Joint inspection method and system

Abstract

The present application relates to a joint inspection method and system, which utilizes a drone to automatically move to a position to be inspected according to a flight mission route, and to capture a target image after hovering. After completing the capture of the target image of the current position to be inspected, the drone automatically moves to the next position to be inspected according to the flight mission route, until completing the capture of the target images of all positions to be inspected, and then returns to the starting position; the acquired target image is sent to the central controller. The central controller calls the training library to identify the target in the target image, and generates a wall coking detection result of the boiler; based on the wall coking detection result, a wall climbing robot inspection route is generated. The wall climbing robot performs wall thickness measurement inspections according to the inspection route. Compared with the traditional manual inspection method, the full process of heating surface inspection in the furnace is automated, intelligent, and easy to operate, effectively shortening the heating surface inspection cycle, improving inspection efficiency, and reducing maintenance costs and the risk of personnel working in dangerous areas.

Description

Technical Field

[0001] The present application relates to the technical field of nondestructive testing, and in particular to a combined inspection method and system. Background Art

[0002] In the coal-fired boiler furnace of a large thermal power station, high-temperature corrosion near the main burner of the water-cooled wall and the hard damage of the cold ash hopper are becoming more and more prominent, macro cracks in the pipes near the soot blower are repeatedly found, the partition screen is locally thermally fatigued, the mechanical properties of the 12Cr1MoVG inlet pipe are lower than the lower limit of the standard value, the highest spheroidization level has reached 4.5, the ceiling superheater has sunk, the threat of the flue gas corridor in the tail flue has always existed, the deformation and aging of the heating surface in the furnace are becoming more and more prominent, and the maintenance tasks are also increasing. The power plant regularly conducts inspections of the heating surface in the furnace every year, mainly relying on manual scaffolding and handheld instruments to complete the inspection and detection tasks. It is an internal space high-altitude operation, the light in the furnace is poor, the concentration of inhalable particulate matter is high, and it has the characteristics of poor working environment, high risk, low efficiency, limited inspection area, long cycle and high cost.

[0003] The above furnace maintenance operation method has been used in the power industry at home and abroad for decades. Except for the technical upgrade of detection equipment and tools, there is no essential change, and the goal of safe, efficient and fast inspection has not been achieved. The furnace maintenance personnel work for a long time, and diseases occur due to inhalation of particulate matter, and the detection efficiency is low. Therefore, there is a lack of equipment and methods to replace manual labor to achieve rapid inspection of the heating surface in the furnace. Summary of the invention

[0004] Based on this, the present application provides a joint inspection method and system to address the above technical issues.

[0005] The present application provides a joint inspection method, comprising:

[0006] The drone automatically moves to the location to be inspected according to the flight mission route, and takes images of the target after hovering;

[0007] After completing the target image shooting of the current position to be inspected, the UAV automatically moves to the next position to be inspected according to the flight mission route, and returns to the starting position after completing the target image shooting of all the positions to be inspected;

[0008] Sending the acquired target image to a central controller;

[0009] The central controller calls the training library to identify the target in the target image and generates a boiler wall coking detection result;

[0010] Generate a wall-climbing robot inspection route according to the wall coking detection result;

[0011] The wall-climbing robot performs wall thickness measurement inspection according to the inspection route.

[0012] In one embodiment, the step of generating an inspection route of a wall-climbing robot according to the wall coking detection result comprises:

[0013] Determining the coking position according to the wall coking detection result;

[0014] The inspection route is generated according to the coking position so that the wall-climbing robot avoids the coking position.

[0015] In one embodiment, the step of obtaining the flight mission route includes:

[0016] Using a three-dimensional positioning signal transmitting device to establish a three-dimensional positioning model of the boiler;

[0017] The flight mission route is generated according to the received flight instruction and the three-dimensional positioning model, and the flight mission route includes the coordinate information of each position to be inspected.

[0018] In one embodiment, it also includes:

[0019] When the wall-climbing robot is conducting a wall thickness measurement inspection according to the inspection route, a drone is used to perform video monitoring of the wall-climbing robot.

[0020] In one embodiment, it also includes:

[0021] The wall-climbing robot compares the detected wall thickness information with a threshold to determine whether there is a defect and marks the defect location.

[0022] In one embodiment, it also includes:

[0023] Sending the detected wall thickness information and the defect location to the central controller;

[0024] The central controller controls the UAV or the wall-climbing robot to recheck the defect location according to the wall thickness information and the defect location.

[0025] Based on the same inventive concept, the present application provides a joint inspection system, including:

[0026] The drone system is used to automatically move to the position to be inspected according to the flight mission route, and photograph the target image after hovering; when the target image of the current position to be inspected is photographed, the drone system controls the drone to automatically move to the next position to be inspected according to the flight mission route, and returns to the starting position after the target images of all the positions to be inspected are photographed;

[0027] The central controller is used to obtain the target image, call the training library to identify the target in the target image, generate the wall coking detection result of the boiler, and generate the inspection route of the wall climbing robot according to the wall coking detection result;

[0028] The wall-climbing robot system is used to control the wall-climbing robot to perform wall thickness measurement inspection according to the inspection route.

[0029] In one embodiment, the central controller includes an identification module and a task formulation module, the identification module is used to determine the coking position according to the wall coking detection result, and the task formulation module is used to generate the inspection route according to the coking position so that the wall-climbing robot avoids the coking position.

[0030] In one embodiment, the central controller also includes a three-dimensional model management module, which is used to establish a three-dimensional positioning model of the boiler using a three-dimensional positioning signal transmitting device. The task formulation module is also used to generate the flight mission route based on the received flight instructions and the three-dimensional positioning model, and the flight mission route includes the coordinate information of each position to be inspected.

[0031] In one of the embodiments, the wall-climbing robot system is also used to compare the detected wall thickness information with a threshold to determine whether there is a defect and mark the defect location. The wall-climbing robot system sends the detected defect location to the central controller, and the central controller generates a three-dimensional data report based on all defect locations obtained in a patrol mission.

[0032] In the above-mentioned joint inspection method and system, the drone is first used to automatically move to the position to be inspected according to the flight mission route, and the target image is captured after hovering. After the target image of the current position to be inspected is captured, the drone automatically moves to the next position to be inspected according to the flight mission route until the target image of all the positions to be inspected is captured, and then returns to the starting position. Secondly, the acquired target image is sent to the central controller. The central controller calls the training library to identify the target in the target image and generates the wall coking detection result of the boiler. Finally, the wall climbing robot inspection route is generated according to the wall coking detection result. The wall climbing robot performs wall thickness measurement inspection according to the inspection route. The present application prevents the drone from colliding with the wall of the boiler in a dark environment by pre-setting the flight mission route, and then realizes autonomous flight. The drone and the wall climbing robot jointly inspect, firstly, the drone is used to scan the furnace of the boiler as a whole, automatically recognize the image to help the maintenance personnel quickly analyze and determine the key inspection area, and generate the wall climbing robot inspection route. The wall climbing robot completes the wall thickness measurement inspection task according to the inspection route. Compared with the traditional manual inspection method, the whole process of heating surface inspection in the furnace is automated, intelligent and easy to operate, which effectively shortens the inspection cycle of the heating surface, improves the inspection efficiency, and reduces the maintenance cost and the risk of personnel working in dangerous areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the conventional technology, the drawings required for use in the embodiments or the conventional technology descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0034] Figure 1 A schematic diagram of a joint inspection method flow chart provided for one embodiment of the present application;

[0035] Figure 2 A schematic diagram of a joint inspection method flow chart provided for another embodiment of the present application;

[0036] Figure 3 A schematic diagram of the structure of a joint inspection system provided for one embodiment of the present application;

[0037] Figure 4 A schematic diagram of the structure of a joint inspection system provided for another embodiment of the present application.

[0038] Description of main component reference numbers

[0039] 10. UAV system; 20. Central controller; 21. Identification module; 22. Task formulation module; 23. Three-dimensional model management module; 30. Wall-climbing robot system. DETAILED DESCRIPTION

[0040] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are described in detail below in conjunction with the accompanying drawings. In the following description, many specific details are set forth to facilitate a full understanding of the present application. However, the present application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without violating the connotation of the present application, so the present application is not limited by the specific implementation disclosed below.

[0041] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, without departing from the scope of this application, a first acquisition module may be referred to as a second acquisition module, and similarly, a second acquisition module may be referred to as a first acquisition module. Both the first acquisition module and the second acquisition module are acquisition modules, but they are not the same acquisition module.

[0042] It should be noted that when an element is referred to as being "disposed on" another element, it may be directly on the other element or there may be an intermediate element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be an intermediate element at the same time.

[0043] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0044] Based on this, see Figure 1 The present application provides a joint inspection method. The joint inspection method comprises:

[0045] S10, the UAV automatically moves to the inspection location according to the flight mission route, and takes images of the target after hovering;

[0046] S20, when the target image of the current position to be inspected is captured, the UAV automatically moves to the next position to be inspected according to the flight mission route, and returns to the starting position after the target image of all positions to be inspected is captured;

[0047] S30, sending the acquired target image to a central controller;

[0048] S40, the central controller calls the training library to identify the target in the target image and generates a boiler wall coking detection result;

[0049] S50, generating an inspection route for a wall-climbing robot according to the wall coking detection result;

[0050] S60, the wall-climbing robot performs a wall thickness inspection according to the inspection route.

[0051] It should be noted that the above-mentioned joint inspection method can be applied to the detection of heating surfaces in coal-fired boilers of large thermal power plants. Water cooling pipes are laid on the heating surfaces (walls) in coal-fired boilers. The above-mentioned joint inspection method can detect problems such as deformation and aging of water cooling pipes due to heat.

[0052] Before the inspection, the platform can be built and the spatial positioning signal can be set. Specifically, the simple platform and the three-dimensional positioning signal transmitter can be transported into the furnace through the 80cm×70cm manhole about 10 meters away from the boiler, and a simple platform can be set up in the top area of ​​the cold ash hopper in the boiler furnace. The simple platform is used to arrange the three-dimensional positioning signal transmitter in the furnace. Furthermore, the setting can be adjusted to select the position of the center area of ​​the platform as the zero point of the three-dimensional space coordinates in the furnace, and the circular area with a radius of 0.5 meters and the zero point as the center is set as the automatic take-off and landing platform for the drone. Taking the zero point of the drone coordinates as the origin (i.e. the center of the simple platform), the furnace area space is divided into 4 faces, namely the front, back, left and right, and the three-dimensional positioning model of the boiler is established through the three-dimensional positioning signal transmitter. It should be noted that, since the platform needs to be rebuilt and the spatial positioning signal needs to be set up again before each inspection, in order to avoid manual errors, the three-dimensional positioning model needs to be recalibrated before each inspection to ensure that the coordinate positioning carried by the detection data is consistent with the physical space position.

[0053] In step S10, the step of obtaining the flight mission route may include: using a three-dimensional positioning signal transmitting device to establish a three-dimensional positioning model of the boiler; generating the flight mission route according to the received flight instructions and the three-dimensional positioning model. The flight mission route includes the coordinate information of each of the positions to be inspected. The flight instruction may include the number of positions to be inspected and the physical space position. The flight mission route can be displayed on the terminal console display so that the staff can control the flight mission route of the drone on the display. After the flight mission route is determined, it can be determined whether the power of the drone meets the minimum flight market requirements (the minimum flight time is determined by testing). If so, it will take off. If not, it will prompt to replace the battery.

[0054] Many inspection locations can be set up in one flight mission. When the drone reaches a location to be inspected, the coordinates are confirmed again; then the heated surface is photographed to obtain the target image. The drone has the necessary anti-collision and anti-stuck functions. It is generally equipped with temperature sensors, high-definition image sensors, thermal infrared imaging sensors and ranging devices. The camera has a self-cleaning function. The real-time detection image of the drone can be synchronously transmitted to the central controller on the simple platform by wireless means, and then transmitted to the data analysis and management center through a wired network. The drone's ranging device can obtain the relative position of the target image and the hovering point, so that each target image can be labeled with a position tag (the coordinate information of the target image can be obtained based on the coordinates of the hovering point and the relative position of the target image and the hovering point).

[0055] The specific steps included in step S20 may be that the drone takes pictures, and can start from the first autonomous detection point (the position to be inspected). The drone maintains a stable hovering position of one meter away from the surface of the heated surface through flight control and autonomous hovering control. Through the cooperation of the intelligent fill light system, the heated surface is automatically photographed twice in a row, and the image resolution is 1mm*1mm. Then, the drone flies horizontally or vertically to the next photo point. After completing the inspection and shooting tasks for all preset points according to the flight route, the drone returns to the drone landing platform based on the three-dimensional spatial positioning information.

[0056] In steps S30 and S40, the drone photography can be to divide the single-sided heating surface into grids in horizontal and vertical forms, and the geometric center of the grid is the vertical coordinate of the aircraft hovering, and the corresponding hovering coordinates of the aircraft are obtained by conversion; when the single-sided heating surface autonomous inspection and photography task is completed, the data can be uniformly transmitted back to the central controller, and then transmitted to the server platform of the engineer station outside the furnace via the network, and spliced ​​into a large picture; each picture uses the image intelligent algorithm to identify abnormal conditions such as dust accumulation and coking on the surface of the heating surface, and the abnormal pictures are uniformly pushed to generate a test result report, and the overall distribution of defects is viewed by splicing large pictures to help production personnel conduct relevant analysis. The image intelligent algorithm can be an image recognition convolution deep learning algorithm. Of course, the image intelligent algorithm can also use other algorithms that can identify targets in the target image.

[0057] In step S50, although the wall-climbing robot can move forward and backward along the water-cooled wall tubes on the heated surface of the water-cooled wall, or move horizontally between the water-cooled wall tube rows to perform the detection task. The wall-climbing robot has a certain obstacle-crossing ability (local deformation and coking of the water-cooled wall), and is conventionally equipped with temperature sensors, high-definition image sensors and thermal infrared imaging sensors, and electromagnetic ultrasonic wall thickness measuring devices. The camera should have a self-cleaning function. However, when a large area of ​​coking occurs on the heated surface, the wall-climbing robot may fail to cross the obstacle and fall off the heated surface, causing the inspection to fail. Therefore, a drone is used to scan the entire furnace first, and the automatic image recognition helps maintenance personnel to quickly analyze and determine the key inspection areas, coking locations and areas, and then the inspection route can be generated based on the coking locations and coking areas, so that the wall-climbing robot avoids large areas of coking locations and completes the detection task.

[0058] In step S60, when the wall-climbing robot performs a wall thickness measurement inspection according to the inspection route, the detected wall thickness information can be transmitted back to the central controller in real time. The wall-climbing robot can also compare the detected wall thickness information with the threshold to determine whether there is a defect. Of course, the step of determining whether there is a defect can also be performed in the central controller. The defect can be the expansion of the water-cooling pipe due to heat or the thinning of the wall of the water-cooling pipe. The wall-climbing robot is provided with a paint spraying port. When it is determined that this inspection position has a defect, the paint spraying port of the wall-climbing robot can be used to spray paint this inspection position to mark the defective position. Workers can inspect the water-cooling pipe according to the marked position.

[0059] In this embodiment, the drone is first used to automatically move to the position to be inspected according to the flight mission route, and the target image is captured after hovering. After the target image of the current position to be inspected is captured, the drone automatically moves to the next position to be inspected according to the flight mission route until the target images of all the positions to be inspected are captured, and then returns to the starting position. Secondly, the acquired target image is sent to the central controller. The central controller calls the training library to identify the target in the target image and generates the wall coking detection result of the boiler. Finally, the wall climbing robot inspection route is generated according to the wall coking detection result. The wall climbing robot performs wall thickness measurement inspection according to the inspection route. The present application prevents the drone from colliding with the wall of the boiler in a dark environment by pre-setting the flight mission route, and then realizes autonomous flight. The drone and the wall climbing robot jointly inspect, firstly, the drone is used to scan the furnace of the boiler as a whole, and the image is automatically recognized to help the maintenance personnel quickly analyze and determine the key inspection area, and generate the wall climbing robot inspection route. The wall climbing robot completes the wall thickness measurement inspection task according to the inspection route. Compared with the traditional manual inspection method, the whole process of heating surface inspection in the furnace is automated, intelligent and easy to operate, which effectively shortens the inspection cycle of the heating surface, improves the inspection efficiency, and reduces the maintenance cost and the risk of personnel working in dangerous areas.

[0060] Please also see Figure 2 In one embodiment, the joint inspection method further includes:

[0061] When the wall-climbing robot is conducting wall thickness inspection according to the inspection route, the wall-climbing robot is monitored by a drone. The drone can transmit the video monitoring information of the wall-climbing robot back to the central controller in real time, so that the staff can adjust the inspection route of the wall-climbing robot at any time according to the video monitoring information, so that the wall-climbing robot can complete the inspection task well.

[0062] In one embodiment, the joint inspection method further includes:

[0063] The detected wall thickness information and the defect location are sent to the central controller; the central controller controls the drone or the wall-climbing robot to recheck the defect location based on the wall thickness information and the defect location. When it is determined that the defect may need repair based on the wall thickness information and the defect location, the drone or the wall-climbing robot is controlled to recheck the defect location to obtain more comprehensive information to facilitate further determination of whether repair is needed.

[0064] In one embodiment, the joint inspection method further includes:

[0065] sending the detected defect location to the central controller;

[0066] The central controller generates a three-dimensional data report based on all defect positions obtained in one inspection task.

[0067] It can be understood that the three-dimensional data report can reflect the number of all defect points detected by the wall-climbing robot in this inspection task, and the three-dimensional point coordinates of each defect point in the coal-fired boiler furnace can be viewed in the three-dimensional data report.

[0068] See also Figure 3 Based on the same inventive concept, the present application provides a joint inspection system. The joint inspection system includes a drone system 10, a central controller 20 and a wall-climbing robot system 30.

[0069] The drone system 10 is used to automatically move to the position to be inspected according to the flight mission route, and take a target image after hovering; when the target image of the current position to be inspected is taken, the drone system 10 controls the drone to automatically move to the next position to be inspected according to the flight mission route, until the target images of all the positions to be inspected are taken, and then returns to the starting position. The central controller 20 is used to obtain the target image, call the training library to identify the target in the target image, generate the wall coking detection result of the boiler, and generate the wall climbing robot inspection route according to the wall coking detection result. The wall climbing robot system 30 is used to control the wall climbing robot to perform wall thickness measurement inspection according to the inspection route.

[0070] The drone system 10 may have the necessary functions including anti-collision and anti-stuck functions, conventionally configured temperature sensors, high-definition image sensors, thermal infrared imaging sensors and distance measuring devices, and the camera has a self-cleaning function. The drone system 10 may also include a gimbal, a GPS module and a gyroscope.

[0071] The wall-climbing robot system 30 has a certain obstacle-crossing capability (local deformation and coking of the water-cooled wall), and is conventionally equipped with a temperature sensor, a high-definition image sensor and a thermal infrared imaging sensor, and an electromagnetic ultrasonic wall thickness measuring device. The camera should have a self-cleaning function.

[0072] The structure of the central controller 20 is not specifically limited, as long as the above functions can be realized. The joint inspection system of the present application can realize the above joint inspection method.

[0073] See also Figure 4In one embodiment, the central controller 20 includes an identification module 21 and a task formulation module 22, wherein the identification module 21 is used to determine the coking position according to the wall coking detection result, and the task formulation module 22 is used to generate the inspection route according to the coking position so that the wall-climbing robot avoids the coking position.

[0074] In one embodiment, the central controller 20 also includes a three-dimensional model management module 23, which is used to establish a three-dimensional positioning model of the boiler using a three-dimensional positioning signal transmitting device. The task formulation module 22 is also used to generate the flight mission route based on the received flight instructions and the three-dimensional positioning model, and the flight mission route includes the coordinate information of each position to be inspected.

[0075] In one embodiment, the wall-climbing robot system 30 is also used to compare the detected wall thickness information with a threshold value to determine whether there is a defect and mark the defect position. The wall-climbing robot system sends the detected defect position to the central controller, and the central controller generates a three-dimensional data report based on all defect positions obtained in a patrol mission. When it is determined that the defect may need repair based on the wall thickness information and the defect position, the drone or the wall-climbing robot is controlled to review the defect position to obtain more comprehensive information to facilitate further determination of whether repair is required.

[0076] The step of obtaining the flight mission route may include: using a three-dimensional positioning signal transmitting device to establish a three-dimensional positioning model of the boiler; generating the flight mission route according to the received flight instructions and the three-dimensional positioning model. The flight mission route includes the coordinate information of each of the positions to be inspected. The flight instruction may include the number of positions to be inspected and the physical space position. The flight mission route can be displayed on the terminal console display so that the staff can control the flight mission route of the drone on the display. After the flight mission route is determined, it can be determined whether the power of the drone meets the minimum flight market requirements (the minimum flight time is determined by testing). If so, take off. If not, it will prompt to replace the battery.

[0077] Many inspection positions can be set up in one flight mission. When the drone reaches a certain inspection position, the coordinates are confirmed again; then the heated surface is photographed to obtain the target image. The drone has the necessary anti-collision and anti-stuck functions, and is conventionally equipped with temperature sensors, high-definition image sensors, thermal infrared imaging sensors and ranging devices. The camera has a self-cleaning function. The real-time detection image of the drone can be synchronously transmitted to the central controller 20 on the simple platform via wireless, and then transmitted to the data analysis and management center via a wired network. The ranging device of the drone can obtain the relative position of the target image and the hovering point, so that each target image can be labeled with a position tag (the coordinate information of the target image can be obtained based on the coordinates of the hovering point and the relative position of the target image and the hovering point).

[0078] The drone can take pictures starting from the first autonomous detection point (the position to be inspected). The drone uses flight control and autonomous hovering control to maintain a stable hovering position one meter away from the heated surface. With the cooperation of the intelligent fill light system, it takes two consecutive automatic photos of the heated surface with an image resolution of 1mm*1mm, and then flies horizontally or vertically to the next photo point. After completing the inspection and shooting tasks for all preset points according to the flight route, the drone returns to the drone landing platform based on the three-dimensional spatial positioning information.

[0079] Drone photography can be done by dividing the single-sided heating surface into grids in horizontal and vertical forms. The geometric center of the grid is the vertical coordinate of the aircraft hovering, and the corresponding hovering coordinates of the aircraft are obtained by conversion; after completing the single-sided heating surface autonomous inspection and photography task, the data can be uniformly transmitted back to the central controller 20, and then transmitted to the server platform of the engineer station outside the furnace via the network, and spliced ​​into a large picture; each picture uses an image intelligent algorithm to identify abnormal conditions such as dust accumulation and coking on the surface of the heating surface, and the abnormal pictures are uniformly pushed to generate a test result report, and the overall distribution of defects can be viewed by splicing large pictures to help production personnel conduct relevant analysis. The image intelligent algorithm can be an image recognition convolution deep learning algorithm. Of course, the image intelligent algorithm can also use other algorithms that can identify targets in the target image.

[0080] Although the wall-climbing robot can move forward and backward along the water-cooled wall tubes on the heated surface of the water-cooled wall, or move horizontally between the water-cooled wall tube rows to perform inspection tasks. The wall-climbing robot has a certain obstacle-crossing ability (local deformation and coking of the water-cooled wall), and is conventionally equipped with temperature sensors, high-definition image sensors and thermal infrared imaging sensors, and electromagnetic ultrasonic wall thickness measuring devices. The camera should have a self-cleaning function. However, when a large area of ​​coking occurs on the heated surface, the wall-climbing robot may fail to cross the obstacle and fall off the heated surface, causing the inspection to fail. Therefore, a drone is used to scan the entire furnace first, and the automatic image recognition helps maintenance personnel quickly analyze and determine the key inspection areas, coking locations and areas, and then the inspection route can be generated based on the coking locations and coking areas, so that the wall-climbing robot can avoid large areas of coking locations and complete the inspection task.

[0081] When the wall-climbing robot performs wall thickness measurement inspection according to the inspection route, the detected wall thickness information can be transmitted back to the central controller 20 in real time. The wall-climbing robot can also compare the detected wall thickness information with the threshold to determine whether there is a defect. Of course, the step of determining whether there is a defect can also be performed in the central controller 20. The defect can be the expansion of the water-cooling pipe due to heat or the thinning of the wall of the water-cooling pipe. A paint spraying port is provided on the wall-climbing robot. When it is determined that this inspection position has a defect, the paint spraying port of the wall-climbing robot can be used to spray paint this inspection position to mark the defective position. Workers can inspect the water-cooling pipe according to the marked position.

[0082] When the wall-climbing robot performs wall thickness inspection according to the inspection route, the wall-climbing robot is monitored by a drone. The drone can transmit the video monitoring information of the wall-climbing robot back to the central controller 20 in real time, so that the staff can adjust the inspection route of the wall-climbing robot according to the video monitoring information at any time, so that the wall-climbing robot can complete the inspection task well.

[0083] In this embodiment, the flight mission route is pre-set to prevent the UAV from colliding with the wall of the boiler in a dark environment, thereby achieving autonomous flight. The UAV and the wall-climbing robot jointly inspect the boiler. First, the UAV is used to scan the furnace of the boiler as a whole. The automatic image recognition helps the maintenance personnel to quickly analyze and determine the key inspection areas, and generate the inspection route of the wall-climbing robot. The wall-climbing robot completes the wall thickness inspection task according to the inspection route. Compared with the traditional manual inspection method, the full process of heating surface inspection in the furnace is automated, intelligent, and easy to operate, which effectively shortens the inspection cycle of the heating surface, improves the inspection efficiency, and reduces the maintenance cost and the risk of personnel working in dangerous areas.

[0084] The present application provides a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the joint inspection method described in any one of the above embodiments when executing the computer program.

[0085] The memory, as a computer-readable storage medium, can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the magnetic resonance imaging method in the embodiment of the present application. The processor executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory, that is, realizing the above-mentioned joint inspection method.

[0086] The memory may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function. The data storage area may store data created according to the use of the terminal, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0087] In this embodiment, the above-mentioned computer device implements the above-mentioned joint inspection method, firstly, the drone is used to automatically move to the position to be inspected according to the flight mission route, and the target image is captured after hovering. After the target image of the current position to be inspected is captured, the drone automatically moves to the next position to be inspected according to the flight mission route, until the target image of all the positions to be inspected is captured, and then returns to the starting position. Secondly, the acquired target image is sent to the central controller. The central controller calls the training library to identify the target in the target image and generates the wall coking detection result of the boiler. Finally, the wall climbing robot inspection route is generated according to the wall coking detection result. The wall climbing robot performs wall thickness measurement inspection according to the inspection route. The present application prevents the drone from colliding with the wall of the boiler in a dark environment by pre-setting the flight mission route, and then can realize autonomous flight. The drone and the wall climbing robot jointly inspect, firstly, the drone is used to scan the furnace of the boiler as a whole, automatically recognize the image to help the maintenance personnel quickly analyze and determine the key inspection area, and generate the wall climbing robot inspection route. The wall climbing robot completes the wall thickness measurement inspection task according to the inspection route. Compared with the traditional manual inspection method, the whole process of heating surface inspection in the furnace is automated, intelligent and easy to operate, which effectively shortens the inspection cycle of the heating surface, improves the inspection efficiency, and reduces the maintenance cost and the risk of personnel working in dangerous areas.

[0088] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0089] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the patent application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent application shall be subject to the attached claims.

Claims

1. A joint inspection method, characterized in that: include: The drone automatically moves to the position to be inspected according to the flight mission route, and takes a target image after hovering; the flight mission route contains the coordinate information of each position to be inspected; the distance measuring device of the drone obtains the relative position of the target image and the hovering point, so that each target image has a position label; After completing the target image shooting of the current position to be inspected, the UAV automatically moves to the next position to be inspected according to the flight mission route, and returns to the starting position after completing the target image shooting of all the positions to be inspected; Sending the acquired target image to a central controller; The central controller calls the training library to identify the target in the target image and generates a boiler wall coking detection result; Generate a wall-climbing robot inspection route according to the wall coking detection result; The wall-climbing robot performs wall thickness inspection according to the inspection route; The step of generating an inspection route for a wall-climbing robot according to the wall coking detection result comprises: Determining the coking position according to the wall coking detection result; According to the coking position, generating the inspection route so that the wall-climbing robot avoids the coking position; The central controller calls the training library to identify the target in the target image and generates a boiler wall coking detection result, including: The target images are spliced ​​to obtain a spliced ​​image, and the dust and coking results on the surface of the heating surface are identified by an image intelligent algorithm to obtain the wall coking detection result of the boiler.

2. The joint inspection method according to claim 1, characterized in that: The steps of obtaining the flight mission route include: Using a three-dimensional positioning signal transmitting device to establish a three-dimensional positioning model of the boiler; The flight mission route is generated according to the received flight instruction and the three-dimensional positioning model, and the flight mission route includes the coordinate information of each position to be inspected.

3. The joint inspection method according to claim 2, characterized in that: The flight instruction includes the number and physical space location of the positions to be inspected; the flight mission route is displayed on the terminal console display so that the staff can control the flight mission route of the UAV on the display.

4. The joint inspection method according to claim 1, characterized in that: Also includes: When the wall-climbing robot is conducting a wall thickness measurement inspection according to the inspection route, a drone is used to perform video monitoring of the wall-climbing robot.

5. The joint inspection method according to claim 1, characterized in that: Also includes: The wall-climbing robot compares the detected wall thickness information with a threshold to determine whether there is a defect and marks the defect location.

6. The joint inspection method according to claim 5, characterized in that: Also includes: Sending the detected wall thickness information and the defect location to the central controller; The central controller controls the UAV or the wall-climbing robot to recheck the defect location according to the wall thickness information and the defect location.

7. A joint inspection system, characterized in that: include: The unmanned aerial vehicle system is used to automatically move to the position to be inspected according to the flight mission route and take target images after hovering; the flight mission route contains the coordinate information of each position to be inspected; the distance measuring device of the unmanned aerial vehicle obtains the relative position of the target image and the hovering point, so that each target image has a position label; After the target image of the current position to be inspected is captured, the drone system controls the drone to automatically move to the next position to be inspected according to the flight mission route, and returns to the starting position after the target image of all positions to be inspected is captured; The central controller is used to obtain the target image, call the training library to identify the target in the target image, generate the wall coking detection result of the boiler, and generate the inspection route of the wall climbing robot according to the wall coking detection result; A wall-climbing robot system, used to control the wall-climbing robot to perform wall thickness inspection according to the inspection route; The central controller includes an identification module and a task formulation module. The identification module is used to determine the coking position according to the wall coking detection result, and the task formulation module is used to generate the inspection route according to the coking position so that the wall-climbing robot avoids the coking position; the central controller is also used to splice the target images to obtain a spliced ​​image, and identify the dust accumulation and coking results on the surface of the heating surface through an image intelligent algorithm to obtain the wall coking detection result of the boiler.

8. The combined inspection system according to claim 7, characterized in that: The central controller also includes a three-dimensional model management module, which is used to establish a three-dimensional positioning model of the boiler using a three-dimensional positioning signal transmitting device. The task formulation module is also used to generate the flight mission route based on the received flight instructions and the three-dimensional positioning model. The flight mission route includes the coordinate information of each position to be inspected.

9. The combined inspection system according to claim 8, characterized in that: The flight instruction includes the number and physical space location of the positions to be inspected; the flight mission route is displayed on the terminal console display so that the staff can control the flight mission route of the UAV on the display.

10. The combined inspection system according to claim 7, characterized in that: The wall-climbing robot system is also used to compare the detected wall thickness information with a threshold to determine whether there is a defect and mark the defect location. The wall-climbing robot system sends the detected defect location to the central controller, and the central controller generates a three-dimensional data report based on all defect locations obtained in a patrol mission.

Images