Fastener monitoring method and system during building assembly

Abstract

The invention relates to the technical field of building assembly quality monitoring, in particular to a fastener monitoring method and system during building assembly, an image acquisition module acquires image information of an assembly position, extracts preset assembly information of a corresponding fastener according to a two-dimensional code in an image, and sends the preset assembly information to a working terminal; the electric wrench obtains an actual torque value of the fastener in the assembling period through the torque sensor and sends the actual torque value to the working terminal; the working terminal receives preset assembly information and an actual torque value during assembly and sends the information to the cloud platform; the cloud platform receives the preset assembly information from the working terminal and the actual torque value in the assembly period, and determines that the fastener is tightened by comparing the actual torque value with the ideal torque range in the preset assembly information; and by comparing the number of the remaining fasteners with the number of the fasteners in the preset assembly information and combining the obtained number information of the remaining to-be-assembled hole sites, it is determined that no fastener omission occurs in the current assembly position. The influence degree of operators on the assembling operation quality is reduced, and the assembling quality is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of building assembly quality monitoring, and in particular to a fastener monitoring method and system during building assembly. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] The assembly of building components involves tightening numerous fasteners, a task traditionally performed manually. This process is plagued by low efficiency, poor precision, and inconsistent quality. In some building assembly scenarios, electric wrenches are used to assist operators, improving assembly efficiency to a certain extent.

[0004] A large number of fasteners are involved during building assembly. As the operation progresses, operators may miss or fail to tighten them, affecting the assembly quality. Untightened fasteners may become loose or fall off during the operation of the building, and may even cause accidents. Summary of the Invention

[0005] In response to the problems raised in the background technology, the present invention provides a method and system for monitoring fasteners during building assembly, which obtains the QR code of the assembly position to determine the preset assembly information of the fastener, obtains the actual torque value of the electric wrench during assembly, uses the cloud platform to call the preset assembly information of the fastener corresponding to the QR code and compares it with the actual torque value to determine whether it is tightened, and uses the number of remaining holes and the number of fasteners in the preset assembly information to determine whether there is any missing tightening. When missing tightening or not tightening occurs, an alarm is issued.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] A first aspect of the present invention provides a fastener monitoring system during building assembly, comprising;

[0008] Image acquisition module, used to obtain image information of the assembly position, extract the preset assembly information in the QR code, and send it to the work terminal;

[0009] An electric wrench is used to perform fastener assembly, and the actual torque value during fastener assembly is obtained through a torque sensor and sent to the work terminal;

[0010] The work terminal is connected to the electric wrench and the image acquisition module to receive the preset assembly information and the actual torque value during assembly and send it to the cloud platform;

[0011] The cloud platform receives the preset assembly information and the actual torque value during assembly from the work terminal, and determines that the fasteners have been tightened by comparing the actual torque value with the ideal torque range in the preset assembly information. By comparing the number of remaining fasteners with the number of fasteners in the preset assembly information, combined with the obtained information on the number of remaining holes to be assembled, it is determined that no fasteners are missing in the current assembly position.

[0012] Furthermore, the image acquisition module includes a camera arranged on the top of the safety helmet, and the camera has a built-in processor for obtaining image information of the assembly position, extracting the QR code and the corresponding preset assembly information in the image, and sending it to the work terminal.

[0013] Furthermore, the electric wrench has a torque sensor and a microcontroller. The torque sensor is used to obtain the torque value during assembly and output a voltage signal; the microcontroller converts the voltage signal into a torque value and uses a communication module to send the torque data to the work terminal.

[0014] Furthermore, the work terminal is worn on the operator to receive information from the electric wrench and the camera and forward it to the cloud platform, receive and display information from the cloud platform, and output an alarm signal.

[0015] Furthermore, a QR code is set at the assembly position of the component to be assembled, and the QR code stores the assembly information required for the assembly position.

[0016] Furthermore, before the assembly begins, the work terminal communicates with the cloud platform to obtain all the preset assembly information required for the assembly operation, and extracts and displays the corresponding preset assembly information based on the QR code obtained by the image acquisition module.

[0017] Furthermore, the cloud platform determines whether the fastener has been tightened by comparing the actual torque value with the ideal torque range in the preset assembly information; specifically:

[0018] If the actual torque value exceeds the ideal torque range in the preset assembly information, a "torque unqualified" warning message is issued to the work terminal; if the actual torque value does not exceed the set range in the preset assembly information, the torque is qualified and the current data is saved.

[0019] Furthermore, the cloud platform determines that no fasteners are missing at the current assembly position by comparing the number of remaining fasteners with the number of fasteners in the preset assembly information and combining it with the obtained information on the number of remaining holes to be assembled; specifically:

[0020] The image acquisition module obtains image information of the assembly position and extracts the number of remaining holes to be assembled;

[0021] When the number of data sets of the actual torque value is not less than the number of fasteners in the preset assembly information, and the number of remaining holes to be assembled is 0, no fasteners are missing at the current assembly position;

[0022] If the number of remaining holes to be assembled is not 0, a fastener is missing at the current assembly position.

[0023] Furthermore, if the actual torque value exceeds the ideal torque range in the preset assembly information, or the number of remaining holes to be assembled is not 0, the cloud platform sends a corresponding alarm signal to the work terminal.

[0024] A second aspect of the present invention provides a method for monitoring fasteners during building assembly, comprising the following steps:

[0025] Obtain image information of the assembly position and extract preset assembly information of the corresponding fastener based on the QR code in the image;

[0026] Obtain actual torque values ​​during fastener assembly;

[0027] By comparing the actual torque value with the ideal torque range in the preset assembly information, it is determined that the fastener has been tightened;

[0028] By comparing the number of remaining fasteners with the number of fasteners in the preset assembly information and combining the obtained information on the number of remaining holes to be assembled, it is determined that no fasteners are missing in the current assembly position;

[0029] When a fastener is not tightened or is missing, an alarm is issued.

[0030] Compared with the existing technology, one or more of the above technical solutions have the following beneficial effects:

[0031] 1. The preset assembly information for the fastener is determined through the QR code in the assembly position image. The actual torque value during assembly performed by the electric wrench is obtained. The preset assembly information for the fastener corresponding to the QR code is retrieved from the cloud platform and compared with the actual torque value to determine whether it is tightened. The number of remaining holes is compared with the number of fasteners in the preset assembly information. The obtained number of remaining holes to be assembled is used to determine whether there are any missing holes. If there are any missing holes or under-tightening, an alarm is issued. By changing the process of determining whether tightening and omissions have occurred from traditional manual judgment to cloud platform judgment, the impact of operators on assembly quality is reduced, and the phenomenon of operator fatigue and other factors affecting assembly quality is minimized.

[0032] 2. Through the built-in torque sensor and the real-time comparison function of the cloud platform, it can ensure that the torque value of each fastener accurately meets the design requirements, avoiding the torque deviation problem caused by lack of experience or fatigue in traditional manual operation, thereby improving the reliability and safety of building assembly.

[0033] 3. The use of advanced real-time target detection algorithms, combined with QR code information, can quickly and accurately determine whether there is any fastener leaking. This not only reduces the tedious process of manual inspection, but also significantly reduces the leaking rate and ensures assembly quality.

[0034] 4. Real-time data storage, analysis, and visualization are achieved through the cloud platform. Operators can quickly obtain key information such as torque value and number of hole positions. By comparing with ideal values, abnormal situations can be discovered and handled in a timely manner, providing strong support for subsequent quality traceability and process optimization.

[0035] 5. The cloud platform supports remote monitoring and management functions. Managers can grasp the assembly progress and quality status in real time, adjust production plans or provide technical support in a timely manner, significantly improving the transparency and management efficiency of the assembly process.

[0036] 6. Through the collaborative work of cameras, electric wrenches and cloud platforms, seamless human-machine interaction is achieved. Operators only need to follow the system prompts to complete high-quality assembly tasks, which not only reduces operational complexity but also greatly improves assembly efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The accompanying drawings, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0038] Figure 1 is a schematic diagram of the operation process of the fastener monitoring system provided by one or more embodiments of the present invention;

[0039] Figure 2 is a schematic diagram of the structure of a safety helmet equipped with a camera provided by one or more embodiments of the present invention;

[0040] Figure 3 is a schematic diagram of the working process of the cloud platform provided by one or more embodiments of the present invention;

[0041] Figure 4 is a schematic diagram of a torque comparison process provided by one or more embodiments of the present invention;

[0042] Figure 5 The figure is a schematic diagram of a process for determining a missing screw provided by one or more embodiments of the present invention. DETAILED DESCRIPTION

[0043] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0044] It should be noted that the following detailed descriptions are exemplary and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present invention belongs.

[0045] Example 1:

[0046] like Figure 1 A fastener monitoring system during building assembly is shown, comprising:

[0047] The image acquisition module, installed on the top of the helmet, is used to obtain image information of the assembly position, extract the QR code in the image using its own processor, decode the QR code to the preset assembly information of the fastener, and take a snapshot at the same time. The assembly information and pictures can be sent to the cloud platform through the work terminal;

[0048] The electric wrench is used to perform fastener assembly and fill-in lighting operations. It uses a built-in torque sensor to obtain the torque value during the actual fastener assembly and sends it to the cloud platform through the work terminal;

[0049] The work terminal is worn by the operator and communicates with the electric wrench and the image acquisition module respectively. It is used to receive the preset assembly information corresponding to the QR code and the torque value during the actual assembly, and send them to the cloud platform;

[0050] The cloud platform receives the preset assembly information and the torque value during the actual assembly and the real-time picture of the work area from the work terminal. By comparison, it determines that all fasteners at the assembly position have completed the assembly according to the set torque requirements. When the torque does not meet the set torque requirement or the actual number of fasteners assembled is less than the preset assembly information, an early warning is issued through the work terminal.

[0051] As a further embodiment, fasteners are commonly used parts during building assembly. The following content takes "screws" as an example to further explain this solution.

[0052] A QR code is pre-set at the assembly location. Due to the complex environmental and lighting conditions at the assembly site, and the camera being located relatively high up on the top of a hard hat, the QR code should be clearly distinguished from the surrounding environment for better recognition. This can be engraved on a metal nameplate and placed near the screws being tightened. An electric wrench with a built-in fill light can also be used for supplementary lighting in dimly lit environments. The QR code contains the required assembly information for the location, including the number of screws, their location, the ideal torque for each screw, and associated data tags. This "preset assembly information" is pre-stored on the cloud platform.

[0053] A high-definition industrial identification camera is installed on the top of the helmet, and a protective cover is added to the outside of the camera to ensure the normal operation of the camera. Figure 2 The helmet with a camera shown in the figure ensures that the camera can communicate with the working terminal. During assembly, the camera obtains image information of the assembly position, extracts the QR code and the preset assembly information contained in the QR code.

[0054] As a further implementation, the preset assembly information contained in the QR code is extracted by using the camera's built-in processor and calling the Open CV library for image processing, including steps such as denoising, binarization, and edge detection, to improve the accuracy of QR code recognition. After image processing, the QR code region is extracted, and the Pyzbar library is used to decode the QR code and extract the preset assembly information contained in the code.

[0055] In this embodiment, Pyzbar is a Python encapsulation based on ZBar, which runs completely locally and relies on image processing algorithms to parse the QR code / barcode content without the need for a network connection.

[0056] The preset assembly information contained in the QR code is sent to the cloud platform through the work terminal, and the work terminal displays the number of screws, position number and ideal torque information.

[0057] The electric wrench has a built-in torque sensor, an STM32 microcontroller, and a fill light module. The torque sensor is used to measure the applied torque value and output a voltage signal; the fill light module can help the camera more clearly identify the QR code and screw hole information in a dim environment; the STM32 microcontroller is responsible for reading the voltage signal of the torque sensor, converting it into a torque value, and transmitting the torque data to the cloud platform through the work terminal via Bluetooth or WiFi module.

[0058] As a further implementation method, when the electric wrench tightens each screw, the torque sensor will obtain the corresponding torque information and transmit the torque information to the cloud platform through the work terminal via the Bluetooth module.

[0059] As a further embodiment, Figure 3 As shown in the figure, the STM32 microcontroller converts the voltage value into the torque value by calling the HAL library. It can configure the ADC peripheral to read the voltage signal of the sensor and then convert it into the actual torque value according to the linear relationship of the sensor. Use the Python script to read the data of the Bluetooth or WiFi module and send the MQTT message to the cloud platform. Use the MQTT client to subscribe to the target topic and verify the message reception.

[0060] The camera on the helmet obtains the preset assembly information and feeds it back to the work terminal. After confirmation, the operator sets the output torque of the electric wrench according to the torque requirements in the preset assembly information and operates the electric wrench to perform assembly. At the same time, the working pictures of the area can be captured in real time during the work process.

[0061] During assembly, the cloud platform determines whether the screws are tightened based on the comparison of the actual torque value obtained by the electric wrench with the preset assembly information. At the same time, by comparing the number of data groups of the actual torque value and the number of fasteners in the preset assembly information, as well as the number of remaining holes to be assembled, it determines whether there is any missing of tightening, and sends a reminder signal to the work terminal if it is not tightened or missed.

[0062] As a further implementation method, the work terminal is worn on the operator to receive information from the electric wrench and camera and forward it to the cloud platform. It can also receive information from the cloud platform and has functions such as display, alarm and networking.

[0063] The cloud platform determines whether the screws are tightened, specifically:

[0064] Before the assembly operation begins, the cloud platform stores all pre-set assembly information for the task. During assembly, the operator uses the camera on their helmet to scan the QR code corresponding to the assembly location. This allows them to locate the pre-set assembly information for the current location. Because the camera is mounted on the operator's helmet, it can also locate the current assembly location.

[0065] The operator sets the output torque of the electric wrench according to the preset assembly information fed back on the work terminal, and operates the electric wrench to perform assembly.

[0066] like Figure 4 As shown, during assembly, the electric wrench generates an actual torque value corresponding to the screw, and the actual torque value is sent to the cloud platform through the work terminal. The cloud platform compares the actual torque value obtained in real time with the preset assembly information through the rule engine. If the actual torque value exceeds or does not reach the set range in the preset assembly information, a "torque failure" warning message is issued and fed back to the work terminal; if it is within the set range in the preset assembly information, the torque is considered qualified and the current data is saved.

[0067] The cloud platform determines whether there is a missing fastener phenomenon. If the number of data sets of actual torque values ​​is not less than the number of fasteners in the preset assembly information, and the number of remaining holes to be assembled is 0, there is no missing fastener in the current assembly position;

[0068] Specifically:

[0069] This example uses the real-time object detection algorithm YOLO to identify screw holes on buildings and determine their number. This object detection algorithm model is deployed and integrated into a cloud platform to enable real-time detection of the number of screw holes. First, a dataset of building screw holes is prepared and a YOLO environment is deployed. The screw holes are then annotated and the resulting information is converted into a format recognizable by YOLO. The dataset is trained, validated, and inference tested. Finally, the model is exported into a suitable deployment format. The model is then deployed and integrated into the cloud platform to enable real-time detection of the number of screw holes.

[0070] When constructing a dataset, a large amount of image data containing screw holes should be collected from building assembly scenes. This should cover different lighting conditions (such as strong light, weak light, shadows, etc.), background interference (such as other components, tools, etc.), and the position and angle of the screw holes. This ensures that these image data cover different lighting conditions, background interference, and the diversity of screw hole positions and sizes to ensure that the YOLO model can better perform the recognition process. To ensure YOLO's recognition process, the dataset was enhanced before training, including image denoising and adding filters. During the training process, the training accuracy can be improved by adjusting the model's learning rate and improving the loss function.

[0071] After the YOLO model is deployed on the cloud platform, it can obtain image information transmitted by the work terminal through the communication protocol, use the integrated YOLO model to perform real-time analysis of the image, and identify the number of screw holes. The cloud platform maintains real-time communication with the work terminal to ensure the timeliness and reliability of data transmission, thereby ensuring the process of the YOLO model identifying screw holes.

[0072] like Figure 5 As shown, in the process of judging whether there is a phenomenon of missing screws in the area, after the QR code is scanned and decoded by the camera, the cloud platform will obtain the number of corresponding screws, and the number of screw holes in the area can also be understood. The algorithm model is deployed locally on the cloud platform, and the number of screw holes in the area can be identified in real time. The cloud platform will obtain a real-time photo of the working area forwarded by the work terminal and process it. By comparing the number of remaining holes and the number of fasteners in the preset assembly information, combined with the obtained number of remaining holes to be assembled, it is determined whether there is a phenomenon of missing screws. In the process of judging missing screws, in order to fully confirm that there is no missing screwing in the area, while using the YOLO model to identify the screw holes, the number of data groups of actual torque values ​​is compared with the number of fasteners in the preset assembly information. If the image recognition result is 0, and the number of data groups of actual torque values ​​is the same as the number of fasteners in the preset assembly information, it is determined that there is no missing screwing in the area.

[0073] The cloud platform sends a reminder signal to the work terminal when there is any under-tightening or missing of tightening, specifically:

[0074] The process of determining whether the torque is acceptable and whether there are any leaks in the area relies on a cloud platform, which in turn relies on computer algorithms and models. When determining whether the torque is acceptable, the cloud platform scans and decodes the QR code with a camera, obtaining the torque information of the corresponding screw. During operation, the cloud platform receives real-time torque information transmitted by the torque sensor and Bluetooth or WiFi module. A comparison algorithm is used on the cloud platform to compare the real-time torque with the ideal torque. Due to errors, if the real-time torque is within the error range of the ideal torque, it is considered acceptable; otherwise, if it is unacceptable, a warning prompt is triggered. This comparison algorithm requires comparing the real-time torque with a fixed torque within the error range.

[0075] T fixed -ΔT≤T real ≤T fixed +ΔT (1)

[0076] Among them, T fixed is a fixed torque value, T real is the real-time torque value, and ΔT is the error range.

[0077] During the comparison process, if the torque is unqualified or exceeds the torque range, or there is a missing tightening phenomenon in the area, the cloud platform will give a corresponding warning prompt. Real-time torque information is uploaded to the cloud platform through the built-in torque sensor of the electric wrench and the Bluetooth or WiFi module, and the real-time number of screw holes is recognized by the camera and uploaded to the cloud platform through the Bluetooth or WiFi module. The cloud platform analyzes the transmitted data in real time to determine whether it meets the preset conditions: if the torque value is lower than the minimum value or higher than the maximum value, the cloud platform triggers a "torque failure" warning; if the actual tightening number does not match the expected number, and the image recognition result shows that the number of screw holes is not 0, the cloud platform will trigger a "missing tightening" warning. At this time, the cloud platform will send the corresponding alarm information to the work terminal and display it on the work terminal.

[0078] As a further implementation method, the cloud platform may be an existing mature platform, such as the "Alibaba Cloud Internet of Things Platform".

[0079] The system of this embodiment has high-precision torque control: through the built-in high-precision torque sensor and the real-time comparison function of the cloud platform, it can ensure that the torque value of each screw accurately meets the design requirements, avoiding the torque deviation problem caused by lack of experience or fatigue in traditional manual operation, thereby improving the reliability and safety of building assembly.

[0080] The system in this embodiment features intelligent missed-tightening detection: It uses the advanced YOLO real-time object detection algorithm, combined with QR code information, to quickly and accurately determine whether a screw is missing. This intelligent detection method not only reduces the tedious manual inspection process, but also significantly reduces the missed-tightening rate, ensuring assembly quality.

[0081] The system in this embodiment features efficient data management and analysis: Through real-time data storage, analysis, and visualization via a cloud platform, operators can quickly access key information such as torque values ​​and screw hole counts. Using a rules engine, operators can compare these values ​​with ideal values, identifying and addressing anomalies promptly. This efficient data management approach provides strong support for subsequent quality traceability and process optimization.

[0082] The system of this embodiment has remote monitoring and management capabilities: the cloud platform supports remote monitoring and management functions, allowing managers to grasp the assembly progress and quality status in real time, adjust production plans or provide technical support in a timely manner, and significantly improve the transparency and management efficiency of the assembly process.

[0083] The system in this embodiment offers highly efficient human-machine collaboration: through the coordinated operation of the camera, electric wrench, and cloud platform, seamless human-machine interaction is achieved. Operators simply need to follow the system's prompts to complete high-quality assembly tasks, reducing operational complexity and significantly improving assembly efficiency.

[0084] Example 2:

[0085] A method for monitoring fasteners during building assembly, comprising the following steps:

[0086] Step 1: Obtain information about the fastener to be assembled

[0087] A high-definition industrial camera integrated into a hardhat automatically scans the QR code marked on the workpiece surface. The Open CV library is used for image processing, including denoising, binarization, and edge detection, to improve QR code recognition accuracy. After image processing, the QR code region is extracted and decoded using the Pyzbar library. The QR code contains pre-defined assembly information, such as position and torque. The camera simultaneously captures image data of this region in real time and communicates with the cloud platform via a Bluetooth module via the work terminal, transmitting this information to the work terminal to ensure real-time and reliable data. The Bluetooth module must be resistant to interference to prevent data transmission interruptions. For example, if a QR code contains information about five screws, scanning the code displays the position numbers and ideal torque information for each screw on the work terminal. The operator can confirm the QR code information is correct before tightening the fasteners.

[0088] Step 2: Fastening process

[0089] During the tightening process, ensure that the torque sensor is correctly installed on the electric wrench (or electric screwdriver) and connected to the Bluetooth module. The sensor must have high precision and the measurement error must be controlled within ±1%. During the tightening process of the fasteners, when each fastener is tightened, the torque sensor will obtain the corresponding torque information and transmit the torque information to the cloud platform. The torque is compared with the ideal torque. Due to the error, the ideal torque has an error range. If the corresponding torque is not reached, that is, the current torque value is lower or higher than the ideal torque value range, an alarm will be issued immediately. The cloud platform will transmit the warning information to the work terminal and display the "torque unqualified" message on the work terminal. Repeat the above process when assembling the next fastener.

[0090] While judging whether the fasteners are tightened, the helmet camera captures images of the area covered by the QR code and identifies the number of screw holes. The recognition process uses the Open CV library for edge detection and feature extraction to ensure accuracy. By identifying the number of fasteners to be assembled (i.e. the number of remaining bolt holes), it is determined whether there is a missing screw phenomenon. If the number of remaining bolt holes is zero, and the number of data groups of the actual torque value in the area is the same as the number of fasteners in the preset assembly information, then there is no missing screw phenomenon in the area; if the number of remaining bolt holes in the area is not zero, it is determined that there is a missing screw phenomenon in the area. At this time, the cloud platform will give a corresponding warning, and the cloud platform will transmit the warning information to the work terminal and display the "missing screw" information in the work terminal. When the system detects insufficient torque, excessive torque or missing screw phenomenon, the operator must immediately stop the current operation and make adjustments according to the system prompts. After the adjustment is completed, the tightening operation is repeated and the processing process is recorded.

[0091] Step 3: Data Saving

[0092] The system features automatic data save and restore, ensuring that completed data is not lost in the event of an error, allowing operators to continue working from where they left off. All torque data and alarm information are stored in real time on the cloud platform for subsequent analysis and traceability. Data is stored in CSV or JSON formats, supporting export and analysis.

[0093] Step 4: Switch to the next work area

[0094] When the next QR code is scanned, if the system does not issue an under-tightening warning and there is no missing screw warning, it is determined that all screws corresponding to the previous QR code are tightened and no missing screws are present. At this point, the system can proceed to the next QR code and work on the screw corresponding to that QR code. By focusing the camera on the next QR code, the system repeats the scanning and decoding process in step 1 to obtain new screw information.

[0095] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A fastener monitoring system during building assembly, characterized in that include: An image acquisition module is used to obtain image information of the assembly position, extract the QR code and the corresponding fastener preset assembly information in the image, and send it to the work terminal; An electric wrench is used to perform fastener assembly, and the actual torque value during fastener assembly is obtained through a torque sensor and sent to the work terminal; The work terminal is connected to the electric wrench and the image acquisition module to receive the preset assembly information and the actual torque value during assembly and send it to the cloud platform; The cloud platform receives the preset assembly information and the actual torque value during assembly from the work terminal, and determines whether the fastener has been tightened by comparing the actual torque value with the ideal torque range in the preset assembly information; By comparing the number of remaining fasteners with the number of fasteners in the preset assembly information and combining the obtained information on the number of remaining holes to be assembled, it is determined that no fasteners are missing at the current assembly position.

2. A fastener monitoring system during building assembly according to claim 1, characterized in that: The image acquisition module includes a camera installed on the top of the helmet, which has a built-in processor. The camera obtains image information of the assembly position, uses the built-in processor to extract the QR code in the image, as well as the preset assembly information of the fastener corresponding to the QR code, and sends it to the work terminal.

3. A fastener monitoring system during building assembly as claimed in claim 1, characterized in that: The electric wrench has a torque sensor and a microcontroller. The torque sensor obtains the torque value during the assembly process of the electric wrench and outputs a voltage signal. The microcontroller converts the voltage signal output by the torque sensor into a torque value and uses a communication module to send the torque data to the work terminal.

4. A fastener monitoring system during building assembly as claimed in claim 1, characterized in that: The work terminal is worn by the operator and is used to receive information from the electric wrench and camera and forward it to the cloud platform, receive and display information from the cloud platform, and output alarm signals.

5. A fastener monitoring system during building assembly as claimed in claim 1, characterized in that: A QR code is set at the assembly position of the component to be assembled. The QR code stores the assembly information required for the assembly position. The assembly information includes at least the number and position of fasteners, the ideal torque range of each fastener, and the associated data tags, forming "preset assembly information" that is pre-stored in the cloud platform.

6. A fastener monitoring system during building assembly as claimed in claim 1, characterized in that: Before assembly begins, the work terminal communicates with the cloud platform to obtain all the preset assembly information required for the assembly operation, and extracts the corresponding preset assembly information based on the QR code obtained by the image acquisition module and displays it.

7. A fastener monitoring system during building assembly as claimed in claim 1, characterized in that: The cloud platform determines whether the fastener has been tightened by comparing the actual torque value with the ideal torque range in the preset assembly information. Specifically, if the actual torque value exceeds the ideal torque range in the preset assembly information, a "torque failure" warning message is issued to the work terminal. If the actual torque value does not exceed the set range in the preset assembly information, the torque is qualified and the current data is saved.

8. A fastener monitoring system during building assembly as claimed in claim 1, characterized in that: The cloud platform compares the number of remaining fasteners with the number of fasteners in the preset assembly information, and combines the obtained information on the number of remaining assembly holes to determine whether there are any missing fasteners in the current assembly position; specifically: The image acquisition module obtains image information of the assembly position and extracts the number of remaining holes to be assembled; When the number of data sets of the actual torque value is not less than the number of fasteners in the preset assembly information and the number of remaining holes to be assembled is 0, no fasteners are missing at the current assembly position; If the number of remaining holes to be assembled is not 0, a fastener is missing at the current assembly position.

9. A fastener monitoring system during building assembly as claimed in claim 1, characterized in that: If the actual torque value exceeds the ideal torque range in the preset assembly information, or the number of remaining holes to be assembled is not 0, the cloud platform will send an alarm signal to the work terminal.

10. A method for monitoring fasteners during building assembly based on the system of any one of claims 1 to 9, characterized in that: The following steps are involved: Obtain image information of the assembly position and extract preset assembly information of the corresponding fastener based on the QR code in the image; Obtain actual torque values ​​during fastener assembly; By comparing the actual torque value with the ideal torque range in the preset assembly information, it is determined that the fastener has been tightened; By comparing the number of remaining fasteners with the number of fasteners in the preset assembly information and combining the obtained information on the number of remaining holes to be assembled, it is determined that no fasteners are missing in the current assembly position; When a fastener is not tightened or is missing, an alarm is issued.

Images