Device and method for rapidly detecting microcracks on rigid pavement of airfield runway

Abstract

The invention discloses an airfield runway rigid pavement micro-crack rapid detection system and method, and belongs to the technical field of airfield runway detection, vehicle-mounted three-dimensional structured light dual equipment is adopted for cooperative work, micro-cracks of 1-1.5 mm are accurately identified through high-resolution three-dimensional images and depth information, and the detection accuracy is improved. A machine learning model is utilized to predict future evolution types (corner fracture, plate edge peeling or common cracks) of the cracks, maintenance priorities are generated based on the number, types, development rates and historical data of the micro cracks of each plate, and maintenance resources are reasonably allocated through comprehensive evaluation and repair suggestions, so that specific task guidance is provided for maintenance personnel, and the maintenance efficiency is improved. The runway management efficiency is effectively improved, and the safety and long-term reliability of the runway are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of airport pavement detection, and particularly to a rapid detection device and method for microcracks in rigid airport runway pavements. Background Art

[0002] As an important infrastructure for air transportation, the safety of the airport runway pavement is directly related to the safety of aircraft operation. Cracks often occur in the runway concrete pavement due to high-load operation. If the cracks are not detected and treated in time, it may lead to concrete spalling, forming foreign object debris (FOD) during aircraft operation, thus seriously threatening the safety of the aircraft.

[0003] Since the rigid runway slabs are usually composed of blocks, the further development of microcracks is mainly manifested as corner breaks, edge spalling, and ordinary cracks. The harmfulness of these three types of cracks decreases in turn, and corner breaks and edge spalling cause the most serious damage to the runway.

[0004] However, the existing detection technologies based on image recognition can usually only identify larger cracks, and have poor recognition ability for microcracks (1 mm to 1.5 mm), resulting in microcracks not being discovered and treated in time, and may gradually expand into more serious cracks without being noticed, bringing potential hazards to the runway.

[0005] Therefore, the present invention aims to provide a microcrack detection and evaluation method based on three-dimensional structured light, which can efficiently and accurately detect microcracks in airport runways, especially in difficult-to-identify areas such as corners and edges, and predict the development trend of microcracks to make maintenance decisions in advance. Summary of the Invention

[0006] The present invention aims to provide a rapid detection system and method for microcracks in rigid airport runway pavements to solve the problems raised in the above background art.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A rapid detection device for microcracks in rigid airport runway pavements, comprising:

[0009] A vehicle-mounted integrated device, responsible for carrying all detection devices and performing mobile acquisition on the runway; including a vehicle body, a power system, a control system, and a data storage system;

[0010] A dual three-dimensional structured light camera, used for synchronously collecting three-dimensional image data of the pavement, with a collection resolution of not less than 1 mm;

[0011] A high-precision GNSS+RTK positioning system, used for accurately positioning the image data;

[0012] A data processing unit for image preprocessing, crack identification and development trend determination;

[0013] A display and control system for real-time display of detection results and generation of maintenance decision reports based on crack prediction results.

[0014] Preferably, the vehicle-mounted integrated device can achieve rapid and full-range micro-crack detection of runway pavements without suspending airport operations.

[0015] Preferably, the minimum crack width resolution of the dual three-dimensional camera device is 1 mm, and the coverage width of each acquisition is not less than 5.2 m.

[0016] A method for a rapid micro-crack detection device for airport runway rigid pavements, characterized in that: the method steps include:

[0017] S1: Using a vehicle-mounted three-dimensional structured light device, through the collaborative work of dual devices, collecting three-dimensional image data of the airport runway pavement, with a detection resolution not lower than 1 mm;

[0018] S2: Preprocessing the collected image data, including denoising, light equalization, etc., to improve the image quality;

[0019] S3: Based on the preprocessed image data, using artificial intelligence algorithms to identify micro-cracks, judge the type, development trend and possible future form of the cracks, and predict whether the cracks will develop into corner breaks, slab edge spalls or ordinary cracks;

[0020] S4: According to the development trend of the cracks, provide decision support for runway maintenance and take treatment measures in advance to avoid further deterioration of the cracks.

[0021] Preferably, the detection resolution of micro-cracks in step S3 is 1 mm, and micro-cracks in the range of 1 mm to 1.5 mm can be effectively detected.

[0022] Preferably, the future development trend of micro-cracks in step S3 is predicted by analyzing characteristic parameters such as the shape, width, depth, and expansion rate of the cracks.

[0023] Preferably, the types of micro-cracks include corner breaks, slab edge spalls and ordinary cracks, and the harmfulness of the cracks to the runway is judged according to the type, and priority suggestions are provided for maintenance decision-making.

[0024] Compared with the prior art, the present invention has the following beneficial effects:

[0025] (1) High-precision micro-crack detection:

[0026] By using an in-vehicle three-dimensional structured light device and combining it with a GNSS+RTK high-precision positioning system, the present invention can accurately collect pavement data during high-speed driving and effectively identify microcracks (1mm - 1.5mm) through three-dimensional depth information. Compared with traditional two-dimensional image recognition methods, the depth information of the three-dimensional structured light device can clearly distinguish between cracked and uncracked areas, enabling microcracks to be accurately identified and avoiding missed or misdetected situations in traditional methods.

[0027] (2) Real-time and high efficiency:

[0028] Using an in-vehicle device for data collection can not only quickly cover a large area of the runway but also ensure real-time data transmission and processing. Traditional manual detection and static scanning methods are relatively slow, while the solution of the present invention achieves high efficiency in runway detection through an in-vehicle system (speed can reach 50 - 60 km / h), enabling rapid full-area detection without affecting airport operations and greatly improving the detection efficiency.

[0029] (3) Prediction of the development trend of microcracks:

[0030] By combining the physical characteristics of cracks with external environmental factors (such as temperature, humidity, traffic volume, etc.) and using machine learning algorithms to predict the future development trend of cracks, the present invention can evaluate cracks at their tiny stage and predict whether cracks will develop into corner breaks, edge spalls, or ordinary cracks. Through this prediction, the maintenance work of airport runways can be planned in advance, avoiding the deterioration of cracks into serious diseases and enhancing the foresight and scientific nature of runway maintenance.

[0031] (4) Automated maintenance decision support:

[0032] The system can provide detailed priority suggestions for maintenance personnel and automatically dispatch maintenance tasks by automatically generating maintenance decision support and combining the development trend and harmfulness of microcracks. In this way, it not only reduces the error of manual judgment but also realizes the efficient management of maintenance tasks, improving the accuracy and timeliness of maintenance work.

[0033] (5) Long-term monitoring and data update:

[0034] The present invention can gradually optimize the machine learning model and improve the prediction accuracy through regular detection and real-time data update. As the amount of detection data increases, the prediction ability of the model will continuously enhance, thereby providing continuous technical support and decision-making basis for the long-term safe operation of airport runways. Description of the Drawings

[0035] Figure 1 It is a method flow chart of a rapid detection device for microcracks in the rigid pavement of an airport runway;

[0036] Figure 2 It is a module relationship diagram of a rapid detection device for microcracks on the rigid pavement of an airport runway;

[0037] Figure 3 It is a schematic diagram of the structure of an on-vehicle integrated device for a rapid detection device for microcracks on the rigid pavement of an airport runway;

[0038] Figure 4 It is a schematic diagram for crack identification and development trend analysis;

[0039] Figure 5 They are 2D and 3D images of the road surface. Specific implementation manners

[0040] The present invention will be further described in detail below in conjunction with the accompanying drawings and implementation manners:

[0041] The specific implementation process is as follows:

[0042] As Figures 1-5 shown, a rapid detection device and method for microcracks on the rigid pavement of an airport runway,

[0043] The microcrack detection and evaluation system of the present invention consists of the following main modules:

[0044] (1) Vehicle-mounted platform system

[0045] The vehicle-mounted platform is the core part of this system, responsible for carrying all detection devices and performing mobile acquisition on the runway. The platform system includes a vehicle body, a power system, a control system, a data storage system, etc.

[0046] (2) Three-dimensional structured light detection device

[0047] It is composed of a dual three-dimensional structured light camera, a laser emitter, a receiver, etc., and is responsible for real-time acquisition of three-dimensional image data of the road surface, identifying and evaluating microcracks.

[0048] (3) GNSS+RTK positioning system

[0049] It provides centimeter-level accurate positioning data to ensure that the acquired data is highly consistent with the actual runway position.

[0050] (4) Data processing and transmission system

[0051] It includes a vehicle-mounted computer, an image processing unit, a transmission module, etc., and is responsible for real-time data transmission and processing and analysis of the acquired image data.

[0052] (5) Artificial intelligence analysis and evaluation system

[0053] It analyzes the acquired images through a deep learning model, judges the type, width, depth and development trend of the cracks, and outputs an evaluation report.

[0054] (6) Maintenance Decision - making and Management Platform

[0055] Responsible for generating maintenance suggestions, formulating maintenance plans and tracking maintenance effects.

[0056] 2. Equipment Configuration and Technical Parameters

[0057] (1) Vehicle - mounted Platform System

[0058] ① Dimensions and Weight:

[0059] Length: approximately 3.5 meters, Width: approximately 2 meters, Height: approximately 1.5 meters

[0060] Total Weight: approximately 1500 kg (varies according to platform and equipment configuration)

[0061] ② Power System:

[0062] Battery Capacity: Provide at least 6 - hour continuous working ability

[0063] Electric Drive System: The power system supports a driving speed of 0 - 60 km / h, meeting the inspection requirements of the runway.

[0064] ③ Control System:

[0065] The operating system supports the automatic inspection function of vehicle - mounted equipment and can monitor information such as equipment status, location, speed in real - time.

[0066] Wireless Communication System: Support wireless data transmission between the equipment and the control platform to ensure smooth data transmission.

[0067] ④ Adaptability and Reliability:

[0068] The vehicle - mounted platform can adapt to various complex environments of the airport runway, including high temperature, low temperature, and slippery conditions.

[0069] The vehicle suspension system design can effectively reduce vibration and ensure high - precision detection.

[0070] (2) 3D Structured Light Detection Equipment

[0071] ① 3D Camera Configuration:

[0072] Camera Type: Dual 3D Structured Light Cameras (using laser scanning and image comparison technology)

[0073] Resolution: The resolution of each camera reaches 4096×2048 pixels

[0074] Minimum Crack Resolution: Can accurately identify cracks with a width of not less than 1 mm

[0075] Collection Width: When two devices work together, the detection width for each collection is 5.2 meters

[0076] Collection Frequency: 20 frames of data are collected per second to ensure stable acquisition of high-quality images even at high speeds.

[0077] ② Laser Transmitter and Receiver:

[0078] Laser Wavelength: 850nm, ensuring high-precision depth information can be provided

[0079] Measurement Accuracy: The depth accuracy is 0.1mm, capable of accurately capturing depth changes in tiny cracks.

[0080] Working Distance and Accuracy:

[0081] Working Distance: The distance between the camera and the detection area is 2m to 10m, adapting to the measurement requirements of different widths and lengths of the runway.

[0082] Accuracy: The measurement accuracy of cracks is ±0.2mm, ensuring that micro-cracks can be accurately identified.

[0083] ③ Equipment Layout and Advantages of Dual Devices:

[0084] Dual-Device Configuration: Cameras are installed in the front and on the side of the vehicle platform, symmetrically positioned. Data collection is carried out through synchronous triggering to ensure data accuracy and coverage.

[0085] Balance between High Precision and High Efficiency: The dual devices can provide a collection width of no less than 5.2 meters each time. Compared with the 3.8-meter width of a single device, the detection range is increased, and the time consumption of multiple collections is reduced. In this way, within the vast area of the runway, data collection can be completed more efficiently, avoiding any area being missed.

[0086] Reduction of Dead Zones and Redundancy: The two devices work together. Through complementary perspectives, it is ensured that when driving at high speeds, regardless of how the road surface conditions change, the crack positions can be comprehensively and accurately captured, avoiding situations that may be missed by a single device.

[0087] High-Speed Driving and Full-Area Coverage Capability: Runway detection requires high-speed driving (50 - 60 km / h). The dual devices can complete large-area road surface detection in a shorter time, avoiding micro-cracks in some areas not being detected in a timely manner due to equipment angle problems.

[0088] Complementary Nature of Depth Information: The dual devices provide depth data from different angles, which can be fused and used to calculate more accurate three-dimensional information, overcoming the data deficiency problem caused by the perspective limitation of a single device.

[0089] Equipment Redundancy and Stability: In case one of the devices fails, the other device can still continue to work, thus ensuring the stability of the system.

[0090] (3) GNSS + RTK positioning system

[0091] Positioning accuracy: centimeter-level positioning accuracy, with an error not exceeding ±2 cm.

[0092] Operating frequency: The RTK system operates at a frequency of 1 Hz to ensure real-time position information update during high-speed driving.

[0093] System configuration: It includes main and auxiliary antennas and a differential correction receiver. The main antenna is installed on the roof of the vehicle, and the auxiliary antenna is installed at the front end of the device. The positioning accuracy is improved through differential correction.

[0094] (4) Data processing and transmission system

[0095] ① Vehicle-mounted computer:

[0096] Processing capacity: An industrial-grade computer equipped with at least 8 GB of memory and a 1 TB solid-state drive to ensure high-speed data processing and storage.

[0097] Processing speed: It processes 100 MB of data stream per second to ensure efficient processing of real-time image data.

[0098] Operating system: It supports common operating systems such as Windows / Linux and is compatible with existing software tools and control systems.

[0099] ② Data transmission and storage:

[0100] Wireless transmission: The collected image data is transmitted to the control platform in real time through a 10 Gigabit Ethernet port and 5G / 4G wireless communication modules.

[0101] Storage system: The vehicle-mounted computer is equipped with a large-capacity hard drive (at least 1 TB) to store the collected image data and historical records, supporting offline viewing.

[0102] (5) Artificial intelligence analysis and evaluation system

[0103] ① Deep learning algorithm:

[0104] Model: A convolutional neural network (CNN) model based on deep learning for crack identification and classification. During the training process, the model will identify the morphological characteristics of microcracks (1 mm to 1.5 mm) and determine whether there is a risk of expansion.

[0105] Training data: The system will continuously optimize and update the identification model based on historical data and real-time collected data to improve the accuracy of crack classification and prediction.

[0106] ② Analysis output:

[0107] The system automatically outputs the crack type (such as corner break, edge spalling or ordinary crack), the specific location, width, depth, expansion trend of the crack, and the predicted maintenance priority.

[0108] (6) Maintenance Decision - making and Management Platform

[0109] ① Decision - making Support System:

[0110] The system generates maintenance decision - making suggestions based on real - time detection results and historical data. It provides priority handling suggestions for high - risk areas and automatically assigns work orders to maintenance personnel.

[0111] ② Decision - making Logic: The system combines the crack expansion trend, hazard assessment and repair cost to generate the optimal maintenance plan.

[0112] ③ Task Management and Tracking:

[0113] Maintenance tasks are automatically managed and scheduled through the platform. The system will real - time track the execution progress of maintenance tasks and conduct effectiveness evaluation.

[0114] II. Crack Identification and Development Trend Analysis

[0115] 1. Crack Identification Method

[0116] Crack identification is the core part of this system. The purpose is to accurately identify micro - cracks on the runway through the image data collected by three - dimensional structured light, and provide a basis for subsequent crack development trend analysis. Due to the complex structure and high - load operation environment of the airport runway, traditional image recognition methods may miss tiny cracks. Therefore, advanced three - dimensional image processing and artificial intelligence algorithms need to be introduced to improve the recognition accuracy.

[0117] 1.1 Image Pre - processing

[0118] Image pre - processing is the first step in crack identification, mainly including operations such as denoising, light equalization, and distortion correction. During the image acquisition process, it may be affected by factors such as vehicle vibration and light changes. Therefore, the collected images need to be processed to improve the accuracy of subsequent analysis.

[0119] Denoising Processing: Use a denoising algorithm based on convolutional neural network (CNN) to remove noise and interference in the image, especially the impact brought by vehicle - mounted platform vibration.

[0120] Light Equalization: By performing light equalization processing on the image, eliminate the impact caused by uneven environmental illumination and enhance the visibility of cracks.

[0121] Distortion Correction: Considering the camera perspective and optical distortion, use the camera calibration method for distortion correction to ensure the geometric accuracy of the image and avoid affecting the judgment of crack position and shape.

[0122] 1.2 Crack Feature Extraction

[0123] The feature extraction of cracks is the basis for differentiating crack types. Based on the data after image preprocessing, we extract the following crack features for further analysis:

[0124] (1) Crack length: The length of a crack can directly affect its harmfulness. Longer cracks usually imply a higher risk of propagation.

[0125] Quantification index: The minimum recognizable range of crack length is 1 mm, and the system can identify and record cracks exceeding 1 mm.

[0126] (2) Crack width: The width of a crack directly affects its impact on the runway structure. Larger cracks may lead to a decrease in the runway's bearing capacity.

[0127] Quantification index: The minimum width recognition accuracy is 1 mm, and for every increase of 0.5 mm in crack width, the potential risk of its propagation and impact increases.

[0128] (3) Crack depth: Through the depth data collected by three-dimensional structured light, the depth of the crack can be clearly judged. Cracks with a larger depth usually indicate more serious damage to the pavement and greater development potential.

[0129] Quantification index: The depth range of cracks can be from 1 mm to 10 mm, with an accuracy of 0.1 mm. Cracks with a depth exceeding 5 mm are usually marked as high-risk cracks.

[0130] (4) Crack curvature: The curvature of a crack affects its propagation direction. Cracks with a larger curvature usually extend along areas such as the slab edge and corner, which may lead to more serious damage (such as slab edge spalling and corner fracture).

[0131] Quantification index: The minimum measurable range of crack curvature is 0.1 mm / mm. The system can effectively distinguish between curved cracks and straight cracks. Cracks with a curvature greater than 0.5 mm / mm are considered to have a higher risk of propagation.

[0132] (5) Crack propagation direction: The crack propagation direction can help us determine whether a crack may develop into corner fracture, slab edge spalling, or an ordinary crack. Cracks extending along joints or slab edges may cause more serious diseases.

[0133] Quantification index: When the angle between the crack propagation direction and the joint or slab corner is greater than 30°, it is determined that it may develop into slab edge spalling or corner fracture.

[0134] 2. Analysis of the Development Trend of Microcracks

[0135] The analysis of the development trend of microcracks is to predict the future expansion of cracks. By comprehensively analyzing the historical data of cracks and the real-time collected image data, it can effectively determine whether cracks will develop into corner fractures, edge spalling, or ordinary cracks in the future.

[0136] 2.1 Input Features for Development Trend Analysis

[0137] The input features for development trend analysis include the physical features of cracks (such as length, width, depth, curvature, and propagation direction) and external environmental factors (such as temperature, humidity, traffic volume, etc.). All these features will be used as input data for training the machine learning model.

[0138] Physical features of cracks: Physical features such as length, width, depth, curvature, and propagation direction have been mentioned in the crack identification section, and they directly affect the future development potential of cracks.

[0139] External environmental factors:

[0140] Temperature: Drastic changes in temperature (especially the diurnal temperature difference) can cause the expansion and contraction of pavement materials, exacerbating the expansion of cracks. Especially under extreme weather conditions (such as low temperature or high temperature), the expansion rate of microcracks will accelerate.

[0141] Quantification index: When the temperature change amplitude is greater than 5℃ / hour, the crack expansion rate may accelerate, and key monitoring is required.

[0142] Humidity: The change in humidity also has a great impact on concrete pavements. Especially in an environment with high humidity, cracks may accelerate their expansion due to water penetration.

[0143] Quantification index: When the humidity change exceeds **30%**, the crack expansion risk increases, especially when the humidity and temperature fluctuate greatly.

[0144] Traffic volume: The traffic volume of the runway, the takeoff and landing frequency, and the weight of the aircraft will impose additional loads on the pavement. Especially under high-load conditions, microcracks are more likely to expand into more serious cracks.

[0145] Quantification index: When the traffic volume exceeds 500 flight operations per day, the crack expansion risk is relatively high.

[0146] 2.2 Machine Learning Model

[0147] By collecting a large amount of historical data and combining the physical features of cracks with external environmental factors, a machine learning prediction model is constructed. We have selected a deep learning model that combines the **Long Short-Term Memory Network (LSTM) and Convolutional Neural Network (CNN)** suitable for crack development prediction. This model can handle multi-dimensional inputs of historical data and image features and accurately predict the crack expansion trend.

[0148] Sample data collection: Historical detection data, temperature and humidity data, traffic volume data, etc. are collected and labeled with the type of crack development (such as corner break, edge spalling, or ordinary crack).

[0149] Training and optimization: By training this data, the machine learning model can learn the expansion patterns of cracks and the impact of different feature combinations on the future development trend of cracks.

[0150] Prediction and output: The trained model can, based on real-time data, output the probabilities of cracks developing into corner breaks, edge spalling, or ordinary cracks in the future, and provide a basis for maintenance decisions.

[0151] 2.3 Quantitative indicators for crack development trends

[0152] Corner break: When a crack is located at the corner of a pavement slab, with a crack width exceeding 1.5 mm, a depth exceeding 5 mm, and an expansion direction close to between **45° and 90°**, it is judged as a high-risk crack for corner break.

[0153] Edge spalling: When a crack is located at the four edges (joints) of a pavement slab, with a crack width exceeding 2 mm, a depth exceeding 4 mm, and an expansion direction along the edge of the slab, it is judged as edge spalling.

[0154] Ordinary crack: When a crack has a small width (usually less than 1.5 mm) and an expansion direction extending into the interior of the slab, it is judged as an ordinary crack.

[0155] III. Maintenance decision support

[0156] The maintenance decision support module, based on the structural characteristics of the airport runway pavement consisting of multiple slabs, takes the slab as the smallest processing unit for maintenance decisions. By comprehensively evaluating factors such as the number of micro-cracks and development trends (such as whether it will evolve into a corner break, edge spalling, or ordinary crack) within each slab, it provides specific maintenance tasks, priorities, and repair suggestions for maintenance personnel. This decision support system can customize a reasonable repair plan for each slab according to the specific conditions of the slab, improving the maintenance efficiency and accuracy.

[0157] 1. Input data and decision basis

[0158] The input data for maintenance decisions comes from the following aspects:

[0159] Number and distribution of micro-cracks within the slab:

[0160] The number and size of cracks within each slab, especially the number of micro-cracks (1 mm to 1.5 mm), will serve as an important basis for maintenance decisions.

[0161] Crack development trend:

[0162] Whether the micro-cracks within each slab will evolve into corner fractures, edge spalling, and ordinary cracks, the prediction model will evaluate the hazard level of the slab based on the type and development trend of the cracks.

[0163] Crack severity assessment:

[0164] Characteristics such as the length, width, depth, and propagation rate of the cracks determine the harmfulness of the cracks. Severe cracks require a higher maintenance priority.

[0165] Crack propagation rate and historical data:

[0166] Combining the speed of crack propagation with historical detection data can provide an intuitive basis for maintenance decisions. Slabs with rapid crack propagation need to be repaired first.

[0167] 2. Comprehensive evaluation method

[0168] The present invention proposes a comprehensive evaluation method, which combines the number, type, expansion trend of cracks within the slab and external factors to comprehensively evaluate each slab and determine whether repair is needed and the repair priority.

[0169] The specific process is as follows:

[0170] 2.1 Crack evaluation and type identification

[0171] Crack type identification:

[0172] The system identifies the crack types on each slab through the physical characteristics and development trend prediction model of the cracks, including:

[0173] Corner fracture (high-risk crack)

[0174] Edge spalling (medium-high-risk crack)

[0175] Ordinary crack (low-risk crack)

[0176] For each crack type, the system assigns a weight value:

[0177] Corner fracture: weight 5

[0178] Edge spalling: weight 4

[0179] Ordinary crack: weight 2

[0180] Crack quantity and area assessment:

[0181] Count the number and distribution area of cracks within each slab. Slabs with a larger number and area of cracks have a higher risk and a higher priority.

[0182] Quantitative indicators: For slabs with more than 5 cracks or an area exceeding 20%, they are considered to require key attention.

[0183] 2.2 Crack development trend assessment

[0184] Expansion rate assessment:

[0185] The system calculates the expansion rate of cracks in each slab, especially the expansion rate of micro-cracks (1mm to 1.5mm). Cracks with a faster expansion rate will have their potential hazards evaluated in advance and be assigned a higher maintenance priority.

[0186] Quantitative indicators: If the crack width increases by more than 1mm / half year, the system classifies it as "rapid expansion" and gives it priority treatment.

[0187] Predicting crack evolution:

[0188] Based on the characteristics of crack morphology, expansion direction, depth, etc., combined with a machine learning model, it is predicted that cracks may develop into corner breaks, edge spalling, or ordinary cracks in the future.

[0189] Quantitative indicators: Cracks predicted to be corner breaks or edge spalling have a higher maintenance priority.

[0190] 2.3 Comprehensive assessment and decision output

[0191] Through a comprehensive analysis of factors such as crack type, quantity, and development trend, the system generates a maintenance priority for each slab and outputs decision-making suggestions. The specific decision-making process is as follows:

[0192] Assessment priority:

[0193] Each slab calculates a comprehensive score based on factors such as the severity of its cracks (crack type, expansion rate), historical data, etc., as the maintenance priority.

[0194] Comprehensive score formula:

[0195] Comprehensive score = (crack type weight) × (crack quantity) × (expansion rate) + (historical repair record)

[0196] The higher the comprehensive score, the higher the priority, and the repair tasks will be processed first.

[0197] Repair methods and suggestions:

[0198] For slabs that need to be repaired, the system will automatically generate repair suggestions. According to the type and size of the cracks, corresponding repair methods such as filling, cutting, or relaying are recommended.

[0199] Maintenance task assignment:

[0200] Based on the priority, the system automatically assigns tasks to maintenance personnel and sets the execution time window for the tasks. The sections with higher priority need to be repaired within a shorter time.

[0201] Cost and resource optimization:

[0202] The system also estimates the repair cost according to the scale of the maintenance task and resource allocation (such as personnel, equipment, budget, etc.) and provides optimization suggestions to ensure the optimal allocation of resources.

[0203] The above are only the embodiments of the present invention. Specific technical solutions and / or common knowledge such as characteristics well known in the art are not described in detail herein. It should be noted that for those skilled in the art, without departing from the technical solution of the present invention, several deformations and improvements can still be made, which should also be regarded as the protection scope of the present invention, and these will not affect the implementation effect of the present invention and the practicality of the patent. The protection scope required by this application shall be subject to the content of its claims, and the specific implementation manners and the like recorded in the specification can be used to interpret the content of the claims.

Claims

1. A rapid detection system for microcracks in the rigid pavement of airport runways, characterized in that: The system includes: A vehicle-mounted integrated device, which is responsible for carrying all detection devices and performing mobile acquisition on the runway; it includes a vehicle body, a power system, a control system, and a data storage system; A dual three-dimensional structured light camera, which is used to synchronously collect three-dimensional image data of the pavement, and the acquisition resolution is not less than 1 mm; A high-precision GNSS+RTK positioning system, which is used to accurately position the image data; A data processing unit, which is used for image preprocessing, crack identification, and determination of development trends; A display and control system, which is used to display the detection results in real time and generate a maintenance decision report according to the crack prediction results.

2. The rapid detection system for micro-cracks on the rigid pavement of an airport runway according to claim 1, characterized in that: The vehicle-mounted integrated device can realize rapid and full-range micro-crack detection of the runway pavement without suspending airport operations.

3. The rapid detection system for microcracks on the rigid pavement of an airport runway according to claim 1, wherein: The minimum crack width resolution of the dual three-dimensional camera device is 1 mm, and the coverage width of each acquisition is not less than 5.2 m.

4. A method for a rapid detection system of microcracks in the rigid pavement of an airport runway, characterized in that: The method steps include: S1: Use a vehicle-mounted three-dimensional structured light device to collect three-dimensional image data of the airport runway pavement through the collaborative work of two devices, and the detection resolution is not less than 1 mm; S2: Preprocess the collected image data, including denoising, light equalization, etc., to improve the image quality; S3: Based on the preprocessed image data, use artificial intelligence algorithms to identify micro-cracks, judge the type, development trend, and possible future form of the cracks, and predict whether the cracks will develop into corner breaks, edge spalls, or ordinary cracks; S4: Provide decision support for runway maintenance according to the development trend of the cracks, and take treatment measures in advance to prevent the cracks from deteriorating further.

5. The method of a rapid detection system for microcracks in the rigid pavement of an airport runway according to claim 2, characterized in that: The detection resolution of micro-cracks in step S3 is 1 mm, which can effectively detect micro-cracks in the range of 1 mm to 1.5 mm.

6. The method of a rapid detection system for micro-cracks in rigid airport runway pavements according to claim 2, wherein: The future development trend of micro-cracks in step S3 is predicted by analyzing characteristic parameters such as the shape, width, depth, and propagation rate of the cracks.

7. A method for a rapid detection system of microcracks in rigid airport runway pavements according to claim 2, characterized in that: The types of micro-cracks include corner breaks, edge spalls, and ordinary cracks, and the harmfulness of the cracks to the runway is judged according to the type of cracks, and priority suggestions are provided for maintenance decisions.

Images