Tunnel lining detection system based on wall-attached unmanned aerial vehicle and working method

Abstract

According to the tunnel lining detection system based on the wall-attached unmanned aerial vehicle and the working method, image data in a tunnel lining can be automatically obtained, and a three-dimensional model is formed to be matched with a geological radar to detect lining diseases. The system comprises an aircraft, an image acquisition module arranged at the front side of the aircraft and used for scanning a tunnel lining, a geological radar arranged at the top of the aircraft and used for detecting the tunnel lining, a processor arranged in the middle of the aircraft, and a data transmission module arranged at the tail of the aircraft and used for data interaction. The front side of the aircraft is fixedly connected with a holder, the image acquisition module is fixedly connected to the interaction end of the holder, and the processor is electrically connected with the image acquisition module and the data transmission module. The method is applied to the technical field of tunnel lining detection.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel lining detection, and in particular to a tunnel lining detection system and a working method based on a wall-attached unmanned aerial vehicle. Background Art

[0002] With the rapid development of China's economy, the contradiction between the rapid expansion of urban space demand and the limited ground space has become increasingly prominent, and the effective development and utilization of urban underground space has become more and more urgent. As an important lifeline project for human use of underground space, the construction of tunnel structure has achieved unprecedented development. However, since tunnels are semi-concealed projects built in underground rock and soil media, and my country's tunnels were built in different periods, under different geological conditions and at different technical levels. After years of operation, many tunnels have developed various diseases, and lining cracks are one of the most common and serious diseases. The automatic and rapid identification and detection of tunnel lining crack diseases is of great fundamental significance for the safety assessment of tunnel lining structures and the safe operation and management of tunnels. It is an urgent need in practical engineering applications and is also a hot and cutting-edge issue in the field of tunnel engineering at home and abroad.

[0003] The current tunnel disease detection method mainly relies on manual labor, but manual detection has many limitations. First, the detection accuracy of manual detection is limited, and there may be problems such as missed detection and wrong detection; second, there are certain safety risks in manual disease detection in the tunnel environment; third, the traditional manual detection method is highly dependent on equipment and tools, and the detection efficiency is low. It is time-consuming and laborious to conduct comprehensive inspections of long-distance tunnels. Summary of the invention

[0004] The technical problem to be solved by the present invention is to overcome the shortcomings of the prior art and provide a tunnel lining detection system and working method based on a wall-mounted drone, which can automatically obtain image data inside the tunnel lining, form a three-dimensional model and cooperate with geological radar to detect lining defects.

[0005] The technical solution adopted by the present invention is: the present invention includes an aircraft, an image acquisition module arranged on the front side of the aircraft for scanning the tunnel lining, a geological radar arranged on the top of the aircraft for detecting the tunnel lining, a processor arranged in the middle of the aircraft, and a data transmission module arranged at the tail of the aircraft for data interaction, the front side of the aircraft is fixedly connected with a gimbal, the image acquisition module is fixedly connected to the interactive end of the gimbal, and the processor is electrically connected to the image acquisition module and the data transmission module.

[0006] Furthermore, a mounting frame is provided at the bottom of the aircraft, and the processor is fixedly connected to the mounting frame.

[0007] Furthermore, landing gears are provided on both sides of the aircraft, and each landing gear is provided with a rubber pad for mitigating impact force.

[0008] Furthermore, the aircraft is provided with a plurality of lift driving components, each of which includes a connecting rod, a locking block, a mounting block, a rotating motor and a rotor, the connecting rod is fixedly connected to the aircraft, the locking block is arranged at one end of the connecting rod, the locking block is threadedly connected to the aircraft, the mounting block is arranged at the other end of the connecting rod, the rotating motor is fixedly connected to the upper part of the mounting block, and the rotor is connected to the output end of the rotating motor.

[0009] Furthermore, the working method comprises:

[0010] S1. Control the aircraft to take off, inspect the designated area according to the set corresponding cruising altitude and route, and obtain the tunnel lining image data in real time through the image acquisition module carried on the aircraft gimbal;

[0011] S2, the processor constructs a real-time display three-dimensional model of the tunnel site according to the image data collected by the image acquisition module, and determines the aircraft detection route;

[0012] S3, the aircraft reaches the corresponding detection route of the tunnel lining, performs a large-angle scan through the geological radar, and records the position of the target body when a strong reflective target body is scanned;

[0013] S4, the collected data is sent to the processor for analysis, and the data transmission module synchronously transmits the data to the external central control processing mechanism. If there are gaps and holes in the tunnel lining, alarm information is generated in the real-time 3D display 3D model for marking;

[0014] S5. The aircraft moves to the next area and repeats steps S3 and S4 until the entire tunnel lining is inspected.

[0015] Furthermore, in step S2, the construction method of the three-dimensional model is displayed in real time:

[0016] S2.1 constructing a real-scene three-dimensional model of the construction site according to the tunnel lining image data;

[0017] S2.2 performs AI recognition on the tunnel lining image data to obtain construction personnel data and construction equipment data at the construction site to form a construction data set;

[0018] S2.3 constructing a three-dimensional engineering model based on the tunnel lining image data;

[0019] S2.4 loading the construction data set by the processor to render the real-scene three-dimensional model;

[0020] S2.5 superimposes the rendered real-scene three-dimensional model and the rendered engineering three-dimensional model to obtain a real-time display three-dimensional model.

[0021] Further, the scanning process of the geological radar in step S3 is as follows:

[0022] 3.1 Control the position and angle of the radar antenna so that the transmitting and absorbing ends of the antenna are in the working position;

[0023] 3.2 Detect the tunnel lining position and collect data to generate radar beam control parameters including waveform amplitude, frequency and pulse period;

[0024] 3.3 Control parameters calculate the real-time wave control code value of the phase shifter, the feeding amplitude of each power divider and the working status of the antenna, and transmit the data to the processor.

[0025] The beneficial effects of the present invention are: since the aircraft of the present invention uses the image acquisition module carried by the front gimbal to shoot and scan the tunnel, the data obtained is automatically recognized and processed by AI to form a three-dimensional model. The staff can quickly determine the aircraft detection route through the three-dimensional model obtained by the scan, so that the operation process can be visualized and three-dimensional. The aircraft can identify and track according to the image recognition and processing algorithm, and then realize automatic obstacle avoidance. A deep learning model is set in the processor, which can automatically identify the type and location of the disease through the radar beam control parameters of the geological radar waveform amplitude, frequency and each pulse period. The data is transmitted to the external central control processing mechanism to automatically mark and alarm in the three-dimensional modeling. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a schematic diagram of the process of the present invention;

[0027] Figure 2 It is a schematic diagram of the structure of the present invention;

[0028] Figure 3 It is a schematic diagram of the structure of the present invention;

[0029] Figure 4 yes Figure 3 A partial enlarged view of part A.

[0030] In the figure: 1. Aircraft; 11. Mounting frame; 12. Landing gear; 13. Rubber pad; 14. Lift drive assembly; 141. Connecting rod; 142. Locking block; 143. Mounting block; 144. Rotating motor; 145. Rotor; 2. Image acquisition module; 3. Geological radar; 4. Processor; 5. Data transmission module; 6. Gimbal. DETAILED DESCRIPTION

[0031] like Figures 1 to 4As shown, in this embodiment, the present invention includes an aircraft 1, an image acquisition module 2 arranged at the front side of the aircraft 1 for scanning the tunnel lining, a geological radar 3 arranged at the top of the aircraft 1 for detecting the tunnel lining, a processor 4 arranged at the middle of the aircraft 1, and a data transmission module 5 arranged at the tail of the aircraft 1 for data interaction. The front side of the aircraft 1 is fixedly connected with a gimbal 6, the image acquisition module 2 is fixedly connected to the interactive end of the gimbal 6, the processor 4 is electrically connected to the image acquisition module 2 and the data transmission module 5, the image acquisition module 2 is a panoramic camera and a laser scanner, which is used to shoot and scan the tunnel lining, and the collected tunnel lining appearance data is transmitted to the processor 4, and at the same time, the distance between the aircraft 1 and the tunnel lining can be identified to ensure that the aircraft 1, the aircraft 1 is a four-rotor 145 aircraft 1, and the aircraft 1 is a four-rotor 145 aircraft 1. The aircraft 1 shoots and scans the tunnel through the image acquisition module 2 carried by the front gimbal 6, and the obtained data is automatically recognized and processed by AI to form a three-dimensional model. The staff quickly determines the detection route of the aircraft 1 through the three-dimensional model obtained by the scan, so that the operation process is visualized and three-dimensional. The aircraft 1 can identify and track according to the image recognition and processing algorithm, and then realize automatic obstacle avoidance. The processor 4 is equipped with a deep learning model, which can automatically identify the type and location of the disease through the radar beam control parameters of the waveform amplitude and frequency of each pulse period of the geological radar 3. The data is transmitted to the external central control processing organization to automatically mark and alarm in the three-dimensional modeling. At the same time, it can also automatically judge the electromagnetic interference of the environment in which the geological radar 3 is located and filter and reduce the noise in time, enhance the radar system's active learning ability of the electromagnetic environment in which it is located, realize intelligent anti-interference processing, and improve the signal-to-noise ratio of the signal.

[0032] In this embodiment, a mounting frame 11 is provided at the bottom of the aircraft 1, and the processor 4 is fixedly connected to the mounting frame 11. The mounting frame 11 is used to connect and fix the processor 4. The mounting frame 11 is made of carbon fiber, is light in weight and has high impact resistance.

[0033] In this embodiment, landing gears 12 are provided on both sides of the aircraft 1, and each landing gear 12 is provided with a rubber pad 13 for mitigating impact force. The rubber pad 13 is used to buffer the impact force when the aircraft 1 contacts the ground during landing.

[0034] In this embodiment, the aircraft 1 is provided with a plurality of lift drive assemblies 14, each of the lift drive assemblies 14 includes a connecting rod 141, a locking block 142, a mounting block 143, a rotating motor 144 and a rotor 145, the connecting rod 141 is fixedly connected to the aircraft 1, the locking block 142 is arranged at one end of the connecting rod 141, the locking block 142 is threadedly connected to the aircraft 1, the mounting block 143 is arranged at the other end of the connecting rod 141, the rotating motor 144 is fixedly connected to the upper part of the mounting block 143, the rotor 145 is connected to the output end of the rotating motor 144, and the rotating motor 144 is a DC brushless synchronous motor.

[0035] In this embodiment, the working method includes:

[0036] S1, control the aircraft 1 to take off, inspect the designated area according to the set corresponding cruising altitude and route, and obtain the tunnel lining image data in real time through the image acquisition module 2 carried by the gimbal 6 of the aircraft 1;

[0037] S2, the processor 4 constructs a real-time display three-dimensional model of the tunnel site according to the image data collected by the image acquisition module 2, and determines the detection route of the aircraft 1;

[0038] S3, the aircraft 1 reaches the corresponding detection route of the tunnel lining, performs a large-angle scan through the geological radar 3, and records the position of the target body when a strong reflective target body is scanned;

[0039] S4, the collected data is sent to the processor 4 for analysis, and the data transmission module 5 synchronously transmits the data to the external central control processing mechanism. If there are gaps and holes in the tunnel lining, alarm information is generated in the real-time three-dimensional display three-dimensional model for marking;

[0040] S5. The aircraft 1 moves to the next area and repeats steps S3 and S4 until the inspection of the entire tunnel lining is completed.

[0041] In this embodiment, the construction method of the three-dimensional model is displayed in real time in step S2:

[0042] S2.1 constructing a real-scene three-dimensional model of the construction site according to the tunnel lining image data;

[0043] S2.2 performs AI recognition on the tunnel lining image data to obtain construction personnel data and construction equipment data at the construction site to form a construction data set;

[0044] S2.3 constructing a three-dimensional engineering model based on the tunnel lining image data;

[0045] S2.4 loading the construction data set by the processor 4 to render the real-scene three-dimensional model;

[0046] S2.5 superimposes the rendered real-scene three-dimensional model and the rendered engineering three-dimensional model to obtain a real-time display three-dimensional model.

[0047] In this embodiment, the scanning process of the geological radar 3 in step S3 is as follows:

[0048] 3.1 Control the position and angle of the radar antenna so that the transmitting and absorbing ends of the antenna are in the working position;

[0049] 3.2 Detect the tunnel lining position and collect data to generate radar beam control parameters including waveform amplitude, frequency and pulse period;

[0050] 3.3 Control parameters calculate the real-time wave control code value of the phase shifter, the feeding amplitude of each power distributor and the working status of the antenna, and transmit the data to the processor 4.

[0051] Although the embodiments of the present invention are described with practical solutions, they do not constitute limitations on the meaning of the present invention. For those skilled in the art, it is obvious to modify the implementation scheme and combine it with other solutions based on this description.

Claims

1. A tunnel lining inspection system based on a wall-attached drone, characterized by: The invention comprises an aircraft (1), an image acquisition module (2) arranged at the front side of the aircraft (1) for scanning a tunnel lining, a geological radar (3) arranged at the top of the aircraft (1) for detecting the tunnel lining, a processor (4) arranged at the middle of the aircraft (1), and a data transmission module (5) arranged at the tail of the aircraft (1) for data interaction, wherein the front side of the aircraft (1) is fixedly connected to a gimbal (6), the image acquisition module (2) is fixedly connected to the interactive end of the gimbal (6), and the processor (4) is electrically connected to the image acquisition module (2) and the data transmission module (5).

2. The tunnel lining detection system based on a wall-attached drone according to claim 1 is characterized in that: A mounting frame (11) is provided at the bottom of the aircraft (1), and the processor (4) is fixedly connected to the mounting frame (11).

3. The tunnel lining detection system based on a wall-attached drone according to claim 1 is characterized in that: Landing gears (12) are arranged on both sides of the aircraft (1), and each of the landing gears (12) is provided with a rubber pad (13) for relieving impact force.

4. The tunnel lining detection system based on a wall-attached drone according to claim 1 is characterized in that: The aircraft (1) is provided with a plurality of lift driving components (14), each of the lift driving components (14) comprises a connecting rod (141), a locking block (142), a mounting block (143), a rotating motor (144) and a rotor (145), the connecting rod (141) being fixedly connected to the aircraft (1), the locking block (142) being arranged at one end of the connecting rod (141), the locking block (142) being threadedly connected to the aircraft (1), the mounting block (143) being arranged at the other end of the connecting rod (141), the rotating motor (144) being fixedly connected to the upper part of the mounting block (143), and the rotor (145) being connected to the output end of the rotating motor (144).

5. A working method of a tunnel lining detection system based on a wall-attached UAV according to claim 1, characterized in that: The working method includes: S1, controlling the aircraft (1) to take off, inspecting the designated area according to the set corresponding cruising altitude and route, and acquiring tunnel lining image data in real time through the image acquisition module (2) carried on the gimbal (6) of the aircraft (1); S2, the processor (4) constructs a real-time display three-dimensional model of the tunnel site according to the image data collected by the image acquisition module (2), and determines the detection route of the aircraft (1); S3, the aircraft (1) reaches the corresponding detection route of the tunnel lining, performs a large-angle scan through the geological radar (3), and when a strong reflective target is scanned, the position of the target is recorded; S4, the collected data is sent to the processor (4) for analysis, and the data transmission module (5) synchronously transmits the data to the external central control processing mechanism. If there are gaps and holes in the tunnel lining, alarm information is generated in the real-time three-dimensional display three-dimensional model for marking; S5. The aircraft (1) moves to the next area and repeats steps S3 and S4 until the entire tunnel lining is inspected.

6. The working method of a tunnel lining detection system based on a wall-attached UAV according to claim 5 is characterized in that: In step S2, the construction method of the three-dimensional model is displayed in real time: S2.1 constructing a real-scene three-dimensional model of the construction site according to the tunnel lining image data; S2.2 performs AI recognition on the tunnel lining image data to obtain construction personnel data and construction equipment data at the construction site to form a construction data set; S2.3 constructing a three-dimensional engineering model based on the tunnel lining image data; S2.4 loading the construction data set through the processor (4) to render the real-scene three-dimensional model; S2.5 superimposes the rendered real-scene three-dimensional model and the rendered engineering three-dimensional model to obtain a real-time display three-dimensional model.

7. The working method of a tunnel lining detection system based on a wall-attached drone according to claim 5 is characterized in that: The scanning process of the geological radar (3) in step S3 is as follows: 3.1 Control the position and angle of the radar antenna so that the transmitting and absorbing ends of the antenna are in the working position; 3.2 Detect the tunnel lining position and collect data to generate radar beam control parameters including waveform amplitude, frequency and pulse period; 3.3 Control parameters calculate the real-time wave control code value of the phase shifter, the feeding amplitude of each power distributor and the working state of the antenna, and transmit the data to the processor (4).

Images