A method and system for detecting and predicting the quality of a car tightening process

Abstract

The application provides a car tightening process quality detection and prediction method, comprising the following steps: constructing a digital twin model of a tightening device on a car tightening production line, and collecting operation parameters of the tightening device; detecting a quality state of the tightening device by using the digital twin model and the current operation parameters of the tightening device; predicting the quality state of the tightening device by using the digital twin model and historical operation parameters of the tightening device; and sending the quality state detection result and the quality state prediction result to a control terminal. The application also provides a car tightening process quality detection and prediction system and a data processing device for car tightening process quality detection and prediction.

Description

Technical Field

[0001] This invention relates to the field of automotive tightening processes, and more specifically, to a method and system for quality inspection and prediction of automotive tightening processes based on a digital twin model. Background Technology

[0002] The tightening system is applied to a highly automated, fully robotic four-door and two-hood production line for automotive welding. Together with an online inspection system, robot system, PLC, PLUS, and server, it forms a highly intelligent tightening process, representing a milestone in intelligent manufacturing. The specific implementation path of the tightening process communication control is as follows: After the body-in-white arrives, Robot 1, carrying the tightening shaft, goes to the automatic nail feeding station to retrieve the nails. Robot 2, holding the workpiece, reaches the measurement position, detecting dimensional data such as the gap, smoothness, distance, and contour between the workpiece and the body, calculating the deviation from the theoretical data, and outputting the offset value to Robot 1. Robot 1 reaches the precise tightening position obtained from the "original trajectory data + offset value," and the floating mechanism adaptively reaches the final tightening position. The tightening system performs the tightening. After tightening, the tightening data is uploaded to the server for storage for 7 years. The body data is then measured again and uploaded to PLUS.

[0003] Intelligent manufacturing production lines achieve highly intelligent operation and traceable process data. However, under the pressure of high output, high line speed, high precision, and a large number of tightening positions on BOSCH's intelligent manufacturing production lines, determining which tightening device was used at which position on the vehicle body and whether the tightening quality was up to standard becomes the most urgent and real-time task for production line workers. Otherwise, if the tightening quality is substandard, the time spent identifying the fault point will seriously affect output and create production risks. With hundreds of tightening process positions, if a tightening NOK occurs, how to quickly find out which tightening shaft is causing the problem at which tightening position is a significant challenge. Furthermore, even if the faulty tightening shaft is identified, how to perform online control and testing to save fault diagnosis time is another challenge.

[0004] Furthermore, even if the tightening quality data is uploaded, if the fault point is not resolved, continuous quality defects will cause batch vehicle quality problems, creating quality risks. Therefore, intelligent manufacturing production lines urgently need digital twin technology to achieve real-time monitoring and display of tightening positions, tightening equipment, and tightening quality information, thereby controlling the production situation, quickly and efficiently locating fault points, and eliminating potential quality risks. This is an advanced means to improve the reliability of automobile manufacturing and equipment health management. Summary of the Invention

[0005] To address the above problems, this invention provides a method for quality inspection and prediction in automotive tightening processes, comprising: constructing a digital twin model of tightening equipment on an automotive tightening production line and collecting the operating parameters of the tightening equipment; using the digital twin model to detect the quality status of the tightening equipment based on its current operating parameters; using the digital twin model to predict the quality status of the tightening equipment based on its historical operating parameters; and sending the quality status detection results and the quality status prediction results to a control terminal.

[0006] The method for quality inspection and prediction of automotive tightening process according to the present invention includes constructing a digital twin model based on the attribute parameters of the tightening equipment; and constructing an equivalent mapping between the digital twin model and the tightening equipment based on the current operating parameters.

[0007] The automotive tightening process quality detection and prediction method of the present invention includes the following operating parameters: the tightening position and position number of the vehicle body, the number of the tightening shafts participating in the tightening operation on the tightening equipment, the posture of each tightening shaft and tightening operation data; based on the current operating parameters of the tightening equipment, a tightening state model of the current vehicle body is generated through the digital twin model, and the quality state of the current tightening operation is determined according to the tightening state model; when the number of times the quality state of the tightening operation is NOK after tightening operations are completed on multiple vehicle bodies consecutively exceeds the quality prediction threshold, a quality event is predicted to occur.

[0008] The automotive tightening process quality detection and prediction method of the present invention predicts that when the same tightening equipment completes tightening operations on N car bodies in a continuous manner, and the quality status of the N1 tightening operations is NOK, a quality event involving the trajectory of the tightening equipment will occur. To resolve the quality event, it is necessary to adjust the working trajectory and working angle of each tightening axis when the tightening equipment performs tightening operations. N and N1 are positive integers, and N > N1.

[0009] The automotive tightening process quality detection and prediction method of the present invention, when the same tightening equipment continuously completes tightening operations on N vehicle bodies of the same batch, and the quality status of the N2 tightening operations is NOK, then predicts that a quality event involving the body size of the vehicle body has occurred. In this case, resolving the quality event requires adjusting the installation dimensions of the four doors and two hoods of the vehicle body. N and N2 are positive integers, where N > N2.

[0010] The automotive tightening process quality detection and prediction method of the present invention predicts that when the same tightening equipment uses the same batch of bolts to continuously tighten N vehicle bodies, and the quality status of the N3 tightening operations is NOK, a quality event involving the bolt process is predicted to occur. In this case, solving the quality event requires improving the process quality of the bolt. N and N3 are positive integers, where N > N3.

[0011] The automotive tightening process quality detection and prediction method of the present invention predicts that a quality event involving the tightening shaft will occur when the quality status of a tightening shaft of the same tightening equipment is NOK after N4 consecutive tightening operations. The solution to the quality event requires the replacement or repair of the tightening shaft, where N4 is a positive integer.

[0012] The automotive tightening process quality detection and prediction method of the present invention predicts a quality event involving an error in the tightening process parameters or an error in the selection of the tightening shaft when the quality status of tightening operations is NOK for N5 consecutive times, and the process parameters of the tightening equipment are normal, the condition of the tightening shaft of the tightening equipment is normal, the body size of the vehicle body is normal, and the quality of the bolts used in the tightening operation is normal.

[0013] The automotive tightening process quality inspection and prediction method of the present invention uses a digital twin model to perform big data analysis on the historical quality problems of the tightening equipment and the corresponding historical quality process parameters in order to predict the quality problems of the tightening equipment.

[0014] This invention also proposes a quality inspection and prediction system for automotive tightening processes, comprising: a model building module for building a digital twin model of the tightening equipment on the automotive tightening production line and collecting the operating parameters of the tightening equipment; a quality inspection module for using the digital twin model to inspect the quality status of the tightening equipment based on its current operating parameters; a quality prediction module for using the digital twin model to predict the quality status of the tightening equipment based on its historical operating parameters; and a status feedback module for sending the quality status inspection results and the quality status prediction results to a control terminal.

[0015] The present invention also proposes a computer-readable storage medium storing computer-executable instructions, characterized in that, when the computer-executable instructions are executed, the aforementioned method for detecting and predicting automotive tightening process quality is implemented.

[0016] The present invention also proposes a data processing device, including the computer-readable storage medium as described above, wherein when the processor of the data processing device retrieves and executes the computer-executable instructions in the computer-readable storage medium, it performs automotive tightening process quality detection and prediction. Attached Figure Description

[0017] Figure 1 This is a flowchart of the process for detecting and predicting the quality of automotive tightening processes according to the present invention.

[0018] Figure 2 This is a flowchart of the digital twin model construction process of the present invention.

[0019] Figure 3 This is a schematic diagram of the data processing device of the present invention. Detailed Implementation

[0020] To make the present invention more apparent and understandable, specific embodiments are described below, and detailed descriptions are provided in conjunction with the accompanying drawings.

[0021] Figure 1 This is a flowchart illustrating the detection and prediction process for the automotive tightening process quality according to the present invention. Figure 1 As shown, this invention provides a digital twin-based method for monitoring the quality of automotive tightening processes, which can detect and predict the quality of automotive tightening processes, including:

[0022] Step S1: Construct a digital twin model of the automotive tightening production line and collect the operating parameters of the tightening production line. Here, a unified digital twin model can be established for all tightening equipment on the automotive tightening production line, or a digital twin model can be established for a single tightening equipment on the automotive tightening production line. The operating parameters of the tightening production line also include the current operating parameters of the tightening equipment (real-time operating parameters) and the operating parameters of the tightening operations completed by the tightening equipment (historical operating parameters).

[0023] Based on the attribute parameters of the tightening production line (tightening equipment), a digital twin model of the tightening production line (tightening equipment) is constructed; and an equivalent mapping between the digital twin model and the tightening production line (tightening equipment) is constructed using the real-time operating parameters of the tightening production line (tightening equipment).

[0024] The operating parameters include: the tightening position and position number of the vehicle body, the number of the tightening shafts involved in the tightening operation on the tightening equipment, the posture of each tightening shaft and the tightening operation data;

[0025] Step S2: Use a digital twin model to detect the quality status of the tightening equipment using real-time operating parameters. For example, use the real-time operating parameters of the tightening equipment to generate a tightening status model of the current vehicle body using a digital twin model, and determine the quality status of the current tightening operation based on the tightening status model. Alternatively, compare all real-time operating parameters with process data monitoring thresholds, and identify a quality event (quality problem) in the current tightening operation if one or more real-time operating parameters exceed the process data monitoring thresholds. That is, the current tightening operation is NOK.

[0026] Store real-time operating parameters as historical operating parameters;

[0027] Step S3: Use a digital twin model to perform big data analysis on the historical operating parameters of the tightening equipment to obtain a prediction of the quality status of the tightening equipment; when the number of times the quality status of the tightening operation is NOK after tightening operations are completed on multiple car bodies in a row is greater than the quality prediction threshold, a quality event is predicted to occur.

[0028] For example, if multiple tightening shafts carried by the same tightening equipment continuously complete tightening operations on N car bodies, and the quality status of the tightening operation is NOK for N1 times, then a quality event involving the trajectory of the tightening equipment is predicted to occur. It is necessary to adjust the working trajectory and working angle of each tightening shaft when the tightening equipment performs tightening operations to resolve the quality event. In the embodiment of the present invention, N is the total number of tightening operations completed by the tightening equipment in a day, and N1 = 10, that is, the tightening equipment has 10 tightening operations with a quality status of NOK (car body tightening quality NOK) in a day.

[0029] When the same tightening equipment continuously completes tightening operations on N vehicle bodies in the same batch, and the quality status of the N2 tightening operations is NOK, it is predicted that a quality event involving the vehicle body size has occurred. It is necessary to adjust the installation dimensions of the four doors and two hoods of the vehicle body to resolve the quality event. In the embodiment of the present invention, N=100, N2=10, that is, the tightening equipment performs 10 tightening operations in 100 consecutive operations and the quality status of the tightening operation is NOK (vehicle body tightening quality NOK).

[0030] When the same tightening equipment uses the same batch of bolts to continuously tighten N vehicle bodies, and the quality status of the tightening operation is NOK in N3 tightening operations, a quality event involving the bolt process is predicted to occur. It is necessary to improve the process quality of the bolt to resolve the quality event. In the embodiment of the present invention, N=100, N3=15, that is, the tightening equipment performs 100 tightening operations in 15 of them and the quality status of the tightening operation is NOK (vehicle body tightening quality NOK).

[0031] If a tightening shaft of the same tightening equipment experiences a quality status of NOK after N4 consecutive tightening operations, a quality event involving the tightening shaft is predicted. The tightening shaft needs to be replaced or repaired to resolve the quality event. In the embodiment of the present invention, N4 = 10, that is, a tightening shaft of the tightening equipment experiences a quality status of NOK (vehicle tightening quality NOK) after 10 consecutive tightening operations.

[0032] If the quality status of tightening operations is NOK for N5 consecutive times, and the process parameters of the tightening equipment are normal, the condition of the tightening shaft of the tightening equipment is normal, the body size of the vehicle body is normal, and the quality of the bolts used in the tightening operation is normal, then a quality event involving an error in the process parameters of the tightening operation or an error in the selection of the tightening shaft is predicted. It is necessary to optimize the process parameters or reselect the tightening shaft. In the embodiment of the present invention, N5 = 10.

[0033] Step S4: Send the quality status detection results and quality status prediction results to the control terminal (user terminal) for visualization display.

[0034] In another embodiment of the present invention, the quality status detection and prediction of tightening operations are performed through the following steps: reading product production process data during the tightening process and determining whether the tightening process data is in a qualified state. The tightening process data includes at least tightening torque, speed, angle, etc.; setting process data monitoring thresholds, and analyzing and judging whether the quality of process points during the tightening process is qualified based on the tightening data; transmitting the quality results to a PLC, which analyzes, processes, and displays them to a digital twin model to obtain real-time monitoring information of the tightening quality; the real-time monitoring information includes a tightening position diagram, tightening shaft number, quality monitoring point color, etc.; configuring a corresponding online control scheme based on the tightening shaft number information type to test and judge whether the tightening shaft is faulty.

[0035] In the context of existing automotive tightening processes involving hundreds of tightening points, and the occurrence of tightening quality issues, the following technical solution can be adopted to quickly determine which tightening point on the vehicle is causing the problem and which subsequent work stations are prone to issues.

[0036] First, set up tightening process steps, including steps such as cap recognition, high-speed belt loosening and bottoming, tightening to the specified torque, loosening detection, and tightening to the specified torque again. Set torque threshold, speed threshold, angle threshold and time threshold for each tightening step.

[0037] Second, if all process parameters are within the threshold, the tightening quality is OK; if the process parameters exceed the threshold, the tightening quality is NOK. The tightening system sends the tightening quality result to the PLC.

[0038] Third, establish a digital twin model on the PC and configure information such as tightening position diagram, tightening shaft number, quality monitoring point color, and tightening shaft number into the digital twin model;

[0039] Fourth, the PLC displays the quality results to the digital twin model, enabling real-time monitoring of the tightening quality results of each vehicle;

[0040] Fifth, configure online control functions on the PC, including the tightening quality status of the entire tightening shaft group, whether the tightening shaft group process is completed, whether the tightening shaft group is in the initial state, start the tightening action, start the loosening action, stop tightening, tightening in progress, tightening completed, etc. If a tightening quality NOK occurs, the specified action of the tightening shaft cannot be achieved by testing through the online control function, and the tightening shaft failure can be determined.

[0041] Sixth, the tightening quality information is transferred from the PLC to the data storage center and then to the front-end panel of the user terminal, realizing big data visualization monitoring of the tightening quality of all tightening equipment in all factories and all workstations.

[0042] Seventh, through big data analysis of the quality process parameters related to tightening, while maintaining monitoring, we can also calculate the causes of quality problems to the greatest extent possible and predict whether there are hardware problems with the tightening shaft.

[0043] Figure 2 This is a flowchart illustrating the digital twin model construction process of this invention. (For example...) Figure 2 As shown, the specific implementation methods include:

[0044] Step S11: Before creating the digital twin model, you need to find the nail number and the image element of the car part to be tightened at this station from the process file; open the digital model editing software, create a new page, right-click on the new page, select save as, and rename it to the name of the station to be worked on, following the standard format; open the ScrewOverview process file, find the 3D car part image to be extracted, note that the image size should not be too large, and save it on your computer; insert an image, find the import image option in the properties, select the image to be imported, and click OK to complete the image import;

[0045] Step S12: Make some edits to the image to make it more intuitive and clear. First, add lines for annotation. Select the line tool in the toolbar and drag it to the image editing area to add a line. Next, add annotations. Select the tool in the toolbar and click "Add Text Annotation". Right-click the added annotation and select "Edit Text". After editing, click "OK". The annotation has been added. Repeat this step to add the positions where screws need to be tightened, the screw numbers, and the workstations. Next, add the monitoring points. Select the tightening shaft group to which the monitoring point belongs, and drag the monitoring point to the corresponding empty space in the parameter editor. Note the indicator color when the monitoring point is 1. Normally, green represents quality OK and red represents quality NOK. If you want to add OK, enter clGreen in this field. After editing, click OK to save. This completes the addition of one monitoring point. Add NOK monitoring points again in the same way. After adding the monitoring points, to clearly see which nail's quality it is, combine the two points. Click the toolbar, select Add Panel, click the added panel, then click Properties to modify the parameters. Then drag the panel to the positions of the two added monitoring points and arrange them neatly. After adding them one by one, you need to add the function group buttons as well. As mentioned before, select the corresponding function group in FG-Liste, find the corresponding model in the standard model library. This time, you need to find the FG function group button. After finding the model, drag it to the left side of the screen, and then click Save in the upper left corner. Now a new page has been added. Next, we need to create the associated visuals. Click ProjectManagement, find the main screen of the workstation, click Template Overview, find the standard button model of the FG function group, drag it to the editing page, and after adding it, we need to adjust the size of the button because the text description to be added will be quite long. Click the added button, right-click to bring up the selection bar, select Editor, stretch it and arrange it neatly, then click the added button, then click Properties, fill in the name in the FGName and Parameters fields, and click Save in the upper left corner. Now the visual creation is basically complete.

[0046] Step S13: Next, you need to compile and upload the edited screen to the online screen. Click "Compile," and a prompt box will pop up saying that it is compiling. Note that you must not close the software during the compilation process. After a few minutes, the compilation will be completed, and a prompt box will pop up saying that the compilation was successful. Click "OK." After opening the software, click the hidden menu bar in the upper left corner and select "HMIbuild." A prompt box will pop up asking if you want to import the AWL file again. Click "NO" here. Clicking this box is only to check if there are still any errors in the screen. On the HMI screen, click the workstation screen to open it. You will see that the "Add" button has been displayed. Click it to test whether you can jump to the tightening quality screen normally. If the screen displays normally, the digital twin model is now established.

[0047] Step S14: The following is a brief introduction on how to set up tightening quality monitoring on the tightening equipment. First, open the HMI software on the equipment side, select a specific tightening shaft at a particular workstation, and create a new process instruction for the tightening shaft, which includes the steps specified in the instruction manual. These steps typically include cap recognition, high-speed tightening with loose thread to the bottom, tightening to the specified torque, loosening detection, and tightening again to the specified torque. For each tightening step, set torque threshold, speed threshold, angle threshold, and time threshold. For example, if the ideal torque is 45N, set the threshold to ±1. If the torque exceeds this range, the equipment side will send quality NOK information to the PLC, which will then be displayed on the digital twin model created earlier.

[0048] Step S15: The following is a brief introduction on how to set up a tightening quality visualization dashboard on the user terminal. Log in to the user terminal system, click the "Create Visualization" menu option, select a suitable visualization style, such as a line graph, select the tightening index, select the coordinates corresponding to the X and Y axes, such as the workstation and NOK count. This will display the NOK count statistics for all workstations under this index. In the upper right corner, you can select which time period to view the graph for. Finally, click "Save" and select a name for the visualization dashboard.

[0049] Figure 3 This is a schematic diagram of the data processing apparatus of the present invention. Figure 3As shown, embodiments of the present invention also provide a computer-readable storage medium and a data processing apparatus. The computer-readable storage medium of the present invention stores computer-executable instructions. When these computer-executable instructions are executed by the processor of the data processing apparatus, the aforementioned method for quality detection and prediction of automotive tightening processes is implemented. Those skilled in the art will understand that all or part of the steps in the above method can be implemented by a program instructing related hardware (e.g., processor, FPGA, ASIC, etc.), and the program can be stored in a readable storage medium, such as a read-only memory, a disk, or an optical disk. All or part of the steps in the above embodiments can also be implemented using one or more integrated circuits. Accordingly, each module in the above embodiments can be implemented in hardware, for example, by implementing its corresponding function through an integrated circuit, or it can be implemented in the form of a software functional module, for example, by a processor executing a program / instruction stored in memory to implement its corresponding function. Embodiments of the present invention are not limited to any particular combination of hardware and software.

[0050] This invention constructs a digital twin model to monitor and control the tightening process of automobiles in real time and online. By using this model to perform big data analysis on the historical tightening process of automobiles, the quality status of tightening equipment can be predicted, which can significantly improve the speed and visualization of tightening quality and achieve high-speed production.

[0051] The above embodiments are only used to illustrate the present invention and are not intended to limit the present invention. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, all equivalent technical solutions also fall within the scope of the present invention, and the patent protection scope of the present invention should be defined by the claims.

Claims

1. A method for quality inspection and prediction of automotive tightening processes, characterized in that, include: Construct a digital twin model of the tightening equipment on the automotive tightening production line and collect the operating parameters of the tightening equipment; The quality status is detected using the digital twin model based on the current operating parameters of the tightening equipment; This digital twin model uses historical operating parameters of the tightening equipment to predict the quality status. If, after multiple tightening operations on multiple vehicle bodies, the number of times the quality status of the tightening operation is NOK exceeds a quality prediction threshold, a quality event is predicted; including: When the same tightening equipment completes tightening operations on N car bodies in a row, the quality status of the N1 tightening operations is NOK, and a quality event involving the trajectory of the tightening equipment is predicted to occur. When the same tightening equipment completes tightening operations on N vehicle bodies in the same batch, and the quality status of the N2 tightening operations is NOK, a quality event involving vehicle body dimensions is predicted to occur. If the same tightening equipment uses the same batch of bolts to continuously tighten N vehicle bodies, and the quality status of the N3 tightening operations is NOK, then a quality event involving the bolt process is predicted to occur. When a tightening shaft of the same tightening equipment experiences N4 consecutive tightening operations with a quality status of NOK, a quality event involving the tightening shaft is predicted. If the quality status of tightening operations is NOK for N5 consecutive times, and the process parameters of the tightening equipment are normal, the condition of the tightening shaft of the tightening equipment is normal, the body size of the vehicle is normal, and the quality of the bolts used in the tightening operation is normal, a quality event involving incorrect tightening operation process parameters or incorrect selection of tightening shaft is predicted. The quality status detection results and quality status prediction results are sent to the control terminal.

2. The method for quality inspection and prediction of automotive tightening processes as described in claim 1, characterized in that, Based on the attribute parameters of the tightening equipment, a digital twin model is constructed; an equivalent mapping between the digital twin model and the tightening equipment is constructed using the current operating parameters of the tightening equipment.

3. The method for quality inspection and prediction of automotive tightening processes as described in claim 2, characterized in that, The operating parameters include: the vehicle body tightening position and position number, the tightening shaft number participating in the tightening operation on the tightening equipment, the posture of each tightening shaft and tightening operation data; Based on the current operating parameters of the tightening equipment, a tightening status model of the current vehicle body is generated through the digital twin model, and the quality status of the current tightening operation is determined based on the tightening status model.

4. The method for quality inspection and prediction of automotive tightening processes as described in claim 3, characterized in that, To resolve this quality issue involving the tightening equipment's trajectory, it is necessary to adjust the working trajectory and angle of each tightening shaft during tightening operations.

5. The method for quality inspection and prediction of automotive tightening processes as described in claim 3, characterized in that, To resolve this quality issue involving vehicle body dimensions, it is necessary to adjust the installation dimensions of the four doors and two hoods of the vehicle body.

6. The method for quality inspection and prediction of automotive tightening processes as described in claim 3, characterized in that, To resolve this quality issue involving the bolt manufacturing process, it is necessary to improve the manufacturing quality of the bolt.

7. The method for quality inspection and prediction of automotive tightening processes as described in claim 3, characterized in that, Resolving this quality issue involving the tightening shaft requires replacing or repairing the tightening shaft.

8. The method for quality inspection and prediction of automotive tightening processes as described in claim 1, characterized in that, The digital twin model is used to conduct big data analysis on the historical quality problems of the tightening equipment and the corresponding historical quality process parameters in order to predict the quality problems of the tightening equipment.

9. A quality inspection and prediction system for automotive tightening processes, characterized in that, include: The model building module is used to build a digital twin model of the tightening equipment on the automotive tightening production line and collect the operating parameters of the tightening equipment. The quality inspection module is used to inspect the quality status of the tightening equipment using the digital twin model and the current operating parameters of the tightening equipment. The quality prediction module uses the digital twin model to predict the quality status of the tightening equipment based on its historical operating parameters. It predicts a quality event when the number of times the quality status of a tightening operation is NOK (No K) exceeds a quality prediction threshold after multiple vehicle bodies have been tightened consecutively. This includes: predicting a quality event related to the tightening equipment's trajectory when the same tightening equipment has continuously tightened N vehicle bodies and the quality status is NOK N1 times; predicting a quality event related to the vehicle body dimensions when the same tightening equipment has continuously tightened N vehicle bodies from the same batch and the quality status is NOK N2 times; and predicting a quality event related to the vehicle body dimensions when the same tightening equipment has continuously tightened N vehicle bodies from the same batch. If a tightening machine uses the same batch of bolts to continuously tighten N vehicle bodies, and the quality status of the N3 tightening operations is NOK, then a quality event involving the bolt process is predicted. If the quality status of a tightening shaft of the same tightening machine is NOK for N4 consecutive tightening operations, then a quality event involving the tightening shaft is predicted. If the quality status of the tightening operations is NOK for N5 consecutive tightening operations, and the process parameters of the tightening machine are normal, the condition of the tightening shaft of the tightening machine is normal, the body dimensions of the vehicle body are normal, and the quality of the bolts used in the tightening operation is normal, then a quality event involving incorrect tightening process parameters or incorrect selection of the tightening shaft is predicted. The status feedback module is used to send the quality status detection results and quality status prediction results to the control terminal.

10. A computer-readable storage medium storing computer-executable instructions, characterized in that, When the computer-executable instructions are executed, the method for detecting and predicting the quality of automotive tightening processes as described in any one of claims 1 to 8 is implemented.

11. A data processing apparatus comprising the computer-readable storage medium as claimed in claim 10, wherein when the processor of the data processing apparatus retrieves and executes computer-executable instructions in the computer-readable storage medium, it performs automotive tightening process quality detection and prediction.

Images