An ai-based construction scaffold structure health monitoring abnormal data diagnosis system

Abstract

The application discloses an AI-based construction scaffold structure health monitoring abnormal data diagnosis system, and belongs to the technical field of scaffolds, which comprises a data acquisition module, a plurality of sensors arranged in advance on a construction scaffold rod, the sensors being used to acquire detection data on the construction scaffold; a data processing module used to calculate data changes between every two detection data and obtain change data; a feature extraction module used to extract features from the change data according to a preset feature extraction method and obtain change features; and an AI diagnosis module used to input the change features into a construction scaffold structure health monitoring abnormal data AI diagnosis model generated by pre-training, output data diagnosis results corresponding to the change features, and perform abnormal warning when the data diagnosis results are abnormal. The system can more efficiently, accurately and timely monitor the construction scaffold structure health, thereby ensuring construction safety.

Description

Technical Field

[0001] This invention belongs to the field of scaffolding monitoring technology, specifically relating to an AI-based system for diagnosing abnormal data in the health monitoring of construction scaffolding structures. Background Technology

[0002] In the construction industry, construction scaffolding is a crucial temporary structure, providing a safe and reliable working platform for construction workers while also serving as a storage area for building materials and equipment. However, the structural health of scaffolding is affected by various factors during its use. Traditional methods for monitoring the structural health of scaffolding mainly rely on periodic manual inspections, which have several limitations. The inspection intervals are often long, potentially missing some potential problems that may occur during these periods. Furthermore, the accuracy of manual inspections is greatly affected by the experience and skill level of the inspectors, and some minor structural changes or initial damage may not be detected in time. In addition, for large and complex scaffolding systems, the comprehensiveness of manual inspections is difficult to guarantee. Summary of the Invention

[0003] In view of this, the purpose of this invention is to provide an AI-based construction scaffolding structure health monitoring and abnormal data diagnosis system, which can monitor the health of construction scaffolding structures more efficiently, accurately and in real time, thereby ensuring construction safety.

[0004] To achieve the above objectives, the present invention provides the following technical solution: This invention discloses an AI-based system for diagnosing abnormal data in the health monitoring of construction scaffolding structures, comprising: The data acquisition module includes multiple sensors pre-installed on the construction scaffold members, which are used to acquire detection data on the construction scaffold. The data processing module is used to calculate the data changes between every two detection data points and obtain the change data; The feature extraction module is used to extract features from changing data according to a preset feature extraction method to obtain the changing features; The AI ​​diagnostic module is used to input the changing characteristics into the pre-trained AI diagnostic model for abnormal data of construction scaffold structure health monitoring, output the data diagnostic results corresponding to the changing characteristics, and issue anomaly warnings when the data diagnostic results are abnormal.

[0005] The system disclosed in this invention uses a data acquisition module to acquire real-time detection data on scaffold members. Compared with traditional manual inspection methods, it can achieve 24-hour uninterrupted monitoring, avoiding missed inspections caused by insufficient manual inspection frequency. Sensors are deployed at key stress points, which can comprehensively cover the dynamic changes of the scaffold, improving the comprehensiveness and accuracy of data acquisition.

[0006] Secondly, the data processing module can identify subtle anomalies in the scaffolding structure, such as member deformation and loose connections, by calculating the changes between every two detection data points, thus detecting potential risks at an early stage. This method of calculating changing data is more flexible than simply relying on static thresholds and can adapt to dynamic changes in different construction environments. The AI ​​diagnostic module performs intelligent analysis based on pre-trained models, learning the differences between normal and abnormal scaffolding states, thereby issuing timely warnings when data anomalies occur. The introduction of this module significantly improves the intelligence level of monitoring, enabling the system to have self-learning capabilities and continuously optimize diagnostic accuracy as data accumulates.

[0007] Furthermore, when the detected data is displacement data, the data processing module performs the following operations: The deformation data of each member is obtained by measuring the displacement data at both ends of the same member. The deformation data of the member is then compared with a first threshold, and the first diagnostic result is output.

[0008] Furthermore, the displacement data of the fastener is obtained by using the displacement data of two detection points adjacent to the fastener, and the vibration data of the fastener is obtained by using the displacement data of the fastener. The vibration frequency and amplitude of each fastener are compared to determine whether the vibration is consistent. The number of fasteners whose vibration frequency or amplitude is significantly different from other points is counted. This number is compared with the second threshold, and the second diagnostic result is output. When the number exceeds the second threshold, it is judged as an abnormal data result.

[0009] Furthermore, when the number of fasteners whose vibration frequency or amplitude is significantly different from other points does not exceed the second threshold, the data processing module also performs the following operations: using the fastener position information of the pre-installed fasteners on the platform plate erected on the upper-level members and the scaffold model, it obtains the deformation data of the upper-level members corresponding to the fasteners; using the fastener position information and the corresponding upper-level member deformation data, it obtains the displacement data of the fastener connection points; using the displacement data of the fastener connection points, it obtains the average displacement and maximum displacement difference of all fastener connection points; when the average displacement exceeds the preset third threshold or the maximum displacement difference exceeds the fourth threshold, it outputs the third diagnostic result and the fourth diagnostic result respectively.

[0010] Furthermore, the data processing module also performs the following operations: based on the displacement data of the rods near the fastener connection, it obtains the degree of fastener opening; by comparing the degree of fastener opening with a fifth threshold, it outputs a fifth diagnostic result; when the degree of opening is greater than the fifth threshold, it is judged that the data result is abnormal.

[0011] Furthermore, a sixth threshold, smaller than the fifth threshold, is preset. The number and location of fasteners whose opening degree falls between the sixth and fifth thresholds are counted, and the impact of these fasteners on the platform board is calculated. When the impact exceeds the seventh threshold, the data result is judged to be abnormal. , , These represent the distances between the platform plate and the current fastener in the x, y, and z directions, respectively. M, N, and O represent the number of fasteners separating the current fastener from the simulated weight in the x, y, and z directions, respectively. The preset influence coefficient; in For vibration resistance efficiency related to fasteners; This is the attenuation coefficient related to the scaffolding material.

[0012] The beneficial effects of this invention are as follows: This invention discloses an AI-based structural health monitoring and abnormal data diagnosis system for construction scaffolding. By deploying sensors to collect structural data of construction scaffolding in real time, and combining it with the rapid analysis of the AI ​​diagnostic module, it can promptly detect potential structural anomalies and issue warnings when data anomalies occur, effectively preventing safety accidents such as scaffolding collapses.

[0013] Other advantages, objectives, and features of the invention will be set forth in the following description and will be apparent to those skilled in the art in some respects, or may be learned by practice of the invention. The objectives and other advantages of the invention can be realized and obtained through the following description. Attached Figure Description

[0014] To make the objectives, technical solutions, and beneficial effects of this invention clearer, the following figures are provided for illustration: Figure 1 This is a flowchart of the data diagnostic system of the present invention; Figure 2 This is a schematic diagram showing the connection between the platform plate and the scaffolding model of the present invention; Figure 3 This is a diagram illustrating the connection of the fasteners; Figure 4 This is a diagram illustrating the connection of the clips. Detailed Implementation

[0015] like Figures 1-4 As shown, the present invention discloses an AI-based system for diagnosing abnormal data in the health monitoring of construction scaffolding structures, comprising: The data acquisition module includes multiple sensors pre-installed on the construction scaffold members, which are used to acquire detection data on the construction scaffold. The data processing module is used to calculate the data changes between every two detection data points and obtain the change data; The feature extraction module is used to extract features from changing data according to a preset feature extraction method to obtain the changing features; The AI ​​diagnostic module is used to input the changing characteristics into the pre-trained AI diagnostic model for abnormal data of construction scaffold structure health monitoring, output the data diagnostic results corresponding to the changing characteristics, and issue anomaly warnings when the data diagnostic results are abnormal.

[0016] This invention's technical solution utilizes multiple sensors deployed on the scaffolding's fasteners to collect real-time data on scaffolding changes under varying load conditions. Combined with an AI diagnostic module, the system can quickly identify anomalies and issue timely warnings, helping construction workers take preventative measures to avoid accidents. The data processing module calculates the changes between every two data points, ensuring data continuity and accuracy. Through a feature extraction module, the system can extract key features from large amounts of data, reducing redundant information and improving diagnostic accuracy. The AI ​​diagnostic module, based on a pre-trained model, automatically analyzes the extracted features to determine if any anomalies exist in the scaffolding structure. Compared to traditional manual inspection, AI diagnosis is more efficient and accurate, capable of handling large amounts of complex data, and reduces the possibility of human error.

[0017] In this embodiment, when the detected data is displacement data, the data processing module performs the following operations: This system obtains deformation data for each member by measuring displacement data at both ends of the same member. The deformation data is then compared with a first threshold to output a preliminary diagnostic result. By calculating deformation using displacement data from both ends of the same member, this system directly reflects the degree of bending, twisting, or stretching, avoiding misjudgments caused by relying solely on single-point data. For example, when scaffolding is subjected to uneven loads, members may experience localized deformation, which traditional methods may struggle to capture. This method, by comparing displacement at both ends, can more accurately assess the actual stress state of the members. Furthermore, by testing displacement data at only two points, it avoids the increased costs and installation inconvenience associated with multiple testing points.

[0018] The deformation data of each member is obtained by measuring the displacement data at both ends of the same member. Specifically, the displacement vectors of the displacement detection points A and B at both ends are assumed to be... and , , Then axial deformation , Assuming the bending occurs in the XY plane, then the bending deformation... , Torsion angle of torsional deformation Set the Z-axis as the axis of the rod, and the length of the rod as L, which is approximately equal to the distance between the two detection points.

[0019] In this embodiment, the displacement data of the fastener is obtained by using the displacement data of two detection points adjacent to the fastener, and the vibration data of the fastener is obtained by using the displacement data of the fastener. The vibration frequency and amplitude of each fastener are compared to determine whether the vibration is consistent. The number of fasteners whose vibration frequency or amplitude is significantly different from other points is counted. This number is compared with a second threshold, and a second diagnostic result is output. When the number exceeds the second threshold, it is determined that the data result is abnormal.

[0020] When statistically analyzing the displacement data of fasteners, it is assumed that the fasteners rigidly connect two rods, and that the rods undergo linear deformation after being subjected to force. Then... ,in For the displacement data of the fastener, and These represent the displacements of two adjacent detection points. Obtaining vibration data at the fastener based on displacement data at the fastener is existing technology, as will be understood by those skilled in the art.

[0021] In this embodiment, when the number of fasteners whose vibration frequency or amplitude is significantly different from other points does not exceed the second threshold, the data processing module further performs the following operations: using the fastener position information of the pre-installed fasteners on the platform plate erected on the upper-level members and the scaffold model, it obtains the deformation data of the upper-level members corresponding to the fasteners; using the fastener position information and the corresponding upper-level member deformation data, it obtains the displacement data of the fastener connection points; using the displacement data of the fastener connection points, it obtains the average displacement and maximum displacement difference of all fastener connection points; when the average displacement exceeds the preset third threshold or the maximum displacement difference exceeds the fourth threshold, it outputs the third diagnostic result and the fourth diagnostic result respectively.

[0022] Since the deformation data of each member has already been obtained, and the upper-level members are located at the top of the scaffold, their deformation data can be obtained based on their Z-axis coordinates. The position information of each upper-level member can be obtained through the scaffold model. When the position information of a clip coincides with that of an upper-level member, it indicates that the upper-level member corresponds to the clip, and these upper-level members are set as platform plate support members.

[0023] Assume the distance between the buckle and point A is L1 Assuming the deformation of the member conforms to the small deformation theory, the displacement changes linearly along the length of the member. The displacement data at the snap-fit ​​connection point is the displacement data of the member at that point.

[0024] Displacement of the snap-fit ​​connection point .

[0025] In this embodiment, the data processing module also performs the following operations: based on the displacement data of the rods near the fastener connection point, the opening degree of the fastener is obtained; by comparing the opening degree of the fastener with a fifth threshold, a fifth diagnostic result is output; when the opening degree is greater than the fifth threshold, it is determined that the data result is abnormal.

[0026] In this embodiment, a sixth threshold smaller than the fifth threshold is preset. The number and location information of fasteners whose opening degree falls between the sixth and fifth thresholds are counted, and the influence of these fasteners on the platform plate is calculated. When the impact exceeds the seventh threshold, the data result is judged to be abnormal. , , These represent the distances between the platform plate and the current fastener in the x, y, and z directions, respectively. M, N, and O represent the number of fasteners separating the current fastener from the simulated weight in the x, y, and z directions, respectively. The preset influence coefficient; in For vibration resistance efficiency related to fasteners; This is the attenuation coefficient related to the scaffolding material.

[0027] Because the effect of the simulated weight's predicted position on each fastener is non-linear, depending not only on the distance between the simulated weight's predicted position and the current fastener, but also on the number of fasteners in between, it exhibits non-linear characteristics. By considering the number and position of intermediate fasteners, a more accurate mathematical model can be established, more realistically reflecting the actual situation of vibration transmission. The vibration resistance efficiency related to the fasteners is affected by the fasteners themselves. When there are many fasteners separating the simulated weight prediction position from the current fastener, the intermediate fasteners act as dampers during vibration transmission, absorbing and attenuating some vibration energy. Therefore, when there are many fasteners separating the simulated weight prediction position from the current fastener, the vibration signal will be weakened due to the obstruction of the intermediate fasteners, resulting in a decrease in the intensity of the vibration signal received by the current fastener.

[0028] Finally, it should be noted that the above preferred embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail through the above preferred embodiments, those skilled in the art should understand that various changes can be made to it in form and detail without departing from the scope defined by the claims of the present invention.

Claims

1. An AI-based system for diagnosing abnormal data in the health monitoring of construction scaffolding structures, characterized in that, include: The data acquisition module includes multiple sensors pre-installed on the construction scaffold members, which are used to acquire detection data on the construction scaffold. The data processing module is used to calculate the data changes between every two detection data points and obtain the change data; The feature extraction module is used to extract features from changing data according to a preset feature extraction method to obtain the changing features; The AI ​​diagnostic module is used to input the changing characteristics into the pre-trained AI diagnostic model for abnormal data of construction scaffold structure health monitoring, output the data diagnostic results corresponding to the changing characteristics, and issue anomaly warnings when the data diagnostic results are abnormal.

2. The AI-based construction scaffolding structure health monitoring and abnormal data diagnosis system according to claim 1, characterized in that, When the detected data is displacement data, the data processing module performs the following operations: The deformation data of each member is obtained by measuring the displacement data at both ends of the same member. The deformation data of the member is then compared with a first threshold, and the first diagnostic result is output.

3. The AI-based construction scaffolding structure health monitoring and abnormal data diagnosis system according to claim 2, characterized in that, The displacement data of the fastener is obtained by using the displacement data of two detection points adjacent to the fastener. The vibration data of the fastener is obtained by using the displacement data of the fastener. The vibration frequency and amplitude of each fastener are compared to determine whether the vibration is consistent. The number of fasteners whose vibration frequency or amplitude is significantly different from other points is counted. This number is compared with the second threshold, and the second diagnostic result is output. When the number exceeds the second threshold, the data result is judged to be abnormal.

4. The AI-based construction scaffolding structural health monitoring and abnormal data diagnosis system according to claim 3, characterized in that, When the number of fasteners whose vibration frequency or amplitude is significantly different from other points does not exceed the second threshold, the data processing module also performs the following operations: using the fastener position information of the fasteners pre-installed on the platform plate erected on the upper-level members and the scaffold model, it obtains the deformation data of the upper-level members corresponding to the fasteners; using the fastener position information and the corresponding upper-level member deformation data, it obtains the displacement data of the fastener connection points; using the displacement data of the fastener connection points, it obtains the average displacement and maximum displacement difference of all fastener connection points; when the average displacement exceeds the preset third threshold or the maximum displacement difference exceeds the fourth threshold, it outputs the third diagnostic result and the fourth diagnostic result respectively.

5. The AI-based construction scaffolding structure health monitoring and abnormal data diagnosis system according to claim 2, characterized in that, The data processing module also performs the following operations: based on the displacement data of the rods near the fastener connection, it obtains the opening degree of the fastener; by comparing the opening degree of the fastener with a fifth threshold, it outputs a fifth diagnostic result; when the opening degree is greater than the fifth threshold, it is judged that the data result is abnormal.

6. The AI-based construction scaffolding structural health monitoring and abnormal data diagnosis system according to claim 5, characterized in that, A sixth threshold, smaller than the fifth threshold, is preset. The number and location of fasteners whose opening degree falls between the sixth and fifth thresholds are counted, and the impact of these fasteners on the platform board is calculated. When the impact exceeds the seventh threshold, the data result is judged to be abnormal. , , These represent the distances between the platform plate and the current fastener in the x, y, and z directions, respectively. M, N, and O represent the number of fasteners separating the current fastener from the simulated weight in the x, y, and z directions, respectively. The preset influence coefficient; in For vibration resistance efficiency related to fasteners; This is the attenuation coefficient related to the scaffolding material.

Images