An online monitoring method and system based on steel structure construction status

Abstract

The present application discloses an online monitoring method and system based on the construction status of a steel structure, comprising: a steel structure weld data acquisition module, a steel structure weld data preprocessing module, a steel structure weld data feature extraction module, a steel structure weld quality monitoring model training module, and an online monitoring and feedback module. The method adopts technical means such as the steel structure weld data acquisition module, thereby effectively solving the technical problems in the prior art, and further realizing that during the steel structure construction process, the model will predict the current quality status of the weld based on these data. The system can also provide feedback based on the prediction results to guide construction personnel to perform corresponding quality control and repair operations, thereby improving the safety, reliability and durability of steel structure construction and ensuring the quality effect of steel structure construction.

Description

Technical Field

[0001] The present application relates to the technical field of online monitoring of steel structure construction status, and more specifically, to an online monitoring method and system based on steel structure construction status. Background Art

[0002] Online monitoring based on the construction status of steel structures covers many aspects, aiming to ensure safety, quality and efficiency during the construction process. The following are some common monitoring aspects:

[0003] Structural safety monitoring: Monitor the load conditions of steel structures, including static and dynamic loads, to ensure that the structure is not overloaded or produces excessive stress. Detect structural deformation, such as displacement, deformation rate, etc., and whether the structure meets the design requirements. Monitor the vibration of the structure to evaluate the stability and dynamic response of the structure.

[0004] Quality monitoring: Check the quality of welds, including the strength, density, and defects of weld joints, to ensure that the welding quality meets the standards. Monitor the coating conditions on the surface of steel structures, such as coating thickness, coating adhesion, and coating protective properties.

[0005] Safety monitoring: Monitor the safety of the construction site, including the safety behavior of construction personnel, the use of safety equipment, etc., to promptly identify and address potential safety hazards. Monitor the safety of steel structure hoisting and installation to ensure that hoisting operations comply with regulations and avoid accidents.

[0006] Through online monitoring of the above aspects, problems in the steel structure construction process can be discovered and solved in a timely manner, ensuring construction quality and safety, and improving the overall efficiency and reliability of the project.

[0007] The document with the prior art publication number CN115200538B provides an online monitoring method and system based on the construction status of the steel structure. The device adopts differential real-time monitoring to obtain the easily deformed position of the steel structure during the construction process, and implements low-frequency monitoring and control at the position that is not easy to deform, thereby reducing the redundancy of data processing volume, and implements high-frequency monitoring and control at the position that is easy to deform, thereby reducing the risk of deformation.

[0008] Although the above-mentioned prior art solution can achieve the relevant beneficial effects through the structure of the prior art, it still has the following defects: when the steel structure is constructed, it is necessary to perform welding construction between the steel structures. At this time, since the device is not convenient for real-time quality monitoring of the welds of the steel structure, the welds have quality defects, which affects the strength of the steel structure and has poor practicality.

[0009] In view of this, we propose an online monitoring method and system based on the construction status of steel structures. Summary of the invention

[0010] 1. Technical issues to be solved

[0011] The purpose of this application is to provide an online monitoring method and system based on the construction status of steel structures, which solves the technical problems raised in the above-mentioned background technology and achieves the technical effect of facilitating real-time quality monitoring of the welds of steel structures.

[0012] 2. Technical solution

[0013] The embodiment of the present application provides an online monitoring method and system based on the construction status of a steel structure, comprising the following steps:

[0014] S1. Steel structure weld data acquisition module: During the steel structure construction process, the steel structure weld data acquisition module continuously collects ultrasonic signal data of the weld through ultrasonic detection equipment;

[0015] S2, steel structure weld data preprocessing module: the steel structure weld data preprocessing module preprocesses the collected raw data to improve the quality and availability of the data;

[0016] S3, steel structure weld data feature extraction module: the steel structure weld data feature extraction module extracts useful features from the collected ultrasonic data, such as the propagation time of the sound wave, the spectrum characteristics of the reflection intensity, the waveform shape, etc.;

[0017] S4, steel structure weld quality monitoring model training module: the steel structure weld quality monitoring model training module selects an appropriate machine learning model and uses the preprocessed data to train the model to achieve real-time monitoring of weld quality;

[0018] S5. Online monitoring and feedback module: During the steel structure construction process, the online monitoring and feedback module inputs the pre-processed real-time ultrasonic data into the trained machine learning model. The model predicts the current quality status of the weld based on this data and provides quality feedback.

[0019] As an optional solution to the technical solution of the present application document, the steel structure weld data acquisition module selects suitable ultrasonic detection equipment during the steel structure construction process to ensure that it can perform effective ultrasonic detection on the steel structure welds, continuously collects ultrasonic signal data of the welds through the ultrasonic detection equipment, transmits the collected ultrasonic signal data to the data processing system, and stores it.

[0020] As an optional solution of the technical solution of the present application document, the steel structure weld data preprocessing module preprocesses the collected raw data to improve the quality and availability of the data, including missing value processing and data smoothing. The missing value processing: processing the missing values ​​that may exist in the collected data, which can be filled by interpolation methods, or data repair according to actual conditions;

[0021] Data smoothing: smoothing the collected data to eliminate mutations or fluctuations in the data, making it more continuous and stable.

[0022] As an optional solution of the technical solution of the present application document, the steel structure weld data feature extraction module extracts useful features from the collected ultrasonic data, such as the propagation time of the sound wave, the spectrum characteristics of the reflection intensity, the waveform shape, etc. The sound wave propagation time: calculates the time interval from the emission to the reception of the ultrasonic wave, which can provide information about the internal structure of the object being measured, such as the thickness of the weld or the location of the defect;

[0023] Spectral characteristics of the reflection intensity: performing spectrum analysis on the ultrasonic signal to extract spectrum characteristics, such as peak frequency and energy distribution of the spectrum, so as to capture information within different frequency ranges;

[0024] The waveform shape: analyzes the waveform shape of the ultrasonic signal, including the amplitude, period, pulse width and other characteristics of the waveform, to extract more detailed information, such as the shape and location of the defect.

[0025] As an optional solution to the technical solution of the present application document, the steel structure weld quality monitoring model training module selects a machine learning model of a support vector machine and uses preprocessed data to train the model to achieve real-time monitoring of weld quality.

[0026] As an optional solution of the technical solution of this application document, during the steel structure construction process, the online monitoring and feedback module inputs the pre-processed real-time ultrasonic data into the trained machine learning model. The model predicts the current quality status of the weld based on these data, and displays the prediction results in a visual form to the construction personnel and management personnel so that they can understand the weld quality in a timely manner. At the same time, the system can also provide feedback based on the prediction results to guide the construction personnel to perform corresponding quality control and repair operations, which can improve the safety, reliability and durability of steel structure construction and ensure the quality of steel structure construction.

[0027] 3. Beneficial effects

[0028] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0029] 1. Since this application adopts technical means such as steel structure weld data acquisition module, it effectively solves the technical problems in the prior art, and then realizes that during the steel structure construction process, the model will predict the current quality status of the weld based on these data. The system can also provide feedback based on the prediction results to guide construction personnel to perform corresponding quality control and repair operations, which can improve the safety, reliability and durability of steel structure construction and ensure the quality of steel structure construction.

[0030] 2. This application sets up a liquid extraction mechanism, and driven by the driving blow-drying mechanism, the liquid extraction airbag continuously sprays the solvent in the solvent seat onto the weld to clean the welding area, ensure the welding surface is clean, and ensure the accuracy of the collected data.

[0031] 3. This application sets a driving and drying mechanism to drive the weld brush to rotate, thereby cleaning the weld and avoiding the adhesion of welding slag. At the same time, under the action of the wind blades, the cleaned position is blown dry for rapid drying, which facilitates data collection and further ensures the accuracy of weld quality monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 A schematic diagram of the overall structural steel structure weld quality monitoring process of an online monitoring method and system based on the steel structure construction status disclosed in a preferred embodiment of the present application;

[0033] Figure 2 The overall structural diagram of an online monitoring method and system based on the steel structure construction status disclosed in a preferred embodiment of the present application;

[0034] Figure 3 A partial cross-sectional schematic diagram of the overall structure of an online monitoring method and system based on the construction status of a steel structure disclosed in a preferred embodiment of the present application;

[0035] Figure 4 A schematic diagram of the structure of a handheld frame and the like of an online monitoring method and system based on the construction status of a steel structure disclosed in a preferred embodiment of the present application;

[0036] Figure 5 A schematic cross-sectional view of a movable seat structure of an online monitoring method and system based on the steel structure construction status disclosed in a preferred embodiment of the present application;

[0037] Figure 6 A partial structural diagram of an online monitoring method and system based on the construction status of a steel structure disclosed in a preferred embodiment of the present application;

[0038] Explanation of the numbers in the figure: 1. Hand-held frame; 2. Screw rod; 3. Moving seat; 4. Drive drying mechanism; 5. Weld brush; 6. Liquid extraction mechanism; 101. Solvent seat; 102. Motor A; 301. Electric push rod; 302. Ultrasonic probe; 303. Baffle; 304. Spring; 401. Motor B; 402. Fan blade; 403. Driving wheel; 404. Driven wheel; 405. Universal joint; 406. Worm; 407. Pressure rod; 601. Liquid extraction air bag; 602. Pressure plate; 501. Worm gear. DETAILED DESCRIPTION

[0039] The present application is further described in detail below in conjunction with the accompanying drawings.

[0040] Reference Figure 1 , an online monitoring method and system based on the construction status of a steel structure, comprising the following steps:

[0041] S1. Steel structure weld data acquisition module: During the steel structure construction process, the steel structure weld data acquisition module continuously collects ultrasonic signal data of welds through ultrasonic detection equipment;

[0042] S2. Steel structure weld data preprocessing module: The steel structure weld data preprocessing module preprocesses the collected raw data to improve the quality and availability of the data;

[0043] S3, Steel structure weld data feature extraction module: The steel structure weld data feature extraction module extracts useful features from the collected ultrasonic data, such as the propagation time of the sound wave, the spectrum characteristics of the reflection intensity, the waveform shape, etc.;

[0044] S4. Steel structure weld quality monitoring model training module: The steel structure weld quality monitoring model training module selects an appropriate machine learning model and uses the preprocessed data to train the model to achieve real-time monitoring of weld quality;

[0045] S5. Online monitoring and feedback module: During the steel structure construction process, the online monitoring and feedback module inputs the pre-processed real-time ultrasonic data into the trained machine learning model. The model will predict the current quality status of the weld based on this data and provide quality feedback.

[0046] As an optional solution to the technical solution of this application document, the steel structure weld data acquisition module selects appropriate ultrasonic detection equipment during the steel structure construction process to ensure that it can perform effective ultrasonic detection on the steel structure welds, continuously collects ultrasonic signal data of the welds through the ultrasonic detection equipment, transmits the collected ultrasonic signal data to the data processing system, and stores it.

[0047] As an optional solution of the technical solution of this application document, the steel structure weld data preprocessing module preprocesses the collected raw data to improve the quality and availability of the data, including missing value processing and data smoothing. Missing value processing: processing the missing values ​​that may exist in the collected data, which can be filled by interpolation methods, or data repair according to actual conditions;

[0048] Data smoothing: Smoothing the collected data to eliminate mutations or fluctuations in the data, making it more continuous and stable.

[0049] As an optional solution of the technical solution of this application document, the steel structure weld data feature extraction module extracts useful features from the collected ultrasonic data, such as the propagation time of the sound wave, the spectrum characteristics of the reflection intensity, the waveform shape, etc. The propagation time of the sound wave: calculates the time interval from the emission to the reception of the ultrasonic wave, which can provide information about the internal structure of the object being measured, such as the thickness of the weld or the location of the defect;

[0050] Spectral characteristics of reflection intensity: Spectral analysis of ultrasonic signals is performed to extract spectral characteristics, such as peak frequency and energy distribution of the spectrum, to capture information in different frequency ranges;

[0051] Waveform shape: Analyze the waveform shape of the ultrasonic signal, including the amplitude, period, pulse width and other characteristics of the waveform, to extract more detailed information, such as the shape and location of the defect.

[0052] As an optional solution of the technical solution of this application document, the steel structure weld quality monitoring model training module selects a machine learning model of a support vector machine and uses preprocessed data to train the model to achieve real-time monitoring of weld quality.

[0053] As an optional solution of the technical solution of this application document, the online monitoring and feedback module inputs the pre-processed real-time ultrasonic data into the trained machine learning model during the steel structure construction process. The model will predict the current quality status of the weld based on these data, and display the prediction results in a visual form to the construction personnel and management personnel so that they can understand the quality of the weld in a timely manner. At the same time, the system can also provide feedback based on the prediction results to guide the construction personnel to perform corresponding quality control and repair operations, which can improve the safety, reliability and durability of steel structure construction and ensure the quality of steel structure construction.

[0054] Reference Figure 2 and Figure 3 An online monitoring method and system based on the construction status of a steel structure, comprising a handheld frame 1, a screw rod 2, a movable seat 3, a driving blow-drying mechanism 4, a weld brush 5, and a liquid extraction mechanism 6,

[0055] A screw rod 2 is rotatably connected inside the handheld frame 1, a movable seat 3 is threadedly connected to the screw rod 2, a driving blow-drying mechanism 4 is fixedly connected to the movable seat 3, a welding brush 5 is rotatably connected to the bottom of the movable seat 3, and a liquid extraction mechanism 6 is fixedly connected to the movable seat 3.

[0056] Reference Figure 4 A solvent seat 101 is fixedly connected to the handheld frame 1, and a motor A102 is fixedly connected to one end of the handheld frame 1. The motor A102 is fixedly connected to the screw rod 2.

[0057] Reference Figure 5 An electric push rod 301 is fixedly connected to the inner wall of one side of the movable seat 3, an ultrasonic probe 302 is fixedly connected to the output end of the electric push rod 301, a baffle 303 is slidably provided on the inner wall of the middle part of the movable seat 3, and a spring 304 is connected between the baffle 303 and the movable seat 3. The baffle 303 separates the drying and the cleaning.

[0058] Reference Figure 6 The driving and drying mechanism 4 includes a motor B401. The output end of the motor B401 located in the movable seat 3 is connected and fixedly provided with a fan blade 402. The output end of the motor B401 is connected and fixedly provided with a driving wheel 403. A driven wheel 404 is meshingly transmitted on one side of the driving wheel 403. The driven wheel 404 is rotatably connected to the movable seat 3 through a universal joint 405. The other end of the universal joint 405 passes through the movable seat 3 and is connected with a worm 406. The worm 406 is meshingly transmitted with a worm wheel 501 connected to the weld brush 5.

[0059] Reference Figure 6 The liquid extraction mechanism 6 includes a liquid extraction airbag 601, the input end of the liquid extraction airbag 601 is connected to the solvent seat 101 through a hose, the output end of the liquid extraction airbag 601 extends to the outside through the inner wall of the movable seat 3, and a pressure plate 602 is movably provided on one side of the liquid extraction airbag 601. The pressure plate 602 is rotatably connected to the inner wall of the movable seat 3, and the pressure plate 602 is slidably contacted with the pressure rod 407 connected to the universal joint 405.

[0060] The implementation principle of the online monitoring method and system based on the construction status of the steel structure in the embodiment of the present application is as follows: after the welding construction of the steel structure, the handheld frame 1 is held by hand to make the weld brush 5 close to the weld, and then the motor B401 is used to drive the driving wheel 403 to rotate, so that the driving wheel 403 drives the universal joint 405 connected to the driven wheel 404 to rotate, so that the universal joint 405 drives the worm 406 to rotate, so that the worm 406 drives the weld brush 5 connected to the worm wheel 501 to rotate, and the weld is brushed, and at this time the universal joint 405 drives the pressure rod 407 to rotate, and at this time the pressure rod 407 drives the pressure plate 602 to swing, thereby squeezing the liquid extraction air bag 601, so that the solvent in the liquid extraction air bag 601 is squeezed out and sprayed on the weld for flushing;

[0061] At the same time, the baffle 303 is separated by the spring 304, and the motor B401 drives the fan blade 402 to rotate, and the solvent at the weld is blown dry. Then, the electric push rod 301 is used to drive the ultrasonic probe 302 to move out, and then the motor A102 is used to drive the screw rod 2 to rotate, thereby driving the moving seat 3 to move, so that the ultrasonic probe 302 collects data at the weld.

[0062] Then, during the steel structure construction process, the steel structure weld data acquisition module selects appropriate ultrasonic detection equipment to ensure that it can perform effective ultrasonic detection on the steel structure welds, continuously collects ultrasonic signal data of the welds through the ultrasonic detection equipment, transmits the collected ultrasonic signal data to the data processing system, and stores it;

[0063] The steel structure weld data preprocessing module is used to preprocess the collected raw data to improve the quality and availability of the data, including missing value processing and data smoothing. Missing value processing: processing the missing values ​​that may exist in the collected data, which can be filled by interpolation methods, or data repair according to actual conditions;

[0064] Data smoothing: Smoothing the collected data to eliminate mutations or fluctuations in the data, making it more continuous and stable;

[0065] The steel structure weld data feature extraction module is used to extract useful features from the collected ultrasonic data, such as the propagation time of the sound wave, the spectrum characteristics of the reflection intensity, the waveform shape, etc. The propagation time of the sound wave: calculates the time interval from the emission to the reception of the ultrasonic wave, which can provide information about the internal structure of the object being measured, such as the thickness of the weld or the location of the defect;

[0066] Spectral characteristics of reflection intensity: Spectral analysis of ultrasonic signals is performed to extract spectral characteristics, such as peak frequency and energy distribution of the spectrum, to capture information in different frequency ranges;

[0067] Waveform shape: Analyze the waveform shape of the ultrasonic signal, including the amplitude, period, pulse width and other characteristics of the waveform, to extract more detailed information, such as the shape and location of the defect;

[0068] Then the steel structure weld quality monitoring model training module selects the machine learning model of the support vector machine and uses the preprocessed data to train the model to achieve real-time monitoring of the weld quality;

[0069] During the steel structure construction process, the online monitoring and feedback module is used to input the pre-processed real-time ultrasonic data into the trained machine learning model. The model will predict the current quality status of the weld based on this data and display the prediction results in a visual form to the construction personnel and management personnel so that they can understand the weld quality in a timely manner. At the same time, the system can also provide feedback based on the prediction results to guide the construction personnel to perform corresponding quality control and repair operations, which can improve the safety, reliability and durability of steel structure construction and ensure the quality of steel structure construction.

Claims

1. An online monitoring system based on the construction status of a steel structure, comprising: Steel structure weld data acquisition module: During the steel structure construction process, the steel structure weld data acquisition module continuously collects ultrasonic signal data of the weld through ultrasonic detection equipment; Steel structure weld data preprocessing module: The steel structure weld data preprocessing module preprocesses the collected raw data to improve the quality and availability of the data; Steel structure weld data feature extraction module: The steel structure weld data feature extraction module extracts useful features from the collected ultrasonic data, including the propagation time of the sound wave, the spectrum characteristics of the reflection intensity, and the waveform shape; Steel structure weld quality monitoring model training module: The steel structure weld quality monitoring model training module selects an appropriate machine learning model and uses the preprocessed data to train the model to achieve real-time monitoring of weld quality; Online monitoring and feedback module: During the steel structure construction process, the online monitoring and feedback module inputs the pre-processed real-time ultrasonic data into the trained machine learning model. The model predicts the current quality status of the weld based on the data and provides quality feedback. The ultrasonic testing equipment comprises: a handheld frame, a screw rod, a movable seat, a driving blowing mechanism, a weld brush and a liquid extraction mechanism, wherein the handheld frame is rotatably connected with a screw rod, a movable seat is threadedly connected with the screw rod, a driving blowing mechanism is fixedly connected with the movable seat, a weld brush is rotatably connected with the bottom of the movable seat, and a liquid extraction mechanism is fixedly connected with the movable seat; The driving and drying mechanism includes a motor B, a fan blade is fixedly provided at the output end of the motor B, a driving wheel is fixedly provided at the output end of the motor B, a driven wheel is meshingly provided at one side of the driving wheel, the driven wheel is rotatably connected to the moving seat through a universal joint, the other end of the universal joint passes through the moving seat and is connected to a worm, and the worm is meshingly provided with a worm wheel connected to the weld brush; The liquid extraction mechanism includes a liquid extraction air bag, the input end of which is connected to the solvent seat on the handheld frame through a hose, the output end of which passes through the inner wall of the movable seat and extends to the outside, a pressure plate is movably provided on one side of the liquid extraction air bag, the pressure plate is rotatably connected to the inner wall of the movable seat, and the pressure plate is slidably contacted to the pressure rod connected to the universal joint; By setting up a liquid extraction mechanism, under the drive of the blowing mechanism, the liquid extraction air bag continuously sprays the solvent in the solvent seat onto the weld to clean the welding area and ensure that the welding surface is clean. By setting up a driving blowing mechanism, the weld brush is driven to rotate to clean the weld to avoid the adhesion of welding slag. Under the action of the fan blades, the cleaned position is blown dry to ensure the accuracy of weld quality monitoring.

2. The online monitoring system based on the steel structure construction status according to claim 1 is characterized in that: During the steel structure construction process, the steel structure weld data acquisition module continuously acquires ultrasonic signal data of the weld through ultrasonic detection equipment, transmits the acquired ultrasonic signal data to the data processing system, and stores it.

3. The online monitoring system based on the steel structure construction status according to claim 1 is characterized in that: The steel structure weld data preprocessing module preprocesses the collected raw data to improve the quality and availability of the data, including missing value processing and data smoothing. The missing value processing: processing the missing values ​​that may exist in the collected data, which can be filled by interpolation methods, or data repair according to actual conditions; Data smoothing: smoothing the collected data to eliminate mutations or fluctuations in the data, making it more continuous and stable.

4. The online monitoring system based on the steel structure construction status according to claim 1 is characterized in that: The steel structure weld data feature extraction module extracts useful features from the collected ultrasonic data, including the propagation time of the sound wave, the spectrum characteristics of the reflection intensity and the waveform shape. The sound wave propagation time: calculates the time interval from the emission to the reception of the ultrasonic wave, which can provide information about the internal structure of the object under test, including the thickness of the weld or the location of the defect; Spectral characteristics of the reflection intensity: performing spectrum analysis on the ultrasonic signal to extract spectrum characteristics, including peak frequency and energy distribution of the spectrum, so as to capture information within different frequency ranges; The waveform shape: analyzes the waveform shape of the ultrasonic signal, including the amplitude, period and pulse width characteristics of the waveform, to extract more detailed information, including the shape and location of the defect.

5. The online monitoring system based on the steel structure construction status according to claim 1 is characterized in that: The steel structure weld quality monitoring model training module selects a machine learning model of a support vector machine and uses preprocessed data to train the model to achieve real-time monitoring of weld quality.

6. The online monitoring system based on the steel structure construction status according to claim 1 is characterized by: During the steel structure construction process, the online monitoring and feedback module inputs the pre-processed real-time ultrasonic data into the trained machine learning model. The model predicts the current quality status of the weld based on this data and displays the prediction results in a visual form to the construction personnel and management personnel. At the same time, the system can also provide feedback based on the prediction results to guide the construction personnel to perform corresponding quality control and repair operations.

Images