Strain clamp defect detection method and system based on unmanned aerial vehicle digital X-ray

Abstract

The invention relates to the technical field of intelligent defect detection, in particular to a strain clamp defect detection method and system based on unmanned aerial vehicle digital X-rays. The method comprises the steps of obtaining target equipment information, and obtaining a detection strategy parameter according to the target equipment information; an imaging control parameter is generated by acquiring spatial positioning data and combining detection strategy parameters, a detection area is divided into a plurality of scanning subareas, and a special detection angle, hovering time and an image overlapping rate are set for each subarea; the defect detection result is subjected to confidence analysis, the detection confidence is calculated, when the detection confidence is lower than an acceptable range, a detection optimization adjustment instruction can be automatically triggered, self-adaptive adjustment is executed according to compensation control information, and detection parameters and a detection process are dynamically optimized; and the detection precision, reliability and adaptability are improved.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent defect detection, and in particular to a method and system for detecting defects in tension clamps based on drone digital X-rays. Background Art

[0002] As a key connecting component of transmission lines, tension clamps play the vital role of securing conductors and bearing tension. As power systems continue to expand and equipment ages, tension clamps are susceptible to fatigue cracks, corrosion defects, and loose bolts due to long-term exposure to mechanical stress, electrical loads, and environmental corrosion. These problems seriously impact the safe and stable operation of transmission lines, necessitating regular defect inspection.

[0003] Existing methods use drones equipped with X-ray equipment to perform radiographic inspections on tension clamps, which can reveal internal defects such as cracks and corrosion. Compared to traditional manual inspections, this method improves efficiency, avoids the safety risks of working at height, and, to a certain extent, meets the needs of non-destructive testing of power transmission equipment.

[0004] However, the detection parameter setting of existing X-ray detection technology mainly relies on experience and lacks adaptive adjustment capabilities, resulting in unstable detection accuracy and possible missed detection or false detection; this situation needs further improvement. Summary of the Invention

[0005] To address the problem of unstable detection accuracy caused by the lack of adaptive adjustment capability in existing X-ray detection technology, this application provides a method and system for detecting defects in tension clamps based on drone digital X-rays, which adopts the following technical solutions: In a first aspect, the present application provides a method for detecting defects in tension clamps based on drone digital X-rays, comprising the following steps: Obtain target device information, and obtain detection strategy parameters based on the target device information; Acquire spatial positioning data, and acquire imaging control parameters based on the spatial positioning data and the detection strategy parameters, wherein the detection area is divided into a plurality of scanning subareas, the imaging control parameters include the detection angle, hovering time, and image overlap rate of each subarea, and the spatial positioning data refers to the three-dimensional coordinate relationship of the UAV relative to each scanning subarea; triggering a scan execution instruction according to the imaging control parameters and the detection strategy parameters; Acquire an X-ray detection image according to the scan execution instruction, perform defect recognition analysis on the X-ray detection image, and obtain a defect detection result; Performing confidence analysis on the defect detection results, calculating detection confidence, comparing the detection confidence with a set acceptable range, and triggering a detection optimization adjustment instruction if the confidence is lower than the acceptable range; According to the detection optimization adjustment instruction, compensation control information is obtained, and according to the compensation control information, an adaptive adjustment instruction is triggered.

[0006] By adopting the above-mentioned technical solution, in order to solve the problem of lack of targetedness and adaptive adjustment capability of detection parameter settings in existing X-ray detection technology; this application obtains target device information, and obtains detection strategy parameters based on the target device information; generates imaging control parameters by obtaining spatial positioning data and combining detection strategy parameters, divides the detection area into several scanning partitions and sets a special detection angle, hovering time and image overlap rate for each partition; performs confidence analysis on the defect detection results and calculates the detection confidence. When the detection confidence is lower than the acceptable range, it can automatically trigger the detection optimization adjustment instruction and perform adaptive adjustment according to the compensation control information, dynamically optimize the detection parameters and the detection process, and improve the detection accuracy, reliability and adaptability.

[0007] Optionally, the target device information includes the model, installation location, and service life of the tension clamp, and the detection strategy parameters include flight path planning, radiographic detection mode, and image acquisition sequence. Acquiring the target device information and acquiring the detection strategy parameters based on the target device information specifically includes the following steps: According to the model of the tension clamp, determine the material thickness and structural characteristics of the clamp, and match it to obtain the corresponding radiographic detection mode; According to the installation location, obtain the tower coordinates and line direction information, and formulate the UAV flight path plan; Based on the years of operation, determine the degree of equipment aging and vulnerable parts, and develop a corresponding image acquisition sequence; Among them, the ray detection mode includes the setting parameters of the ray tube voltage and exposure time; the flight path planning includes the detection route and hovering point position; and the image acquisition sequence includes the detection angle sequence and the number of shots at each angle.

[0008] By adopting the above-mentioned technical solution, this application matches the X-ray detection mode by determining the material thickness and structural characteristics according to the tension clamp model, thereby ensuring the rationality of parameters such as the X-ray tube voltage and exposure time, and avoiding imaging quality problems caused by improper parameters; by obtaining the tower coordinates and line direction information according to the installation position to formulate flight path planning, the detection route and hovering point position are optimized, and the detection efficiency and safety are improved; by determining the aging degree of equipment and vulnerable parts according to the years of operation to formulate the image acquisition sequence, the targeted arrangement of the detection angle sequence and the number of shots is achieved, and the defect detection rate is improved; compared with the existing technology that adopts a fixed detection strategy, the formulation of intelligent detection strategies based on equipment characteristics is realized, which significantly improves the targetedness, efficiency and reliability of detection.

[0009] Optionally, according to the strain clamp model, the material thickness and structural characteristics of the clamp are determined, and the corresponding radiographic detection mode is matched, which specifically includes the following steps: According to the tension clamp model, the corresponding material density, equivalent thickness and structural complexity parameters are obtained from a preset equipment parameter library; Based on the material density and the equivalent thickness, calculating the energy range required for the ray to penetrate the wire clamp, and determining a reference value of the ray tube voltage; Correcting a reference value of the ray tube voltage according to the structural complexity parameter; Calculate the corresponding exposure time parameters based on the corrected tube voltage value and the preset imaging quality requirements; The corrected ray tube voltage value and the exposure time parameter are combined to generate a ray detection mode for the tension clamp model.

[0010] By adopting the above technical scheme, the existing X-ray detection method is unable to accurately calculate and match the radiation parameters according to the specific materials and structural characteristics of different tension clamps; this application establishes a preset equipment parameter library and obtains key parameters such as material density, equivalent thickness and structural complexity according to the tension clamp model; the energy range required for radiation penetration is calculated based on the material density and equivalent thickness to determine the reference value of the radiation tube voltage, thereby ensuring the matching of the radiation energy with the physical properties of the object being inspected; by correcting the voltage reference value according to the structural complexity parameter, the influence of the internal structure of the clamp on the radiation propagation is fully considered, thereby improving the accuracy of the parameter setting; by calculating the corresponding exposure time parameters based on the corrected radiation tube voltage value and the preset imaging quality requirements, the coordinated optimization of voltage and exposure time is achieved, thereby ensuring the stability of imaging quality; and significantly improving the adaptability of detection of different models of tension clamps and the consistency of imaging quality.

[0011] Optionally, the detection angle includes a partitioned forward detection angle and a partitioned lateral detection angle, and obtaining spatial positioning data, and obtaining imaging control parameters according to the spatial positioning data and the detection strategy parameters, specifically includes the following steps: Obtain the three-dimensional coordinate relationship of the drone relative to each scanning partition and determine the spatial orientation information of each partition; Calculating the forward detection angle of the partition and the lateral detection angle of the partition according to the flight path planning and the spatial orientation information of each partition; Determining the hovering time of each partition according to the relationship between the ray detection mode and the three-dimensional coordinates of each partition; The image overlap ratio between each partition is calculated based on the image acquisition sequence and the spatial position relationship between adjacent partitions.

[0012] By adopting the above-mentioned technical solution, the present application determines the spatial orientation information by obtaining the three-dimensional coordinate relationship of the UAV relative to each scanning partition, and calculates the partition forward detection angle and the partition lateral detection angle by combining the flight path planning and spatial orientation information, thereby improving the comprehensiveness of defect detection; by determining the hovering time of each partition according to the X-ray detection mode and the three-dimensional coordinate relationship, the hovering time is accurately matched with the detection requirements, which not only ensures the imaging quality but also improves the detection efficiency; by calculating the image overlap rate according to the image acquisition sequence and the spatial position relationship of adjacent partitions, the seamless coverage of the detection area and the accuracy of image stitching are ensured, and detection blind spots and repeated detection are avoided; the dynamic optimization of imaging control parameters based on spatial positioning data is realized, which significantly improves the spatial accuracy, coverage integrity and stability of imaging quality of detection.

[0013] Optionally, acquiring an X-ray detection image according to the scan execution instruction, performing defect recognition analysis on the X-ray detection image, and obtaining a defect detection result specifically includes the following steps: According to the scanning execution instruction, the drone is controlled to sequentially acquire X-ray detection images according to the imaging control parameters of each partition; Preprocessing the X-ray detection image to obtain a standardized detection image, and identifying a body area, a connection area, and a fastener area of ​​the tension clamp based on the standardized detection image; Extracting defect features from the body area, the connection area, and the fastener area to detect defect types; According to the preset defect judgment criteria, the detected defects are classified and the severity is evaluated to generate the defect detection results for each partition.

[0014] By adopting the above-mentioned technical solution, the present application controls the UAV to obtain X-ray detection images in sequence according to the imaging control parameters of each partition based on the scanning execution instruction; preprocesses the X-ray detection images to obtain standardized detection images, and identifies the main body area, connection area and fastener area of ​​the tension clamp based on the standardized detection images; extracts defect features and detects defect types in different areas respectively; classifies and evaluates the severity of detected defects according to preset defect judgment criteria; and significantly improves the systematicity, accuracy and reliability of defect detection.

[0015] Optionally, performing confidence analysis on the defect detection result and calculating the detection confidence specifically include the following steps: Extracting defect feature parameters detected in each partition according to the defect detection results, wherein the defect feature parameters include defect boundary clarity, feature contrast, and shape integrity; Based on the defect characteristic parameters, calculating the reliability index of defect identification of each partition and generating a partition confidence value; Calculating image quality confidence based on imaging quality parameters of the standardized detection image, wherein the imaging quality parameters include image clarity and signal-to-noise ratio; Performing weighted fusion of the partition confidence value and the image quality confidence to calculate a comprehensive detection confidence; The comprehensive detection confidence is normalized to obtain a final detection confidence.

[0016] By adopting the above technical solution, the existing X-ray detection method lacks a mechanism for quantitatively evaluating the reliability of the detection results, and is unable to judge the accuracy and credibility of defect detection, resulting in difficulty in judging the detection results and difficulty in controlling the risks of false detection and missed detection; the present application extracts defect feature parameters such as defect boundary clarity, feature contrast and shape integrity detected in each partition; calculates the reliability index of defect recognition in each partition based on the defect feature parameters and generates a partition confidence value; calculates the image quality confidence based on imaging quality parameters such as image clarity and signal-to-noise ratio of the standardized detection image; finally, the partition confidence value and the image quality confidence are weightedly fused to calculate the comprehensive detection confidence; the final detection confidence is obtained by normalizing the comprehensive detection confidence; a complete confidence analysis system is established, which provides a reliable basis for detection quality control and result judgment, and significantly improves the intelligence level of the detection system and the credibility of the results.

[0017] Optionally, obtaining compensation control information according to the detection optimization adjustment instruction, and triggering the adaptive adjustment instruction according to the compensation control information specifically includes the following steps: Identifying the location of the partition with low confidence and the reason for the low confidence according to the detection optimization adjustment instruction; Determining compensation control information according to the cause of the low position, the compensation control information including a detection position fine-tuning instruction, a hovering attitude stabilization control instruction, and a repeated shooting instruction; According to the priority order of the compensation control information, the corresponding adaptive adjustment instructions are executed in sequence.

[0018] By adopting the above-mentioned technical solution, the present application identifies the partition positions with low confidence and the reasons for the low confidence based on the detection optimization adjustment instructions, and determines the compensation control information including the detection position fine-tuning instructions, the hovering attitude stabilization control instructions and the repeated shooting instructions according to the reasons for the low confidence, so as to take corresponding compensation measures for different types of detection problems; execute the corresponding adaptive adjustment instructions in sequence according to the priority order of the compensation control information, realize the systematic execution of the adjustment strategy and the optimal allocation of resources; and significantly improve the intelligence and adaptability of the detection system.

[0019] In a second aspect, the present application provides a tension clamp defect detection system based on drone digital X-ray, comprising: A detection strategy parameter acquisition module is used to obtain target device information and obtain detection strategy parameters based on the target device information; An imaging control parameter acquisition module is configured to acquire spatial positioning data and, based on the spatial positioning data and the detection strategy parameters, acquire imaging control parameters, wherein the detection area is divided into a plurality of scanning subareas, and the imaging control parameters include the detection angle, hovering time, and image overlap ratio of each subarea. The spatial positioning data refers to the three-dimensional coordinate relationship of the UAV relative to each scanning subarea. A scanning execution module, configured to trigger a scanning execution instruction according to the imaging control parameters and the detection strategy parameters; a defect detection module, configured to acquire an X-ray detection image according to the scan execution instruction, perform defect recognition analysis on the X-ray detection image, and obtain a defect detection result; A confidence analysis module is used to perform confidence analysis on the defect detection results, calculate the detection confidence, compare the detection confidence with a set acceptable range, and trigger a detection optimization adjustment instruction if the confidence is lower than the acceptable range; The adaptive adjustment module is used to obtain compensation control information according to the detection optimization adjustment instruction, and trigger the adaptive adjustment instruction according to the compensation control information.

[0020] In a third aspect, the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned method for detecting defects in tension clamps based on drone digital X-rays are implemented.

[0021] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-mentioned method for detecting defects in tension clamps based on drone digital X-rays.

[0022] In summary, this application includes at least one of the following beneficial technical effects: 1. This application obtains target device information and, based on this information, obtains detection strategy parameters. By acquiring spatial positioning data and combining it with the detection strategy parameters to generate imaging control parameters, the detection area is divided into several scanning zones, and each zone is assigned a specific detection angle, hovering time, and image overlap rate. By performing confidence analysis on defect detection results and calculating detection confidence, when the detection confidence falls below an acceptable range, it automatically triggers detection optimization adjustment instructions and performs adaptive adjustments based on compensation control information, dynamically optimizing detection parameters and the detection process. This improves detection accuracy, reliability, and adaptability. 2. This application matches the X-ray detection mode by determining the material thickness and structural characteristics based on the tension clamp model, ensuring the rationality of parameters such as X-ray tube voltage and exposure time, and avoiding imaging quality problems caused by inappropriate parameters. By obtaining the tower coordinates and line direction information based on the installation location to formulate flight path planning, the detection route and hovering point position are optimized, improving detection efficiency and safety. By determining the equipment aging degree and vulnerable parts based on the operating years to formulate the image acquisition sequence, the detection angle sequence and the number of shots are arranged in a targeted manner, thereby improving the defect detection rate. Compared with the existing technology that adopts a fixed detection strategy, this method realizes the formulation of intelligent detection strategies based on equipment characteristics, significantly improving the targetedness, efficiency and reliability of detection. 3. This application controls the drone to obtain X-ray detection images in sequence according to the imaging control parameters of each partition based on the scanning execution instruction; preprocesses the X-ray detection images to obtain standardized detection images, and identifies the main body area, connection area and fastener area of ​​the tension clamp based on the standardized detection images; extracts defect features and detects defect types in different areas respectively; classifies and evaluates the severity of detected defects according to preset defect judgment standards; and significantly improves the systematicity, accuracy and reliability of defect detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a flow chart of a method for detecting defects in tension clamps using drone digital X-rays according to an embodiment of the present application; Figure 2 This is a flow chart of step S100 in the method for detecting defects in tension clamps based on drone digital X-rays according to an embodiment of the present application; Figure 3This is a flow chart of step S110 in the method for detecting defects in tension clamps based on drone digital X-rays in an embodiment of the present application; Figure 4 This is a flow chart of step S200 in the method for detecting defects in tension clamps based on drone digital X-rays according to an embodiment of the present application; Figure 5 This is a flow chart of step S400 in the method for detecting defects in tension clamps based on drone digital X-rays according to an embodiment of the present application; Figure 6 This is a flow chart of step S500 in the method for detecting defects in tension clamps based on drone digital X-rays according to an embodiment of the present application; Figure 7 This is a flow chart of step S600 in the method for detecting defects in tension clamps based on drone digital X-rays according to an embodiment of the present application; Figure 8 This is a module schematic diagram of a tension clamp defect detection system based on drone digital X-rays according to an embodiment of the present application; Figure 9 This is a diagram of the internal structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0024] The terms used in the following examples of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification and appended claims of this application, the singular expressions "a," "an," "said," "above," "the," and "this" are intended to include plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in this application refers to any or all possible combinations comprising one or more of the listed items.

[0025] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood to imply or suggest relative importance or implicitly indicate the number of the technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of this application, unless otherwise specified, "plurality" means two or more.

[0026] The embodiments of the present application are described in further detail below with reference to the accompanying drawings.

[0027] In the first aspect, the present application provides a method for detecting defects in tension clamps based on drone digital X-rays, referring to Figure 1 , including the following steps: S100: Obtain target device information, and obtain detection strategy parameters based on the target device information.

[0028] In this embodiment, the target device information refers to the basic attribute information of the tension clamp to be inspected, including the model, installation location and operating years of the tension clamp; the detection strategy parameters refer to the detection configuration parameters formulated for specific target devices, including flight path planning, X-ray detection mode and image acquisition sequence.

[0029] S200 , obtaining spatial positioning data, and obtaining imaging control parameters according to the spatial positioning data and detection strategy parameters.

[0030] The detection area is divided into several scanning partitions. The imaging control parameters include the detection angle, hovering time and image overlap rate of each partition. The spatial positioning data refers to the three-dimensional coordinate relationship of the drone relative to each scanning partition.

[0031] In this embodiment, spatial positioning data refers to the three-dimensional coordinate relationship of the drone relative to each scanning partition, including distance information, angle information, and altitude information, obtained through the GPS positioning system and laser ranging sensor. Imaging control parameters refer to specific parameters that control the operation of the X-ray imaging equipment. Partition scanning can fully utilize the penetration range and imaging field of view of X-rays. A single shot can cover a continuous area containing multiple wire clamps and their connection points, achieving regular flight path planning. Compared with the jump scanning of each wire clamp, it reduces the drone's frequent direction changes and large position adjustments, improving detection efficiency and battery life. At the same time, the images generated by partition scanning have preset overlapping areas, which facilitates subsequent image stitching and three-dimensional reconstruction, avoiding the problem of single wire clamp scanning forming detection blind spots at the connection points.

[0032] Specifically, the system pre-establishes a spatial partitioning strategy library and formulates partitioning plans based on the distribution density and structural characteristics of wire clamps of different lines.

[0033] S300 , triggering a scan execution instruction according to imaging control parameters and detection strategy parameters.

[0034] In this embodiment, the scanning execution instruction refers to the UAV flight control instruction generated by integrating the imaging control parameters and the detection strategy parameters, including the flight path instruction, the equipment operation instruction, and the timing control instruction; the trigger mechanism refers to the control logic that automatically starts the scanning process after the parameter verification is completed.

[0035] Specifically, the system pre-establishes a parameter verification rule library that contains validity check rules for imaging control parameters and detection strategy parameters. The system first verifies whether the detection angle is within the operating range of the equipment, whether the hovering time meets the imaging stability requirements, and whether the image overlap rate meets the requirements for subsequent stitching processing. Once all parameters pass verification, the system automatically generates a scan execution instruction sequence including takeoff instructions, waypoint navigation instructions, and equipment startup instructions. These are executed in sequence according to the preset timing logic to ensure that the drone reaches each scanning area according to the planned path and starts the X-ray detection equipment at the designated location to complete image acquisition.

[0036] S400 , acquiring an X-ray detection image according to a scan execution instruction, performing defect recognition analysis on the X-ray detection image, and obtaining a defect detection result.

[0037] In this embodiment, the X-ray detection image refers to the internal structure image of the tension clamp obtained by a digital X-ray imaging device; defect recognition analysis refers to the process of identifying abnormal areas in the image through an image processing algorithm; the defect detection result refers to the identified defect type and location information, including crack defects, corrosion defects and deformation defects.

[0038] Specifically, the system pre-establishes a defect feature reference library, storing typical image feature parameters for different defect types. Image preprocessing utilizes histogram equalization and noise filtering. Feature extraction utilizes an edge detection algorithm to identify the wire clamp outline and a texture analysis algorithm to extract surface features. Defect classification is achieved by matching similarity with feature templates in the reference library. When the detected feature's similarity with the crack template exceeds a threshold, it is identified as a crack defect. When it matches the corrosion template, it is identified as a corrosion defect. Detection results are generated, including the defect type, location coordinates, and severity.

[0039] S500 , performing confidence analysis on the defect detection results, calculating the detection confidence, comparing the detection confidence with the set acceptable range, and triggering the detection optimization adjustment instruction if it is lower than the acceptable range.

[0040] In this embodiment, confidence analysis refers to the process of quantitatively evaluating the reliability of defect detection results, and the confidence value is calculated by analyzing image quality indicators and feature matching. Detection confidence refers to a value that indicates the degree of credibility of the detection result.

[0041] S600 : Acquire compensation control information according to the detection optimization adjustment instruction, and trigger the adaptive adjustment instruction according to the compensation control information.

[0042] In this embodiment, compensation control information refers to adjustment measures formulated to address detection quality issues, including position compensation, parameter compensation, and time compensation; adaptive adjustment instructions refer to device control instructions automatically executed based on compensation control information, including flight attitude adjustment instructions, imaging parameter adjustment instructions, and repeated detection instructions.

[0043] In one embodiment, the target equipment information includes the tension clamp model, installation location and operating years, and the detection strategy parameters include flight path planning, radiographic detection mode and image acquisition sequence; Figure 2 In step S100, target device information is obtained, and detection strategy parameters are obtained based on the target device information, which specifically includes the following steps: S110. Determine the material thickness and structural characteristics of the tension clamp according to the model of the tension clamp, and match the corresponding radiographic detection mode.

[0044] In this embodiment, the model of the tension clamp refers to the product specification identification set by the manufacturer, including the material code, size code and voltage level code; the material thickness refers to the wall thickness parameter of the main component of the clamp, which affects the penetration ability of X-rays; the structural characteristics refer to the geometric shape and internal structure of the clamp, including the spatial layout of the clamping part, the connecting part and the insulating part; the radiation detection mode refers to the working parameter configuration of the X-ray equipment, including the voltage range of the radiation tube and the exposure time range.

[0045] S120. According to the installation location, obtain the tower coordinates and line direction information, and formulate the UAV flight path plan.

[0046] In this embodiment, the installation location refers to the specific geographical location of the tension clamp in the power line, which is identified by the tower number and span information; the tower coordinates refer to the longitude and latitude coordinates and altitude information of the tower; the line direction information refers to the spatial direction and inclination angle of the conductors between adjacent towers; and the flight path planning refers to the navigation route of the UAV from the starting position to each detection point, including the detection route and the hovering point position.

[0047] S130. Determine the aging degree and vulnerable parts of the equipment based on the years of operation, and formulate a corresponding image acquisition sequence.

[0048] In this embodiment, the service life refers to the cumulative usage time of the tension clamp from commissioning to inspection; the degree of equipment aging refers to the level of performance degradation of the clamp material and structure over time; vulnerable parts refer to key parts that are prone to defects at a specific degree of aging, including stress concentration areas, connection interfaces and exposed surfaces; image acquisition sequence refers to the shooting order and parameters formulated for different parts, including the order of detection angles and the number of shots at each angle.

[0049] Specifically, the system pre-establishes a rule base for equipment aging assessment, which categorizes equipment aging based on years of operation. Mild aging is defined as 0-5 years of operation, focusing primarily on manufacturing defects and installation stresses, with vulnerable areas concentrated in bolted connections and clamping surfaces. Moderate aging is defined as 6-15 years of operation, focusing primarily on fatigue cracks and surface corrosion, with vulnerable areas extending to load-bearing structures and bending parts. Severe aging is defined as 16-30 years of operation, focusing primarily on material degradation and structural deformation, with vulnerable areas extending throughout the entire structure. The system develops differentiated image acquisition sequences based on the degree of aging: Mild aging utilizes a key area inspection sequence, capturing connections from both frontal and side angles, with one to two captures per angle. Moderate aging utilizes a comprehensive inspection sequence, capturing images from four angles: 0, 45, 90, and 135 degrees, with two to three captures per angle. Severe aging utilizes a detailed inspection sequence, capturing images from twelve angles at 30-degree intervals, with three to five captures at key angles, ensuring comprehensive identification of potential defects.

[0050] In one embodiment, referring to Figure 3 In step S110, the material thickness and structural characteristics of the tension clamp are determined according to the model of the tension clamp, and the corresponding radiographic detection mode is obtained by matching. Specifically, the following steps are included: S111. According to the tension clamp model, corresponding material density, equivalent thickness and structural complexity parameters are obtained from a preset equipment parameter library.

[0051] In this embodiment, the tension clamps include bolt type, wedge type, compression type and pre-twisted wire type, and have different models. The equipment parameter library refers to a pre-established database of technical parameters of tension clamps, which stores the physical properties and geometric parameters of different models of clamps; material density refers to the mass density of the clamp material, which affects the absorption coefficient of X-rays; equivalent thickness refers to the equivalent ray penetration thickness after considering the complex geometric shape of the clamp; the structural complexity parameter refers to a numerical value that quantifies the complexity of the internal structure of the clamp, including comprehensive evaluation indicators such as cavity distribution, wall thickness change, and geometric irregularity.

[0052] S112. Based on the material density and equivalent thickness, calculate the energy range required for the X-ray to penetrate the wire clamp and determine the reference value of the X-ray tube voltage.

[0053] In this embodiment, the radiation penetration energy refers to the minimum energy value required for X-rays to penetrate a specific material and thickness, which is related to the linear attenuation coefficient of the material; the energy range refers to the upper and lower energy limits taking into account the imaging quality requirements while ensuring penetration; and the radiation tube voltage reference value refers to the initial setting value of the X-ray tube operating voltage determined based on the penetration energy requirement.

[0054] S113. Correct the reference value of the ray tube voltage according to the structural complexity parameter.

[0055] In this embodiment, structural complexity correction refers to the process of adjusting the X-ray tube voltage according to the complexity of the internal structure of the wire clamp. Complex structures require higher X-ray energy to obtain clear internal details; the correction coefficient refers to the voltage adjustment multiple calculated based on the structural complexity parameter; the corrected X-ray tube voltage value refers to the final voltage setting value after the structural complexity adjustment.

[0056] Specifically, the system pre-establishes a structural complexity correction coefficient table that maps structural complexity scores to voltage correction coefficients. For structural complexity scores of 1.0-2.0, the correction coefficient ranges from 1.0-1.15, indicating a relatively simple structure and requiring no significant adjustment to the baseline voltage. For scores of 2.1-3.5, the correction coefficient ranges from 1.15-1.35, indicating a moderately complex structure requiring a moderately increased voltage to penetrate complex areas. For scores of 3.6-5.0, the correction coefficient ranges from 1.35-1.6, indicating a highly complex structure requiring a significantly increased voltage to ensure clear internal details. The system multiplies the baseline voltage by the corresponding correction coefficient to obtain the corrected tube voltage.

[0057] S114 , calculating corresponding exposure time parameters based on the corrected ray tube voltage value and the preset imaging quality requirement.

[0058] In this embodiment, the imaging quality requirement refers to the preset X-ray image quality standard, including quantitative indicators of image contrast, clarity and noise level; the exposure time parameter refers to the duration of X-ray exposure, which affects the brightness and signal-to-noise ratio of the image; the calculation process determines the optimal exposure time based on the inverse relationship between radiation intensity and exposure time.

[0059] S115. Combining the corrected ray tube voltage value and exposure time parameter to generate a ray detection mode for the tension clamp model.

[0060] In one embodiment, the detection angle includes a partition forward detection angle and a partition lateral detection angle, referring to Figure 4 In step S200, spatial positioning data is obtained, and imaging control parameters are obtained according to the spatial positioning data and detection strategy parameters, which specifically includes the following steps: S210: Obtain the three-dimensional coordinate relationship of the drone relative to each scanning partition, and determine the spatial orientation information of each partition.

[0061] In this embodiment, the three-dimensional coordinate relationship refers to the relative position relationship between the current position of the drone and the center point of each scanning partition in the three-dimensional space, including the distance vector, azimuth angle and pitch angle; the spatial orientation information refers to the parameters that describe the orientation and posture of each partition in space, including the normal vector, tilt angle and rotation angle of the partition plane, which are used to determine the optimal detection viewing angle and flight posture.

[0062] S220 . Calculate the forward detection angle and the lateral detection angle of each partition based on the flight path planning and the spatial orientation information of each partition.

[0063] In this embodiment, the forward detection angle of the partition refers to the detection angle at which the X-ray beam penetrates the main plane of the partition vertically, which can obtain a clear projection of the internal structure of the partition; the lateral detection angle of the partition refers to the detection angle at which the X-ray beam penetrates the partition from the side angle, which is used to detect defects that are difficult to detect at the forward angle; the calculation process determines the optimal detection angle combination based on the spatial geometric relationship and the ray propagation characteristics.

[0064] It is worth noting that the partition-level detection angle is used to determine the basic detection position of the drone relative to the detection area; while the device-level detection sequence is based on the determined partition detection position and realizes multi-angle detection of a single wire clamp by adjusting the pointing angle of the X-ray equipment.

[0065] S230 : Determine the hovering time of each partition according to the ray detection mode and the three-dimensional coordinate relationship of each partition.

[0066] In this embodiment, the hovering time refers to the time that the drone remains relatively stationary at each partition detection position, including the flight attitude stabilization time, equipment preparation time, image acquisition time and data transmission time; the determination process comprehensively considers the exposure requirements of the X-ray detection mode and the impact of the partition space complexity on stability.

[0067] S240 , calculating the image overlap ratio between each partition based on the image acquisition sequence and the spatial position relationship between adjacent partitions.

[0068] In this embodiment, the image overlap rate refers to the spatial repeated coverage ratio of adjacent partition detection images, which is used to ensure the continuity of the detection area and the reliability of image stitching; the calculation process determines the optimal overlap ratio based on the field of view range and the spatial interval between adjacent partitions in the image acquisition sequence; the spatial position relationship includes the partition spacing, relative angle and height difference.

[0069] In one embodiment, referring to Figure 5 In step S400, an X-ray detection image is acquired according to a scan execution instruction, and defect recognition analysis is performed on the X-ray detection image to obtain a defect detection result, which specifically includes the following steps: S410 , according to the scan execution instruction, controlling the drone to sequentially acquire X-ray detection images according to the imaging control parameters of each partition.

[0070] S420: Preprocess the X-ray detection image to obtain a standardized detection image, and identify the body area, connection area, and fastener area of ​​the tension clamp based on the standardized detection image.

[0071] In this embodiment, region recognition refers to the process of automatically locating and segmenting different functional parts in a standardized image. The main body area refers to the main load-bearing structure of the wire clamp, the connection area refers to the clamping part in contact with the wire, and the fastener area refers to the connection part composed of bolts, washers, and pins.

[0072] Specifically, a segmentation algorithm based on shape template matching is adopted, and the system pre-establishes a standard shape template library for various parts of the tension clamp. By matching the shapes of various parts, the main body area, connection area and fastener area are identified.

[0073] S430: Extract defect features from the body area, the connection area, and the fastener area respectively to detect the defect type.

[0074] In this embodiment, defect feature extraction refers to the process of extracting abnormal features from each functional area, including geometric features, texture features, and density features; defect type detection refers to the process of identifying specific defect categories based on the extracted features. The main defect types include cracks, corrosion, deformation, looseness, and wear; the defect manifestations and detection methods in different areas are different, and targeted feature extraction algorithms need to be adopted.

[0075] Specifically, the system pre-establishes a regional defect feature library, which stores the characteristic parameters and identification thresholds of typical defects in different areas. The defect feature extraction of the main body area adopts edge detection and connectivity analysis methods, the crack feature is identified by detecting the length-to-width ratio of the linear low-density area, and the corrosion feature is identified by analyzing the density reduction area with irregular boundaries. The connection area adopts shape analysis and contact surface detection methods, the deformation feature is identified by measuring the geometric deviation of the clamping part from the standard contour, and the loose feature is identified by detecting the change in the contact surface gap. The fastener area adopts roundness analysis and density gradient detection methods, the wear feature is identified by analyzing the change in the roundness of the bolt head, and the loose feature is identified by detecting the gradient change of the density distribution around the bolt. The system compares the extracted feature parameters with the preset threshold. When the feature parameters exceed the normal range, it automatically identifies it as the corresponding defect type and marks the specific location of the defect in the image.

[0076] S440: Classify and evaluate the severity of the detected defects according to the preset defect judgment standard, and generate defect detection results for each partition.

[0077] In one embodiment, referring to Figure 6 In step S500, the defect detection results are subjected to confidence analysis. The calculation of the detection confidence specifically includes the following steps: S510 , extracting defect feature parameters detected in each partition according to the defect detection result.

[0078] Among them, defect characteristic parameters include defect boundary clarity, feature contrast and shape integrity.

[0079] S520 : Based on the defect characteristic parameters, calculate the reliability index of defect identification of each partition and generate a partition confidence value.

[0080] In this embodiment, the reliability index refers to a quantitative value of the reliability of defect identification calculated based on the defect characteristic parameters; the partition confidence value refers to a comprehensive score indicating the reliability of the partition detection result, and the value range is usually between 0 and 1.

[0081] Specifically, the system pre-establishes a reliability index calculation model. This model maps characteristic parameters to test reliability based on statistical analysis of a large amount of historical test data. The model uses a weighted scoring method, combining three parameters: boundary clarity, feature contrast, and shape integrity, with different weights.

[0082] S530 , calculating image quality confidence according to imaging quality parameters of the standardized detection image, where the imaging quality parameters include image clarity and signal-to-noise ratio.

[0083] In this embodiment, the imaging quality parameter refers to an objective indicator reflecting the imaging effect of the X-ray image, which directly affects the accuracy of defect detection; image clarity refers to the sharpness and detail retention ability of the image, which is evaluated by analyzing the high-frequency components of the image; the signal-to-noise ratio refers to the ratio of useful information to noise in the image, reflecting the purity of the image; and the image quality confidence refers to the degree to which the image evaluated based on the imaging quality parameters can be used for reliable detection.

[0084] Specifically, the system establishes an association model between image quality and detection reliability. When the image quality parameters reach the preset standards, the image quality confidence is set to a higher value; when the image quality parameters are lower than the standard requirements, the confidence is reduced accordingly.

[0085] S540: Perform weighted fusion of the partition confidence value and the image quality confidence to calculate the comprehensive detection confidence.

[0086] In this embodiment, weighted fusion refers to the process of combining the partition confidence value and the image quality confidence according to preset weights. The comprehensive detection confidence refers to the final reliability score obtained after fusing multiple confidence indicators, which comprehensively reflects the overall credibility of the detection results. The weight setting needs to consider the degree of influence of different confidence indicators on the final detection results.

[0087] Specifically, the system pre-establishes a confidence fusion strategy library, assigning appropriate weighted combinations based on different inspection scenarios and task requirements. The fusion strategy utilizes an adaptive weighting approach, dynamically adjusting the weights of various confidence indicators based on the actual inspection situation. When image quality is good, the weight of the partition confidence value is set higher, primarily assessing the overall confidence level based on the quality of the defect detection results. When image quality is problematic, the weight of the image quality confidence value is set higher to avoid misjudgments due to image quality issues.

[0088] S550: Normalize the comprehensive detection confidence to obtain a final detection confidence.

[0089] In one embodiment, referring to Figure 7 In step S600, according to the detection optimization adjustment instruction, compensation control information is obtained, and according to the compensation control information, an adaptive adjustment instruction is triggered, which specifically includes the following steps: S610: Identify the location of the partition with low confidence and the reason for the low confidence according to the detection optimization adjustment instruction.

[0090] In this embodiment, the detection optimization adjustment instruction refers to the adjustment trigger instruction automatically generated by the system when the detection confidence is lower than the acceptable range, which includes the partition identification and adjustment type suggestion that needs to be re-detected; the partition position with low confidence refers to the specific partition number and spatial coordinates where the detection confidence does not reach the preset threshold; the reason for the low confidence refers to the specific factors that lead to insufficient confidence, including image quality problems, detection angle problems, environmental interference problems, and equipment parameter problems.

[0091] S620: Determine compensation control information based on the reason for the low position, where the compensation control information includes a detection position fine-tuning instruction, a hovering attitude stabilization control instruction, and a repeat shooting instruction.

[0092] In this embodiment, compensation control information refers to a set of adjustment measures formulated for specific reasons for low deviation, which is used to correct problems in the detection process and improve the detection quality; detection position fine-tuning instructions refer to control instructions for adjusting the position of the drone relative to the detection target, including distance adjustment, angle adjustment and height adjustment; hovering attitude stabilization control instructions refer to control instructions for improving the hovering stability of the drone, including attitude control parameter optimization, wind disturbance enhancement and position maintenance accuracy improvement; repeat shooting instructions refer to control instructions for re-executing image acquisition, including parameter reset, angle change and increase in number of times.

[0093] Specifically, the system pre-establishes a problem-measure mapping table that maps different types of low-angle causes to corresponding compensatory control measures. If the diagnosis result is image blur, the system generates a detection position fine-tuning instruction to adjust the distance between the drone and the target or change the detection angle to optimize the imaging geometry. If the diagnosis result is posture instability, the system generates a hovering attitude stabilization control instruction to enhance position maintenance accuracy and anti-interference capabilities. If the diagnosis result is inappropriate parameter settings, the system generates a repeat shooting instruction to re-acquire the image using the corrected radiation parameters.

[0094] S630 , executing corresponding adaptive adjustment instructions in sequence according to the priority order of the compensation control information.

[0095] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0096] Secondly, the present application provides a tension wire clamp defect detection system based on drone digital X-rays. The tension wire clamp defect detection system based on drone digital X-rays of the present application is described below in combination with the above-mentioned tension wire clamp defect detection method based on drone digital X-rays.

[0097] Reference Figure 8 , a tension clamp defect detection system based on drone digital X-ray, including: The detection strategy parameter acquisition module is used to obtain target device information and obtain detection strategy parameters based on the target device information; The imaging control parameter acquisition module is used to obtain spatial positioning data. Based on the spatial positioning data and detection strategy parameters, imaging control parameters are obtained. The detection area is divided into several scanning partitions. The imaging control parameters include the detection angle, hovering time, and image overlap rate of each partition. The spatial positioning data refers to the three-dimensional coordinate relationship of the UAV relative to each scanning partition. A scanning execution module is used to trigger a scanning execution instruction according to imaging control parameters and detection strategy parameters; The defect detection module is used to obtain X-ray detection images according to the scanning execution instruction, perform defect recognition analysis on the X-ray detection images, and obtain defect detection results; The confidence analysis module is used to perform confidence analysis on defect detection results, calculate detection confidence, and compare the detection confidence with the set acceptable range. If it is lower than the acceptable range, the detection optimization adjustment instruction is triggered; The adaptive adjustment module is used to obtain compensation control information according to the detection optimization adjustment instruction, and trigger the adaptive adjustment instruction according to the compensation control information.

[0098] In one embodiment, the present application provides an electronic device, which may be a server, and its internal structure diagram may be as follows: Figure 9 As shown. The electronic device includes a processor, a memory and a network interface connected via a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the electronic device is used to store data. The network interface of the electronic device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for detecting defects in tension clamps based on drone digital X-rays is implemented.

[0099] Those skilled in the art will understand that Figure 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the electronic device to which the solution of the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0100] In one embodiment, an electronic device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0101] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The above-described computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the above-described method embodiments. Any reference to memory, storage, database, or other media used in the embodiments provided herein may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0102] The above are all preferred embodiments of the present application, and are not intended to limit the scope of protection of the present application. Therefore, any equivalent changes made based on the structure, shape, and principle of the present application should be included in the scope of protection of the present application.

Claims

1. A method for detecting defects in tension clamps based on drone digital X-rays, characterized in that: The steps include: Obtain target device information, and obtain detection strategy parameters based on the target device information; Acquire spatial positioning data, and acquire imaging control parameters based on the spatial positioning data and the detection strategy parameters, wherein the detection area is divided into a plurality of scanning subareas, the imaging control parameters include the detection angle, hovering time, and image overlap rate of each subarea, and the spatial positioning data refers to the three-dimensional coordinate relationship of the UAV relative to each scanning subarea; triggering a scan execution instruction according to the imaging control parameters and the detection strategy parameters; Acquire an X-ray detection image according to the scan execution instruction, perform defect recognition analysis on the X-ray detection image, and obtain a defect detection result; Performing confidence analysis on the defect detection results, calculating detection confidence, comparing the detection confidence with a set acceptable range, and triggering a detection optimization adjustment instruction if the confidence is lower than the acceptable range; According to the detection optimization adjustment instruction, compensation control information is obtained, and according to the compensation control information, an adaptive adjustment instruction is triggered.

2. The method for detecting defects in tension clamps based on drone digital X-ray according to claim 1, characterized in that: The target device information includes the model, installation location, and service life of the tension clamp, and the detection strategy parameters include flight path planning, radiographic detection mode, and image acquisition sequence. Acquiring the target device information and acquiring the detection strategy parameters based on the target device information specifically includes the following steps: According to the model of the tension clamp, determine the material thickness and structural characteristics of the clamp, and match it to obtain the corresponding radiographic detection mode; According to the installation location, obtain the tower coordinates and line direction information, and formulate the UAV flight path plan; Based on the years of operation, determine the degree of equipment aging and vulnerable parts, and develop a corresponding image acquisition sequence; Among them, the ray detection mode includes the setting parameters of the ray tube voltage and exposure time; the flight path planning includes the detection route and hovering point position; and the image acquisition sequence includes the detection angle sequence and the number of shots at each angle.

3. The method for detecting defects in tension clamps based on drone digital X-ray according to claim 2, characterized in that: According to the model of the tension clamp, the material thickness and structural characteristics of the clamp are determined, and the corresponding radiographic detection mode is matched, which specifically includes the following steps: According to the tension clamp model, the corresponding material density, equivalent thickness and structural complexity parameters are obtained from a preset equipment parameter library; Based on the material density and the equivalent thickness, calculating the energy range required for the ray to penetrate the wire clamp, and determining a reference value of the ray tube voltage; Correcting a reference value of the ray tube voltage according to the structural complexity parameter; Calculate the corresponding exposure time parameters based on the corrected tube voltage value and the preset imaging quality requirements; The corrected ray tube voltage value and the exposure time parameter are combined to generate a ray detection mode for the tension clamp model.

4. The method for detecting defects in tension clamps based on UAV digital X-ray according to claim 2, characterized in that: The detection angle includes a partitioned forward detection angle and a partitioned lateral detection angle, and obtaining spatial positioning data. Based on the spatial positioning data and the detection strategy parameters, obtaining imaging control parameters specifically includes the following steps: Obtain the three-dimensional coordinate relationship of the drone relative to each scanning partition and determine the spatial orientation information of each partition; Calculating the forward detection angle of the partition and the lateral detection angle of the partition according to the flight path planning and the spatial orientation information of each partition; Determining the hovering time of each partition according to the relationship between the ray detection mode and the three-dimensional coordinates of each partition; The image overlap ratio between each partition is calculated based on the image acquisition sequence and the spatial position relationship between adjacent partitions.

5. The method for detecting defects in tension clamps based on UAV digital X-ray according to claim 1, characterized in that: Acquiring an X-ray detection image according to the scan execution instruction, performing defect recognition analysis on the X-ray detection image, and obtaining a defect detection result specifically includes the following steps: According to the scanning execution instruction, the drone is controlled to sequentially acquire X-ray detection images according to the imaging control parameters of each partition; Preprocessing the X-ray detection image to obtain a standardized detection image, and identifying a body area, a connection area, and a fastener area of ​​the tension clamp based on the standardized detection image; Extracting defect features from the body area, the connection area, and the fastener area to detect defect types; According to the preset defect judgment criteria, the detected defects are classified and the severity is evaluated to generate the defect detection results for each partition.

6. The method for detecting defects in tension clamps based on drone digital X-ray according to claim 5, characterized in that: Performing confidence analysis on the defect detection results and calculating the detection confidence specifically include the following steps: Extracting defect feature parameters detected in each partition according to the defect detection results, wherein the defect feature parameters include defect boundary clarity, feature contrast, and shape integrity; Based on the defect characteristic parameters, calculating the reliability index of defect identification of each partition and generating a partition confidence value; Calculating image quality confidence based on imaging quality parameters of the standardized detection image, wherein the imaging quality parameters include image clarity and signal-to-noise ratio; Performing weighted fusion of the partition confidence value and the image quality confidence to calculate a comprehensive detection confidence; The comprehensive detection confidence is normalized to obtain a final detection confidence.

7. The method for detecting defects in tension clamps based on drone digital X-ray according to claim 1, characterized in that: Acquiring compensation control information according to the detection optimization adjustment instruction, and triggering the adaptive adjustment instruction according to the compensation control information, specifically includes the following steps: Identifying the location of the partition with low confidence and the reason for the low confidence according to the detection optimization adjustment instruction; Determining compensation control information according to the cause of the low position, the compensation control information including a detection position fine-tuning instruction, a hovering attitude stabilization control instruction, and a repeated shooting instruction; According to the priority order of the compensation control information, the corresponding adaptive adjustment instructions are executed in sequence.

8. A tension clamp defect detection system based on drone digital X-ray, characterized in that: include: A detection strategy parameter acquisition module is used to obtain target device information and obtain detection strategy parameters based on the target device information; An imaging control parameter acquisition module is configured to acquire spatial positioning data and, based on the spatial positioning data and the detection strategy parameters, acquire imaging control parameters, wherein the detection area is divided into a plurality of scanning subareas, and the imaging control parameters include the detection angle, hovering time, and image overlap ratio of each subarea. The spatial positioning data refers to the three-dimensional coordinate relationship of the UAV relative to each scanning subarea. A scanning execution module, configured to trigger a scanning execution instruction according to the imaging control parameters and the detection strategy parameters; a defect detection module, configured to acquire an X-ray detection image according to the scan execution instruction, perform defect recognition analysis on the X-ray detection image, and obtain a defect detection result; A confidence analysis module is used to perform confidence analysis on the defect detection results, calculate the detection confidence, compare the detection confidence with a set acceptable range, and trigger a detection optimization adjustment instruction if the confidence is lower than the acceptable range; The adaptive adjustment module is used to obtain compensation control information according to the detection optimization adjustment instruction, and trigger the adaptive adjustment instruction according to the compensation control information.

9. An electronic device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the method for detecting defects of tension clamps based on drone digital X-rays according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for detecting defects in tension clamps based on drone digital X-rays according to any one of claims 1 to 7 are implemented.

Images