Aircraft-based concrete structure safety quantification nondestructive monitoring method and system

Abstract

The invention relates to the technical field of civil engineering structure safety monitoring and aircraft image detection, and discloses a safety quantification nondestructive monitoring method and system based on an aircraft concrete structure, and the method comprises the steps: constructing a multi-target path optimization model, and generating a track point sequence; the aircraft collects an image and calculates an image reliability score; identifying crack and spalling defects by using a deep learning model; calculating a structure risk index SFI based on a partial least squares regression model; a monitoring report is generated and uploaded to the cloud. The technical problem that in the prior art, the safety quantitative evaluation based on the in-flight image structure cannot be realized by depending on a manual inspection or static image recognition mode, especially under the conditions of a special-shaped curved surface structure, shielding of a complex area or violent illumination change is solved. Due to the fact that three-dimensional path optimization, an image reliability scoring mechanism and AI defect recognition are fused, intelligent recognition of structure surface covering and crack peeling is achieved, and the automation degree of concrete structure monitoring is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of civil engineering structure safety monitoring and aircraft image detection, and in particular to a method and system for quantitative non-destructive monitoring of concrete structure safety based on aircraft. Background Art

[0002] Currently, safety inspections of concrete structures mostly rely on manual inspections, local image acquisition, and post-processing analysis. However, these methods have significant shortcomings. For example, manual inspections are inefficient, susceptible to subjective experience, and difficult to systematically record the evolution of structural defects. Traditional static image recognition methods rely on single-angle or low-coverage images, often failing to fully capture early signs of degradation on the concrete surface, such as fine cracks, spalling, and exposed rebar. In engineering practice, especially for structures with complex geometric curves or obstructions, such as bridge piers, tunnel linings, and tall towers, aircraft are limited by imperfect trajectory planning, unstable flight attitudes, and image blur. This often leads to inconsistent image data quality, unclear crack boundary identification, and incomplete defect feature extraction, severely impacting subsequent image data processing and the accuracy of structural risk assessments. Existing technologies still have significant shortcomings in image acquisition stability, adaptive image data processing, structural defect parameter quantification, and automatic reporting, failing to fully meet the practical needs for efficient, accurate, quantitative, closed-loop, nondestructive monitoring of concrete structures in complex environments. Therefore, there is an urgent need for an aircraft monitoring method that integrates three-dimensional structural modeling, trajectory adaptive optimization, in-flight image quality assessment, AI defect recognition and structural risk quantification model. It can achieve high-quality processing of image data and intelligent quantitative expression of structural damage under conditions of attitude disturbance, illumination changes and complex structural morphology, so as to comprehensively improve the intelligence level, assessment accuracy and remote linkage capability of the concrete structure monitoring system. Summary of the Invention

[0003] In response to the above-mentioned technical deficiencies, the purpose of the present invention is to propose a method for quantitative non-destructive monitoring of concrete structure safety based on aircraft, aiming to solve the technical problem that the existing technology relies on manual inspection or static image recognition, especially in the case of irregular curved surface structures, complex occlusion areas or drastic lighting changes, and cannot achieve quantitative assessment of structural safety based on in-flight images.

[0004] In order to solve the above technical problems, the present invention adopts the following technical solutions: The present invention provides a method for quantitative non-destructive monitoring of concrete structure safety based on aircraft. The method for quantitative nondestructive monitoring of concrete structure safety based on aircraft includes: Step S10: Acquire the 3D laser point cloud data or BIM model data of the target concrete structure, extract the surface morphology data of the target concrete structure from it, and discretize the surface morphology data into a facet set S; set the candidate track point sequence according to the angle between the normal vector of each facet in the facet set S and the preset aircraft camera shooting angle, the minimum visual distance and the occlusion condition ; Construct a multi-objective path optimization model, the objective function in the multi-objective path optimization model includes the first objective function , the second objective function And the third objective function , combined with the non-dominated sorting genetic algorithm to solve the multi-objective path optimization model, and output a set of optimized track point sequences ; Step S20: Based on the optimized track point sequence The image captured at time t is obtained by shooting with the aircraft , according to the captured image Executing an optimized image optimization task to obtain an optimized captured image set; Step S30: Use model inference to extract crack and peeling defect areas from the optimized image set, and output defect parameters; the defect parameters include the bounding box of the defect area k , defect area boundary confidence , crack length , average crack width , number of cracks , number of peeling blocks and boundary roughness ; Step S40: Calculating the structural risk index SFI using the partial least squares regression method based on the defect parameters; Step S50: If the structural risk index SFI exceeds the preset high risk threshold, a non-destructive monitoring risk report is generated based on the structural risk index SFI, defect parameters and optimized captured image set, and uploaded to the cloud database using the aircraft's WIFI module and a preset API interface.

[0005] Preferably, in step S20, according to the captured image The steps of performing the optimized image optimization task to obtain the optimized captured image set include: obtaining the inertial measurement unit angular velocity of the aircraft at time t and angular acceleration and the total amplitude of attitude disturbance ; For the captured image Image clarity indicators are obtained based on pixel extraction, including Laplace variance , mean brightness and exposure offset , and combined with the angular velocity and angular acceleration and the total amplitude of attitude disturbance Comprehensive calculation of image reliability score , when the image reliability score Less than the preset image reliability score threshold When marking the image It is an untrustworthy image and records the time t as the position to be retaken; the retake task is performed according to the position to be retaken, combined with the captured image Generates a collection of optimized captured images.

[0006] Preferably, in step S10, the first objective function is the image coverage function, which is used to maximize the effective coverage of the track point shooting range to the target patch set; the second objective function is the path length minimization function, which is used to minimize the cumulative distance of the aircraft from the beginning to the end; the third objective function It is the imaging view quality function, which is used to optimize the angle between the camera optical axis and the surface normal to be close to vertical to improve the image geometric resolution and defect recognition ability.

[0007] Preferably, in step S30, the step of extracting crack and spalling defect areas from the optimized captured image set by using a model inference method and outputting defect parameters specifically includes: using a lightweight U-Net model to perform pixel-level segmentation on the images in the captured image set and outputting a crack mask. With peel mask , call the YOLOv8 target detection model in parallel to detect the defect area boundaries of the images in the image collection, and output the bounding box of the defect area k , defect area boundary confidence ; For crack mask Extract centerline and calculate crack length based on pixels , Calculate the average crack width using the sliding window vertical width measurement method ; Statistical calculation of the number of cracks , number of peeling blocks and crack boundary roughness .

[0008] Preferably, in step S30, the boundary roughness The "tortuosity" and "nonlinearity" used to effectively depict the crack edge are image geometric feature parameters for judging the degree of structural damage evolution. The calculation steps include: using Canny edge detection to detect the crack mask. Perform edge extraction to obtain crack edge pixels and divide the image into multiple Grid unit Box of different sizes, count the number of grid unit Boxes that can cover the pixels at the edge of the crack ; Change the size of the grid unit Box and repeat the iteration. During the iteration process of the grid unit Box size, the boundary roughness is obtained using logarithmic coordinate fitting , boundary roughness ,in, The value range is between 1 and 2. , indicating that the crack is straight; if , indicating that the cracks have many tortuous branches and the risk is higher.

[0009] Preferably, in step S40, the step of calculating the structural risk index SFI based on the defect parameters by using the partial least squares regression method specifically includes: normalizing the defect parameters to form a feature vector , input feature vector Input into the trained partial least squares regression model to obtain the structural risk index SFI, SFI ,in, are the variables after normalization of each parameter, and is the regression coefficient obtained by training historical crack and spalling annotation data; SFI , SFI indicates the degree of structural risk, and a higher SFI value indicates a more serious structural degradation.

[0010] Preferably, in step S20, the image reliability score The calculation formula is: , in, For the moment Capture images Image reliability score; The angular velocity and angular acceleration The total amplitude of the posture disturbance when the image was taken was calculated; is the Laplace variance in the image clarity index; image The mean brightness of It is the preset ideal brightness exposure reference point; is the exposure offset; To take the exponential function; and is the weight coefficient, satisfying , determined by experience or training data; are the sensitivity attenuation factors that control the total amplitude of attitude disturbance and the influence of the brightness mean, respectively.

[0011] The present invention also provides a non-destructive monitoring system for aircraft-based concrete structure safety quantification, comprising: The 3D modeling and path optimization module is used to obtain the 3D laser point cloud data or BIM model data of the target concrete structure, extract the surface morphology data of the target concrete structure from it, and discretize the surface morphology data into a facet set S; the candidate track point sequence is set according to the angle between the normal vector of each facet in the facet set S and the preset aircraft camera shooting angle, the minimum visual distance and the occlusion condition. ; Construct a multi-objective path optimization model, the objective function in the multi-objective path optimization model includes the first objective function , the second objective function And the third objective function , combined with the non-dominated sorting genetic algorithm to solve the multi-objective path optimization model, and output a set of optimized track point sequences ; Image acquisition and optimization module, used to optimize the track point sequence The image captured at time t is obtained by shooting with the aircraft , according to the captured image Executing an optimized image optimization task to obtain an optimized captured image set; The defect recognition and parameter extraction module is used to extract the crack and spalling defect areas from the optimized image set using model reasoning and output the defect parameters; the defect parameters include the bounding box of the defect area k , defect area boundary confidence , crack length , average crack width , number of cracks , number of peeling blocks and boundary roughness ; Structural risk calculation module, used to calculate the structural risk index SFI based on defect parameters using partial least squares regression method; The risk warning and upload module is used to generate a non-destructive monitoring risk report based on the structural risk index SFI, defect parameters and optimized captured image set if the structural risk index SFI exceeds the preset high-risk threshold, and upload it to the cloud database using the aircraft's WiFi module and preset API interface.

[0012] The present invention also provides a nondestructive monitoring device based on the safety quantification of aircraft concrete structures, comprising: a memory, a processor, and a nondestructive monitoring program based on the safety quantification of aircraft concrete structures stored in the memory and executable on the processor. When the nondestructive monitoring program based on the safety quantification of aircraft concrete structures is executed by the processor, a nondestructive monitoring method based on the safety quantification of aircraft concrete structures is implemented.

[0013] The present invention also provides a computer program product, including a program for nondestructive monitoring of aircraft concrete structure safety quantification. When the program is executed by a processor, the method for nondestructive monitoring of aircraft concrete structure safety quantification is implemented.

[0014] The beneficial effects of the present invention are as follows: by constructing a trajectory optimization and image data processing mechanism that integrates structural geometry, flight attitude and image quality indicators, high coverage and high stability of structural surface image acquisition are achieved, solving the problems of many blind spots in image shooting and blurred and unstable images in the existing technology.

[0015] The introduction of a deep learning-based image data processing model and a structural risk index regression method can automatically identify and extract parameters of concrete cracks and spalling defects, and realize quantitative assessment of the structural safety status, thereby improving the intelligence and assessment accuracy of the monitoring system. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1 The figure is a flow chart of a first embodiment of a method for quantitative nondestructive monitoring of aircraft concrete structure safety according to the present invention.

[0018] Figure 2 The present invention is a schematic diagram of a device for quantitative non-destructive monitoring of aircraft concrete structure safety. DETAILED DESCRIPTION

[0019] 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.

[0020] Example 1: Figure 1 FIG. 1 is a flow chart of a first embodiment of a method for quantitative nondestructive monitoring of aircraft concrete structure safety according to the present invention, and provides a first embodiment of a method for quantitative nondestructive monitoring of aircraft concrete structure safety according to the present invention.

[0021] In the first embodiment, the method for quantitative nondestructive monitoring of aircraft concrete structure safety includes: Step S10: Acquire the 3D laser point cloud data or BIM model data of the target concrete structure, extract the surface morphology data of the target concrete structure from it, and discretize the surface morphology data into a facet set S; set the candidate track point sequence according to the angle between the normal vector of each facet in the facet set S and the preset aircraft camera shooting angle, the minimum visual distance and the occlusion condition ; Construct a multi-objective path optimization model, the objective function in the multi-objective path optimization model includes the first objective function , the second objective function And the third objective function , combined with the non-dominated sorting genetic algorithm to solve the multi-objective path optimization model, and output a set of optimized track point sequences ; It should be noted that in step S10, the first objective function is the image coverage function, which is used to maximize the effective coverage of the track point shooting range to the target patch set; the second objective function is the path length minimization function, which is used to minimize the cumulative distance of the aircraft from the beginning to the end; the third objective function It is the imaging view quality function, which is used to optimize the angle between the camera optical axis and the surface normal to be close to vertical to improve the image geometric resolution and defect recognition ability.

[0022] It should be noted that when setting the candidate track point sequence, the spatial orientation of each facet extracted from the 3D model is first analyzed, that is, the direction of its surface normal is obtained. Based on the normal direction of each facet, multiple combination points of the aircraft's shooting position and attitude direction are preset within a certain range in front of it. Then, each combination point is sequentially determined to meet the following three conditions: First, the angle between the aircraft's camera's shooting direction and the facet's normal vector is determined to be nearly perpendicular, for example, between 75 and 105 degrees. This ensures that the camera is essentially facing the target surface during image acquisition, reducing distortion and enhancing defect detection. Second, the distance from the shooting point to the facet is determined to be within the set effective imaging range, for example, between 1 and 3 meters. This ensures that the image is neither out of focus due to distance or insufficient field of view due to proximity. Finally, it is determined whether the line of sight from the shooting point to the target facet is blocked by other structures. Occlusion judgment can be based on the spatial visibility analysis of the positional relationship of other facets in three-dimensional space. If there is occlusion, the candidate point is excluded. Only shooting points that meet all three conditions will be included in the candidate track point sequence for subsequent path optimization module to screen and sort.

[0023] It should be understood that, through the above-mentioned optimized path generation method, compared with the traditional uniform-speed linear flight or regular grid shooting method, this method can not only achieve high-coverage imaging of the concrete structure surface in complex shapes (such as arches, curved surfaces, and T-sections), but also significantly reduce the image resolution degradation and defect recognition errors caused by angle deviation, thereby providing highly reliable data support for subsequent image quality judgment and defect extraction.

[0024] In addition, based on the principle of the electrolytic cell, the flow and changes of current in different areas are monitored. During the corrosion process, the conduction of current will be affected by the distribution of electrolyte concentration. By utilizing this diffusion phenomenon (after a reinforced concrete structure in service reaches a certain service life, the ions in the concrete of the protective layer of its steel bars have interacted for many years, which can be approximately considered to satisfy the diffusion phenomenon), the current and voltage changes caused by corrosion can be detected in real time, and the degree of corrosion can be quantitatively analyzed. By combining image processing methods with electrochemical signals, the accuracy of the detection results of defects caused by corrosion can be further improved. Correspondingly, the aircraft in the present invention adopts a spring-type adaptive flight control rust quantitative non-destructive monitoring equipment, which uses a spring-type Internet of Things sensor. The sensor is equipped with 9 equal-height 5cm high trapezoidal spring contacts, and the ultimate elastic force of each trapezoidal spring is Lift with drones Set the optimal relationship, the formula is: ,in It is a constant spring coefficient. Through this design, the risk of structural defects caused by rust pits can be warned more than one year in advance.

[0025] Step S20: Based on the optimized track point sequence The image captured at time t is obtained by shooting with the aircraft , according to the captured image Executing an optimized image optimization task to obtain an optimized captured image set; It should be noted that, in step S20, according to the captured image The steps of performing the optimized image optimization task to obtain the optimized captured image set include: obtaining the inertial measurement unit angular velocity of the aircraft at time t and angular acceleration and the total amplitude of attitude disturbance ; For the captured image Image clarity indicators are obtained based on pixel extraction, including Laplace variance , mean brightness and exposure offset , and combined with the angular velocity and angular acceleration and the total amplitude of attitude disturbance Comprehensive calculation of image reliability score , when the image reliability score Less than the preset image reliability score threshold When marking the image It is an untrustworthy image and records the time t as the position to be retaken; the retake task is performed according to the position to be retaken, combined with the captured image Generate an optimized collection of captured images. Image reliability score The calculation formula is: ,in, For the moment Capture images Image reliability score; The angular velocity and angular acceleration The total amplitude of the posture disturbance when the image was taken was calculated; is the Laplace variance in the image clarity index; image The mean brightness of It is the preset ideal brightness exposure reference point; is the exposure offset; To take the exponential function; and is the weight coefficient, satisfying , determined by experience or training data; are the sensitivity attenuation factors that control the total amplitude of attitude disturbance and the influence of the brightness mean, respectively.

[0026] As can be understood, by incorporating a dual-factor assessment mechanism based on both posture disturbances and image content, the present invention can proactively identify image unreliability caused by flight jitter, focus failure, or abnormal lighting within the first instance of image acquisition, significantly reducing the incidence of subsequent recognition errors. Image reliability scores not only serve as an image screening criterion but also form an important foundation for credibility in subsequent defect recognition tasks, helping to ensure the stability of defect detection input data.

[0027] Step S30: Use model inference to extract crack and peeling defect areas from the optimized image set, and output defect parameters; the defect parameters include the bounding box of the defect area k , defect area boundary confidence , crack length , average crack width , number of cracks , number of peeling blocks and boundary roughness ; It should be noted that in step S30, the step of extracting crack and spalling defect areas from the optimized captured image set by using a model inference method and outputting defect parameters specifically includes: using a lightweight U-Net model to perform pixel-level segmentation on the images in the captured image set and outputting a crack mask. With peel mask , call the YOLOv8 target detection model in parallel to detect the defect area boundaries of the images in the image collection, and output the bounding box of the defect area k , defect area boundary confidence ; For crack mask Extract centerline and calculate crack length based on pixels , Calculate the average crack width using the sliding window vertical width measurement method ; Statistical calculation of the number of cracks , number of peeling blocks and crack boundary roughness . Boundary roughness The "tortuosity" and "nonlinearity" used to effectively depict the crack edge are image geometric feature parameters for judging the degree of structural damage evolution. The calculation steps include: using Canny edge detection to detect the crack mask. Perform edge extraction to obtain crack edge pixels and divide the image into multiple Grid unit Box of different sizes, count the number of grid unit Boxes that can cover the pixels at the edge of the crack ; Change the size of the grid unit Box and repeat the iteration. During the iteration process of the grid unit Box size, the boundary roughness is obtained using logarithmic coordinate fitting , boundary roughness ,in, The value range is between 1 and 2. , indicating that the crack is straight; if , indicating that the cracks have many tortuous branches and the risk is higher.

[0028] It should be noted that during defect region extraction from the optimized image set, a lightweight U-Net model is first used to perform pixel-level segmentation on the image. This U-Net model takes the original RGB image as input and employs an encoder-decoder architecture to extract semantic and boundary features layer by layer. The encoder, consisting of multiple layers of convolution, batch normalization, and max pooling modules, progressively extracts the spatial semantic features of crack and spalling regions. The decoder, using deconvolution and skip connections, gradually restores the high-dimensional feature maps to the original image resolution, achieving pixel-level segmentation of crack and spalling regions. The output layer consists of two independent channels, representing the probability maps of crack and spalling masks, respectively. Higher pixel values in the masks indicate a higher confidence level that the corresponding location is a defect class. Simultaneously, to quickly obtain bounding boxes and confidence information for structural defects, a pre-trained YOLOv8 object detection model is used in parallel. This model utilizes a multi-scale feature fusion architecture, enabling full-image defect candidate regression and classification confidence assessment in a single forward inference pass. The YOLOv8 model's detection process includes: taking the original image as input, extracting deep features through the Backbone network; feeding the feature map into the Neck network for multi-scale fusion to accommodate defects of varying sizes; and performing regression and classification on each candidate detection box in the Head network. The output includes: the coordinates of the bounding box surrounding the defect area; the defect category identifier; and the defect boundary confidence score, which indicates the model's confidence that the detection result is a valid defect area. Finally, the segmentation mask generated by the U-Net model is aligned with the bounding box detection results from the YOLOv8 model, and the categories are fused.

[0029] It is understandable that by deploying the pixel-level segmentation model and the target detection model in parallel, on the one hand, the boundaries of cracks and spalling areas can be accurately tracked (U-Net); on the other hand, it ensures that defective areas can be quickly and accurately located in complex backgrounds (YOLOv8). The two complement each other's advantages, improving the overall robustness and computational efficiency of structural defect identification.

[0030] Step S40: Calculating the structural risk index SFI using the partial least squares regression method based on the defect parameters; It should be noted that in this step, a multidimensional feature vector of the structural state is constructed based on the multiple defect parameters extracted in step S30. The parameters include: the bounding box size of the defect area, boundary confidence, total crack length, average width, number of cracks, number of spalled blocks, and crack boundary roughness. To eliminate the influence of different parameters in terms of dimension and scale, all defect parameters are normalized and arranged and combined into a unified input vector in a preset order. Subsequently, the partial least squares regression method is used to model and analyze the above feature vector. This method extracts the main direction features that best explain the output variables from the input features, establishes a mapping relationship between the features and the structural risk, and thus obtains the risk index (SFI) of the current structural state. As a comprehensive evaluation indicator, the SFI can reflect the comprehensive safety level of the target concrete structure in its current state. The numerical range of this risk index is usually divided into three levels: low risk, medium risk, and high risk, which is used to support the decision logic of whether to trigger subsequent on-site review or special reinforcement.

[0031] It is understandable that the partial least squares regression method has the advantage of processing defect parameters with high dimensional correlation, and can effectively avoid the problem of unstable prediction of traditional linear models in the context of variable collinearity, making the model more sensitive to abnormal changes in image parameters. By establishing a quantitative relationship between image defect parameters and structural safety status, an automated quantitative assessment of the structural health status is achieved.

[0032] Step S50: If the structural risk index SFI exceeds the preset high risk threshold, a non-destructive monitoring risk report is generated based on the structural risk index SFI, defect parameters and optimized captured image set, and uploaded to the cloud database using the aircraft's WIFI module and a preset API interface.

[0033] It should be noted that by introducing the aircraft communication interface and standardized API structure, the present invention enables the image data processing results to have remote synchronization capabilities, supports cross-platform risk visualization and subsequent big data management, and further enhances the engineering practicality and data closed-loop management capabilities of the image-driven non-destructive monitoring system.

[0034] Embodiment 2: In addition, the present invention provides a system for quantitative nondestructive monitoring of aircraft concrete structure safety, which adopts a method for quantitative nondestructive monitoring of aircraft concrete structure safety in the above embodiment, and can solve the technical problem of quantitative nondestructive monitoring of aircraft concrete structure safety. Compared with the prior art, the beneficial effects of the system for quantitative nondestructive monitoring of aircraft concrete structure safety provided by the present invention are the same as the beneficial effects of the method for quantitative nondestructive monitoring of aircraft concrete structure safety provided by the above embodiment, and the other technical features of the system for quantitative nondestructive monitoring of aircraft concrete structure safety are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0035] Example 3: The present invention provides a non-destructive monitoring device for aircraft concrete structure safety quantification, please refer to Figure 2A nondestructive monitoring device for aircraft concrete structure safety quantification includes: at least one processor; and a memory in communication with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method for aircraft concrete structure safety quantification and nondestructive monitoring described in the first embodiment. The nondestructive monitoring device for aircraft concrete structure safety quantification in the embodiment of the present invention may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (e.g., vehicle-mounted navigation terminals), and fixed terminals such as digital TVs and desktop computers. The nondestructive monitoring device for aircraft concrete structure safety quantification is merely an example and should not limit the functionality and scope of use of the embodiment of the present invention. A nondestructive monitoring device for aircraft concrete structure safety quantification may include a processing device 1001 (e.g., a central processing unit, graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 1002 or programs loaded from a storage device 1003 into a random access memory (RAM) 1004. RAM 1004 also stores various programs and data required for the operation of the nondestructive monitoring device for aircraft concrete structure safety quantification. Processing device 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input device 1007 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output device 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage device 1003 including, for example, a magnetic tape, hard disk, etc.; and communication device 1009. Communication device 1009 can allow the aircraft concrete structure safety quantification and nondestructive monitoring device to communicate with other devices wirelessly or wired to exchange data. While the figure shows an aircraft concrete structure safety quantification and nondestructive monitoring device with various systems, it should be understood that implementation or presence of all the illustrated systems is not required. More or fewer systems may alternatively be implemented or present.

[0036] Example 4: The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the aforementioned method for quantitative nondestructive monitoring of aircraft concrete structures. The computer program product provided by the present invention can solve the technical problem of quantitative nondestructive monitoring of aircraft concrete structures. Compared with the prior art, the beneficial effects of the computer program product provided by the present invention are the same as the beneficial effects of the method for quantitative nondestructive monitoring of aircraft concrete structures provided in the aforementioned embodiment, and are not further described here.

[0037] In particular, according to the embodiments disclosed in the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present invention are performed.

[0038] It should be understood that the various parts disclosed in the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any appropriate manner in any one or more embodiments or examples.

[0039] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A method for quantitative nondestructive monitoring of aircraft concrete structure safety, characterized in that: Methods include: Step S10: Acquire the 3D laser point cloud data or BIM model data of the target concrete structure, extract the surface morphology data of the target concrete structure from it, and discretize the surface morphology data into a facet set S; set the candidate track point sequence according to the angle between the normal vector of each facet in the facet set S and the preset aircraft camera shooting angle, the minimum visual distance and the occlusion condition ; Construct a multi-objective path optimization model, the objective function in the multi-objective path optimization model includes the first objective function , the second objective function And the third objective function , combined with the non-dominated sorting genetic algorithm to solve the multi-objective path optimization model, and output a set of optimized track point sequences ; Step S20: Based on the optimized track point sequence The image captured at time t is obtained by shooting with the aircraft , according to the captured image Executing an optimized image optimization task to obtain an optimized captured image set; Step S30: Use model inference to extract crack and peeling defect areas from the optimized image set, and output defect parameters; the defect parameters include the bounding box of the defect area k , defect area boundary confidence , crack length , average crack width , number of cracks , number of peeling blocks and boundary roughness ; Step S40: Calculating the structural risk index SFI using the partial least squares regression method based on the defect parameters; Step S50: If the structural risk index SFI exceeds the preset high risk threshold, a non-destructive monitoring risk report is generated based on the structural risk index SFI, defect parameters and optimized captured image set, and uploaded to the cloud database using the aircraft's WIFI module and a preset API interface.

2. A method for quantitative nondestructive monitoring of aircraft concrete structure safety as claimed in claim 1, characterized in that: In step S20, according to the captured image The steps of performing the optimized image optimization task to obtain the optimized captured image set include: obtaining the inertial measurement unit angular velocity of the aircraft at time t and angular acceleration and the total amplitude of attitude disturbance ; For the captured image Image clarity indicators are obtained based on pixel extraction, including Laplace variance , mean brightness and exposure offset , and combined with the angular velocity and angular acceleration and the total amplitude of attitude disturbance Comprehensive calculation of image reliability score , when the image reliability score Less than the preset image reliability score threshold When marking the image It is an untrustworthy image and records the time t as the position to be retaken; the retake task is performed according to the position to be retaken, combined with the captured image Generates a collection of optimized captured images.

3. The method for quantitative nondestructive monitoring of aircraft concrete structure safety according to claim 1, characterized in that: In step S10, the first objective function is the image coverage function, which is used to maximize the effective coverage of the track point shooting range to the target patch set; the second objective function is the path length minimization function, which is used to minimize the cumulative distance of the aircraft from the beginning to the end; the third objective function It is the imaging view quality function, which is used to optimize the angle between the camera optical axis and the surface normal to be close to vertical to improve the image geometric resolution and defect recognition ability.

4. The method for quantitative nondestructive monitoring of aircraft concrete structure safety according to claim 1, characterized in that: In step S30, the crack and peeling defect areas are extracted from the optimized captured image set by using a model inference method, and the defect parameters are output. Specifically, the steps include: using a lightweight U-Net model to perform pixel-level segmentation on the images in the captured image set, and outputting a crack mask. With peel mask , call the YOLOv8 target detection model in parallel to detect the defect area boundaries of the images in the image collection, and output the bounding box of the defect area k , defect area boundary confidence ; For crack mask Extract centerline and calculate crack length based on pixels , Calculate the average crack width using the sliding window vertical width measurement method ; Statistical calculation of the number of cracks , number of peeling blocks and crack boundary roughness .

5. The method for quantitative nondestructive monitoring of aircraft concrete structure safety according to claim 4, characterized in that: In step S30, the boundary roughness The "tortuosity" and "nonlinearity" used to effectively depict the crack edge are image geometric feature parameters for judging the degree of structural damage evolution. The calculation steps include: using Canny edge detection to detect the crack mask. Perform edge extraction to obtain crack edge pixels and divide the image into multiple Grid unit Box of different sizes, count the number of grid unit Boxes that can cover the pixels at the edge of the crack ; Change the size of the grid unit Box and repeat the iteration. During the iteration process of the grid unit Box size, the boundary roughness is obtained using logarithmic coordinate fitting , boundary roughness ,in, The value range is between 1 and 2. , indicating that the crack is straight; if , indicating that the cracks have many tortuous branches and the risk is higher.

6. The method for quantitative nondestructive monitoring of aircraft concrete structure safety according to claim 1, characterized in that: In step S40, the step of calculating the structural risk index SFI based on the defect parameters using the partial least squares regression method specifically includes: normalizing the defect parameters to form a feature vector , input feature vector Input into the trained partial least squares regression model to obtain the structural risk index SFI, SFI ， in, is the bounding box of defect area k , defect area boundary confidence , crack length , average crack width , number of cracks , number of peeling blocks and boundary roughness After normalization, the variables and is the regression coefficient obtained by training historical crack and spalling annotation data; SFI , SFI indicates the degree of structural risk, and a higher SFI value indicates a more serious structural degradation.

7. The method for quantitative nondestructive monitoring of aircraft concrete structure safety as claimed in claim 2, characterized in that: In step S20, image reliability score The calculation formula is: ， in, For the moment Capture images Image reliability score; The angular velocity and angular acceleration The total amplitude of the posture disturbance when the image was taken was calculated; is the Laplace variance in the image clarity index; is the normalized lower bound of the Laplace variance of image clarity; is the normalized upper bound of the Laplace variance of image clarity; image The mean brightness of It is the preset ideal brightness exposure reference point; is the exposure offset; To take the exponential function; and is the weight coefficient, satisfying , determined by experience or training data; are the sensitivity attenuation factors that control the total amplitude of attitude disturbance and the influence of the brightness mean, respectively.

8. A system for quantitative nondestructive monitoring of concrete structure safety based on aircraft, applied to a method for quantitative nondestructive monitoring of concrete structure safety based on aircraft according to any one of claims 1 to 7, characterized in that: The aircraft-based concrete structure safety quantitative non-destructive monitoring system includes: The 3D modeling and path optimization module is used to obtain the 3D laser point cloud data or BIM model data of the target concrete structure, extract the surface morphology data of the target concrete structure, and discretize the surface morphology data into a facet set S; the candidate track point sequence is set according to the angle between the normal vector of each facet in the facet set S and the preset aircraft camera shooting angle, the minimum visual distance and the occlusion condition. ; Construct a multi-objective path optimization model, the objective function in the multi-objective path optimization model includes the first objective function , the second objective function And the third objective function , combined with the non-dominated sorting genetic algorithm to solve the multi-objective path optimization model, and output a set of optimized track point sequences ; Image acquisition and optimization module, used to optimize the track point sequence The image captured at time t is obtained by shooting with the aircraft , according to the captured image Executing an optimized image optimization task to obtain an optimized captured image set; The defect recognition and parameter extraction module is used to extract the crack and spalling defect areas from the optimized image set using model reasoning and output the defect parameters; the defect parameters include the bounding box of the defect area k , defect area boundary confidence , crack length , average crack width , number of cracks , number of peeling blocks and boundary roughness ; Structural risk calculation module, used to calculate the structural risk index SFI based on defect parameters using partial least squares regression method; The risk warning and upload module is used to generate a non-destructive monitoring risk report based on the structural risk index SFI, defect parameters and optimized captured image set if the structural risk index SFI exceeds the preset high-risk threshold, and upload it to the cloud database using the aircraft's WiFi module and preset API interface.

9. A non-destructive monitoring device for aircraft concrete structure safety quantification, characterized in that: The equipment for nondestructive monitoring of aircraft concrete structure safety quantification includes: a memory, a processor, and a nondestructive monitoring program for aircraft concrete structure safety quantification stored in the memory and executable on the processor. When the nondestructive monitoring program for aircraft concrete structure safety quantification is executed by the processor, a method for nondestructive monitoring of aircraft concrete structure safety quantification according to any one of claims 1 to 7 is implemented.

10. A computer program product, characterized in that The computer program product includes a nondestructive monitoring program based on the safety quantification of aircraft concrete structures. When the nondestructive monitoring program based on the safety quantification of aircraft concrete structures is executed by a processor, a nondestructive monitoring method based on the safety quantification of aircraft concrete structures according to any one of claims 1 to 7 is implemented.

Images