Large drainage pipe culvert detection method based on multiple sensors

Abstract

The invention relates to the technical field of urban drainage pipeline detection, and discloses a large-scale drainage pipe culvert detection method based on multiple sensors, and the method comprises the steps: carrying a pipeline sonar, a two-dimensional image sonar and a high-definition camera through an unmanned remote control submersible, obtaining first pipeline parameter data of a drainage pipe culvert, and obtaining a first abnormal position point in the drainage pipe culvert; carrying an optical fiber through an unmanned remote control submersible, welding the optical fiber and the distributed optical fiber temperature measurement system, and collecting temperature space-time sequence data in the drainage pipe culvert to obtain a second abnormal position point in the drainage pipe culvert; a high-definition camera and a laser radar are carried by the unmanned aerial vehicle, second pipeline parameter data of the drainage pipe culvert are obtained, and a third abnormal position point in the drainage pipe culvert is obtained; and coupling the data information of the three abnormal position points to obtain the abnormal position points in the drainage pipe culvert. The invention provides a multi-sensor coupled pipe culvert facility defect efficient detection method, which realizes high-precision detection of a large drainage pipe culvert.

Description

Technical Field

[0001] The present invention relates to the technical field of urban drainage pipe detection, and in particular to a large-scale drainage pipe culvert detection method based on multiple sensors. Background Art

[0002] With the acceleration of urbanization, the safety and reliability of urban infrastructure have become increasingly prominent. In particular, large box culverts are an important part of the urban drainage system. Their safety and effectiveness are directly related to the city's flood control and drainage capabilities and operational safety. However, due to the long-term influence of water scouring, soil pressure, geological changes, sewage corrosion and other factors, drainage culverts are prone to structural damage, leakage, blockage and other problems. If these problems are not discovered and repaired in time, they may lead to serious consequences such as urban waterlogging, environmental pollution and road collapse. Therefore, it is very necessary to inspect large drainage culverts.

[0003] Traditional drainage culvert detection methods often rely on manual inspections inside the drainage culverts. This method is not only inefficient, but also poses safety risks when working inside the drainage culverts. It is difficult to meet the needs of modern urban management. In addition, traditional detection methods use a single sensor, which cannot fully obtain pipeline information.

[0004] At the same time, with the development of urban construction, higher requirements are placed on the accuracy, comprehensiveness and real-time performance of drainage culvert detection.

[0005] In view of this, the present invention proposes a large-scale drainage culvert detection method based on multiple sensors to solve the above problems. Summary of the invention

[0006] In view of this, the present invention proposes a large-scale drainage culvert detection method based on multiple sensors, which can detect the abnormal position of the drainage culvert more intelligently, efficiently, comprehensively and accurately to improve the safety of the drainage culvert.

[0007] In one aspect, the present invention proposes a large-scale drainage culvert detection method based on multiple sensors, comprising:

[0008] Acquire first pipeline parameter data of the drainage culvert by using a pipeline sonar, a two-dimensional image sonar and a high-definition camera carried by an unmanned remote-controlled submersible; and obtain a first abnormal position point in the drainage culvert based on the first pipeline parameter data;

[0009] An unmanned remote-controlled submersible is used to carry an optical fiber, lay the optical fiber inside a drainage culvert, and fuse the optical fiber with a distributed optical fiber temperature measurement system;

[0010] Collecting the temperature time-space sequence data in the drainage culvert continuously monitored by the distributed optical fiber temperature measurement system; and obtaining the second abnormal position point in the drainage culvert according to the temperature time-space sequence data;

[0011] When the drainage culvert is running at a low water level and / or the drainage culvert is dry, the second pipe parameter data of the drainage culvert is obtained by using a drone equipped with a high-definition camera and a laser radar;

[0012] Constructing a three-dimensional model of the drainage culvert according to the second pipeline parameter data and the laser radar point cloud data, and obtaining a third abnormal position point in the drainage culvert according to the three-dimensional model;

[0013] The data information of the first abnormal position point, the second abnormal position point and the third abnormal position point are coupled, and the abnormal position point in the drainage culvert is obtained according to the coupled data information.

[0014] Furthermore, the step of obtaining a second abnormal position point in the drainage culvert according to the temperature spatiotemporal series data includes:

[0015] Draw a water temperature spatiotemporal map according to the temperature spatiotemporal series data;

[0016] Obtain the background noise threshold of the current pipe temperature data in the drainage culvert;

[0017] Eliminating background noise of the water temperature spatiotemporal map according to the background noise threshold;

[0018] The abnormal temperature point is determined based on the water temperature spatiotemporal map after eliminating the background noise.

[0019] Furthermore, a method for drawing a water temperature spatiotemporal map based on the temperature spatiotemporal sequence data includes:

[0020] Taking the measurement time series of the temperature spatiotemporal series data as the vertical axis;

[0021] Taking the optical fiber position of the temperature time-space series data as the horizontal axis;

[0022] The measured temperatures of the temperature time-space series data are plotted in different colors within the coordinate axis.

[0023] Furthermore, when constructing a three-dimensional model of the drainage culvert pipeline according to the second pipeline parameter data and the laser radar point cloud data, the step of generating the laser radar point cloud data includes:

[0024] The laser radar is used to emit a laser beam to the inner wall of the drainage culvert and receive the reflected light;

[0025] Recording the reflection time of the reflected light reaching the laser radar;

[0026] Calculate the distance and direction of the inner wall of the drainage culvert pipe according to the speed of light and the reflection time difference;

[0027] According to the distance and orientation of the inner wall of the drainage culvert pipe, three-dimensional point cloud data of the inner wall surface of the drainage culvert pipe is generated.

[0028] Furthermore, when the first pipeline parameter data of the drainage culvert is obtained by using a pipeline sonar, a two-dimensional image sonar and a high-definition camera carried by an unmanned remote-controlled submersible, the pipeline sonar performs information detection on the pipeline structure of the drainage culvert under the water surface.

[0029] Furthermore, when the first pipeline parameter data of the drainage culvert is obtained by using the pipeline sonar, two-dimensional image sonar and high-definition camera equipped with an unmanned remote-controlled submersible, the high-definition camera performs information detection on the pipeline structure of the drainage culvert on the water surface.

[0030] Furthermore, when the second pipe parameter data of the drainage culvert is obtained by using a drone equipped with a high-definition camera and a laser radar, the drone performs a long-distance, non-contact inspection of the drainage culvert pipe.

[0031] Furthermore, the temperature spatiotemporal sequence data includes: sequence data of measured temperature, optical fiber position and measurement time.

[0032] Furthermore, the background noise threshold is determined according to the probability distribution of the temperature difference between two adjacent points in the drainage culvert pipe space.

[0033] Furthermore, the pipeline parameter data includes: image data of the drainage culvert pipeline and pipeline defect information data; the pipeline defect information data includes: the shape of the underwater drainage culvert, the bottom siltation of the drainage culvert, and the damage defects on the structure of the drainage culvert.

[0034] Compared with the prior art, the present invention has the following beneficial effects:

[0035] The method of the present invention realizes real-time monitoring and early warning of the internal environment, structural status and potential risks of drainage culverts by using multiple sensors such as pipeline sonar, two-dimensional image sonar, high-definition camera and laser radar equipped on unmanned submersibles and drones. The correlated fluctuations of the sewage temperature time series in the drainage culvert are analyzed by a distributed optical fiber temperature measurement system to realize dynamic monitoring of the internal conditions of the drainage culvert pipeline and identification of abnormal points. The intelligent and efficient detection process is improved, providing strong technical support for the safety management of urban infrastructure.

[0036] The present invention can generate complementary information or new information by integrating multiple sensor technologies to make the detection of drainage culverts more comprehensive, and couple the data information of multiple sensors to detect abnormal position points of drainage culverts, so as to facilitate the timely discovery of abnormal conditions during pipeline operation, provide an important basis for pipeline maintenance and troubleshooting, reduce the uncertainty of the entire drainage culvert detection process, and improve the accuracy of the detection results. When a sensor fails, other sensors can provide information to troubleshoot, which is conducive to improving the stability and reliability of detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0038] Figure 1 A flowchart of a large-scale drainage culvert detection method based on multiple sensors is provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0039] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art. It should be noted that, in the absence of conflict, the embodiments of the present invention and the features described in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0040] Traditional drainage culvert detection methods often rely on manual inspections inside the drainage culverts. This method is not only inefficient, but also poses safety risks when working inside the drainage culverts. It is difficult to meet the needs of modern urban management. In addition, traditional detection methods use a single sensor, which cannot fully obtain pipeline information.

[0041] At the same time, with the development of urban construction, higher requirements are placed on the accuracy, comprehensiveness and real-time performance of drainage culvert detection.

[0042] Therefore, the present invention proposes a large-scale drainage culvert detection method based on multiple sensors to solve the above problems.

[0043] Reference Figure 1 As shown, in some embodiments of the present application, a large-scale drainage culvert detection method based on multiple sensors includes:

[0044] S1. Obtaining first pipeline parameter data of the drainage culvert by using a pipeline sonar, a two-dimensional image sonar and a high-definition camera carried by an unmanned remote-controlled submersible; and obtaining a first abnormal position point in the drainage culvert according to the first pipeline parameter data;

[0045] S2, using an unmanned remote-controlled submersible to carry an optical fiber, laying the optical fiber inside the drainage culvert, and fusing the optical fiber with a distributed optical fiber temperature measurement system;

[0046] S3, collecting the temperature time-space sequence data in the drainage culvert continuously monitored by the distributed optical fiber temperature measurement system; and obtaining the second abnormal position point in the drainage culvert according to the temperature time-space sequence data;

[0047] S4. When the drainage culvert is running at a low water level and / or the drainage culvert is dry, the second pipe parameter data of the drainage culvert is obtained by using a drone equipped with a high-definition camera and a laser radar;

[0048] S5. constructing a three-dimensional model of the drainage culvert according to the second pipeline parameter data and the laser radar point cloud data, and obtaining a third abnormal position point in the drainage culvert according to the three-dimensional model;

[0049] S6. Couple the data information of the first abnormal location point, the second abnormal location point and the third abnormal location point, and obtain the abnormal location point in the drainage culvert according to the coupled data information.

[0050] Specifically, pipeline sonar uses cross-sectional sonar.

[0051] Specifically, when the drainage culvert is running at a high water level, the inner wall of the drainage culvert is fully inspected and defect information is detected by two-dimensional images and cross-sectional sonar under the water surface to detect the integrity of the inner wall of the culvert and confirm the defects on the inner wall and the bottom siltation. On the water surface, the image of the top of the drainage culvert pipe is collected by a high-definition camera. Combining the cross-sectional information, defect information and image information, a comprehensive judgment can be made to preliminarily obtain an abnormal location point, namely the first abnormal location point.

[0052] Specifically, the distributed fiber optic temperature measurement system conducts continuous detection of drainage culvert pipes with a monitoring length of 360 meters and a monitoring time of 48 hours.

[0053] Specifically, the distributed fiber optic temperature measurement system includes an optical time domain reflectometer, a data interpretation module, a temperature-sensing optical fiber, and a distributed fiber optic temperature meter.

[0054] It can be understood that by analyzing the correlated fluctuations of the sewage temperature time series in the drainage culvert pipe through the distributed optical fiber temperature measurement system, it is possible to realize dynamic monitoring of the internal conditions of the box culvert pipe and identify abnormal points, thereby obtaining the second abnormal location point.

[0055] Specifically, the unmanned submersible can support a variety of external sensor devices and can replace or repair various components and equipment.

[0056] Specifically, the propulsion and control system of the unmanned submersible uses network communication connections to control the operation of external sensors and collect data detected by the external sensors.

[0057] It is understandable that when the drainage culvert is operating at a low water level and / or the drainage culvert is dry, the water volume is small and there is no need to use an unmanned submersible. The drainage culvert can be inspected by a drone equipped with a high-definition camera and a lidar. At this time, the high-definition camera is used to collect images of the drainage culvert on the water surface or when it is dry, and the lidar is used to detect the defect information in the drainage culvert. Combined with the image and defect information in the drainage culvert, the abnormal position point, i.e., the third abnormal position point, can be determined.

[0058] It is understandable that the unmanned remote-controlled submersible inspected the drainage culvert by carrying out pipeline sonar, two-dimensional image sonar and high-definition cameras, and obtained the first abnormal location point; the distributed optical fiber temperature measurement system carried out continuous detection of the drainage culvert and obtained the second abnormal location point; the drone carried out detection of the drainage culvert with high-definition cameras and lidar and obtained the third abnormal location point.

[0059] It can be seen that the method of the present invention realizes real-time monitoring and early warning of the internal environment, structural status and potential risks of the drainage culvert by using multiple sensors such as pipeline sonar, two-dimensional image sonar, high-definition camera and laser radar equipped on unmanned submersibles and drones. The correlated fluctuations of the sewage temperature time series in the drainage culvert are analyzed by the distributed optical fiber temperature measurement system to realize dynamic monitoring of the internal conditions of the drainage culvert pipeline and identification of abnormal points. The intelligent and efficient detection process is improved, providing strong technical support for the safety management of urban infrastructure.

[0060] Reference Figure 1 As shown, in some embodiments of the present application, the step of obtaining a second abnormal position point in the drainage culvert according to the temperature spatiotemporal series data includes:

[0061] S51, drawing a water temperature spatiotemporal map according to the temperature spatiotemporal series data.

[0062] S52: Obtain the background noise threshold of the current pipe temperature data in the drainage culvert.

[0063] S53, eliminating the background noise of the water temperature spatiotemporal map according to the background noise threshold.

[0064] S54, determining the temperature abnormality point according to the water temperature spatiotemporal spectrum after eliminating the background noise.

[0065] Specifically, the water temperature space-time map can display the water temperature at different locations in the drainage culvert through color coding. Warm colors represent high temperature areas, and cold colors represent low temperature areas. By visualizing the temperature data in two dimensions of time and space, the abstract temperature data can be converted into intuitive graphics.

[0066] It is understandable that normal water temperature distribution and changes follow a certain pattern. Once an abnormality occurs, the water temperature at a certain location on the map suddenly rises or drops, and the inspectors can quickly find the abnormal area of ​​temperature distribution.

[0067] Specifically, the historical temperature data of the drainage culverts in different seasons and different periods under normal operation are collected, and the historical temperature data are cleaned by computer algorithms to remove abnormal values ​​caused by sensor failure and data transmission errors. Then the data characteristics of the historical temperature data are calculated, and the background noise threshold range is obtained based on the data characteristics.

[0068] It is understandable that under normal operation, the temperature fluctuation in the drainage culvert exists within a certain range, and the background noise is a random interference within this normal fluctuation range. Through statistical analysis of historical data, we can understand the distribution characteristics of normal temperature and determine a reasonable threshold range to define noise.

[0069] Specifically, according to the temperature data point corresponding to the water temperature spatiotemporal map, it is judged whether it is within the background noise threshold range. If the temperature data point is within the threshold range, it is regarded as background noise and smoothed using a filtering algorithm; if the temperature data point is outside the threshold range, its original value is retained.

[0070] It is understandable that the data points within the background noise threshold range are identified as noise. These noises may be caused by small errors in sensors, random interference from the environment, etc., and are not helpful in reflecting the actual temperature anomalies of drainage culverts. By removing or smoothing these noise data, the water temperature spatiotemporal map can more clearly reflect the actual temperature changes, highlight potential temperature anomaly signals, and provide a more reliable data basis for subsequent accurate judgment of temperature anomaly points.

[0071] Specifically, after eliminating the background noise, the processed data is checked again. Data points that exceed the corrected threshold range are marked as possible temperature anomaly points. The threshold range at this time can be adjusted according to the actual situation, and the threshold range can be appropriately narrowed to improve the sensitivity of detection.

[0072] Reference Figure 1 As shown, in some embodiments of the present application, a method for drawing a water temperature spatiotemporal map according to the temperature spatiotemporal sequence data includes:

[0073] The measurement time series of the temperature spatiotemporal series data is taken as the vertical axis.

[0074] The optical fiber position of the temperature space-time series data is taken as the horizontal axis.

[0075] The measured temperatures of the temperature time-space series data are plotted in different colors within the coordinate axis.

[0076] Reference Figure 1 As shown, in some embodiments of the present application, when constructing a three-dimensional model of the drainage culvert pipeline according to the second pipeline parameter data and the laser radar point cloud data, the step of generating the laser radar point cloud data includes:

[0077] The laser radar is used to emit a laser beam to the inner wall of the drainage culvert and receive the reflected light.

[0078] The reflection time of the reflected light reaching the laser radar is recorded.

[0079] The distance and orientation of the inner wall of the drainage culvert are calculated based on the speed of light and the reflection time difference.

[0080] According to the distance and orientation of the inner wall of the drainage culvert pipe, three-dimensional point cloud data of the inner wall surface of the drainage culvert pipe is generated.

[0081] It can be understood that the second pipeline parameter data is feature matched with the three-dimensional point cloud data of the inner wall surface of the drainage culvert, so that the second pipeline parameter data is fused into a unified three-dimensional point cloud data set, and the fused point cloud data is constructed into a triangular mesh model using a triangular meshing algorithm to preliminarily form a three-dimensional surface model of the inner wall surface of the drainage culvert.

[0082] Reference Figure 1 As shown, in some embodiments of the present application, the pipeline sonar performs information detection on the drainage culvert pipeline structure under the water surface.

[0083] Reference Figure 1 As shown, in some embodiments of the present application, a high-definition camera performs information detection on the drainage culvert pipe structure above the water surface.

[0084] It can be seen that the pipeline sonar and high-definition camera can achieve a comprehensive inspection of the drainage culvert pipeline structure, thereby improving the accuracy of the inspection.

[0085] Reference Figure 1 As shown, in some embodiments of the present application, drones perform long-distance, non-contact inspections of drainage culvert pipes.

[0086] Reference Figure 1As shown, in some embodiments of the present application, the temperature spatiotemporal sequence data includes: sequence data of measured temperature, optical fiber position and measurement time.

[0087] Reference Figure 1 As shown, in some embodiments of the present application, the background noise threshold is determined according to the probability distribution of the temperature difference between two adjacent points in the drainage culvert pipe space.

[0088] Specifically, in the drainage culvert space, along the length of the pipe or other spatial dimensions, a series of adjacent points are selected, the temperature values ​​of each pair of adjacent points are measured and recorded, and then the temperature difference between them is calculated. A large amount of temperature difference data of adjacent points is collected, the frequency of occurrence of different temperature differences is counted, and then the probability distribution of the temperature difference is obtained. Based on the obtained probability distribution, the temperature difference corresponding to a certain probability is selected as the background noise threshold. The temperature difference corresponding to the probability can be selected as the temperature difference corresponding to the point where the probability density begins to drop sharply.

[0089] It can be understood that a temperature difference exceeding the background noise threshold is regarded as a non-background noise factor, and a temperature difference within the background noise threshold is regarded as a normal background noise fluctuation.

[0090] Reference Figure 1 As shown, in some embodiments of the present application, the pipeline parameter data includes: image data of the drainage culvert pipeline and pipeline defect information data.

[0091] Specifically, the pipeline defect information data includes: the shape of the underwater drainage culvert, the siltation at the bottom of the drainage culvert, and the structural damage defects inside the drainage culvert.

[0092] It can be understood that pipeline sonar can detect the shape of underwater drainage culverts, the siltation at the bottom of the drainage culverts, and the structural damage defects inside the drainage culverts; high-definition cameras can detect image data of drainage culvert pipes.

[0093] It can be seen that the method of the present invention realizes real-time monitoring and early warning of the internal environment, structural status and potential risks of the drainage culvert by using multiple sensors such as pipeline sonar, two-dimensional image sonar, high-definition camera and laser radar equipped on unmanned submersibles and drones. The correlated fluctuations of the sewage temperature time series in the drainage culvert are analyzed by the distributed optical fiber temperature measurement system to realize dynamic monitoring of the internal conditions of the drainage culvert pipeline and identification of abnormal points. The intelligent and efficient detection process is improved, providing strong technical support for the safety management of urban infrastructure.

[0094] The present invention can generate complementary information or new information by integrating multiple sensor technologies to make the detection of drainage culverts more comprehensive, and couple the data information of multiple sensors to detect abnormal position points of drainage culverts, so as to facilitate the timely discovery of abnormal conditions during pipeline operation, provide an important basis for pipeline maintenance and troubleshooting, reduce the uncertainty of the entire drainage culvert detection process, and improve the accuracy of the detection results. When a sensor fails, other sensors can provide information to troubleshoot, which is conducive to improving the stability and reliability of detection.

[0095] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0096] The present application is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A gardening device having the functions specified in one or more boxes.

[0097] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including a gardening device that implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0098] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1The steps for the functions specified in one or more boxes.

[0099] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A large-scale drainage culvert detection method based on multiple sensors, characterized in that: include: Acquire first pipeline parameter data of the drainage culvert by using a pipeline sonar, a two-dimensional image sonar and a high-definition camera carried by an unmanned remote-controlled submersible; and obtain a first abnormal position point in the drainage culvert based on the first pipeline parameter data; An unmanned remote-controlled submersible is used to carry an optical fiber, lay the optical fiber inside a drainage culvert, and fuse the optical fiber with a distributed optical fiber temperature measurement system; Collecting the temperature time-space sequence data in the drainage culvert continuously monitored by the distributed optical fiber temperature measurement system; and obtaining the second abnormal position point in the drainage culvert according to the temperature time-space sequence data; When the drainage culvert is running at a low water level and / or the drainage culvert is dry, the second pipe parameter data of the drainage culvert is obtained by using a drone equipped with a high-definition camera and a laser radar; Constructing a three-dimensional model of the drainage culvert according to the second pipeline parameter data and the laser radar point cloud data, and obtaining a third abnormal position point in the drainage culvert according to the three-dimensional model; The data information of the first abnormal position point, the second abnormal position point and the third abnormal position point are coupled, and the abnormal position point in the drainage culvert is obtained according to the coupled data information.

2. A multi-sensor based large-scale drainage culvert detection method according to claim 1, characterized in that: The step of obtaining a second abnormal position point in the drainage culvert according to the temperature time-space series data includes: Draw a water temperature spatiotemporal map according to the temperature spatiotemporal series data; Obtain the background noise threshold of the current pipe temperature data in the drainage culvert; Eliminating background noise of the water temperature spatiotemporal map according to the background noise threshold; The temperature anomaly points are determined based on the water temperature spatiotemporal map after background noise is eliminated.

3. A multi-sensor based large-scale drainage culvert detection method according to claim 2, characterized in that: The method for drawing a water temperature spatiotemporal map according to the temperature spatiotemporal sequence data comprises: Taking the measurement time series of the temperature spatiotemporal series data as the vertical axis; Taking the optical fiber position of the temperature time-space series data as the horizontal axis; The measured temperatures of the temperature time-space series data are plotted in different colors within the coordinate axis.

4. A multi-sensor based large-scale drainage culvert detection method according to claim 1, characterized in that: When constructing a three-dimensional model of the drainage culvert pipeline according to the second pipeline parameter data and the laser radar point cloud data, the step of generating the laser radar point cloud data includes: The laser radar is used to emit a laser beam to the inner wall of the drainage culvert and receive the reflected light; Recording the reflection time of the reflected light reaching the laser radar; Calculate the distance and direction of the inner wall of the drainage culvert pipe according to the speed of light and the reflection time difference; According to the distance and orientation of the inner wall of the drainage culvert pipe, three-dimensional point cloud data of the inner wall surface of the drainage culvert pipe is generated.

5. A large-scale drainage culvert detection method based on multiple sensors according to claim 1, characterized in that: When the first pipeline parameter data of the drainage culvert is obtained by using an unmanned remote-controlled submersible equipped with a pipeline sonar, a two-dimensional image sonar and a high-definition camera, the pipeline sonar performs information detection on the pipeline structure of the drainage culvert under the water surface.

6. A large-scale drainage culvert detection method based on multiple sensors according to claim 1, characterized in that: When the first pipeline parameter data of the drainage culvert is obtained by using an unmanned remote-controlled submersible equipped with a pipeline sonar, a two-dimensional image sonar and a high-definition camera, the high-definition camera performs information detection on the pipeline structure of the drainage culvert on the water surface.

7. A large-scale drainage culvert detection method based on multiple sensors according to claim 1, characterized in that: When the second pipe parameter data of the drainage culvert is obtained by using a drone equipped with a high-definition camera and a laser radar, the drone performs a long-distance, non-contact inspection of the drainage culvert pipe.

8. A multi-sensor based large-scale drainage culvert detection method according to claim 2, characterized in that: The temperature time-space sequence data includes: sequence data of measured temperature, optical fiber position and measurement time.

9. A multi-sensor based large-scale drainage culvert detection method according to claim 2, characterized in that: The background noise threshold is determined according to the probability distribution of the temperature difference between two adjacent points in the drainage culvert pipeline space.

10. A large-scale drainage culvert detection method based on multiple sensors according to claim 1, characterized in that: The pipeline parameter data includes: image data of the drainage culvert pipeline and pipeline defect information data; the pipeline defect information data includes: the shape of the underwater drainage culvert, the bottom siltation of the drainage culvert, and the damage defects on the structure of the drainage culvert.

Images