Underground space structure crack detection method and device and electronic equipment

Abstract

The invention discloses underground space structure crack detection, which comprises a detection method, a detection device and electronic equipment. In the detection method, a slide rail system is deployed at the top of an underground space, the mobile detection device automatically moves along a slide rail, and inertial navigation and a global positioning system are integrated to correct positioning data. Trigger sensors are arranged along the sliding rail at intervals, and the key area is arranged for directional detection. The multi-mode sensor collects data, the data processing module processes and recognizes crack characteristics, the crack is judged by comparing a preset threshold value, and the position size is determined. In the aspect of the device, a moving block and a moving detection device are arranged in a sliding rail, movement is achieved through a motor, a gear and the like, a mounting strip is used for mounting the sliding rail, and stability is guaranteed through limiting structures and the like. The electronic equipment comprises a data processing, detecting and controlling unit. The defect of manual inspection is overcome, intensified detection of key areas is realized, the labor cost is reduced, and high-precision crack detection and accurate positioning can be realized in a complex environment.

Description

Technical Field

[0001] The present invention relates to the field of underground engineering monitoring, and in particular to a method, device and electronic equipment for detecting cracks in underground space structures. Background Art

[0002] With the rapid development of the renewable energy photovoltaic power generation industry, substations, as key nodes in the power system, face a significant impact on the stability and reliability of the power grid. The efficiency of fault diagnosis and resolution in these substations directly impacts the stability and reliability of the power grid. As the scale of renewable energy photovoltaic power plants continues to expand, the complexity and failure rate of substation wiring are also increasing. Traditional fault diagnosis methods, which rely primarily on manual inspections and empirical judgment, are inefficient and prone to missed detections.

[0003] Common underground space structure crack detection equipment During the long-term use of underground space structures, cracks may appear in the structures due to factors such as changes in geological conditions, construction quality, and environmental impacts, which pose a threat to the stability and safety of the structures. In the existing technology, crack detection of underground space structures mostly relies on manual inspections, which is inefficient and poses safety hazards. As a result, manual inspections are labor-intensive and inefficient, and it is difficult to ensure operational safety in complex environments. The application of automated detection equipment is still in its infancy. Automated detection equipment is often limited by positioning accuracy and autonomous navigation capabilities, making it difficult to achieve high-precision crack detection and positioning. Therefore, a method, device, and electronic equipment for detecting cracks in underground space structures are proposed. Summary of the Invention

[0004] The present invention provides the following technical solutions: a method, device and electronic equipment for detecting cracks in underground space structures, comprising: The method for detecting cracks in an underground space structure comprises the following steps: S1 rail system deployment and mobile detection device drive: A slide rail is set at the top of the underground space, and a movement detection device is installed on the slide rail, and the movement detection device is driven by the slide rail to move automatically; S101 integrated navigation and positioning system integration and data correction: The inertial navigation system and global positioning system are integrated into the mobile detection device. The mobile detection device has a built-in accelerometer and gyroscope based on the inertial navigation system, which measures the state of motion in real time. At the same time, the ground station in the global positioning system has a built-in GPS signal enhancement module to receive and correct the positioning data of the mobile detection device, thereby improving positioning accuracy in complex environments. S2 trigger-sensing network deployment and detection activation: A plurality of trigger sensors are arranged at intervals along the slide rail, and when the motion detection device moves to the position of the trigger sensor, the detection program is activated; S201 Key Area Directional Detection Trigger Strategy: Trigger sensors are placed at the bends of the rails, near support structures, or in areas with high crack risk to trigger directional detection at specific locations. S3 multimodal sensor data synchronous acquisition: The mobile detection device uses laser radar and visual sensors to scan the surface of underground space structures and obtain three-dimensional structural data and high-definition image data; S4 multi-source data fusion and intelligent identification of crack characteristics: The three-dimensional structure data and image data are processed by the data processing module to identify crack characteristics; S5 crack-non-crack area comparative analysis and interference suppression: The sensor data is pre-processed by noise reduction, grayscale conversion, and edge detection. The shape, texture, and edge contour features of the cracks are extracted using a convolutional neural network. By comparing and analyzing the cracks with non-crack areas, real cracks are distinguished from interference signals. S6 crack risk assessment and quantitative parameter generation: Compare the crack characteristics with the preset threshold to determine whether cracks exist and determine the location and size parameters of the cracks.

[0005] Preferably, the mobile detection device has a built-in deep learning model to perform in-depth analysis of crack characteristics to improve the accuracy of crack identification.

[0006] An underground space structure crack detection device adopts the above-mentioned underground space structure crack detection method, including: a slide rail, a moving block embedded in the inner cavity of the slide rail, a moving detection device installed at the bottom of the moving block, a motor installed on the surface of the moving detection device, a first gear coaxially installed on the rotor of the motor, a second gear engaged with the upper surface of the first gear, a rack installed in the inner cavity of the slide rail, and the second gear engaged with the rack.

[0007] Preferably, mounting bars are installed on the front and back of the slide rail, and threaded rods are evenly distributed on the bottom of the mounting bars. The mounting bars can be installed on the top of the underground space through the threaded rods, thereby installing the slide rail.

[0008] Preferably, a mounting block is installed on the surface of the moving block, and the second gear is mounted on the surface of the mounting block through a rotating shaft. The mounting block can improve the rotation stability of the second gear and prevent the second gear from being separated from the rack.

[0009] Preferably, a fixing plate is installed on the surface of the movement detection device, and the motor is installed on the surface of the fixing plate, and the fixing plate can improve the stability of the motor.

[0010] Preferably, limit blocks are installed on the front and rear sides of the moving block, and limit grooves are opened on the inner wall of the slide rail and at positions corresponding to the limit blocks. The limit blocks are inserted into the limit grooves to limit the moving block so that the moving block can move in a straight line.

[0011] Preferably, both the front and rear sides of the rack are provided with baffles, and the baffles are installed at the bottom of the slide rail. The baffles can limit the second gear to prevent the second gear from offsetting when moving along the rack surface.

[0012] Electronic equipment for detecting cracks in underground space structures: adopts the above-mentioned method for detecting cracks in underground space structures, including: a data processing module, a data detection module and a control unit, the data processing module is installed inside the mobile detection device, the data detection module is installed on the surface of the data processing module, and the control unit is installed on the surface of the data detection module.

[0013] Preferably, a transmission module is installed on the surface of the movement detection device, and the transmission module is connected to the data processing module, and the detected data can be transmitted through the transmission module.

[0014] In summary, compared with the prior art, the present invention provides a method, device, and electronic equipment for detecting cracks in underground space structures, which have the following beneficial effects: 1. The motor added in the present invention can drive the first gear to rotate, thereby driving the second gear to rotate. When the second gear rotates, it will move along the rack, thereby driving the mobile detection device to move, realizing automatic movement of the mobile detection device. The mobile detection device can detect the width and depth of the cracks when moving, and perform quantitative analysis on the cracks, overcoming the defect of the non-fixed manual inspection path. The trigger sensor is arranged in key areas such as the turning points of the slide rails and the supporting structure. When the mobile detection device reaches a high-risk position, the directional detection program is automatically activated. This trigger detection mechanism not only ensures full area coverage, but also realizes enhanced detection of key areas. Compared with the traditional manual inspection method that requires the construction of scaffolding and point-by-point detection, it effectively solves the industry pain points of high labor intensity and high safety risks in manual inspection of underground spaces, and achieves the effect of improving crack detection efficiency and reducing labor costs. 2. The present invention sets trigger sensors at different key positions of the slide rail, such as turning points and near supporting structures. When the detection device reaches these positions, the trigger sensor activates the detection program and starts laser scanning and image acquisition of the tunnel wall. The laser radar is used to obtain accurate three-dimensional structural information, and the visual sensor is used to capture high-definition images. After receiving the data from these sensors, the data processing module uses an image processing algorithm to identify the characteristics of the cracks, such as shape, texture, and size. Then, the identified crack characteristics are compared with the preset crack database to determine whether they are real cracks, and the width and depth of the cracks are further measured to achieve accurate crack detection and positioning, and can achieve high-precision crack detection in complex environments; 3. By integrating an inertial navigation system, a global positioning system, an inertial navigation system, and a built-in accelerometer and gyroscope, the present invention can continuously measure the speed and direction changes of the detection device and calculate the precise position of the device in real time. At the same time, the GPS signal received by the ground station can be used as an auxiliary positioning reference for the inertial navigation system through signal enhancement technology to correct possible cumulative errors. This combined positioning strategy can maintain a high level of positioning accuracy even in the complex and changing environment of underground spaces, ensuring the accuracy and reliability of crack detection, improving the positioning accuracy of the detection device in complex environments, and achieving high-precision crack detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a flow chart of the present invention.

[0016] Figure 2 It is a structural schematic diagram of the slide rail of the present invention.

[0017] Figure 3 It is a schematic diagram of the installation structure of the mobile detection device of the present invention.

[0018] Figure 4 It is a schematic diagram of the structure of the slide rail of the present invention when viewed from above.

[0019] Figure 5 It is a schematic diagram of the internal structure of the movement detection device of the present invention.

[0020] In the figure: 1. Slide rail; 2. Motion detection device; 21. Data processing module; 22. Data detection module; 23. Control unit; 24. Transmission module; 3. Moving block; 4. Motor; 5. First gear; 6. Second gear; 7. Rack; 8. Mounting bar; 9. Threaded rod; 10. Mounting block; 11. Fixed plate; 12. Limit block; 13. Limit slot; 14. Stop bar. DETAILED DESCRIPTION

[0021] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0022] See also Figure 1 The present invention provides the following technical solutions: a method, device and electronic equipment for detecting cracks in underground space structures, including: The method for detecting cracks in an underground space structure comprises the following steps: S1 rail system deployment and mobile detection device drive: A slide rail is set at the top of the underground space, and a movement detection device is installed on the slide rail, and the movement detection device is driven by the slide rail to move automatically; S101 integrated navigation and positioning system integration and data correction: The inertial navigation system and global positioning system are integrated into the mobile detection device. The mobile detection device has a built-in accelerometer and gyroscope based on the inertial navigation system, which measures the state of motion in real time. At the same time, the ground station in the global positioning system has a built-in GPS signal enhancement module to receive and correct the positioning data of the mobile detection device, thereby improving positioning accuracy in complex environments. An inertial navigation system (INS) uses inertial sensors to measure an object's acceleration and angular velocity, and then calculates the object's position, velocity, and attitude through integration. Its core components include accelerometers and gyroscopes. The INS operates based on Newton's second law of motion and the law of conservation of angular momentum. Accelerometers measure an object's acceleration, and through integration, the velocity of the object is calculated. The GPS signal enhancement module of the global positioning system ground station in this solution enhances the GPS signal through various methods such as differential GPS technology, enhanced GPS technology, multi-frequency GPS receivers, ground-based augmentation system (GBAS) and indoor positioning technology. These technologies significantly improve positioning accuracy and reliability by correcting and rectifying positioning errors, combining auxiliary data and sensor information, utilizing multi-band signals and fusing multi-source data, thereby providing users with more accurate and stable positioning services.

[0023] In order to solve the problem of insufficient positioning accuracy of automated detection equipment and its difficulty in adapting to high-precision crack detection in complex environments, the inertial navigation system and the global positioning system are added to assist in positioning, thereby improving the autonomous navigation capability of the detection device and ensuring high-precision positioning even in complex environments. S2 trigger-sensing network deployment and detection activation: A plurality of trigger sensors are arranged at intervals along the slide rail, and when the motion detection device moves to the position of the trigger sensor, the detection program is activated; When the mobile detection device moves to the position of the trigger sensor, the trigger sensor detects the presence of the detection device. By receiving the identification signal of the detection device or detecting the physical proximity of the device, the trigger sensor sends an activation signal to the mobile detection device. After the detection program is started, the laser radar and visual sensor in the mobile detection device start working, scanning the surface of the underground space structure, obtaining three-dimensional structural data and high-definition image data, and then entering the subsequent multi-source data fusion, crack feature recognition, comparative analysis of crack and non-crack areas, and crack risk assessment processes; S201 Key Area Directional Detection Trigger Strategy: Trigger sensors are placed at the bends of the rails, near support structures, or in areas with high crack risk to trigger directional detection at specific locations. After receiving the trigger signal, the mobile detection device starts the directional detection program. During the directional detection program, the mobile detection device adjusts the parameters of the laser radar and visual sensor it carries. For example, at a bend, the laser radar's scanning angle is adjusted to better cover the structural surface in the bend area. Near the supporting structure, the visual sensor's image acquisition resolution is increased to more clearly detect the connection between the supporting structure and other structures, thereby performing more targeted detection at specific locations. S3 multimodal sensor data synchronous acquisition: The mobile detection device uses laser radar and visual sensors to scan the surface of underground space structures and obtain three-dimensional structural data and high-definition image data; S4 multi-source data fusion and intelligent identification of crack characteristics: The three-dimensional structure data and image data are processed by the data processing module to identify crack characteristics; First, the three-dimensional structure data and high-definition image data obtained by scanning the surface of the underground space structure by the laser radar and visual sensor carried by the mobile detection device are obtained from the multimodal sensor data synchronous acquisition step S3; The features extracted from the 3D structure data and the image data are fused, and the curvature anomaly areas in the 3D structure data are spatially aligned with the edge and texture anomaly areas in the image data. The anomaly areas in both data are found. Different weights are assigned to different features according to their importance using methods such as weighted fusion, and the fused features are then constructed into a comprehensive feature vector. The fused feature vector is compared with a predefined crack feature template. The predefined crack feature template can be obtained by training a large amount of known crack sample data and contains typical geometric, texture, and shape features of cracks. If the feature vector has a high degree of match with the crack feature template, it is determined that crack features exist; if the match is low, it is determined to be a non-crack feature area. In this way, the crack features in the underground space structure are finally identified; S5 crack-non-crack area comparative analysis and interference suppression: The sensor data is pre-processed by noise reduction, grayscale conversion, and edge detection. The shape, texture, and edge contour features of the cracks are extracted using a convolutional neural network. By comparing and analyzing the cracks with non-crack areas, real cracks are distinguished from interference signals. S6 crack risk assessment and quantitative parameter generation: Compare the crack characteristics with the preset threshold to determine whether cracks exist and determine the location and size parameters of the cracks.

[0024] First, collect a large amount of sample data on underground space structural cracks. This data can come from previous inspection projects, laboratory simulation data, or industry standard databases. A detailed analysis of the crack characteristics in the sample data is performed, including crack shape characteristics (such as aspect ratio, curvature, etc.), texture characteristics (such as grayscale changes, texture direction, etc.), edge contour characteristics (such as edge roughness and continuity, etc.), and related parameters such as crack location and size. The crack feature extraction results are obtained from the above-mentioned "Crack-Non-Crack Area Comparative Analysis and Interference Suppression" S5 and "Multi-Source Data Fusion and Crack Feature Intelligent Identification" S4 steps; For each crack feature, it is compared with the corresponding preset threshold. Taking crack length as an example, if the extracted crack length is greater than the preset length threshold, it is preliminarily determined that there is a high possibility of a crack at that location. For crack shape features, such as aspect ratio, if the extracted aspect ratio is greater than the preset aspect ratio threshold, it also increases the basis for judging the existence of a crack. When the comparison results of multiple crack features with the corresponding thresholds all indicate the existence of cracks (for example, crack length, shape, texture and other features all meet the crack judgment conditions), the final judgment is that cracks exist. If only some features meet the conditions, further analysis or combination with other detection methods may be required for comprehensive judgment.

[0025] Position determination The position of the crack on the surface of the underground space structure is determined based on the position information in the three-dimensional structural data and image data obtained during the simultaneous acquisition of multimodal sensor data (S3). For example, in the three-dimensional structural data, the specific coordinate position of the crack is determined by the coordinate system; in the image data, the position of the crack in the image can be determined based on the mapping relationship between the pixel position and the actual spatial position, and then converted into the position in the actual structure.

[0026] Size determination The length of the crack is determined based on measurement results from image data or 3D structural data. For image data, the actual length of the crack can be calculated based on the ratio between pixel length and actual length. For 3D structural data, the actual length measurement of the crack on the surface of the structure can be directly obtained. The width of the crack can be determined using similar methods. For example, in image data, the width of the crack in the image can be measured using a specific image processing algorithm and then converted to the actual width. Alternatively, in 3D structural data, the width of the crack can be determined based on the depth information of the surface of the structure and the appearance of the crack. The mobile detection device has a built-in deep learning model to conduct in-depth analysis of crack characteristics, improving the accuracy of crack identification; Inside the urban subway tunnel, customized slide rails are installed using the existing tunnel top space to ensure that the slide rails can bear the weight of the detection device and ensure its smooth movement. Trigger sensors are set at different key positions of the slide rails, such as turns and near supporting structures. When the detection device reaches these positions, the trigger sensor activates the detection program and starts laser scanning and image acquisition of the tunnel wall. LiDAR is used to obtain accurate three-dimensional structural information, and visual sensors are used to capture high-definition images. After receiving the data from these sensors, the data processing module uses image processing algorithms to identify the characteristics of the cracks, such as shape, texture, and size. The identified crack features are then compared with the preset crack database to determine whether they are real cracks, and the width and depth of the cracks are further measured to achieve accurate crack detection and positioning; In order to improve the positioning accuracy of the detection device, in addition to relying on the trigger sensor on the slide rail, the detection device also integrates an inertial navigation system and GPS signals received by the ground station. The inertial navigation system continuously measures the speed and direction changes of the detection device through the built-in accelerometer and gyroscope. Combined with the initial position information, it can calculate the precise position of the device in real time. At the same time, although the GPS signal received by the ground station is weak in the underground environment, it can be used as an auxiliary positioning reference for the inertial navigation system through signal enhancement technology to correct possible cumulative errors. This combined positioning strategy can maintain a high level of positioning accuracy even in the complex and changing environment of the underground space, ensuring the accuracy and reliability of crack detection.

[0027] In order to solve the problem of poor detection accuracy caused by the lack of effective crack identification and positioning technology, a deep learning model is used to conduct in-depth analysis of crack characteristics and improve the accuracy of crack identification.

[0028] The slide rails are made of high-strength, corrosion-resistant metal materials, such as stainless steel. Stainless steel slide rails can not only bear the weight of the mobile detection device, but also maintain stable performance for a long time in a humid underground environment. The surface of the slide rails has been precisely processed and has extremely low roughness, which helps to reduce the friction of the mobile detection device during movement, making the movement more stable and smooth, thereby improving the accuracy of the detection; A deep learning model trained on a large number of crack samples is used to analyze raw data acquired from lidar and vision sensors. The model first preprocesses the input data, including noise reduction, grayscale conversion, and edge detection, to highlight crack features. Subsequently, the model utilizes a convolutional neural network to extract local and global crack features, including their shape, texture, and edge contours. By comparing these features with those of non-cracked areas, the model can distinguish between true cracks and false positives, significantly improving crack identification accuracy. Furthermore, the model can estimate crack width and depth, enabling quantitative crack analysis and providing crucial information for subsequent structural safety assessments.

[0029] See also Figure 2 , underground space structure crack detection device, using the above-mentioned underground space structure crack detection method, including: slide rail 1, please refer to Figure 3 The inner cavity of the slide rail 1 is embedded with a moving block 3, the bottom of the moving block 3 is installed with a moving detection device 2, the surface of the moving detection device 2 is installed with a motor 4, the rotor of the motor 4 is coaxially installed with a first gear 5, the upper surface of the first gear 5 is meshed with a second gear 6, please refer to Figure 4 A rack 7 is installed in the inner cavity of the slide rail 1, and the second gear 6 is engaged with the rack 7.

[0030] The starting motor 4 can drive the first gear 5 to rotate, thereby driving the second gear 6 to rotate. When the second gear 6 rotates, it will move along the rack 7, thereby driving the moving block 3 to move, and further driving the moving detection device 2 to move, thereby realizing automatic movement of the moving detection device 2. When the moving detection device 2 moves, it can detect the width and depth of the crack and perform quantitative analysis of the crack. The automatic movement of the mobile detection device 2 eliminates the limitations of traditional manual detection and can conduct comprehensive and systematic inspections of the surface of underground space structures along a preset path. Compared with manual inspection, automatic movement can avoid the problems of missed inspection points or uneven inspection caused by human factors, greatly improving the efficiency and accuracy of inspection. Moreover, automatic movement can work according to the set speed and inspection frequency, which can adapt to the inspection needs of underground spaces of different sizes and complexities. The housing of the mobile detection device 2 is made of a sturdy and well-sealed material, such as a specially made engineering plastic or metal alloy, which can effectively protect the internal electronic components from dust, moisture, and possible collisions in the underground environment. The moving block 3 fits tightly with the slide rail 1 and has good guidance, ensuring that the mobile detection device 2 can move stably and accurately on the slide rail 1. See also Figure 1 The front and back of the slide rail 1 are both installed with mounting strips 8, and the bottom of the mounting strips 8 are evenly distributed with threaded rods 9. The mounting strips 8 can be installed on the top of the underground space through the threaded rods 9, thereby installing the slide rail 1.

[0031] See also Figure 3 A mounting block 10 is installed on the surface of the moving block 3, and the second gear 6 is installed on the surface of the mounting block 10 through a rotating shaft. The mounting block 10 can improve the rotation stability of the second gear 6 and prevent the second gear 6 from disengaging from the rack 7.

[0032] A fixing plate 11 is installed on the surface of the movement detection device 2 , and the motor 4 is installed on the surface of the fixing plate 11 . The fixing plate 11 can improve the stability of the motor 4 .

[0033] Limiting blocks 12 are installed on the front and rear sides of the moving block 3, and limiting grooves 13 are provided on the inner wall of the slide rail 1 at positions corresponding to the limiting blocks 12. The limiting blocks 12 are inserted into the limiting grooves 13 to limit the moving block 3 so that the moving block 3 can move in a straight line.

[0034] The front and rear sides of the rack 7 are both provided with baffles 14 , which are installed at the bottom of the slide rail 1 . The baffles 14 can limit the second gear 6 to prevent the second gear 6 from offsetting when moving along the surface of the rack 7 .

[0035] See also Figure 5 , electronic equipment for detecting cracks in underground space structures: adopts the above-mentioned method for detecting cracks in underground space structures, including: a data processing module 21, a data detection module 22 and a control unit 23, the data processing module 21 is installed inside the mobile detection device 2, the data detection module 22 is installed on the surface of the data processing module 21, and the control unit 23 is installed on the surface of the data detection module 22.

[0036] First, the data processing module 21 installed in the motion detection device 2 is started up, and the software programs and algorithm libraries required by the data processing module 21 are loaded. These programs and algorithm libraries may include algorithms for processing three-dimensional structural data and image data, algorithms for data fusion and crack feature recognition, etc. The data processing module 21 is then subjected to a hardware self-test to check whether its internal hardware components, such as the processor, memory, and storage device, are functioning properly. For example, the processor clock frequency is checked to ensure that the memory can read and write data correctly, and the storage device can store and read data properly. After the data processing module 21 is initialized, the data detection module 22 is started. The data detection module 22 performs its own initialization settings, including calibrating its internal sensors, such as the LiDAR and the visual sensor. For the LiDAR, distance calibration is performed to ensure accurate distance data. For the visual sensor, white balancing and focusing are performed to obtain clear and accurate image data. The data detection module 22 establishes a communication connection with the data processing module 21 to ensure that the detected data can be accurately transmitted to the data processing module 21. Finally, the control unit 23 on the surface of the data detection module 22 is started, and the control unit 23 performs initialization settings, including loading preset control parameters, such as the moving speed and detection interval of the motion detection device 2. The control unit 23 establishes a communication connection with the data detection module 22 so as to obtain detection data and control the operation of the motion detection device 2 according to the detection results; A transmission module 24 is installed on the surface of the motion detection device 2 . The transmission module 24 is connected to the data processing module 21 . The detected data can be transmitted via the transmission module 24 .

[0037] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0038] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A method for detecting cracks in underground space structures, characterized in that: The following steps are involved: S1 rail system deployment and mobile detection device drive: A slide rail is set at the top of the underground space, and a movement detection device is installed on the slide rail, and the movement detection device is driven by the slide rail to move automatically; S101 integrated navigation and positioning system integration and data correction: The inertial navigation system and global positioning system are integrated into the motion detection device. The motion detection device has a built-in accelerometer and gyroscope based on the inertial navigation system, which measures the state of motion in real time. At the same time, the ground station in the global positioning system has a built-in GPS signal enhancement module to receive and correct the positioning data of the motion detection device. S2 trigger-sensing network deployment and detection activation: A plurality of trigger sensors are arranged at intervals along the slide rail, and when the motion detection device moves to the position of the trigger sensor, the detection program is activated; S201 Key Area Directional Detection Trigger Strategy: Trigger sensors are placed at the bends of the rails, near support structures, or in areas with high crack risk to trigger directional detection at specific locations. S3 multimodal sensor data synchronous acquisition: The mobile detection device uses laser radar and visual sensors to scan the surface of underground space structures and obtain three-dimensional structural data and high-definition image data; S4 multi-source data fusion and intelligent identification of crack characteristics: The three-dimensional structure data and image data are processed by the data processing module to identify crack characteristics; S5 crack-non-crack area comparative analysis and interference suppression: The sensor data is pre-processed by noise reduction, grayscale conversion, and edge detection. The shape, texture, and edge contour features of the cracks are extracted using a convolutional neural network. By comparing and analyzing the cracks with non-crack areas, real cracks are distinguished from interference signals. S6 crack risk assessment and quantitative parameter generation: Compare the crack characteristics with the preset threshold to determine whether cracks exist and determine the location and size parameters of the cracks.

2. The method for detecting cracks in underground space structures according to claim 1, wherein: The mobile detection device has a built-in deep learning model to perform in-depth analysis of crack characteristics.

3. An underground space structure crack detection device, using the underground space structure crack detection method according to any one of claims 1-2, characterized in that: include: A slide rail (1), wherein a moving block (3) is embedded in the inner cavity of the slide rail (1), a moving detection device (2) is installed at the bottom of the moving block (3), a motor (4) is installed on the surface of the moving detection device (2), a first gear (5) is coaxially installed on the rotor of the motor (4), a second gear (6) is meshed with the upper surface of the first gear (5), a rack (7) is installed in the inner cavity of the slide rail (1), and the second gear (6) is meshed with the rack (7).

4. The underground space structure crack detection device according to claim 3, characterized in that: The front and back sides of the slide rail (1) are both installed with mounting strips (8), and the bottoms of the mounting strips (8) are evenly distributed with threaded rods (9).

5. The underground space structure crack detection device according to claim 3, characterized in that: A mounting block (10) is mounted on the surface of the moving block (3), and the second gear (6) is mounted on the surface of the mounting block (10) via a rotating shaft.

6. The underground space structure crack detection device according to claim 3, characterized in that: A fixing plate (11) is installed on the surface of the movement detection device (2), and the motor (4) is installed on the surface of the fixing plate (11).

7. The underground space structure crack detection device according to claim 3, characterized in that: Limiting blocks (12) are installed on both the front and rear sides of the moving block (3), and limiting grooves (13) are provided at positions corresponding to the inner wall of the slide rail (1) and the limiting blocks (12), and the limiting blocks (12) are inserted into the limiting grooves (13).

8. The underground space structure crack detection device according to claim 3, characterized in that: Baffles (14) are provided on both the front and rear sides of the rack (7), and the baffles (14) are installed at the bottom of the slide rail (1).

9. An electronic device for detecting cracks in underground space structures, using the method for detecting cracks in underground space structures according to any one of claims 1 to 2, characterized in that: include: A data processing module (21), a data detection module (22) and a control unit (23), wherein the data processing module (21) is installed inside the mobile detection device (2), the data detection module (22) is installed on the surface of the data processing module (21), and the control unit (23) is installed on the surface of the data detection module (22).

10. The electronic device for detecting cracks in underground space structures according to claim 9, characterized in that: A transmission module (24) is installed on the surface of the movement detection device (2), and the transmission module (24) is connected to the data processing module (21).

Images