A water diversion tunnel lining structure damage detection system and method
An underwater robot system with a camera and three-dimensional sonar device generates a structural model of the tunnel lining, addressing inefficiencies and safety issues in traditional manual detection methods by providing high-precision automated damage assessment in water diversion tunnels.
Patent Information
- Application Number
- CN202110123218.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-01-29
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2041-01-29
AI Technical Summary
Traditional manual detection methods for tunnel lining structure damage in water diversion tunnels are inefficient, inaccurate, and pose safety risks due to the humid and low-oxygen environment, failing to account for the internal pressure of the tunnel.
A system and method utilizing an underwater robot equipped with a camera and a three-dimensional sonar device to collect image and ultrasonic data, which includes a camera device, a three-dimensional sonar device, and a protective cover, to generate a three-dimensional structural model of the tunnel lining, enabling high-precision automated detection without draining the tunnel.
Enables high-precision automated detection of tunnel lining damage evolution characteristics, improving safety and efficiency by avoiding manual intervention and simulating the actual operating state of the tunnel.
Smart Images

Figure CN112946074B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of tunnel structure detection, and in particular to a system and method for detecting damage to the lining structure of a water diversion tunnel in a hydropower project. Background Art
[0002] The diversion tunnel is an underground water conveyance structure used to connect the water inlet and surge chamber of a hydropower station in a hydropower project. It utilizes the natural height difference of the river basin to achieve long-distance water diversion and power generation without a dam, and is an important form of hydropower resource development. The diversion tunnel is full of water during the power generation process and needs to withstand the combined effect of long-term internal and external water pressures. It is a typical pressurized tunnel. The long-term internal and external water environment causes the tunnel lining structure to have potential structural damage risks such as cracking, peeling, hollowing, and deformation.
[0003] In order to avoid adverse effects of structural damage to the lining structure on the power generation system and ensure the safe operation of the hydropower station, it is obviously particularly important to regularly conduct safety inspections on the inner wall lining structure of the tunnel and timely detect structural damage to the water diversion tunnel.
[0004] The detection work of traditional water diversion tunnels mainly adopts the plan of manual emptying and maintenance. That is, when the tunnel is completely emptied, the maintenance personnel manually detect and record the deformation and cracking of the tunnel inner wall lining structure. The manual detection method not only has the defects of long detection cycle, low work efficiency and poor detection accuracy, but the more important defect is that the humid and low-oxygen internal environment of the water diversion tunnel is not conducive to the safety of the maintenance personnel, there is a greater operational risk, and the emptying maintenance does not conform to the actual operating state of the water diversion tunnel with full water internal pressure, which will have an adverse effect on the safe operation of the water diversion tunnel. Summary of the invention
[0005] The present application provides a water diversion tunnel lining structure damage detection system and method, which are used to collect tunnel lining image data and tunnel lining three-dimensional ultrasonic data of the water diversion tunnel by an underwater robot, and then obtain a three-dimensional structural model of the tunnel lining of the water diversion tunnel, so as to realize high-precision automatic detection of the damage evolution characteristics of the tunnel lining structure without draining the water diversion tunnel.
[0006] In a first aspect, the present application provides a diversion tunnel lining structure damage detection system, the detection system comprising an underwater robot and a robot control device;
[0007] The underwater robot is provided with a camera device, a three-dimensional sonar device and a protective cover at the front end of the body. The protective cover isolates the camera device from the external environment of the underwater robot. When the underwater robot enters the water diversion tunnel, the camera device collects tunnel lining image data of the surrounding environment of the underwater robot through the protective cover, and the three-dimensional sonar device collects three-dimensional ultrasonic data of the tunnel lining of the surrounding environment of the underwater robot.
[0008] The robot control device controls the work of the underwater robot in the water diversion tunnel through the wireless network connection established between itself and the underwater robot. After receiving the tunnel lining image data and tunnel lining 3D ultrasonic data transmitted by the underwater robot, it generates a 3D structural model of the tunnel lining of the water diversion tunnel based on the fusion of the image data and the tunnel lining 3D ultrasonic data. Based on the 3D structural model of the tunnel lining, comparative analysis of test results at different times and damage simulation analysis are carried out to obtain the evolution characteristics of the damage and cracking of the tunnel lining surface over time.
[0009] In combination with the first aspect of the present application, in a first possible implementation method of the first aspect of the present application, the robot control device generates a digital surface model (Digital Surface Model, DSM) and a digital orthophoto map (Digital Orthophoto Map, DOM) corresponding to the water diversion tunnel based on the image data and the three-dimensional ultrasonic data, respectively, and fuses the DSM and DOM to obtain a three-dimensional structural model of the tunnel lining.
[0010] In combination with the first aspect of the present application, in a second possible implementation of the first aspect of the present application, the underwater robot is provided with a bionic tail fin driving device at the rear end of the body to drive the underwater robot to move forward and turn;
[0011] Alternatively, the underwater robot is provided with horizontal propeller driving devices on both sides of the body to drive the underwater robot forward and turn;
[0012] Alternatively, the underwater robot is provided with vertical propeller driving devices on both sides of the body to drive the underwater robot to ascend, descend and hover.
[0013] In combination with the first aspect of the present application, in a third possible implementation of the first aspect of the present application, the underwater robot is provided with a circumferentially arranged lighting device on the surface of the body to illuminate the surrounding environment of the underwater robot.
[0014] In combination with the first aspect of the present application, in a fourth possible implementation of the first aspect of the present application, the underwater robot is provided with a supporting device at the bottom of the body, the supporting device includes a first supporting frame and a second supporting frame arranged in a hollow structure, and the tops of the first supporting frame and the second supporting frame are both connected to the bottom of the body.
[0015] In combination with the first aspect of the present application, in a fifth possible implementation method of the first aspect of the present application, the underwater robot is further provided with a water pressure sensor and a temperature sensor on the main body. When the underwater robot enters the water diversion tunnel, the water pressure sensor collects water pressure data of the water diversion tunnel, and the temperature sensor collects temperature data of the water diversion tunnel. After receiving the water pressure data and temperature data transmitted by the underwater robot, the robot control device integrates the tunnel lining image data, the tunnel lining three-dimensional ultrasonic data, the water pressure data and the temperature data to obtain a three-dimensional structural model of the tunnel lining.
[0016] In combination with the first aspect of the present application, in a sixth possible implementation method of the first aspect of the present application, the underwater robot is also provided with an automatic attitude control device on the main body, and the automatic attitude control device includes a 3-axis gyroscope, a 3-axis accelerometer, a 3-axis magnetometer and a GPS, which is used to obtain in real time the three-dimensional attitude information of the underwater robot including position, speed, heading, inclination and roll angle. When the robot control device receives the three-dimensional attitude information transmitted by the underwater robot, the robot control device analyzes and solves the three-dimensional attitude information, obtains and predicts the motion trajectory of the underwater robot at the current moment and the motion trajectory at the next moment. If the motion trajectory at the next moment deviates from the preset route direction, the robot control device sends an attitude correction instruction to correct the three-dimensional attitude of the underwater robot, so that the underwater robot remains in the center line of the tunnel and moves along the preset route direction.
[0017] In a second aspect, the present application provides a method for detecting damage to a lining structure of a water diversion tunnel, the method comprising:
[0018] Acquire tunnel lining image data and tunnel lining three-dimensional ultrasonic data collected by the underwater robot, wherein the image data is data collected by the underwater robot through its own camera device after entering the water diversion tunnel, and the tunnel lining three-dimensional ultrasonic data is data collected by the underwater robot through its own three-dimensional sonar device after entering the water diversion tunnel;
[0019] Based on the tunnel lining image data and the tunnel lining 3D ultrasonic data, a 3D structural model of the tunnel lining of the water diversion tunnel is generated by fusion;
[0020] Based on the three-dimensional structural model of the tunnel lining, comparative analysis of test results at different times and damage simulation analysis were carried out to obtain the evolution characteristics of the damage and cracking of the tunnel lining surface over time.
[0021] In conjunction with the second aspect of the present application, in a first possible implementation of the second aspect of the present application, generating a three-dimensional structural model of the tunnel lining of the water diversion tunnel based on the tunnel lining image data and the tunnel lining three-dimensional ultrasonic data includes:
[0022] Based on the tunnel lining image data and 3D ultrasonic data, the DSM and DOM corresponding to the diversion tunnel are generated respectively;
[0023] The DSM and DOM are integrated to obtain the three-dimensional structural model of the tunnel lining.
[0024] In a third aspect, the present application provides a diversion tunnel lining structure damage detection device, the device comprising:
[0025] an acquisition unit, used to acquire tunnel lining image data and tunnel lining three-dimensional ultrasonic data collected by the underwater robot, wherein the image data is data collected by the underwater robot through its own camera device after entering the water diversion tunnel, and the tunnel lining three-dimensional ultrasonic data is data collected by the underwater robot through its own three-dimensional sonar device after entering the water diversion tunnel;
[0026] A generating unit, for generating a three-dimensional structural model of a tunnel lining of a water diversion tunnel based on the tunnel lining image data and the three-dimensional ultrasonic data of the tunnel lining;
[0027] The analysis unit is used to conduct comparative analysis of test results at different times and damage simulation analysis based on the three-dimensional structural model of the tunnel lining, and obtain the evolution characteristics of the damage and cracking of the tunnel lining surface over time.
[0028] In conjunction with the third aspect of the present application, in a first possible implementation manner of the third aspect of the present application, the generating unit is specifically configured to:
[0029] Based on the tunnel lining image data and 3D ultrasonic data, the DSM and DOM corresponding to the diversion tunnel are generated respectively;
[0030] The DSM and DOM are integrated to obtain the three-dimensional structural model of the tunnel lining.
[0031] In a fourth aspect, the present application provides a processing device, including a processor and a memory, wherein a computer program is stored in the memory, and when the processor calls the computer program in the memory, the method provided by the second aspect of the present application or any possible implementation method of the second aspect of the present application is executed.
[0032] In a fifth aspect, the present application provides a computer-readable storage medium, which stores multiple instructions, and the instructions are suitable for a processor to load to execute the method provided in the second aspect of the present application or any possible implementation of the second aspect of the present application.
[0033] From the above content, it can be concluded that the present application has the following beneficial effects:
[0034] For tunnel detection scenarios, the present application proposes a new detection mechanism, in which the underwater robot collects tunnel lining image data and tunnel lining three-dimensional ultrasonic data of the underwater robot's surrounding environment in the water diversion tunnel through its own configured camera device and three-dimensional sonar device, and then transmits them to the robot control device. The robot control device generates a three-dimensional structural model of the tunnel lining of the water diversion tunnel based on the tunnel lining image data and the tunnel lining three-dimensional ultrasonic data. In this process, the three-dimensional structure of the underwater structure of the tunnel lining of the water diversion tunnel is accurately fitted by combining image acquisition and structural scanning, and a structural damage analysis is performed, thereby completing high-precision automated detection of the damage evolution characteristics of the tunnel lining structure of the water diversion tunnel without draining the water diversion tunnel. BRIEF DESCRIPTION OF THE DRAWINGS
[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.
[0036] Figure 1 A schematic diagram of the structure of the camera device of the present application;
[0037] Figure 2 A schematic diagram of the structure of the underwater robot of this application;
[0038] Figure 3 A schematic diagram of the structure of the tail fin drive device of the present application;
[0039] Figure 4 A schematic diagram of the structure of the lighting device of the present application;
[0040] Figure 5 A schematic diagram of a flow chart of the detection method of the present application;
[0041] Figure 6 A schematic diagram of the structure of the detection device of the present application;
[0042] Figure 7 A schematic diagram of the structure of the processing equipment of this application. DETAILED DESCRIPTION
[0043] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.
[0044] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described here can be implemented in an order other than that illustrated or described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or modules is not necessarily limited to those steps or modules clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices. The naming or numbering of steps in this application does not mean that the steps in the method flow must be executed in the time / logical sequence indicated by the naming or numbering. The process steps that have been named or numbered can change the execution order according to the technical purpose to be achieved, as long as the same or similar technical effects can be achieved.
[0045] The division of modules in this application is a logical division. There may be other division methods when it is implemented in actual applications. For example, multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection between modules can be electrical or other similar forms, which are not limited in this application. In addition, the modules or submodules described as separate components may or may not be physically separated, may or may not be physical modules, or may be distributed in multiple circuit modules, and some or all of the modules may be selected according to actual needs to achieve the purpose of the present application.
[0046] In the present application, the water diversion tunnel lining structure damage detection system includes two aspects: an underwater robot and a robot control device. The underwater robot is responsible for collecting data in the underwater environment of the water diversion tunnel site, while the robot control device can control the work of the underwater robot by remote control, and can also receive the collected data transmitted by the underwater robot; further, the robot control device can also perform data analysis based on the received data to achieve deep underwater detection.
[0047] Among them, the network connection established between the underwater robot and the robot control device is a wireless connection.
[0048] The wireless connection method establishes communication remotely through wireless communication without laying cables. There is no need to consider that the cables may hinder the underwater operation of the underwater robot, and the cables can be avoided from being rubbed by the underwater environment of the water diversion tunnel, such as the stone structure. Therefore, it is more suitable for practical applications and has a wider and more flexible application scenario.
[0049] On the robot control device side, the operation of the underwater robot can be controlled based on the data collected by the sensors configured on the underwater robot body.
[0050] For example, the robot control device can send control instructions to the underwater robot under the manual control of the staff based on the images collected by the camera configured on the body of the underwater robot, so as to control the movement direction, movement speed, body posture or other working states of the underwater robot. The specific details can be adjusted according to the different components configured on the body of the underwater robot, different working modes and other influencing factors.
[0051] Specifically, the robot control device can be configured with a display screen to output relevant content to the staff, such as the equipment parameters of the underwater robot itself, the data collected by the underwater robot, the network connection status, etc.; the robot control device can also include a control handle, and the staff can directly operate the control handle to control the movement of the underwater robot.
[0052] Furthermore, the robot control device can flexibly configure its own components according to the needs of human-computer interaction in actual applications; or, according to the application needs of convenient control, the robot control device can be a fixed device such as a server device, a host device, and an all-in-one computer, as well as a user equipment (User Equipment, UE) such as a laptop computer, a tablet computer, a personal digital assistant (Personal Digital Assistance, PDA), a smart phone, and a controller; or, considering improving data processing capabilities, the robot control device can also be set up in the form of a device cluster. For example, multiple devices can be specifically divided into a control part and a data processing part, and the data processing part of the device can also distribute the data processing tasks to each sub-device by the main device, and each sub-device processes the sub-processing task and then summarizes the task processing results.
[0053] It can be seen from the above that the robot control device provided in the present application, its own components or its own device form can be adjusted according to actual needs, and no specific limitation is made here.
[0054] On the other hand, the underwater robot provided in this application has a relatively fixed hardware structure.
[0055] It can be understood that an underwater robot is a robot used to work in an underwater environment. It collects relevant data on underwater structures in the target area by sailing in the underwater environment. The underwater navigation mode can significantly improve the maneuverability and flexibility of the body, giving it a strong obstacle avoidance ability and the ability to adapt to the underwater environment.
[0056] Of course, underwater robots can also be used to work on the water surface. Even if they have driving devices such as wheels, tracks, and robotic arms, they can also walk on the ground in water and land environments. The specific configuration can be adjusted according to actual needs.
[0057] In the present application, the underwater robot is provided with a lighting device, a camera device, a three-dimensional sonar device and a protective cover at the front end of the body. The lighting device provides sufficient light and vision for the dark underwater environment. The protective cover isolates the camera device from the external environment of the underwater robot. The three-dimensional sonar device can be exposed to the water. When the underwater robot enters the water diversion tunnel, the camera device collects image data of the surrounding environment of the underwater robot through the protective cover, and the three-dimensional sonar device collects three-dimensional ultrasonic data of the tunnel lining of the surrounding environment of the underwater robot.
[0058] The protective cover may be provided with a waterproof sealing ring and a waterproof gasket to ensure sealing, and the protective cover is preferably a transparent protective cover to provide a clear field of view for the camera device.
[0059] For example, the camera device may include a panoramic camera (panoramic camera), which has a wider field of view than a traditional camera. Figure 1 A structural schematic diagram of the camera device of the present application is shown, and the camera device may include a panoramic camera, a rotating connecting rod and a rotating base. The driving device in the underwater robot can adjust the posture of the panoramic camera through a linkage structure composed of a rotating base and a rotating connecting rod to facilitate the capture of panoramic images.
[0060] In practical applications, this application can use an HD panoramic camera with a lens rotation range of ±90° in the horizontal direction and a rotation range of ±45° in the vertical direction. The wide shooting field of view can better collect image data of the tunnel lining structure. The camera can also use an anti-fog function to prevent it from fogging.
[0061] For example, the performance of a high-definition panoramic camera can be referred to the technical parameter table of a high-definition panoramic anti-fog camera shown below:
[0062] Table 1-Technical parameters of high-definition panoramic anti-fog camera
[0063]
[0064] Furthermore, the camera device can also be equipped with a fill light (corresponding to the fill light device mentioned later) to improve the light compensation for the camera shooting, so as to capture the image details more clearly. In practical applications, the fill light of this application can specifically adopt a self-sensing strobe fill light, which is composed of multiple LED lamp beads with an average power of 27w, adopts a low-voltage DC power supply mode, and the light intensity is continuously adjustable in 5 levels, which is used for automatic fill light to ensure the imaging quality of the camera.
[0065] For example, the performance of the fill light can refer to the technical parameter table of the strobe fill light shown below:
[0066] Table 2- Technical parameters of fill light
[0067]
[0068] Exemplarily, the three-dimensional sonar device may include a three-dimensional sonar probe. In actual applications, it may have a data update speed with a higher frequency than that of general sonar, and may perform real-time correction of the navigation posture of the robot body through an automatic posture control device, thereby ensuring accurate identification of the surface of the underwater structure.
[0069] For example, the performance of the three-dimensional sonar can be referred to the three-dimensional sonar technical parameter table shown below:
[0070] Table 3- Technical parameters of underwater 3D sonar
[0071]
[0072] For example, as a more practical implementation, see Figure 2 A schematic diagram of the structure of the underwater robot for detecting damage to the lining structure of a water diversion tunnel according to the present application is shown. Figure 2 It can be seen that the underwater robot provided in the present application adopts a navigation-driven robot structure.
[0073] The main body of the underwater robot mainly includes a closed cabin to ensure sealing. After launching into the water, water does not enter the body of the underwater robot. The cabin is equipped with a power supply device, a communication device and a control device of the underwater robot. The control device is used to control the operation of the components on the underwater robot, the power supply device provides the power required for the operation of these components, and the communication device is used to communicate with the robot control equipment.
[0074] The power supply device includes a battery and a charging device. The charging device is provided with a pressure-activated switch. When the battery is low on power, the staff can manually press the trigger switch to make the charging device pop out from the bottom of the cabin to charge the equipment. The communication module corresponds to the wireless communication method mentioned above and has a related interface to realize the data transmission function. The control device includes a control circuit board, which is electrically connected to the controlled component for data transmission.
[0075] Exemplarily, the enclosed cabin may adopt a double-layer structure in actual application. The inner layer may be formed of aluminum alloy material to form a waterproof and pressure-bearing inner layer, which can withstand the maximum external water pressure of 100 meters deep, to ensure that the components in the cabin can still maintain good working performance in the water diversion tunnel; the outer layer may be formed of porous medium material to form the cabin surface, and the porous medium material attached to the surface of the inner cabin is used to change the fluid properties of the surface layer, reduce navigation resistance, and thus improve endurance.
[0076] For example, the performance of the cabin can be referred to the cabin technical parameter table shown below:
[0077] Table 4- Cabin technical parameters
[0078]
[0079] Furthermore, in some cases, a driving device may be provided in the cabin, and the driving device is used to provide driving power for the driving structure provided on the main body. Figure 2 As shown, the underwater robot may be provided with a bionic tail fin drive device at the rear end of the body to drive the underwater robot forward and turn. Figure 3 A structural schematic diagram of the bionic tail fin drive device of the present application is shown. In the present application, the bionic tail fin drive device may include a tail fin blade, a rotating bearing, and a transmission rod, which is connected to a driving motor of a driving device in a cabin through the transmission rod. When the driving motor is working, the tail fin blade can be driven to swing through a linkage structure formed by the transmission rod, the rotating bearing and the fixed rod. It is designed based on the principles of bionics and fluid mechanics to simulate the efficient, fast, and flexible swimming of fish in an underwater environment through their tail fins, and drive the underwater robot to move along a preset route. In actual applications, the forward speed can be measured to reach 2m / s.
[0080] In addition to the bionic tail fin drive device, the underwater robot can also be equipped with a bionic dorsal fin balancing device. The bionic dorsal fin balancing device simulates the fish's use of the dorsal fin to adjust its posture in the underwater environment, or to adjust its balance, so as to prevent the fuselage from tipping over, thereby further improving the stability of the underwater robot in the underwater environment.
[0081] Of course, the underwater robot may also be driven by a propeller. For example, a propeller driving device may be disposed at the rear end of the main body, and the underwater robot may be driven forward by the recoil force brought to the main body by the propeller when rotating.
[0082] In addition to the rear end, the underwater robot can also be equipped with propeller drive devices at other positions of the body, so as to obtain greater recoil force or adjust the body's operating posture more flexibly. For example, the underwater robot can be equipped with horizontal propeller drive devices and vertical propeller drive devices on both sides, respectively, and the speed difference between the horizontal propeller drive devices on both sides can be adjusted to adjust the left and right direction of the underwater robot when traveling, and the speed and rotation direction of the vertical propeller drive devices on both sides can be adjusted to adjust the ascent, descent and hovering adjustment of the underwater robot when traveling.
[0083] Among them, the propeller driving device can be connected to the body of the underwater robot through the connection method of the mechanical arm.
[0084] like Figure 2 As shown, the underwater robot can also be equipped with a bionic tail fin drive device, a horizontal propeller drive device and a vertical propeller drive device at the same time. In practical applications, the bionic tail fin drive device at the rear end of the robot body is used as the main propulsion device to provide the main driving power for the underwater robot; the horizontal propeller drives on both sides are used as auxiliary propulsion devices to provide backup driving power for the underwater robot when the bionic tail fin drive device fails, or the water flow conditions and surrounding environment structures are not conducive to the operation of the bionic tail fin drive device; the vertical propeller drives on both sides are also used as auxiliary propulsion devices to provide driving power for the vertical lifting and hovering operations of the underwater robot.
[0085] In addition, for the movement control of the underwater robot, the underwater robot can also be provided with an automatic attitude control device on the main body. The automatic attitude control device includes a 3-axis gyroscope, a 3-axis accelerometer, a 3-axis magnetometer and a GPS, which is used to obtain the three-dimensional attitude information of the underwater robot including position, speed, heading, inclination and roll angle in real time. When the robot control device receives the three-dimensional attitude information transmitted by the underwater robot, the robot control device analyzes and solves the three-dimensional attitude information, obtains and predicts the motion trajectory of the underwater robot at the current moment and the motion trajectory at the next moment. If the motion trajectory at the next moment deviates from the preset route direction, the robot control device sends an attitude correction instruction to correct the three-dimensional attitude of the underwater robot, so that the underwater robot remains on the center line of the tunnel and moves along the preset route direction.
[0086] Among them, Figure 2 As shown, the underwater robot can also be equipped with a lighting device on the surface of the body to illuminate the surrounding environment of the underwater robot and provide sufficient light and vision for the dark underwater environment.
[0087] For example, see Figure 4A structural schematic diagram of the lighting device of the present application is shown. In actual application, the lighting device can be arranged in a circular manner at the front end of the body near the camera device. Specifically, it may include a light-transmitting chamber and four arc-shaped light-emitting panels, each of which is provided with a mounting slot and a plurality of high-brightness LED lamp beads. It adopts a low-voltage DC power supply mode, and the light intensity is continuously adjustable in 5 levels, which is used for camera lighting in underwater environments. Compared with traditional point and line arrangement lighting devices, the lighting device with a circular strip arrangement has a more uniform and wider field of view, and is more convenient for video image acquisition.
[0088] Continue reading Figure 2 It can be seen that the underwater robot can also be provided with a supporting device at the bottom of the body, which is used to allow the underwater robot to stop sailing and be fixed on the underwater ground.
[0089] The support device may include a first support frame and a second support frame provided with a hollow structure (which can reduce weight and resistance, and ensure the lightness and flexibility of the fuselage), and the tops of the first support frame and the second support frame are both connected to the bottom of the body. The first support frame and the second support frame may be fixed to the bottom of the body of the underwater robot by means of screws, welding, snaps, etc.
[0090] In practical applications, underwater robots can be equipped with relevant sensors inside or on the surface as needed to collect the data required for detection. The collected data can be transmitted to the robot control device for data analysis.
[0091] For example, the underwater robot can be equipped with a water pressure sensor to collect water pressure data of the underwater robot's environment; or, the underwater robot can be equipped with a temperature sensor to collect water temperature data of the underwater robot's environment or temperature data inside the underwater robot; or, the underwater robot can be equipped with a positioning sensor to collect positioning data of the underwater robot; or, the underwater robot can be equipped with a posture sensor, such as a 3-axis gyroscope, a 3-axis accelerometer, a 3-axis magnetometer, etc., to collect the underwater robot's own three-dimensional posture data, and provide data support for adjusting and correcting the underwater robot's posture.
[0092] Among them, the underwater robot can also be equipped with an early warning mechanism. When the collected data exceeds the preset warning value, such as too high water pressure, too high temperature, too low battery, etc., a warning prompt can be sent to the robot control device, or the early warning indicator light configured on the body of the underwater robot can be triggered.
[0093] It can be understood that the type of sensor can be adjusted according to actual needs and is not specifically limited here.
[0094] The above is a description of the hardware structure of the underwater robot provided in this application. The following is a description of the data processing content involved in the robot control device.
[0095] In the present application, when the robot control device obtains the tunnel lining image data collected by the underwater robot through the camera device and the three-dimensional ultrasonic data of the tunnel lining collected by the three-dimensional sonar device, a three-dimensional structural model of the tunnel lining can be generated based on these two.
[0096] It can be understood that the tunnel lining image data corresponds to the image acquisition aspect, and the tunnel lining three-dimensional ultrasonic data corresponds to the scanning structure aspect. The present application integrates the two, combines photogrammetry and sonar scanning, and uses the principles of photogrammetry and ultrasonic ranging to obtain the image data and ultrasonic data of the underwater structure, and fits the three-dimensional structural model of the underwater structure of the tunnel lining of the water diversion tunnel based on this, and performs structural damage analysis, thereby completing high-precision automated detection of the damage evolution characteristics of the tunnel lining structure of the water diversion tunnel without draining the water diversion tunnel.
[0097] Among them, the data processing can be specifically realized by a neural network model. For different sample water diversion tunnels, sample tunnel lining image data and sample tunnel lining three-dimensional ultrasonic data can be collected, and the corresponding tunnel lining three-dimensional structural model (static data obtained after data processing, used to represent the tunnel lining structure of the corresponding sample water diversion tunnel) can be annotated. The sample tunnel lining image data and sample tunnel lining three-dimensional ultrasonic data of the sample water diversion tunnel are input into the neural network model in turn for forward transmission, and the data of the tunnel lining three-dimensional structural model output by the model after fusing the input image are extracted, and the loss function is calculated by combining the data of the tunnel lining three-dimensional structural model output by the current model and the data of the previously annotated tunnel lining three-dimensional structural model, and the model is back-propagated according to the loss function calculation result, and the model parameters are adjusted and optimized. After multiple rounds of training, when the model training requirements such as the number of training times, training time, and scheduling accuracy are met, the model training can be completed, and the trained model can be built into engineering applications, put into practical application and promotion.
[0098] Among them, the model type can specifically adopt different types of models such as SSD model, YOLOv3 model, R-CNN model, Fast R-CNN model, Faster R-CNN model, Mask R-CNN model, ResNet model, etc.; the loss function can be exemplarily a cross entropy loss function, a Triplet loss function, a center loss function, etc.
[0099] Exemplarily, the generation process of the tunnel lining three-dimensional structural model can specifically combine the tunnel lining image data and the tunnel lining three-dimensional ultrasonic data to generate the DSM and DOM corresponding to the water diversion tunnel respectively, and then fuse the DSM and DOM to obtain the three-dimensional structural model.
[0100] DSM, Digital Surface Model, can be used to realistically represent the actual conditions of the lining surface.
[0101] DOM, digital orthophoto, is an image with both geometric accuracy and image characteristics. It has the advantages of high accuracy, rich information, intuitive and realistic, and quick acquisition. It can provide reliable and powerful data support for damage analysis.
[0102] The three-dimensional structural model of the tunnel lining obtained by integrating the two can combine the advantages of both DSM and DOM and reflect the tunnel lining structure of the water diversion tunnel with high accuracy.
[0103] For example, the processed three-dimensional structural model of the tunnel lining can not only reflect the tunnel lining structure of the water diversion tunnel from the perspective of terrain factors, but also combine the data collected by the underwater robot other than the tunnel lining image data and the tunnel lining three-dimensional ultrasonic data to enrich the data content of the tunnel lining three-dimensional structural model, so as to restore the tunnel lining structure of the water diversion tunnel more richly and realistically.
[0104] For example, after the robot control device receives the water pressure data and temperature data transmitted by the underwater robot, it can also fuse the tunnel lining image data, the tunnel lining three-dimensional ultrasonic data, the water pressure data and the temperature data to obtain a three-dimensional structural model of the tunnel lining of the water diversion tunnel. In this way, the three-dimensional structural model of the tunnel lining can not only reflect the three-dimensional structural characteristics of the tunnel lining of the water diversion tunnel, but also reflect the water pressure and water temperature of the water diversion tunnel, providing more powerful data support.
[0105] After obtaining the three-dimensional structural model of the tunnel lining reflecting the tunnel lining structure of the water diversion tunnel, a comparative analysis of test results at different times or a damage simulation analysis at different times can be performed based on the model to determine the damage detection results of the tunnel lining at different time points (including past time points, current time points and even future time points).
[0106] The damage detection results, or the evolution characteristics of the damage and cracking of the tunnel lining surface over time, can be specifically reflected in three aspects: type, area and degree. Taking cracking characteristics as an example, it can include cracking type, cracking location, cracking width and cracking depth.
[0107] Once the evolution characteristics of damage and cracking over time are determined, or in other words, the damage detection results are determined, specific data support can be provided for the maintenance of the water diversion tunnel, which can help staff understand the aging and damage of the tunnel lining surface structure and promptly arrange corresponding structural remedial measures, personnel evacuation measures, personnel rescue measures and other response measures.
[0108] Corresponding to the data processing performed by the robot control device in the above-mentioned water diversion tunnel lining structure damage detection system, the present application also provides a water diversion tunnel lining structure damage detection method, such as Figure 5 A flow chart of a method for detecting damage to a lining structure of a water diversion tunnel according to the present application is shown. The detection method provided by the present application may specifically include the following steps:
[0109] Step S501, acquiring tunnel lining image data and tunnel lining three-dimensional ultrasonic data collected by the underwater robot, wherein the image data is data collected by the underwater robot through its own camera device after entering the water diversion tunnel, and the tunnel lining three-dimensional ultrasonic data is data collected by the underwater robot through its own three-dimensional sonar device after entering the water diversion tunnel.
[0110] Step S502, generating a three-dimensional structural model of the tunnel lining of the water diversion tunnel based on the tunnel lining image data and the tunnel lining three-dimensional ultrasonic data;
[0111] Step S503, performing comparative analysis of test results at different times and damage simulation analysis based on the three-dimensional structural model of the tunnel lining, and obtaining the evolution characteristics of damage and cracking of the tunnel lining surface over time.
[0112] In an exemplary implementation, generating a three-dimensional structural model of a tunnel lining of a water diversion tunnel based on tunnel lining image data and tunnel lining three-dimensional ultrasonic data may include:
[0113] Based on the tunnel lining image data and 3D ultrasonic data, the DSM and DOM corresponding to the diversion tunnel are generated respectively;
[0114] The DSM and DOM are integrated to obtain the three-dimensional structural model of the tunnel lining.
[0115] For the description of each step of the above method, please refer to the description of the data processing part involved in the above-mentioned water diversion tunnel lining structure damage detection system, and the details will not be repeated here.
[0116] It should be understood that the detection method can be used not only on robot control devices, but also on other devices. When different types of processing devices such as server devices, host devices or UE retrieve the tunnel lining image data and tunnel lining three-dimensional ultrasonic data collected by the underwater robot from the water diversion tunnel, the water diversion tunnel lining structure damage detection method provided by the present application can be applied to obtain the three-dimensional structural model of the tunnel lining of the water diversion tunnel, and based on the three-dimensional structural model of the tunnel lining, a comparative analysis of test results at different times can be performed, or damage simulation analysis at different times can be performed to determine the damage detection results of the tunnel lining at different time points (including past time points, current time points and even future time points), and obtain the evolution characteristics of the damage and cracking of the tunnel lining surface over time.
[0117] Furthermore, the present application also provides a diversion tunnel lining structure damage detection device, see Figure 6 , Figure 6 This is a schematic diagram of a structure of a diversion tunnel lining structure damage detection device of the present application. In the present application, the diversion tunnel lining structure damage detection device 600 may specifically include the following structure:
[0118] The acquisition unit 601 is used to acquire the tunnel lining image data and the tunnel lining three-dimensional ultrasonic data collected by the underwater robot, wherein the image data is the data obtained by the underwater robot through its own camera device to collect the surrounding environment after entering the water diversion tunnel, and the tunnel lining three-dimensional ultrasonic data is the data obtained by the underwater robot through its own three-dimensional sonar device to collect the surrounding environment after entering the water diversion tunnel;
[0119] A generating unit 602 is used to generate a three-dimensional structural model of the tunnel lining of the water diversion tunnel based on the tunnel lining image data and the three-dimensional ultrasonic data of the tunnel lining;
[0120] The analysis unit 603 is used to perform comparative analysis of test results at different times and damage simulation analysis based on the three-dimensional structural model of the tunnel lining, and obtain the evolution characteristics of the damage and cracking of the tunnel lining surface over time.
[0121] In an exemplary implementation, the generating unit 602 is specifically configured to:
[0122] Based on the tunnel lining image data and 3D ultrasonic data, the DSM and DOM corresponding to the diversion tunnel are generated respectively;
[0123] The DSM and DOM are integrated to obtain the three-dimensional structural model of the tunnel lining.
[0124] Furthermore, the present application also provides a processing device, which can be a robot control device or other device in a water diversion tunnel lining structure damage detection system, see Figure 7 , Figure 7 701, a memory 702, and an input / output device 703. The processor 701 is used to execute the computer program stored in the memory 702 to implement the following Figure 5 The steps of the water diversion tunnel lining structure damage detection method in the corresponding embodiment; or, the processor 701 is used to execute the computer program stored in the memory 702 to implement the following Figure 6 Corresponding to the functions of each unit in the embodiment, the memory 702 is used to store the processor 701 executing the above Figure 5 The computer program required by the method for detecting damage to the lining structure of a diversion tunnel in the corresponding embodiment.
[0125] Exemplarily, the computer program may be divided into one or more modules / units, one or more modules / units are stored in the memory 702, and executed by the processor 701 to complete the present application. One or more modules / units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program in the computer device.
[0126] The processing device may include, but is not limited to, a processor 701, a memory 702, and an input / output device 703. Those skilled in the art will appreciate that the illustration is merely an example of a processing device and does not constitute a limitation on the processing device, and may include more or fewer components than shown in the illustration, or a combination of certain components, or different components. For example, the processing device may also include a network access device, a bus, etc., and the processor 701, the memory 702, the input / output device 703, and the network access device, etc. are connected via a bus.
[0127] The processor 701 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the processing device, and uses various interfaces and lines to connect various parts of the entire device.
[0128] The memory 702 can be used to store computer programs and / or modules. The processor 701 implements various functions of the computer device by running or executing the computer programs and / or modules stored in the memory 702 and calling the data stored in the memory 702. The memory 702 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created according to the use of the processing device, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.
[0129] When the processor 701 is used to execute the computer program stored in the memory 702, the following functions can be implemented:
[0130] Acquire tunnel lining image data and tunnel lining three-dimensional ultrasonic data collected by the underwater robot, wherein the image data is data collected by the underwater robot through its own camera device after entering the water diversion tunnel, and the tunnel lining three-dimensional ultrasonic data is data collected by the underwater robot through its own three-dimensional sonar device after entering the water diversion tunnel;
[0131] Generate a 3D structural model of the tunnel lining of the water diversion tunnel based on the tunnel lining image data and the tunnel lining 3D ultrasonic data;
[0132] Based on the three-dimensional structural model of the tunnel lining, comparative analysis of test results at different times and damage simulation analysis were carried out to obtain the evolution characteristics of the damage and cracking of the tunnel lining surface over time.
[0133] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described water diversion tunnel lining structure damage detection device, processing equipment and corresponding units can refer to the following. Figure 5 The description of the water diversion tunnel lining structure damage detection method in the corresponding embodiment will not be repeated here.
[0134] A person of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.
[0135] To this end, the present application provides a computer-readable storage medium, in which a plurality of instructions are stored, and the instructions can be loaded by a processor to execute the present application as follows: Figure 5 The steps in the method for detecting damage to the lining structure of a water diversion tunnel in the corresponding embodiment, the specific operations can be referred to as follows Figure 5 The description of the water diversion tunnel lining structure damage detection method in the corresponding embodiment will not be repeated here.
[0136] The computer-readable storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.
[0137] Due to the instructions stored in the computer-readable storage medium, the present application can be executed. Figure 5 The steps in the method for detecting damage to the lining structure of a water diversion tunnel in the corresponding embodiment are as follows: Figure 5 The beneficial effects that can be achieved by the method for detecting damage to the lining structure of a water diversion tunnel in the corresponding embodiment are detailed in the previous description and will not be repeated here.
[0138] The above is a detailed introduction to the water diversion tunnel lining structure damage detection system, method, device, processing equipment and computer-readable storage medium provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the idea of the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.
Claims
1. A diversion tunnel lining structure damage detection system, It is characterized in that The detection system includes an underwater robot and a robot control device; The underwater robot is provided with a camera device, a three-dimensional sonar device and a protective cover at the front end of the body, and the protective cover isolates the camera device from the external environment of the underwater robot. When the underwater robot enters the target water diversion tunnel, the camera device collects tunnel lining image data of the surrounding environment of the underwater robot through the protective cover, and the three-dimensional sonar device collects three-dimensional ultrasonic data of the tunnel lining of the surrounding environment of the underwater robot; The robot control device controls the work of the underwater robot in the water diversion tunnel through the network connection established between itself and the underwater robot, and generates a three-dimensional structural model of the tunnel lining of the water diversion tunnel based on the image data and the three-dimensional ultrasonic data of the tunnel lining after receiving the tunnel lining image data and the three-dimensional ultrasonic data of the tunnel lining transmitted by the underwater robot, and performs comparative analysis of test results at different times and damage simulation analysis based on the three-dimensional structural model of the tunnel lining to obtain the evolution characteristics of the damage and cracking of the tunnel lining surface over time; The underwater robot is provided with a bionic tail fin driving device at the rear end of the body to drive the underwater robot forward and turn. The bionic tail fin driving device includes a tail fin blade, a rotating bearing, and a transmission rod. The transmission rod is connected to a driving motor of a driving device in the cabin. When the driving motor is working, a linkage structure is formed by the transmission rod, the rotating bearing and the fixed rod to drive the tail fin blade to swing. The underwater robot is also provided with a bionic dorsal fin balancing device for simulating fish to adjust their posture in an underwater environment through their dorsal fins; The underwater robot is provided with horizontal propeller driving devices on both sides of the body to drive the underwater robot to move forward and turn; The underwater robot is also provided with vertical propeller driving devices on both sides of the body to drive the underwater robot to rise, descend and hover; The bionic tail fin drive device is the main propulsion device, providing the main driving power for the underwater robot; the horizontal propeller drive device and the vertical propeller drive device are auxiliary propulsion devices; The robot control device generates a digital surface model DSM and a digital orthophoto map DOM of the water diversion tunnel based on the image data and the three-dimensional ultrasonic data, respectively, and fuses the DSM and the DOM to obtain a three-dimensional structural model of the tunnel lining; The underwater robot is provided with a circumferentially arranged lighting device on the surface of the body to illuminate the surrounding environment of the underwater robot; The underwater robot is provided with a supporting device at the bottom of the body, wherein the supporting device comprises a first supporting frame and a second supporting frame arranged in a hollow structure, and the tops of the first supporting frame and the second supporting frame are both connected to the bottom of the body; The underwater robot is further provided with a water pressure sensor and a temperature sensor on the main body. When the underwater robot enters the water diversion tunnel, the water pressure sensor collects water pressure data of the water diversion tunnel, and the temperature sensor collects temperature data of the water diversion tunnel. After receiving the water pressure data and temperature data transmitted by the underwater robot, the robot control device fuses the tunnel lining image data, the tunnel lining three-dimensional ultrasonic data, the water pressure data and the temperature data to obtain the three-dimensional structural model of the tunnel lining; The underwater robot is also provided with an automatic attitude control device on the main body, and the automatic attitude control device includes a 3-axis gyroscope, a 3-axis accelerometer, a 3-axis magnetometer and a GPS, which is used to obtain the three-dimensional attitude information of the underwater robot including position, speed, heading, inclination and roll angle in real time. When the robot control device receives the three-dimensional attitude information transmitted by the underwater robot, the robot control device analyzes and solves the three-dimensional attitude information, obtains and predicts the motion trajectory of the underwater robot at the current moment and the motion trajectory at the next moment. If the motion trajectory at the next moment deviates from the preset route direction, the robot control device sends a posture correction instruction to correct the three-dimensional attitude of the underwater robot, so that the underwater robot remains in the center line of the tunnel and moves along the preset route direction.
2. A method for detecting damage to a diversion tunnel lining structure according to claim 1, It is characterized in that The method comprises: Acquire tunnel lining image data and tunnel lining three-dimensional ultrasonic data collected by the underwater robot, wherein the image data is data collected by the underwater robot through its own camera device after entering the water diversion tunnel, and the tunnel lining three-dimensional ultrasonic data is data collected by the underwater robot through its own three-dimensional sonar device after entering the water diversion tunnel; Generating a three-dimensional structural model of the tunnel lining of the water diversion tunnel based on the tunnel lining image data and the tunnel lining three-dimensional ultrasonic data; Comparative analysis of test results at different times and damage simulation analysis are performed based on the three-dimensional structural model of the tunnel lining to obtain the evolution characteristics of damage and cracking of the tunnel lining surface over time; The step of generating the three-dimensional structural model of the tunnel lining of the water diversion tunnel based on the tunnel lining image data and the tunnel lining three-dimensional ultrasonic data comprises: Based on the tunnel lining image data and the three-dimensional ultrasonic data, a digital surface model DSM and a digital orthophoto map DOM corresponding to the water diversion tunnel are respectively generated; The DSM and the DOM are fused to obtain the three-dimensional structural model of the tunnel lining.
