan map sample set and the monitoring point sample set as training samples.

[0040] In an embodiment of the present application, after obtaining the plan distribution map and N monitoring areas, the monitoring points in each monitoring area are further determined based on the plan distribution map of the corridor and the N monitoring areas obtained by division, and leakage monitoring devices are set at the monitoring points.

[0041] First, the plane distribution map is cut according to the boundaries of N monitoring areas to obtain N regional plane maps. Specifically, the plane distribution map is segmented with the boundary lines of each monitoring area as the cutting path, and an independent regional plane map is generated for each monitoring area. The regional plane map only contains the pipeline distribution information in the area, and the plane maps of different areas do not overlap with each other. This cutting method can simplify the subsequent selection of monitoring points, so that the monitoring points in each area are arranged independently and do not interfere with each other. Then, a monitoring point selection network model is constructed, and the N regional plane maps are input into the model, and the optimal monitoring points of each area are obtained through model reasoning. The monitoring point selection network model is an intelligent algorithm based on deep learning. By learning a large amount of historical data, the inherent laws and optimization strategies of the monitoring point layout are mastered. Afterwards, leakage monitoring integrated devices are arranged on the acquired monitoring points. The leakage monitoring integrated device is a monitoring device composed of a combination of multiple sensors, including gas sensors, flue gas sensors, moisture sensors, and temperature sensors.

[0042] Specifically, in order to build a monitoring point selection network, first of all, we collect underground pipeline corridor big data. Underground pipeline corridor big data refers to the massive heterogeneous data related to underground pipeline corridors, including pipeline corridor plan CAD data, pipeline laying coordinate data, pipeline corridor inspection record data, pipeline corridor environmental monitoring data, etc. The regional plan sample set is extracted from the pipeline corridor big data. It is the training data set of the monitoring point selection network. It is composed of many regional plan samples. Each sample is an independent regional plan small map obtained by cutting a large number of pipeline corridor plan maps. In the specific implementation, the sliding window cutting method is adopted. A sliding window of a fixed size is slid on the entire pipeline corridor plan map, and the local area covered by the window is extracted as a small map sample. All small map samples are summarized and low-quality samples are removed to obtain a complete regional plan sample set. Then, the optimal monitoring point is marked by the professionals of the pipeline corridor on each regional plan sample in the regional plan sample set. The marking process is based on engineering experience and professional knowledge, and comprehensively considers factors such as pipeline distribution, physical properties, leakage risk, and maintenance difficulty. The monitoring point symbols are drawn or edited on the plan sample. Each monitoring point contains attribute information such as spatial coordinates, covered pipelines, and monitoring parameters. After the labeling work is completed, each sample in the regional plan sample set is marked with a set of optimal monitoring points. These labeling results are matched with the original samples to form a complete monitoring point sample set as label data for subsequent network training. Subsequently, based on the convolutional neural network, the regional plan samples in the regional plan sample set are used as input, and the monitoring point samples in the monitoring point sample set are used as output. Through end-to-end learning and training, the inherent laws and decision-making mechanisms of mapping from regional plan to optimal monitoring points are mastered, thereby obtaining a monitoring point selection network.

[0043] A three-dimensional underground pipeline corridor model of the target underground pipeline corridor is established, and the position of the leakage monitoring integrated device is located using UWB wireless carrier communication technology, and the position positioning result is integrated into the three-dimensional underground pipeline corridor model.

[0044] In the embodiment of the present application, the three-dimensional underground pipeline corridor model is a digital reconstruction of the target underground pipeline corridor. It is a virtual environment consistent with the physical target underground pipeline corridor, which reproduces the geometric elements such as the spatial structure and pipeline layout of the pipeline corridor, and also integrates the semantic content such as the attribute parameters and situation information of the pipeline corridor, laying the foundation for subsequent visual monitoring. First, a three-dimensional laser scanner is used to perform an all-round scan of the interior of the pipeline corridor to obtain high-precision point cloud data; then, the point cloud data is pre-processed by filtering, denoising, registration and splicing to obtain a complete and unified point cloud scene; then, skeleton lines are extracted, surfaces are fitted, and objects are reconstructed in the point cloud scene to generate a geometric model of the pipeline corridor; finally, rendering materials are added to the geometric model, and pipeline attributes are bound one by one to form a three-dimensional pipeline corridor model with rich semantic information. After the three-dimensional pipeline corridor model is constructed, the spatial position of the leakage monitoring integrated device is accurately calibrated by UWB wireless positioning technology, and geometric registration is performed with the three-dimensional underground pipeline corridor model. In the tunnel scenario, the UWB positioning system consists of several fixed base stations and mobile tags. The fixed base stations are installed at known locations inside the tunnel, and the mobile tags are integrated in the leakage monitoring integrated device. When the mobile tag is within the coverage of the UWB network, it communicates wirelessly with the surrounding fixed base stations, uses the TWR ranging algorithm to measure the distance to each base station, and then uses three-sided positioning, least squares and other positioning algorithms to solve its own spatial coordinates and determine the position positioning result. After obtaining the position positioning result, it is mapped to the three-dimensional underground tunnel model to synchronize the monitoring results of the leakage monitoring integrated device to the three-dimensional underground tunnel model in real time and present it in a visual form.

[0045] Based on the leakage monitoring integrated device, leakage monitoring is performed on the target underground pipe gallery, and a leakage monitoring result is compared with a leakage discrimination model simultaneously, wherein the leakage discrimination model has a preset leakage constraint;

[0046] In an embodiment of the present application, a leakage monitoring integrated device is used to collect and analyze the environmental parameters inside the target underground tunnel in real time. Among them, the leakage monitoring integrated device integrates a variety of sensors, such as a fuel gas sensor, a humidity sensor, and a temperature sensor, which can synchronously monitor multiple environmental parameters in the tunnel. During the monitoring process, each sensor continuously collects environmental parameter data at a certain frequency to obtain leakage monitoring results, and compares the leakage monitoring results and the leakage discrimination model in the computing center of the leakage monitoring integrated device to determine whether a leakage occurs. Among them, the leakage discrimination model is based on expert experience and historical data summary, and the normal threshold range of each monitoring parameter is set in the model, such as the combustible gas concentration threshold, humidity threshold, temperature threshold, etc. When the monitoring data exceeds the threshold range of the corresponding parameter and lasts for a certain period of time, it can be determined that a leakage has occurred. Once the leakage monitoring result meets the leakage condition of the leakage discrimination model, the subsequent emergency plan is automatically executed, including accurately locating the leakage point, pushing alarm notifications, and directing on-site disposal. Through active early warning methods based on real-time data and intelligent models, the time for discovering and responding to leaks can be shortened to the maximum extent, thereby minimizing the losses and impacts of leaks.

[0047] When the leakage judgment result exceeds the preset leakage constraint in the leakage discrimination model, the leakage position is determined based on the position positioning result.

[0048] In the embodiment of the present application, when the leakage judgment result exceeds the preset leakage constraint in the leakage discrimination model, that is, the monitoring data is judged to be abnormal, and the preset leakage constraint of the leakage discrimination model is satisfied, it means that a leakage accident is likely to have occurred in the target underground pipe gallery, and at this time, the corresponding leakage monitoring integrated device issues a leakage alarm. Then, based on the position positioning result of the leakage monitoring integrated device, the specific position of the leakage monitoring integrated device that issues the leakage alarm is determined and used as the leakage position.

[0049] Early warning information is generated based on the leakage location and the three-dimensional underground pipe gallery model and displayed visually.

[0050] In an embodiment of the present application, the located leakage position is transformed into the corresponding position under the three-dimensional model through a three-dimensional coordinate transformation. In the three-dimensional model of the pipeline corridor, the leakage position is marked in an intuitive visual form such as a heat map and a bubble map. For example, a red highlighted area or a bubble group is generated at the leakage point to intuitively show the spatial distribution range of the leakage; and the leakage area can be mapped to a color level in combination with the leakage degree and the hazard level to intuitively show the severity of the leakage. Based on the leakage position, the attribute information of the leakage point can also be associated in the three-dimensional underground pipeline corridor model. For example, the pipeline type and number, leakage monitoring value, judgment basis, hazard level, emergency measures, etc. to which the leakage point belongs can be marked in an information box to make the leakage information more comprehensive and complete.

[0051] Through three-dimensional visualization of the leakage location, the spatial information advantages of the three-dimensional underground pipeline corridor model can be fully utilized to make the leakage monitoring results more intuitive and comprehensive, greatly improving the efficiency and accuracy of leakage risk perception. Monitoring personnel can quickly locate the leakage point through the visual interface, intuitively assess the severity of the leakage, and optimize the emergency repair plan.

[0052] Furthermore, the embodiment of the present application includes generating a leakage discrimination model:

[0053] The leakage monitoring integrated device includes a gas sensor, a smoke sensor, a moisture sensor and a temperature sensor;

[0054] The threshold parameters of the gas sensor, the smoke sensor, the moisture sensor and the temperature sensor in the N monitoring areas are respectively set to generate the preset leakage constraints of each monitoring area;

[0055] According to the preset leakage constraints of each monitoring area, the leakage discrimination constraint space of each monitoring area is constructed to generate a leakage discrimination model.

[0056] In a feasible implementation, the leakage monitoring integrated device integrates multiple environmental sensors such as gas sensors, flue gas sensors, moisture sensors and temperature sensors. Among them, the gas sensor is used to monitor the concentration of combustible gases, such as methane and natural gas, and can detect gas pipeline leakage in time; the flue gas sensor is used to monitor combustion products such as smoke and carbon monoxide, and can detect fire hazards such as cables and gas pipelines in time; the moisture sensor is used to monitor air humidity and water vapor concentration, and can detect leakage of water supply and drainage pipelines in time; the temperature sensor is used to monitor the temperature change inside the pipe gallery, and can detect leakage of thermal pipelines in time. Then, based on the historical monitoring data of each monitoring area, the normal background value range of each sensor is automatically fitted using a statistical learning method. Taking the humidity sensor as an example, by extracting the historical data of all humidity sensors in the partition, the normal humidity value range of the partition is estimated using methods such as normal distribution and percentiles, so as to determine the threshold parameters of the humidity sensor. If the humidity monitoring value at a certain moment exceeds the threshold parameters of the humidity sensor, it is determined to be abnormal humidity. Similarly, the threshold parameters of gas sensors, flue gas sensors and temperature sensors can also be determined by similar methods. The threshold parameters of each sensor in each monitoring area are organically combined to form the preset leakage constraints of each monitoring area. Subsequently, the preset leakage constraints of each monitoring area are normalized, and the normalized preset leakage constraints are combined to obtain the leakage discrimination constraint space of each monitoring area. Then, the leakage discrimination constraint space of each monitoring area is integrated to construct a leakage discrimination model covering all scenarios.

[0057] Furthermore, the embodiment of the present application also includes:

[0058] Unmanned aerial vehicle groups and crawler robots are respectively configured in the N monitoring areas, and both the unmanned aerial vehicle groups and crawler robots are equipped with high-definition cameras;

[0059] Acquire a related detection position according to the leakage position, send the leakage position to the tracked robot, and send the related detection position to the drone group;

[0060] Based on the drone group and the tracked robot, the leakage location and the associated detection location are inspected, and the inspection results are displayed visually.

[0061] In a preferred embodiment, by combining the ground and aerial robot systems with the leakage monitoring system to form an integrated three-dimensional inspection mechanism, the leakage verification and disposal capabilities can be further enhanced.

[0062] First, drone groups and crawler robots are deployed in each monitoring area, and high-definition cameras are installed on them. Among them, drones are responsible for high-altitude overlooking and global observation, crawler robots are responsible for close-range leakage confirmation and data collection, and high-definition cameras can clearly record the image data inside the pipe gallery, providing an intuitive reference for leakage analysis. When the leakage location is found, the coordinates of the leakage location are sent to the crawler robot in time, and it is directed to go to the vicinity of the leakage location for close-range inspection; at the same time, the associated locations around the leakage location are sent to the drone group, and it is directed to conduct aerial observation of the leakage area. Through the collaboration of the drone group and the crawler robot, the leakage location can be further accurately locked and confirmed, and the scope of leakage impact can be intuitively grasped. Then, the drone group and the crawler robot automatically plan the route and inspection path according to the received location information, and conduct a detailed investigation of the leakage location and related areas. Through the onboard high-definition camera, the drone takes a bird's-eye view of the area above the leakage location and finds traces of leakage; the crawler robot takes close-range images of the surrounding pipelines of the leakage location to capture the detailed characteristics of the leakage. At the same time, the image data collected by drones and robots are integrated with the three-dimensional underground pipe gallery model in real time as inspection results for visualization. Through the visualization interface, the leakage site can be viewed directly, and the emergency response plan can be optimized accordingly, such as adjusting the repair personnel route, optimizing equipment deployment, etc., to improve the pertinence and timeliness of on-site response.

[0063] In summary, the method for quickly locating underground pipe gallery leakage provided by the embodiment of the present application has the following technical effects:

[0064] Determine the target underground utility corridor, obtain the plane distribution map of the target underground utility corridor, divide the area based on the plane distribution map, and obtain N monitoring areas, which provides a basis for regional division for subsequent distributed monitoring, facilitates the deployment of monitoring points, and improves the pertinence and effectiveness of monitoring. According to the plane distribution map and the N monitoring areas, select monitoring points in the N monitoring areas respectively, and set up leakage monitoring integrated devices at each monitoring point. Compared with a single monitoring point, distributed point layout can fully perceive the status of the utility corridor, greatly improving monitoring efficiency and the probability of problem discovery. Establish a three-dimensional underground utility corridor model of the target underground utility corridor, and use UWB wireless carrier communication technology to locate the position of the leakage monitoring integrated device, and integrate the position positioning results into the three-dimensional underground utility corridor model. The fusion of positioning information and three-dimensional model intuitively reflects the spatial distribution of the monitoring device, providing reliable data support for the accurate determination of the leakage location. Based on the leakage monitoring integrated device, the target underground pipe gallery is monitored for leakage, and the leakage monitoring results and the leakage discrimination model are compared synchronously. The leakage discrimination model has preset leakage constraints, and the preset discrimination rules can automatically identify leakage problems without manual supervision, thereby improving the timeliness and reliability of leakage detection. When the leakage judgment result exceeds the preset leakage constraint in the leakage discrimination model, the leakage location is determined based on the position positioning result, and the leakage location is quickly and accurately determined, which is convenient for the first time to start the emergency plan and carry out emergency repair work. Early warning information is generated based on the leakage location and the three-dimensional underground pipe gallery model, and a visual display is performed to present the leakage situation to the management personnel in an intuitive and easy-to-read manner, prompting key information such as the leakage location and degree, which helps to fully perceive the status of the pipe gallery and make timely and correct decisions and disposal.

[0065] Embodiment 2

[0066] Based on the same inventive concept as the method for quickly locating leakage in underground pipe gallery in the aforementioned embodiment, Figure 2 As shown, an embodiment of the present application provides a rapid positioning system for underground pipe gallery leakage, the system comprising:

[0067] A monitoring area acquisition module 11 is used to determine a target underground utility corridor, obtain a plane distribution map of the target underground utility corridor, divide the area based on the plane distribution map, and obtain N monitoring areas;

[0068] A monitoring point selection module 12, for selecting monitoring points in the N monitoring areas respectively according to the plan distribution map and the N monitoring areas, and setting a leakage monitoring integrated device at each monitoring point;

[0069] A three-dimensional model building module 13 is used to build a three-dimensional underground pipe gallery model of the target underground pipe gallery, locate the position of the leakage monitoring integrated device by using UWB wireless carrier communication technology, and integrate the position positioning result into the three-dimensional underground pipe gallery model;

[0070] A leakage discrimination module 14 is used to perform leakage monitoring on the target underground pipe gallery based on the leakage monitoring integrated device, and to synchronously compare the leakage monitoring result with a leakage discrimination model, wherein the leakage discrimination model has a preset leakage constraint;

[0071] A leakage position determination module 15, configured to determine the leakage position based on the position positioning result when the leakage judgment result exceeds the preset leakage constraint in the leakage discrimination model;

[0072] The warning information display module 16 is used to generate warning information based on the leakage location and the three-dimensional underground pipe gallery model, and perform visual display.

[0073] Furthermore, the monitoring area acquisition module 11 includes the following execution steps:

[0074] Set the complexity constraints and adaptive partitioning frame of the pipe gallery, and initialize the adaptive partitioning frame according to the plane distribution diagram;

[0075] Using an adaptive partitioning frame to slide on the plane distribution map to determine a first area to be divided;

[0076] Obtaining the first area corridor complexity of the first area to be divided, and adjusting the first area to be divided according to the first area corridor complexity and the corridor complexity constraint to obtain a first monitoring area;

[0077] The first monitoring area is added to the N monitoring areas.

[0078] Furthermore, the monitoring area acquisition module 11 further includes the following execution steps:

[0079] Determine a partition frame adjustment step vector according to the complexity of the pipeline gallery in the first area and the complexity constraint of the pipeline gallery;

[0080] Adjusting the first area to be divided by changing the adaptive division frame based on the division frame adjustment step vector;

[0081] When the pipeline corridor complexity of the first area meets the pipeline corridor complexity constraint, the first area to be divided is determined as the first monitoring area.

[0082] Furthermore, the monitoring point selection module 12 includes the following execution steps:

[0083] Cutting the plane distribution map according to the N monitoring areas to obtain N area plane maps;

[0084] A monitoring point selection network is constructed, the N regional plan views are sequentially input into the monitoring point selection network, and the monitoring points are output.

[0085] Furthermore, the monitoring point selection module 12 also includes the following execution steps:

[0086] Based on the underground pipe gallery big data, a regional plan map sample set is obtained, wherein the regional plan map sample set includes a plurality of regional plan map samples;

[0087] Marking monitoring points of the plurality of regional plan map samples to construct a monitoring point sample set;

[0088] Based on a convolutional neural network, a monitoring point selection network is obtained by taking the regional plan map sample set and the monitoring point sample set as training samples.

[0089] Furthermore, the embodiment of the present application also includes a leakage discrimination model generation module, which includes the following execution steps:

[0090] The leakage monitoring integrated device includes a gas sensor, a smoke sensor, a moisture sensor and a temperature sensor;

[0091] The threshold parameters of the gas sensor, the smoke sensor, the moisture sensor and the temperature sensor in the N monitoring areas are respectively set to generate the preset leakage constraints of each monitoring area;

[0092] According to the preset leakage constraints of each monitoring area, the leakage discrimination constraint space of each monitoring area is constructed to generate a leakage discrimination model.

[0093] Furthermore, the embodiment of the present application includes a collaborative inspection module, which includes the following execution steps:

[0094] Unmanned aerial vehicle groups and crawler robots are respectively configured in the N monitoring areas, and both the unmanned aerial vehicle groups and crawler robots are equipped with high-definition cameras;

[0095] Acquire a related detection position according to the leakage position, send the leakage position to the tracked robot, and send the related detection position to the drone group;

[0096] Based on the drone group and the tracked robot, the leakage location and the associated detection location are inspected, and the inspection results are displayed visually.

[0097] Any step of the method described above can be stored as a computer instruction or program in an unlimited computer memory, and can be called and recognized by an unlimited computer processor to implement any method in the embodiments of the present application, without any unnecessary restrictions.

[0098] Furthermore, the first or second mentioned above may not only represent an order relationship, but may also represent a specific concept, and / or refer to multiple elements that can be selected individually or in full. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A rapid location method for underground pipe gallery leakage, characterized in that: The method comprises: Determine a target underground utility corridor, obtain a plane distribution map of the target underground utility corridor, perform area division based on the plane distribution map, and obtain N monitoring areas; According to the plan distribution map and the N monitoring areas, monitoring points are selected in the N monitoring areas respectively, and a leakage monitoring integrated device is set at each monitoring point; Establishing a three-dimensional underground pipe gallery model of the target underground pipe gallery, locating the position of the leakage monitoring integrated device by using UWB wireless carrier communication technology, and integrating the position positioning result into the three-dimensional underground pipe gallery model; Based on the leakage monitoring integrated device, leakage monitoring is performed on the target underground pipe gallery, and a leakage monitoring result is compared with a leakage discrimination model simultaneously, wherein the leakage discrimination model has a preset leakage constraint; When the leakage judgment result exceeds the preset leakage constraint in the leakage discrimination model, determining the leakage position based on the position positioning result; Generate early warning information based on the leakage location and the three-dimensional underground pipe gallery model, and display it visually; Based on the plane distribution map, the regions are divided to obtain N monitoring regions, including: Set the pipeline corridor complexity constraint and adaptive partition frame, and initialize the adaptive partition frame according to the plane distribution diagram, wherein the pipeline corridor complexity constraint is a comprehensive indicator obtained by weighted average and nonlinear combination based on the number of pipeline types, pipeline crossing frequency, and pipeline density; Using an adaptive partitioning frame to slide on the plane distribution map to determine a first area to be divided; Obtaining the first area corridor complexity of the first area to be divided, and adjusting the first area to be divided according to the first area corridor complexity and the corridor complexity constraint to obtain a first monitoring area; Adding the first monitoring area to the N monitoring areas; Adjusting the first area to be divided according to the complexity of the pipeline gallery in the first area and the complexity constraint of the pipeline gallery to obtain a first monitoring area; Determine a partition frame adjustment step vector according to the complexity of the pipeline gallery in the first area and the complexity constraint of the pipeline gallery; Adjusting the first area to be divided by changing the adaptive division frame based on the division frame adjustment step vector; When the complexity of the pipeline corridor in the first area satisfies the complexity constraint of the pipeline corridor, determining the first area to be divided as the first monitoring area; Selecting monitoring points in the N monitoring areas respectively according to the plan distribution map and the N monitoring areas includes: Cutting the plane distribution map according to the N monitoring areas to obtain N area plane maps; A monitoring point selection network is constructed, the N regional plan views are sequentially input into the monitoring point selection network, and the monitoring points are output.

2. The method according to claim 1, characterized in that Construct a monitoring point selection network, including: Based on the underground pipe gallery big data, a regional plan map sample set is obtained, wherein the regional plan map sample set includes a plurality of regional plan map samples; Marking monitoring points of the plurality of regional plan map samples to construct a monitoring point sample set; Based on a convolutional neural network, a monitoring point selection network is obtained by taking the regional plan map sample set and the monitoring point sample set as training samples.

3. The method according to claim 1, characterized in that The method further comprises: The leakage monitoring integrated device includes a gas sensor, a smoke sensor, a moisture sensor and a temperature sensor; The threshold parameters of the gas sensor, the smoke sensor, the moisture sensor and the temperature sensor in the N monitoring areas are respectively set to generate the preset leakage constraints of each monitoring area; According to the preset leakage constraints of each monitoring area, the leakage discrimination constraint space of each monitoring area is constructed to generate a leakage discrimination model.

4. The method according to claim 1, characterized in that: The method further comprises: Unmanned aerial vehicle groups and crawler robots are respectively configured in the N monitoring areas, and both the unmanned aerial vehicle groups and crawler robots are equipped with high-definition cameras; Acquire a related detection position according to the leakage position, send the leakage position to the tracked robot, and send the related detection position to the drone group; Based on the drone group and the tracked robot, the leakage location and the associated detection location are inspected, and the inspection results are displayed visually.

5. A rapid positioning system for underground pipe gallery leakage, characterized in that: A method for quickly locating leakage in an underground pipe gallery according to any one of claims 1 to 4, the system comprising: A monitoring area acquisition module, the monitoring area acquisition module is used to determine a target underground utility corridor, obtain a plane distribution map of the target underground utility corridor, perform area division based on the plane distribution map, and obtain N monitoring areas; A monitoring point selection module, the monitoring point selection module is used to select monitoring points in the N monitoring areas according to the plane distribution map and the N monitoring areas, and set a leakage monitoring integrated device at each monitoring point; A three-dimensional model building module, wherein the three-dimensional model building module is used to build a three-dimensional underground pipe gallery model of the target underground pipe gallery, and locate the position of the leakage monitoring integrated device by using UWB wireless carrier communication technology, and integrate the position positioning result into the three-dimensional underground pipe gallery model; A leakage discrimination module, the leakage discrimination module is used to perform leakage monitoring on the target underground pipe gallery based on the leakage monitoring integrated device, and synchronously compare the leakage monitoring results with a leakage discrimination model, wherein the leakage discrimination model has a preset leakage constraint; A leakage position determination module, wherein the leakage position determination module is used to determine the leakage position based on the position positioning result when the leakage judgment result exceeds the preset leakage constraint in the leakage discrimination model; An early warning information display module is used to generate early warning information based on the leakage location and the three-dimensional underground pipe gallery model for visual display.

Images