A beam-column joint corner deformation early warning method, device, equipment and medium

Abstract

The application discloses a beam-column joint corner deformation early warning method, device, equipment and medium, and relates to the technical field of building structure service state monitoring. The method comprises the following steps: acquiring a first corner deformation value measured by a mechanical corner sensing device; if the first corner deformation value is greater than or equal to a first preset threshold value, it is determined that a first trigger signal is received; acquiring a second corner deformation value measured by a non-contact visual measurement unit; if the second corner deformation value is greater than or equal to a second preset threshold value, it is determined that a second trigger signal is received; it is judged whether the first trigger signal and the second trigger signal are received; if only the first trigger signal is received or only the second trigger signal is received, it is determined that a unilateral trigger state is generated; if the duration of the unilateral trigger state is greater than or equal to a preset time window threshold value, orange early warning information is output. The method improves the accuracy of beam-column joint corner deformation early warning.

Description

Technical Field

[0001] This application relates to the field of building structure service status monitoring technology, and in particular to a method, device, equipment and medium for early warning of corner deformation at beam-column joints. Background Technology

[0002] Frame structures are one of the most widely used structural forms in the construction industry. The beam-column joints, as key components transferring internal forces between beam and column ends, exhibit the most complex stress states. Under earthquakes, wind loads, and long-term service loads, damage accumulation easily occurs at the beam-column joints. The relative angular displacement of the core area of ​​the joint is a core indicator reflecting the degree of joint damage, and continuous monitoring of it is an important means of assessing the structural safety during service.

[0003] Currently, monitoring of angular deformation at beam-column joints mainly employs two approaches: contact sensors and non-contact visual measurement. The data from both methods are then fused using weighted averaging and Kalman filtering to output a single monitoring result, which is then combined with preset thresholds to generate an early warning. However, contact sensors, exposed to the outdoors for extended periods, are prone to zero-point drift and struggle to determine their operational status. Visual measurements are significantly affected by factors such as lighting and occlusion, and similarly lack independent assessment of the reliability of the results. Existing fusion methods operate in a black-box manner, making it impossible for users to distinguish between sensor malfunction and actual structural damage during warnings. Furthermore, thresholds are often set based on experience or specifications, lacking close integration with the actual structural performance.

[0004] In summary, existing technologies cannot effectively distinguish between sensor anomalies and actual structural damage, resulting in low accuracy in early warning of angular deformation at beam-column joints. Summary of the Invention

[0005] This application provides a method, device, equipment, and medium for early warning of corner deformation at beam-column joints, which can improve the accuracy of early warning of corner deformation at beam-column joints.

[0006] To achieve the above objectives, this application adopts the following technical solution: In a first aspect, this application provides a method for early warning of corner deformation at beam-column joints, the method comprising: The first angle deformation value measured by the mechanical angle sensing device is obtained, and it is determined whether the first angle deformation value is greater than or equal to a first preset threshold. If the first angle deformation value is greater than or equal to the first preset threshold, it is determined that a first trigger signal has been received. The first preset threshold corresponds to the angle value corresponding to the starting point of concrete cracking in the core area of ​​the node. The second angle deformation value measured by the non-contact vision measurement unit is obtained, and it is determined whether the second angle deformation value is greater than or equal to a second preset threshold. If the second angle deformation value is greater than or equal to the second preset threshold, it is determined that a second trigger signal has been received. The second preset threshold corresponds to the angle value corresponding to the yielding of the longitudinal reinforcement of the node, and the first preset threshold is less than the second preset threshold. Determine whether the first trigger signal and the second trigger signal have been received, and obtain the first determination result; If the first judgment result indicates that only the first trigger signal is received, or only the second trigger signal is received, it is determined to be a one-sided trigger state; Determine whether the duration of the unilateral trigger state is greater than or equal to a preset time window threshold; If the duration of the single-sided trigger state is greater than or equal to a preset time window threshold, an orange warning message will be output.

[0007] In some possible implementations, the second angular deformation value is obtained by a non-contact visual measurement unit through the following steps: Image data including the beam-column joint is acquired using a fixed-focus industrial camera at a preset frame rate; sub-pixel level coordinates of the bottom edge line of the beam and the side edge line of the column are extracted from the image data including the beam-column joint; object space coordinates are obtained based on the intrinsic parameter matrix, distortion coefficient, exterior orientation elements of the fixed-focus industrial camera relative to the measured node, and the sub-pixel level coordinates; the angle between the bottom edge line of the beam and the side edge line of the column is calculated based on the object space coordinates, and the difference between the angle and the baseline angle is calculated to obtain the second angular deformation value.

[0008] In some possible implementations, the method further includes: If the first judgment result indicates that the first trigger signal and the second trigger signal have been received, it is determined to be a double-sided confirmation state, and a red warning message is output.

[0009] In some possible implementations, the method further includes: If the duration of the unilateral triggering state is less than the preset time window threshold, it is determined to be an occasional interference and no orange warning information is output.

[0010] In some possible implementations, the method further includes: The system monitors the light intensity and visibility of the environment captured by the non-contact vision measurement unit; when the light intensity is less than a preset light threshold or the visibility is less than a preset visibility threshold, a visual state abnormality signal is generated; upon receiving the visual state abnormality signal and receiving the first trigger signal, a red warning message is output.

[0011] In some possible implementations, the method further includes: If a visual state abnormality signal is received but the first trigger signal is not received, a yellow warning message will be output.

[0012] Secondly, this application provides a beam-column joint corner deformation early warning device, the device comprising: The acquisition module is used to acquire a first angle deformation value measured by a mechanical angle sensing device, determine whether the first angle deformation value is greater than or equal to a first preset threshold, and if the first angle deformation value is greater than or equal to the first preset threshold, determine that a first trigger signal has been received; wherein, the first preset threshold corresponds to the angle value corresponding to the starting point of concrete cracking in the core area of ​​the node; acquire a second angle deformation value measured by a non-contact visual measurement unit, determine whether the second angle deformation value is greater than or equal to a second preset threshold, and if the second angle deformation value is greater than or equal to the second preset threshold, determine that a second trigger signal has been received; wherein, the second preset threshold corresponds to the angle value corresponding to the yielding of the longitudinal reinforcement of the node, and the first preset threshold is less than the second preset threshold; The judgment module is used to determine whether a first trigger signal and a second trigger signal are received, and obtain a first judgment result; if the first judgment result indicates that only the first trigger signal is received, or only the second trigger signal is received, it is determined to be a one-sided trigger state; it determines whether the duration of the one-sided trigger state is greater than or equal to a preset time window threshold; if the duration of the one-sided trigger state is greater than or equal to the preset time window threshold, it outputs an orange warning message.

[0013] Thirdly, this application provides a computing device, including a memory and a processor; The memory stores one or more computer programs, the one or more computer programs including instructions; when the instructions are executed by the processor, the computing device performs the method as described in any one of the first aspects.

[0014] Fourthly, this application provides a computer-readable storage medium for storing a computer program for performing the method as described in any one of the first aspects.

[0015] Fifthly, this application provides a computer program product comprising one or more computer instructions, wherein when the computer instructions are executed by a computer, the computer performs the method as described in any one of the first aspects.

[0016] As can be seen from the above technical solution, this application has at least the following beneficial effects: In this application, a first angular deformation value measured by a mechanical angular sensing device is obtained. If the first angular deformation value is greater than or equal to a first preset threshold, a first trigger signal is determined to be received. A second angular deformation value measured by a non-contact visual measurement unit is obtained. If the second angular deformation value is greater than or equal to a second preset threshold, a second trigger signal is determined to be received. It is then determined whether the first and second trigger signals are received. If only the first or only the second trigger signal is received, it is determined to be a unilateral trigger state. If the duration of the unilateral trigger state is greater than or equal to a preset time window threshold, an orange warning message is output. In existing technical solutions, contact sensors are prone to zero-point drift due to long-term exposure to the outdoors and have difficulty determining their working status. Visual measurements are significantly affected by factors such as lighting and occlusion and lack autonomous evaluation of the reliability of the results. Existing fusion methods are black-box, and users cannot distinguish between sensor malfunction and actual structural damage when issuing warnings. Furthermore, thresholds are mostly set based on experience or specifications, which are not closely integrated with the actual performance of the structure, resulting in low accuracy of angular deformation warnings at beam-column joints and frequent false alarms and missed alarms. As can be seen, this application sets up two independent measurement systems, a mechanical corner sensing device and a non-contact visual measurement unit, and cross-determines the trigger signals of the two. It only outputs an orange warning when triggered on one side and the duration exceeds the time window threshold, and outputs a red warning when triggered on both sides at the same time. At the same time, it activates a degradation judgment strategy when the visual measurement conditions deteriorate, which can effectively distinguish between sensor abnormalities and actual structural damage, and improve the accuracy of the warning.

[0017] It should be understood that the descriptions of technical features, technical solutions, beneficial effects, or similar language in this application do not imply that all features and advantages can be achieved in any single embodiment. Rather, it is understood that the description of a feature or beneficial effect means that a specific technical feature, technical solution, or beneficial effect is included in at least one embodiment. Therefore, the descriptions of technical features, technical solutions, or beneficial effects in this specification do not necessarily refer to the same embodiment. Furthermore, the technical features, technical solutions, and beneficial effects described in this embodiment can be combined in any suitable manner. Those skilled in the art will understand that embodiments can be implemented without one or more specific technical features, technical solutions, or beneficial effects of a particular embodiment. In other embodiments, additional technical features and beneficial effects may be identified in specific embodiments that do not embody all embodiments. Attached Figure Description

[0018] Figure 1 A flowchart illustrating a method for early warning of corner deformation at beam-column joints provided in this application embodiment; Figure 2 A schematic diagram of a beam-column joint corner deformation early warning device provided in this application embodiment; Figure 3This is a schematic diagram of a computing device provided in an embodiment of this application. Detailed Implementation

[0019] The terms "first," "second," and "third," etc., used in this application specification and accompanying drawings are used to distinguish different objects, not to limit a specific order.

[0020] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0021] Currently, the monitoring of angular deformation at beam-column joints mainly employs two methods: contact sensors and non-contact visual measurement. However, both methods have their own reliability issues that are difficult to assess independently.

[0022] The existing system performs weighted averaging and Kalman filtering on the data from both sources and outputs a single monitoring result, making it impossible for users to distinguish whether the warning is due to sensor failure or actual structural damage.

[0023] In view of this, this application provides a method for early warning of corner deformation at beam-column joints. This method can be applied to a processing device, which can be a terminal or a server. Terminals include, but are not limited to, smartphones, tablets, laptops, personal digital assistants, or smart wearable devices. Servers can be cloud servers, such as central servers in a central cloud computing cluster or edge servers in an edge cloud computing cluster. Alternatively, servers can be servers in a local data center. A local data center refers to a data center directly controlled by the user. Compared with existing technologies, this application sets up two independent measurement systems: a mechanical corner sensing device and a non-contact visual measurement unit. The trigger signals of both systems are cross-judged. An orange warning is output only when one side triggers the signal and the duration exceeds a time window threshold; a red warning is output when both sides trigger simultaneously. Furthermore, a degradation judgment strategy is activated when visual measurement conditions deteriorate. This effectively distinguishes between sensor anomalies and actual structural damage, improving the accuracy of the warning. To make the technical solution of this application clearer and easier to understand, the following describes a method for early warning of corner deformation at the beam-column joint provided by an embodiment of this application, in conjunction with the accompanying drawings. Figure 1 As shown in the figure, this is a flowchart of a method for early warning of corner deformation at the beam-column joint provided in an embodiment of this application.

[0024] The beam-column joint corner deformation early warning method provided in this application embodiment is applied to a processing device, which is connected to a mechanical corner sensing device and a non-contact visual measurement unit. The processing device includes a threshold determination module and a hierarchical decision module. The hierarchical decision module receives a first trigger signal output by the mechanical corner sensing device and a second trigger signal output by the non-contact visual measurement unit, and outputs a corresponding early warning level according to a preset cross-checking judgment rule. The method includes: S201. The processing device acquires the first angle deformation value measured by the mechanical angle sensing device. If the first angle deformation value is greater than or equal to the first preset threshold, it determines that the first trigger signal has been received. The processing device acquires the second angle deformation value measured by the non-contact visual measurement unit. If the second angle deformation value is greater than or equal to the second preset threshold, it determines that the second trigger signal has been received.

[0025] A mechanical angle sensing device is an angular displacement sensing device that is attached to the beam and column sides of the beam-column joint via rigid force transmission components. The device includes a housing, a rotating shaft, an angle sensing element, and a signal conditioning circuit. The rigid force transmission components include a first force transmission rod and a second force transmission rod. One end of the first force transmission rod is fixedly connected to the beam side, and one end of the second force transmission rod is fixedly connected to the column side. The other ends of the first and second force transmission rods are rigidly connected to the two ends of the rotating shaft, respectively. When relative rotation occurs between the beam and the column, a relative angular displacement is generated between the first and second force transmission rods. This relative angular displacement is transmitted to the rotating shaft through the rigid force transmission components, causing the rotating shaft to rotate. The angle sensing element converts the rotation angle of the rotating shaft into an electrical signal. The signal conditioning circuit amplifies and filters this electrical signal, outputting a measurable angular deformation value. The mechanical angle sensing device has a built-in threshold comparison circuit, which compares the measured angular deformation value with a first preset threshold.

[0026] The mechanical angle sensing device continuously monitors the angle deformation of the beam-column joint, obtains the first angle deformation value, and then uses a threshold comparison circuit to determine whether the measured first angle deformation value exceeds a first preset threshold. If the first angle deformation value is greater than or equal to the first preset threshold, the threshold comparison circuit in the mechanical angle sensing device generates a first trigger signal.

[0027] A non-contact vision measurement unit (NCMU) is a measuring device installed within the visible range of a beam-column joint, typically mounted on a wall or bracket 3 to 5 meters away from the node. This NCMU acquires image data containing the beam-column joint using a fixed-focus industrial camera at a preset frame rate. It extracts sub-pixel coordinates of the beam's bottom edge and the column's side edge from the image data. Based on the fixed-focus industrial camera's intrinsic parameter matrix, distortion coefficients, exterior orientation elements relative to the measured node, and the sub-pixel coordinates, it obtains the object-space coordinates. The NCMU then calculates the angle between the beam's bottom edge and the column's side edge using these object-space coordinates. The difference between this angle and the baseline angle is used to calculate the second angular deformation value. The baseline angle refers to the initial angle between the beam's bottom edge and the column's side edge recorded during system initialization.

[0028] The non-contact vision measurement unit has a built-in threshold comparison subunit, which compares the measured second corner deformation value with a second preset threshold. If the second corner deformation value is greater than or equal to the second preset threshold, the threshold comparison subunit in the non-contact vision measurement unit generates a second trigger signal.

[0029] The first preset threshold corresponds to the angle value at the initiation point of concrete cracking in the core area of ​​the node, and this first preset threshold is predetermined by the threshold determination module through numerical simulation. The second preset threshold corresponds to the angle value at the yielding of the longitudinal reinforcement of the node, and this threshold is predetermined by the threshold determination module through numerical simulation, with the value of the first preset threshold being less than the value of the second preset threshold.

[0030] In some possible implementations, the non-contact visual measurement unit includes an image acquisition subunit, a camera calibration subunit, a feature extraction subunit, an angle calculation subunit, and a threshold comparison subunit.

[0031] The image acquisition subunit uses a fixed-focus industrial camera to acquire image data including the beam-column joint at a preset frame rate, and outputs the acquired image data to the feature extraction subunit.

[0032] The camera calibration subunit adopts the checkerboard calibration method to calibrate the camera during the system installation phase, obtain the camera's intrinsic parameter matrix and distortion coefficients, and determine the camera's exterior orientation elements relative to the measured node through the calibration board. The intrinsic parameter matrix, distortion coefficients, and exterior orientation elements are then output to the feature extraction subunit.

[0033] The feature extraction subunit receives image data output from the image acquisition subunit and intrinsic parameter matrix, distortion coefficients, and exterior orientation elements output from the camera calibration subunit. The feature extraction subunit first performs denoising and enhancement processing on the image, and then uses the Canny edge detection algorithm to extract edge pixels. The feature extraction subunit employs a sub-pixel edge detection method, improving edge localization accuracy to the sub-pixel level by performing polynomial fitting on the gray values ​​near the edges, obtaining sub-pixel level coordinates for the beam bottom edge line and the column side edge line. When extracting edge lines, the feature extraction subunit uses weighted least squares for straight-line fitting, assigning higher weight values ​​to edge pixels closer to the node core area and lower weight values ​​to edge pixels farther from the node core area; the weight value is inversely proportional to the distance from the pixel to the node core area. Based on the intrinsic parameter matrix, distortion coefficients, and exterior orientation elements, the feature extraction subunit converts the sub-pixel level coordinates into object space coordinates and outputs the object space coordinates to the corner calculation subunit.

[0034] The rotation angle calculation subunit receives the object space coordinates output by the feature extraction subunit, calculates the angle between the bottom edge line of the beam and the side edge line of the column in the object space based on the object space coordinates, subtracts the angle of the current frame from the baseline angle recorded during system initialization to obtain the relative rotation angle deformation value, which is the displacement angle of the beam-column node, and outputs the relative rotation angle deformation value as the second rotation angle deformation value to the threshold comparison subunit.

[0035] The threshold comparison subunit receives the second angle deformation value output by the angle calculation subunit and compares the second angle deformation value with the second preset threshold provided by the threshold determination module. If the second angle deformation value is greater than or equal to the second preset threshold, the threshold comparison subunit generates a second trigger signal.

[0036] S202. The processing device determines whether it has received the first trigger signal and the second trigger signal, and obtains the first determination result.

[0037] The hierarchical decision module in the processing device determines whether the first trigger signal and the second trigger signal have been received, and obtains the first judgment result.

[0038] If the first judgment result indicates that only the first trigger signal or only the second trigger signal is received, then S203 is executed; if the first judgment result indicates that both the first trigger signal and the second trigger signal are received, then S205 is executed.

[0039] S203. The processing device is determined to be in a single-sided trigger state. It is then determined whether the duration of the single-sided trigger state is greater than or equal to the preset time window threshold.

[0040] A single-sided triggering state refers to a mechanical single-sided triggering state in which only the first triggering signal is received and the second triggering signal is not received, or a visual single-sided triggering state in which only the second triggering signal is received and the first triggering signal is not received.

[0041] The preset time window threshold is a pre-set time length in the hierarchical decision module used to filter occasional interference. The preset time window can be set to 3 seconds to 5 seconds.

[0042] After the hierarchical decision module determines that the state is in a unilateral triggering state, it checks whether the duration of the unilateral triggering state is greater than or equal to a preset time window threshold. If the hierarchical decision module receives only the first trigger signal and not the second trigger signal, it determines the state as a mechanical unilateral triggering state and marks the first corner deformation value acquired in this state as data to be verified. If the hierarchical decision module receives only the second trigger signal and not the first trigger signal, it determines the state as a visual unilateral triggering state and marks the second corner deformation value acquired in this state as data to be verified.

[0043] If the duration of the unilateral triggering state is greater than or equal to the preset time window threshold, the hierarchical decision module executes S204. If the duration of the unilateral triggering state is less than the preset time window threshold, the hierarchical decision module executes S206.

[0044] This application uses a time window to distinguish between instantaneous sensor noise or external vibration interference and continuous structural deformation. The hierarchical decision module only outputs warnings when the abnormal state persists, avoiding false alarms caused by instantaneous vibrations such as vehicle traffic, personnel activity, and wind vibration.

[0045] S204. If the duration of the single-sided trigger state is greater than or equal to the preset time window threshold, then an orange warning message will be output.

[0046] When the hierarchical decision-making module determines that the duration of a unilateral triggering state is greater than or equal to a preset time window threshold, the hierarchical decision-making module outputs an orange warning message.

[0047] The hierarchical decision-making module identifies unilateral triggering states that exceed the time window threshold as orange alerts, and outputs alert levels between red alerts and no alerts, providing clear verification prompts for operations and maintenance personnel.

[0048] S205. The processing equipment is confirmed to be in a dual-sided confirmation state and outputs a red warning message.

[0049] When the hierarchical decision-making module determines that the first judgment result characterization is simultaneously receiving the first trigger signal and the second trigger signal, the hierarchical decision-making module outputs a red warning message.

[0050] Since the two measurement principles are independent of each other, the probability of failure or interference occurring simultaneously is extremely low. When triggered on both sides, the hierarchical decision module confirms that the node has undergone real over-limit deformation, and therefore outputs the highest level red warning.

[0051] S206. If the duration of the single-sided trigger state is less than the preset time window threshold, it is determined to be an occasional interference and no orange warning information is output.

[0052] Intermittent interference refers to instantaneous triggering signals caused by non-continuous factors such as transient vibration, electromagnetic interference, or image noise. Intermittent interference is not persistent and does not indicate continuous damage or deformation to the structure.

[0053] When the hierarchical decision-making module determines that the duration of a single-sided triggering state is less than the preset time window threshold, the hierarchical decision-making module determines it as an occasional interference and does not output an orange warning message.

[0054] The hierarchical decision-making module eliminates instantaneous interference factors through a time window filtering mechanism, and only triggers an early warning when the abnormal state persists.

[0055] In some embodiments, the light intensity and visibility of the environment captured by the non-contact vision measurement unit are monitored; when the light intensity is less than a preset light threshold or the visibility is less than a preset visibility threshold, a visual state abnormality signal is generated; if a visual state abnormality signal is received and a first trigger signal is received, a red warning message is output. If a visual state abnormality signal is received but the first trigger signal is not received, a yellow warning message is output.

[0056] Specifically, the non-contact vision measurement unit also includes anomaly detection logic. This logic monitors the light intensity and visibility of the shooting environment by using the average grayscale value and the number of effective edge points of the image. When the non-contact vision measurement unit detects that the average grayscale value of the image is lower than a preset light threshold, the anomaly detection logic determines that the light intensity of the current shooting environment is insufficient, which will affect the accuracy of edge detection. When the non-contact vision measurement unit detects that the number of effective edge points is lower than a preset visibility threshold, the anomaly detection logic determines that there is fog or obstruction in the current shooting environment, which will affect image quality. When any of the above situations occur, the anomaly detection logic of the non-contact vision measurement unit generates a visual state anomaly signal. The visual state anomaly signal is used to indicate the deterioration of the measurement conditions of the non-contact vision measurement unit, indicating that the reliability of the visual measurement results is reduced.

[0057] Upon receiving a visual state anomaly signal, the hierarchical decision-making module employs a downgraded judgment strategy. This strategy is a conservative and safety-based decision-making method used by the hierarchical decision-making module when visual measurement results are unreliable. When the hierarchical decision-making module receives both a visual state anomaly signal and the first trigger signal, it directly outputs a red warning message. This approach is based on the principle that when the vision system is unreliable, the trigger signals from mechanical sensors require special attention; from a safety perspective, the measurement results from mechanical sensors are prioritized for judgment. When the hierarchical decision-making module receives a visual state anomaly signal but does not receive the first trigger signal, it outputs a yellow warning message. The yellow warning message is a warning conclusion output by the hierarchical decision-making module when visual measurement conditions deteriorate and the mechanical sensors do not detect any anomalies. This conclusion indicates that the visual measurement unit has malfunctioned and requires maintenance.

[0058] This degradation decision-making strategy allows the hierarchical decision module to switch to degradation mode when the vision system malfunctions due to deteriorating environmental conditions, avoiding monitoring blind spots caused by vision failure. Simultaneously, a yellow warning message prompts maintenance personnel to promptly check the vision measurement unit, ensuring system maintainability.

[0059] Taking a real-world scenario as an example, when the non-contact visual measurement unit detects that the average grayscale value of an image is lower than a preset illumination threshold at dusk, the anomaly detection logic generates a visual state anomaly signal. Upon receiving this signal, if the first angular deformation value measured by the mechanical corner sensor exceeds a first preset threshold, the hierarchical decision module outputs a red warning message. If the first angular deformation value measured by the mechanical corner sensor does not exceed the first preset threshold, the hierarchical decision module outputs a yellow warning message, prompting maintenance personnel to check whether the visual measurement unit has malfunctioned due to insufficient illumination.

[0060] In some embodiments, the threshold determination module determines a first preset threshold and a second preset threshold based on the design parameters and material mechanical properties of the target structure. Specifically, the threshold determination module establishes a refined finite element model of the target beam-column joint, which includes a concrete plastic damage model, a steel reinforcement constitutive model, and a bond-slip model. The threshold determination module applies a low-cycle cyclic load to the refined finite element model to simulate the entire process of the joint from the elastic stage to cracking, yielding, and failure. The threshold determination module extracts the displacement angle corresponding to the first cracking of the concrete from the load-displacement angle curve as the reference value of the first preset threshold, and extracts the displacement angle corresponding to the first yielding of the longitudinal reinforcement as the reference value of the second preset threshold. The threshold determination module multiplies the reference value of the first preset threshold by a first reduction factor to obtain the final first preset threshold. The threshold determination module multiplies the reference value of the second preset threshold by a second reduction factor to obtain the final second preset threshold. The first reduction factor is less than the second reduction factor. In this embodiment, the first reduction factor can be set to 0.7 to 0.8; the second reduction factor can be set to 0.85 to 0.9.

[0061] In some embodiments, during the system installation and commissioning phase, a standard rotation angle of known value is manually applied while simultaneously calibrating the mechanical angle sensing device and the non-contact vision measurement unit. This ensures that the measurement reference of the mechanical angle sensing device and the non-contact vision measurement unit are consistent. This shared-source calibration guarantees that the measurement references of the two measurement methods are identical, making the cross-verification results more accurate.

[0062] In some embodiments, the data storage module stores historical monitoring data and early warning event records. When the hierarchical decision-making module outputs an orange alert, the data storage module automatically extracts and saves video clips and mechanical measurement data of a duration before and after the trigger time for subsequent manual review. Each segment can be up to 30 seconds long. This processing mechanism allows maintenance personnel to retrieve detailed data from the trigger time after receiving an orange alert and manually review the video and measurement curves to determine whether the problem is a sensor malfunction or actual structural damage.

[0063] Based on the above, the method provided in this application generates trigger signals using two independent measurement methods: a mechanical corner sensing device and a non-contact visual measurement unit. The two signal sources are independent of each other, avoiding the influence of random errors from a single measurement method on the warning conclusion. The hierarchical decision module in the processing device categorizes the state into single-sided triggering and double-sided confirmation based on the combination of received trigger signals. When both signals trigger simultaneously, a red warning is directly output. The mutual confirmation using the two independent measurement methods confirms that the node has undergone genuine over-limit deformation. When only one signal triggers, the hierarchical decision module does not directly determine structural damage but instead enters a duration judgment process, outputting a warning only when the abnormal state persists, filtering out occasional false alarms. The hierarchical decision module uses a time window to distinguish between instantaneous sensor noise or external vibration interference and continuous structural deformation, avoiding false alarms caused by instantaneous vibrations such as vehicle traffic, personnel activity, and wind vibration.

[0064] The above text combined Figure 1 The method for early warning of corner deformation at beam-column joints provided in this application embodiment has been described in detail. The device and equipment provided in this application embodiment will be described below with reference to the accompanying drawings.

[0065] This application also provides a beam-column joint corner deformation early warning device, such as... Figure 2 As shown in the figure, this is a schematic diagram of a beam-column joint corner deformation early warning device provided in an embodiment of this application. The device includes: The acquisition module 301 is used to acquire a first angle deformation value measured by a mechanical angle sensing device, determine whether the first angle deformation value is greater than or equal to a first preset threshold, and if the first angle deformation value is greater than or equal to the first preset threshold, determine that a first trigger signal has been received; wherein, the first preset threshold corresponds to the angle value corresponding to the starting point of concrete cracking in the core area of ​​the node; acquire a second angle deformation value measured by a non-contact visual measurement unit, determine whether the second angle deformation value is greater than or equal to a second preset threshold, and if the second angle deformation value is greater than or equal to the second preset threshold, determine that a second trigger signal has been received; wherein, the second preset threshold corresponds to the angle value corresponding to the yielding of the longitudinal reinforcement of the node, and the first preset threshold is less than the second preset threshold; The judgment module 302 is used to determine whether a first trigger signal and a second trigger signal are received, and obtain a first judgment result; if the first judgment result indicates that only the first trigger signal is received, or only the second trigger signal is received, it is determined to be a one-sided trigger state; in the case of the one-sided trigger state, it is determined whether the duration of the one-sided trigger state is greater than or equal to a preset time window threshold; if the duration of the one-sided trigger state is greater than or equal to the preset time window threshold, an orange warning message is output.

[0066] In some possible implementations, the second angular deformation value is obtained by a non-contact visual measurement unit through the following steps: Image data including the beam-column joint is acquired using a fixed-focus industrial camera at a preset frame rate; sub-pixel level coordinates of the bottom edge line of the beam and the side edge line of the column are extracted from the image data including the beam-column joint; object space coordinates are obtained based on the intrinsic parameter matrix, distortion coefficient, exterior orientation elements of the fixed-focus industrial camera relative to the measured node, and the sub-pixel level coordinates; the angle between the bottom edge line of the beam and the side edge line of the column is calculated based on the object space coordinates, and the difference between the angle and the baseline angle is calculated to obtain the second angular deformation value.

[0067] In some possible implementations, the judgment module 302 is further configured to determine a dual-sided confirmation state and output a red warning message if the first judgment result indicates that the first trigger signal and the second trigger signal have been received.

[0068] In some possible implementations, the judgment module 302 is further configured to determine that if the duration of the unilateral triggering state is less than a preset time window threshold, it is an occasional interference and no orange warning information is output.

[0069] In some possible implementations, the device further includes: The monitoring module is used to monitor the light intensity and visibility of the shooting environment of the non-contact vision measurement unit; when the light intensity is less than a preset light threshold or the visibility is less than a preset visibility threshold, a visual state abnormality signal is generated; upon receiving the visual state abnormality signal and receiving the first trigger signal, a red warning message is output.

[0070] In some possible implementations, the monitoring module is also used to output a yellow warning message if a visual state abnormality signal is received but a first trigger signal is not received.

[0071] The beam-column joint corner deformation early warning device according to the embodiments of this application can correspondingly execute the method described in the embodiments of this application, and the other operations and / or functions of each module / unit of the beam-column joint corner deformation early warning device are respectively for implementing Figure 1 For the sake of brevity, the corresponding processes of each method in the illustrated embodiments will not be described in detail here.

[0072] This application also provides a computing device. For example... Figure 3 As shown in the figure, this is a schematic diagram of a computing device provided in an embodiment of this application. The computing device 300 includes a bus 301, a processor 302, a communication interface 303, and a memory 304. The processor 302, the memory 304, and the communication interface 303 communicate with each other via the bus 301.

[0073] Bus 301 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 3 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0074] The processor 302 can be any one or more of the following processors: central processing unit (CPU), graphics processing unit (GPU), microprocessor (MP), or digital signal processor (DSP).

[0075] Communication interface 303 is used for communication with external devices.

[0076] Memory 304 may include volatile memory, such as random access memory (RAM). Memory 304 may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid state drive (SSD).

[0077] The memory 304 stores executable code, and the processor 302 executes the executable code to perform the aforementioned beam-column joint corner deformation early warning method.

[0078] Specifically, in achieving Figure 2 In the case of the illustrated embodiment, and Figure 2 When the modules or units of the beam-column joint corner deformation early warning device described in the embodiment are implemented by software, the execution... Figure 2 The software or program code required for the functions of each module / unit can be partially or entirely stored in memory 304. Processor 302 executes the program code corresponding to each unit stored in memory 304, and executes the aforementioned beam-column joint corner deformation early warning method.

[0079] This application also provides a computer-readable storage medium. The computer-readable storage medium can be any available medium that a computing device can store, or a data storage device such as a data center containing one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive). The computer-readable storage medium includes instructions that instruct the computing device to execute the aforementioned beam-column joint corner deformation early warning method.

[0080] This application also provides a computer program product comprising one or more computer instructions. When the computer instructions are loaded and executed on a computing device, all or part of the processes or functions described in this application are generated.

[0081] The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, or data center to another website, computer, or data center via wired (e.g., coaxial cable, fiber optic) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0082] When the computer program product is executed by a computer, the computer executes any of the aforementioned beam-column joint corner deformation early warning methods. The computer program product can be a software installation package; when any of the aforementioned beam-column joint corner deformation early warning methods is required, the computer program product can be downloaded and executed on the computer.

[0083] The descriptions of the processes or structures corresponding to the above figures each have their own emphasis. For parts of a process or structure that are not described in detail, please refer to the relevant descriptions of other processes or structures.

[0084] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in this application should be covered within the scope of protection of this application.

Claims

1. A method for early warning of corner deformation at beam-column joints, characterized in that, The method includes: The first angle deformation value measured by the mechanical angle sensing device is obtained, and it is determined whether the first angle deformation value is greater than or equal to a first preset threshold. If the first angle deformation value is greater than or equal to the first preset threshold, it is determined that a first trigger signal has been received. The first preset threshold corresponds to the angle value corresponding to the starting point of concrete cracking in the core area of ​​the node. The second angle deformation value measured by the non-contact vision measurement unit is obtained, and it is determined whether the second angle deformation value is greater than or equal to a second preset threshold. If the second angle deformation value is greater than or equal to the second preset threshold, it is determined that a second trigger signal has been received. The second preset threshold corresponds to the angle value corresponding to the yielding of the longitudinal reinforcement of the node, and the first preset threshold is less than the second preset threshold. Determine whether the first trigger signal and the second trigger signal have been received, and obtain the first determination result; If the first judgment result indicates that only the first trigger signal is received, or only the second trigger signal is received, it is determined to be a one-sided trigger state; Determine whether the duration of the unilateral trigger state is greater than or equal to a preset time window threshold; If the duration of the single-sided trigger state is greater than or equal to a preset time window threshold, an orange warning message will be output.

2. The method according to claim 1, characterized in that, The second angular deformation value is obtained by the non-contact visual measurement unit through the following steps: Image data including beam-column joints is acquired using a fixed-focus industrial camera at a preset frame rate. Subpixel-level coordinates of the bottom edge line of the beam and the side edge line of the column are extracted from the image data containing the beam-column joint. Based on the intrinsic parameter matrix, distortion coefficients, exterior orientation elements of the fixed-focus industrial camera relative to the measured node, and the sub-pixel level coordinates, the object space coordinates are obtained. The angle between the bottom edge of the beam and the side edge of the column is calculated based on the object space coordinates. The difference between the angle and the baseline angle is calculated to obtain the second corner deformation value.

3. The method according to claim 1, characterized in that, The method further includes: If the first judgment result indicates that the first trigger signal and the second trigger signal have been received, it is determined to be a double-sided confirmation state, and a red warning message is output.

4. The method according to claim 1, characterized in that, The method further includes: If the duration of the unilateral triggering state is less than the preset time window threshold, it is determined to be an occasional interference and no orange warning information is output.

5. The method according to claim 1, characterized in that, The method further includes: Monitor the light intensity and visibility of the environment captured by the non-contact vision measurement unit; When the light intensity is less than a preset light threshold or the visibility is less than a preset visibility threshold, a visual state abnormality signal is generated. Upon receiving a visual state abnormality signal and the first trigger signal, a red warning message is output.

6. The method according to claim 5, characterized in that, The method further includes: If a visual state abnormality signal is received but the first trigger signal is not received, a yellow warning message will be output.

7. A beam-column joint corner deformation early warning device, characterized in that, The device includes: The acquisition module is used to acquire a first angle deformation value measured by a mechanical angle sensing device, determine whether the first angle deformation value is greater than or equal to a first preset threshold, and if the first angle deformation value is greater than or equal to the first preset threshold, determine that a first trigger signal has been received; wherein, the first preset threshold corresponds to the angle value corresponding to the starting point of concrete cracking in the core area of ​​the node; acquire a second angle deformation value measured by a non-contact visual measurement unit, determine whether the second angle deformation value is greater than or equal to a second preset threshold, and if the second angle deformation value is greater than or equal to the second preset threshold, determine that a second trigger signal has been received; wherein, the second preset threshold corresponds to the angle value corresponding to the yielding of the longitudinal reinforcement of the node, and the first preset threshold is less than the second preset threshold; The judgment module is used to determine whether a first trigger signal and a second trigger signal are received, and obtain a first judgment result; if the first judgment result indicates that only the first trigger signal is received, or only the second trigger signal is received, it is determined to be a one-sided trigger state; it determines whether the duration of the one-sided trigger state is greater than or equal to a preset time window threshold; if the duration of the one-sided trigger state is greater than or equal to the preset time window threshold, it outputs an orange warning message.

8. The apparatus according to claim 7, characterized in that, The judgment module is also used to determine a double-sided confirmation state and output a red warning message if the first judgment result indicates that the first trigger signal and the second trigger signal have been received.

9. A computing device, characterized in that, Including memory and processor; The memory stores one or more computer programs, the one or more computer programs including instructions; when the instructions are executed by the processor, the computing device performs the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store a computer program for performing the method as described in any one of claims 1 to 7.

Images