Material-environment coupled self-adaptive riveting parameter optimization method and system

Abstract

The invention discloses a material-environment coupled self-adaptive riveting parameter optimization method and system. The method comprises the following steps: acquiring force data, speed data, position data, environment data and material data in a riveting process; when the force data is greater than a preset force threshold value, adjusting the parameters of the riveting equipment to obtain stable force data; performing fluctuation mode analysis on the stability strength data to obtain an equipment state report; combining the material data with a preset strength prediction model to obtain initial prediction strength; adjusting the initial prediction force according to the comprehensive correction coefficient to obtain the optimal prediction force; and judging whether the equipment parameters need to be adjusted or not according to the predicted optimal force and stable force data to obtain a judgment result, and adjusting the riveting equipment according to the judgment result and the equipment state report. According to the method, the riveting operation stability and the equipment maintenance efficiency can be improved by predicting and adjusting the riveting force in real time and combining long-term data analysis and identification equipment abrasion and material change.

Description

Technical Field

[0001] The present invention relates to the technical field of rivet monitoring, and in particular to a material-environment coupled adaptive rivet parameter optimization method and system. Background Art

[0002] Currently, many production lines use sensors to monitor and collect various data during the flexible, fully automated riveting process in real time. This data, including riveting force, speed, position, temperature, and humidity, is transmitted to a central processing unit for analysis.

[0003] Existing systems can detect abnormal rivet force using simple thresholds and make adjustments to ensure quality. Some systems also analyze force fluctuations in real time to identify potential issues such as equipment wear or material changes, allowing for a certain degree of early warning and adjustment. However, existing technologies still have limitations in accurately predicting equipment wear and adjusting force in real time, resulting in significant fluctuations in rivet quality and failing to effectively integrate various factors to calculate the optimal force in real time.

[0004] Existing technologies lack effective analysis of equipment wear and material changes, resulting in unstable riveting operations and delayed equipment maintenance. Summary of the Invention

[0005] The present invention provides a material-environment coupled adaptive rivet parameter optimization method and system, which can realize the improvement of rivet operation stability and equipment maintenance efficiency through real-time rivet force prediction and adjustment, combined with long-term data analysis to identify equipment wear and material changes.

[0006] In a first aspect, in order to solve the above technical problems, the present invention provides a material-environment coupled adaptive rivet parameter optimization method, comprising:

[0007] Obtain force data, speed data, position data, environmental data and material data during the riveting process;

[0008] When the force data is greater than a preset force threshold, adjusting the parameters of the riveting equipment is performed to obtain stable force data;

[0009] performing a fluctuation pattern analysis on the stability force data based on the material data to obtain a device status report;

[0010] Combining the material data with a preset force prediction model to obtain an initial predicted force;

[0011] Determining a comprehensive correction coefficient based on the speed data, the position data, and the environmental data in combination with a preset dynamic coupling factor model, and adjusting the initial predicted force based on the comprehensive correction coefficient to obtain a predicted optimal force;

[0012] Based on the predicted optimal force and the stable force data, it is determined whether equipment parameters need to be adjusted, a determination result is obtained, and the riveting equipment is adjusted based on the determination result and the equipment status report.

[0013] Preferably, when the force data is greater than a preset force threshold, adjusting the riveting equipment parameters to obtain stable force data includes:

[0014] When the force data is greater than a preset force threshold, calculating the difference between the force data and the preset force threshold to obtain an abnormality degree;

[0015] Calculating the pressure adjustment amount and the speed adjustment amount based on the abnormality and the preset adjustment coefficient;

[0016] Applying the pressure adjustment amount and the speed adjustment amount to the device pressure value and the device speed value respectively to perform force adjustment to obtain adjustment force data;

[0017] When the adjusted force data is less than or equal to a preset force threshold, the adjusted force data is determined as stable force data.

[0018] Preferably, performing a fluctuation pattern analysis on the stable force data based on the material data to obtain a device status report includes:

[0019] Extracting fluctuation characteristics of the stability force data to obtain a fluctuation value;

[0020] Performing periodic identification and abnormal fluctuation analysis on the fluctuation value to obtain a mode value;

[0021] Analyze the potential trend of equipment wear based on the material data and the mode value to obtain a trend value and a status value;

[0022] A clustering algorithm is used to classify the trend value and the status value to obtain a device status report.

[0023] Preferably, the combining of the material data and a preset force prediction model to obtain an initial predicted force comprises:

[0024] Analyzing hardness data and thickness data in the material data, and determining whether the hardness data and the thickness data meet preset hardness requirements and preset thickness requirements, respectively;

[0025] When the hardness data and the thickness data meet the preset hardness requirement and the preset thickness requirement respectively, obtaining the material elastic modulus, the material cross-sectional area and the original length of the material from the material data;

[0026] Get the current deformation detected by the sensor;

[0027] The elastic modulus of the material, the cross-sectional area of ​​the material, the current deformation and the original length of the material are input into a preset force prediction model to obtain an initial predicted force.

[0028] Preferably, determining the comprehensive correction coefficient based on the speed data, the position data and the environmental data in combination with a preset dynamic coupling factor model includes:

[0029] According to the speed data, the attenuation effect of time on the data is simulated by an exponential decay function to obtain a time attenuation coefficient;

[0030] Calculating a spatial weight based on the Euclidean distance between the location data and the target location;

[0031] Normalizing the temperature and humidity in the environmental data and weighting them to obtain an environmental coupling factor;

[0032] The product of the time attenuation coefficient, the spatial weight and the environmental coupling factor is calculated as a comprehensive correction coefficient.

[0033] Preferably, adjusting the initial predicted strength according to the comprehensive correction coefficient to obtain the predicted optimal strength includes:

[0034] Calculating the product of the comprehensive correction coefficient and the initial predicted strength to obtain the predicted optimal strength;

[0035] The calculation formulas for the initial prediction strength and the optimal prediction strength are expressed as follows:

[0036]

[0037] F pred =α·F physical

[0038] Where, F physical represents the initial predicted force, E represents the elastic modulus of the material, A represents the cross-sectional area of ​​the material, ΔL represents the current deformation, L0 represents the original length of the material; α represents the comprehensive correction coefficient, F pred Indicates the best prediction strength.

[0039] Preferably, judging whether equipment parameters need to be adjusted based on the predicted optimal force and the stable force data, obtaining a judgment result, and adjusting the riveting equipment based on the judgment result and the equipment status report, includes:

[0040] Calculating a relative difference between the predicted optimal force and the stable force data;

[0041] When the relative difference is greater than a preset relative difference, the equipment parameters are adjusted to obtain updated rivet parameters;

[0042] Analyze potential process problems of the equipment based on the equipment status report and obtain optimal working conditions;

[0043] The optimal working conditions and the updated riveting parameters are applied to the riveting equipment.

[0044] In a second aspect, the present invention provides a material-environment coupled adaptive rivet parameter optimization system, comprising:

[0045] A data acquisition module is used to obtain force data, speed data, position data, environmental data and material data during the riveting process;

[0046] A parameter adjustment module is used to adjust the parameters of the riveting equipment when the force data is greater than a preset force threshold to obtain stable force data;

[0047] a fluctuation analysis module for performing a fluctuation pattern analysis on the stability force data based on the material data to obtain a device status report;

[0048] A force prediction module, configured to combine the material data with a preset force prediction model to obtain an initial predicted force;

[0049] a force adjustment module, configured to determine a comprehensive correction coefficient based on the speed data, the position data, and the environmental data in combination with a preset dynamic coupling factor model, and adjust the initial predicted force based on the comprehensive correction coefficient to obtain a predicted optimal force;

[0050] The equipment adjustment module is used to determine whether equipment parameters need to be adjusted based on the predicted optimal force and the stable force data, obtain a judgment result, and adjust the riveting equipment based on the judgment result and the equipment status report.

[0051] In a third aspect, the present invention also provides an electronic device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the adaptive rivet parameter optimization method for material-environment coupling described in any one of the above is implemented.

[0052] In a fourth aspect, the present invention also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned material-environment coupled adaptive rivet parameter optimization methods.

[0053] Compared with the prior art, the present invention has the following beneficial effects:

[0054] (1) Existing technologies have limitations in adjusting force in real time, resulting in large fluctuations in rivet quality. This application obtains force data, speed data, position data, environmental data, and material data during the rivet process, and adjusts rivet equipment parameters when the force data exceeds a preset force threshold to obtain stable force data. This method of real-time monitoring and adjusting force data can promptly detect and correct force anomalies, thereby effectively reducing fluctuations in rivet quality and improving the stability of rivet quality.

[0055] (2) This application performs a fluctuation pattern analysis on the stability force data based on the material data to generate an equipment status report. This fluctuation pattern analysis can more accurately identify potential problems such as equipment wear or material changes, provide a scientific basis for equipment maintenance and process adjustments, and enhance the ability to analyze equipment and material changes.

[0056] (3) Existing technologies fail to effectively combine various factors to calculate the optimal force in real time. This application combines material data with a preset force prediction model to obtain an initial predicted force. Based on speed data, position data, and environmental data, a preset dynamic coupling factor model is used to determine a comprehensive correction coefficient, adjust the initial predicted force, and obtain the predicted optimal force. This process fully considers the impact of multiple factors on rivet force, achieves real-time calculation and adjustment of the optimal force, and improves the adaptability and accuracy of the rivet process.

[0057] (4) This application determines whether equipment parameters need to be adjusted based on the predicted optimal force and stable force data, and makes adjustments based on the equipment status report. This judgment and adjustment method based on data and model analysis can adjust equipment parameters more scientifically and timely, avoiding the risks brought about by blind adjustment and improving the stability and reliability of equipment operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 This is a schematic flow chart of a material-environment coupled adaptive rivet parameter optimization method provided by the first embodiment of the present invention;

[0059] Figure 2 Schematic diagram of the structure of a material-environment coupled adaptive rivet parameter optimization system provided by the second embodiment of the present invention. DETAILED DESCRIPTION

[0060] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0061] Reference Figure 1 The first embodiment of the present invention provides a material-environment coupled adaptive rivet parameter optimization method, comprising the following steps:

[0062] S11, acquiring force data, speed data, position data, environmental data, and material data during the riveting process;

[0063] S12, when the force data is greater than a preset force threshold, adjusting the riveting equipment parameters to obtain stable force data;

[0064] S13, performing a fluctuation pattern analysis on the stability force data based on the material data to obtain a device status report;

[0065] S14, combining the material data and a preset force prediction model to obtain an initial predicted force;

[0066] S15, determining a comprehensive correction coefficient based on the speed data, the position data, and the environmental data in combination with a preset dynamic coupling factor model, and adjusting the initial predicted force based on the comprehensive correction coefficient to obtain a predicted optimal force;

[0067] S16, judging whether equipment parameters need to be adjusted based on the predicted optimal force and the stable force data, obtaining a judgment result, and adjusting the riveting equipment based on the judgment result and the equipment status report.

[0068] In step S11, it is necessary to obtain force data, speed data, position data, environmental data, and material data during the riveting process, including:

[0069] In a specific embodiment, the force data during the riveting process refers to the pressure applied by the riveting equipment to the material, which is collected in real time by the pressure sensor during each riveting operation. To ensure the accuracy and reliability of the data, a high-precision sensor should be selected for collection. Commonly used sensor types are resistive strain gauge force sensors with an accuracy of ±0.01kN and a sampling frequency of 1000 times per second. During the data collection process, the sensor will continuously measure the pressure applied by the equipment during the riveting process and transmit the data in real time to the central processing unit (CPU) for storage and processing.

[0070] Specifically, the sensor must first be calibrated to ensure accurate measurements. Calibration can be performed using a standardized pressure source to ensure that the sensor readings are consistent with the actual pressure. For example, a sensor reading of 0 at a standard pressure should correspond to an actual pressure of 0 kN. The collected force data will include pressure values ​​at multiple time points, reflecting the force fluctuations during the riveting process.

[0071] In one embodiment, speed data refers to the speed of the equipment during the riveting process. This data is acquired by a speed sensor (e.g., an encoder) mounted on the equipment. The speed sensor monitors the speed of the riveting head in real time and transmits this data to a central processing unit for storage and analysis.

[0072] Specifically, speed data is included in the machine control system, which automatically measures the machine's travel and speed. Speed ​​values ​​are expressed in mm / s. The sensor calculates the instantaneous speed by measuring the machine's displacement over a specified period of time. For example, if the rivet head moves 50 mm in 5 seconds, the machine's speed is 10 mm / s.

[0073] In one embodiment, position data describes the specific position of the device or rivet head relative to the workpiece during the riveting process. This data is acquired by a position sensor (such as a photoelectric sensor, displacement sensor, or laser ranging sensor). The position sensor records the absolute or relative position of the rivet head in real time and transmits it to the central processing unit.

[0074] Specifically, position data, used together with velocity data, can help determine the machine's trajectory and whether it meets preset travel requirements. For example, if the machine's travel range is 0mm to 100mm, the position sensor will provide real-time feedback on the current position of the rivet head. If the position exceeds the preset range (for example, reaching 110mm), the system will trigger an alarm or automatically adjust the machine parameters.

[0075] In one specific embodiment, environmental data relates to external conditions during the riveting process, such as temperature, humidity, and air pressure, which have a certain impact on the riveting effect. Environmental data collection relies on environmental sensors, such as temperature and humidity sensors and air pressure sensors. By collecting this environmental data, the system can assess the potential impact of external factors on the riveting process in real time.

[0076] Specifically, temperature and humidity sensors should be installed in the work area around the equipment to ensure accurate capture of environmental changes during the riveting process. For example, a temperature sensor could be installed near the equipment's control box, while a humidity sensor could be placed near the equipment's work area. Environmental data collection should be synchronized with other data to ensure that changes in environmental factors are promptly reflected in data analysis during each riveting operation.

[0077] In a specific embodiment, material data refers to attribute data related to the material of the rivet workpiece, such as the material's hardness, thickness, and elastic modulus. Acquisition of material data relies on material property testing equipment, such as hardness testers, thickness gauges, and material testing instruments. In actual operation, this data can be obtained by periodically or in real time testing the workpiece's material properties.

[0078] Specifically, hardness data can be obtained using equipment such as Brinell and Rockwell hardness testers, which measure the surface hardness of a material. Thickness data can be obtained using equipment such as ultrasonic thickness gauges, which measure whether the workpiece's thickness meets preset standards. Material data is categorized based on the requirements of the riveting operation. Excessively high or low material hardness can affect the riveting effect, making the acquisition of hardness data crucial.

[0079] In a specific embodiment, after acquiring the above data, all data will be transmitted to the central processing unit (CPU) for real-time processing and storage. The central processing unit uses a data cleaning algorithm to screen and denoise the collected raw data to ensure the quality of the data finally transmitted to the analysis module. For example, for force data, if a certain data point collected differs too much from the previous and next data points (outside the set range), it is a sensor failure or external interference, and the data point should be eliminated to avoid affecting subsequent analysis. After data cleaning, the central processing unit will perform a preliminary analysis of various types of data based on preset thresholds, such as determining whether the rivet force exceeds the preset range, whether the rivet position meets the requirements, etc. If the data is found to be abnormal, the system will activate the alarm mechanism or automatically adjust the equipment parameters. In addition, the system will also update the data records in real time to provide a basis for fluctuation pattern analysis, prediction of optimal force calculation, etc. in subsequent steps.

[0080] In step S12, when the force data is greater than a preset force threshold, the riveting equipment parameters are adjusted to obtain stable force data, including:

[0081] When the force data is greater than a preset force threshold, calculating the difference between the force data and the preset force threshold to obtain an abnormality degree;

[0082] Calculating the pressure adjustment amount and the speed adjustment amount based on the abnormality and the preset adjustment coefficient;

[0083] Applying the pressure adjustment amount and the speed adjustment amount to the device pressure value and the device speed value respectively to perform force adjustment to obtain adjustment force data;

[0084] When the adjusted force data is less than or equal to a preset force threshold, the adjusted force data is determined as stable force data.

[0085] In a specific embodiment, the force data collected in real time deviates due to various reasons (such as changes in the elasticity of the material, fluctuations in ambient temperature, wear of equipment components, etc.). When the collected force data exceeds the preset force threshold, the system will consider that the force of the current operation is not within the normal range and needs to be adjusted. In order to accurately reflect the deviation between the current force data and the normal working state, the system will calculate the difference between the real-time force data and the preset force threshold. This difference is the abnormality. The calculation formula for the abnormality is: abnormality = real-time force data - preset force threshold. For example, if the force data collected in real time is 1200N, and the preset force threshold is 1000N, the calculated abnormality is: abnormality = 1200N-1000N = 200N. This abnormality value indicates that the current rivet force is larger than the preset force value. The system quantifies the difference between the equipment and the expected working state through this value, providing a basis for subsequent adjustment operations.

[0086] In one specific embodiment, based on the calculated abnormality, the system needs to further determine how to adjust the device's operating state. To this end, the system incorporates a preset adjustment coefficient, which converts the abnormality into a specific adjustment amount. The adjustment coefficient is a constant set by the system and adjusted based on the device type and operating environment. The adjustment coefficient determines the impact of each unit of abnormality on the device's pressure and speed. The selection of the adjustment coefficient is determined through experimentation or empirical experience, with common adjustment coefficient values ​​ranging from 0.1 to 1.0. The system calculates the pressure and speed adjustment amounts, respectively, using the following formulas: Pressure Adjustment = Abnormality × Adjustment Coefficient; Speed ​​Adjustment = Abnormality × Adjustment Coefficient. For example, assuming an abnormality of 200 N and a setting of 0.5, the pressure and speed adjustment amounts are calculated as follows: Pressure Adjustment = 200 N × 0.5 = 100 N; Speed ​​Adjustment = 200 N × 0.5 = 100 mm / s. This indicates that for every 200 N of abnormality, the system will adjust the device's pressure and speed by 100 N and 100 mm / s, respectively. The calculation of this adjustment depends on the actual operating requirements of the equipment and the material properties, and can, to a certain extent, eliminate the deviation in riveting force caused by equipment instability or material changes.

[0087] In one specific embodiment, once the system calculates the pressure and speed adjustments, the next task is to apply these adjustments to the actual operating state of the device. This means that the device's pressure and speed values ​​need to be adjusted based on the calculated results to ensure that the force during the riveting process returns to the normal range. Specifically, the system adds or subtracts the pressure adjustment from the current device pressure value; similarly, the speed adjustment is added or subtracted from the current device speed value. Through these adjustments, the device's operating state is restored in real time.

[0088] Specifically, assuming the equipment's current pressure value is 900N and its speed value is 10mm / s, and the calculated pressure adjustment is 100N and the speed adjustment is 100mm / s, the adjusted equipment pressure and speed values ​​will be calculated as follows: New Equipment Pressure Value = Current Pressure Value + Pressure Adjustment = 900N + 100N = 1000N; New Equipment Speed ​​Value = Current Speed ​​Value + Speed ​​Adjustment = 10mm / s + 100mm / s = 110mm / s. Through this adjustment, the equipment's operating state can be restored to its normal operating range in a short period of time, avoiding quality fluctuations or equipment failures caused by exceeding the set values.

[0089] In a specific embodiment, after applying the pressure and speed adjustment amount, the system will re-detect the adjusted force data to ensure that it has returned to the range that meets the preset force threshold. If the adjusted force data is still greater than the preset force threshold, the system will continue to perform the adjustment steps; if the adjusted force data is less than or equal to the preset force threshold, it means that the device has returned to normal operating state. At this time, the system will determine the adjusted force data as stable force data and continue to perform subsequent operations. For example, suppose that after adjustment, the pressure of the device is 1000N, and the preset force threshold is also 1000N. At this time, the adjusted force data meets the preset standard, so the system will determine the adjusted pressure value as stable force data. If the device pressure is still higher than 1000N, the system will perform the next round of adjustment until the force returns to the predetermined safety range.

[0090] In one specific embodiment, once the system verifies that the adjusted force data meets the preset threshold, it records the adjusted data and returns it to the control system or device management system as stable force data. At this point, the device has completed the necessary adjustments and can continue to operate in the next riveting operation. If the adjusted force data still does not meet the preset threshold, the system will enter the next round of adjustments until the device status meets the requirements.

[0091] It should be noted that the preset force threshold is a benchmark force value set during the riveting process to ensure operational quality and equipment safety, and is determined based on equipment capabilities, material properties, and process requirements. The equipment capability range determines the maximum and minimum operating pressures, so the preset force threshold should be set within this range. For example, if the maximum pressure of the equipment is 2000N and the minimum pressure is 1000N, the preset force threshold is set within this range. Different materials have different requirements for riveting force. Aluminum alloys require a riveting force of 1000N to 1500N, while stainless steel requires a higher force, such as 1500N to 2200N. Process requirements will also affect the setting of the threshold. Some precision processes require the riveting force to be within a narrower range to ensure the strength and sealing of the connector.

[0092] Preset force thresholds can be set through empirical values, experimental measurements, or dynamic adjustments. Empirical values ​​are based on past production data, while experimental measurements are obtained through actual operation. Dynamic adjustments, on the other hand, rely on real-time data, allowing the system to automatically optimize the threshold based on equipment conditions, environmental changes, and material properties. For example, in the event of equipment wear or material changes, the system can automatically adjust the threshold to adapt to the new operating conditions. Furthermore, the preset force threshold can be calculated through a comprehensive model of equipment condition, environmental factors, and material properties, ensuring that the equipment always operates within a safe and effective force range in complex application scenarios.

[0093] In step S13, it is necessary to perform a fluctuation pattern analysis on the stability force data based on the material data to obtain a device status report, including:

[0094] Extracting fluctuation characteristics of the stability force data to obtain a fluctuation value;

[0095] Performing periodic identification and abnormal fluctuation analysis on the fluctuation value to obtain a mode value;

[0096] Analyze the potential trend of equipment wear based on the material data and the mode value to obtain a trend value and a status value;

[0097] A clustering algorithm is used to classify the trend value and the status value to obtain a device status report.

[0098] In step S13, the stable force data is analyzed for fluctuation patterns based on the material data to generate a device status report. The fluctuation value is obtained by extracting fluctuation characteristics from the stable force data and is used to quantify the fluctuations in the force data. During the riveting process, force data fluctuates due to factors such as the equipment's operating status, material properties, and environmental conditions. Therefore, statistical characteristics such as standard deviation, mean square error (MSE), kurtosis, and skewness are extracted to describe the stability of the force data. The standard deviation measures the magnitude of force fluctuations, the mean square error reflects the consistency of the force, the kurtosis describes the sharpness of the fluctuations, and the skewness reveals whether the force data distribution is symmetrical. By calculating these statistics, a fluctuation value can be obtained, which intuitively reflects the force stability during the riveting process. For example, a small fluctuation value indicates relatively uniform riveting force and normal equipment status. A sudden increase in the fluctuation value may indicate abnormal force application or changes in material thickness, requiring further analysis of the influencing factors.

[0099] After obtaining the fluctuation values, the system needs to identify periodicity and analyze abnormal fluctuations to obtain a pattern value. The pattern value summarizes the fluctuation value's changing pattern to identify regularities and abnormalities during equipment operation. Periodicity identification determines whether the fluctuation values ​​conform to a fixed pattern. For example, during normal operation of riveting equipment, force fluctuations may be affected by the periodicity of the equipment's motion mechanism or the deformation characteristics of the material, resulting in a periodic distribution of fluctuation values. The system can use Fourier transform or sliding window analysis to identify periodicity in the fluctuation values ​​to determine whether they maintain a stable periodic pattern. If the periodicity of the fluctuation values ​​changes or becomes unstable, it may indicate equipment wear, material changes, or operating parameter deviations. Abnormal fluctuation analysis is also used to identify sudden fluctuations that occur over a short period of time. For example, a sudden increase in the fluctuation value at a certain point in time or a long-term nonlinear growth trend may indicate uneven force distribution or sudden changes in material properties. The system can use the Z-score method or a density-based anomaly detection algorithm (such as DBSCAN) to identify abnormal fluctuations and combine other parameters to further analyze the cause of the anomaly.

[0100] The role of fluctuation value and mode value in the riveting process has different focuses. Fluctuation value is used to quantify the stability of riveting force and serves as the basic data for pattern analysis, while mode value is used to extract long-term change trends and abnormal characteristics to identify the operating rules and potential faults of the equipment. For example, when the fluctuation value shows that the fluctuation amplitude of the riveting force is gradually increasing, and the mode value further reveals that the frequency and periodicity of the fluctuation have changed abnormally, it can be judged that the equipment has been worn or the components have aged, thereby prompting the user to perform maintenance in advance. On the contrary, if the mode value shows that the fluctuation value remains within a stable period, it can be considered that the equipment is operating normally and no additional adjustment is required. Therefore, a comprehensive analysis combining fluctuation value and mode value can more accurately evaluate the operating status of the equipment and provide a scientific basis for equipment maintenance, parameter optimization and fault prediction, thereby improving the stability of the riveting process and the service life of the equipment.

[0101] After analyzing the fluctuation pattern, the system combines material data with further trend analysis of the pattern value to assess the equipment's long-term operating status and potential wear. Because the equipment's operating status is not only influenced by the force fluctuation pattern but also closely related to material properties (such as hardness and thickness), changes in both material data and pattern values ​​are crucial when analyzing equipment wear trends. For example, over long-term use, material hardness gradually decreases, leading to increased fluctuations in riveting force. Alternatively, uneven material thickness may increase the frequency of force adjustments required, impacting riveting stability. By analyzing the temporal trends of the pattern value and incorporating material properties, the system calculates a trend value, reflecting the rate of change in equipment wear. Furthermore, the status value indicates the equipment's operating status under current operating conditions, such as whether it is within the normal range, experiencing abnormal fluctuations, or entering a potential failure phase. Together, the trend value and status value provide a quantitative description of the equipment's health, enabling the system to predict future equipment conditions and proactively implement maintenance measures.

[0102] After obtaining trend and status values, the system uses a clustering algorithm to classify these data to generate a device status report. Because different devices may exhibit different wear characteristics, data analysis methods are needed to categorize the device's health status into different categories. For example, based on historical data, the system can use unsupervised learning algorithms such as K-means, DBSCAN, or Gaussian Mixture Models (GMM) to classify device status into categories such as "normal," "light wear," "moderate wear," "heavy wear," or "faulty." The core of cluster analysis is to group samples with similar trend and status values ​​into the same category, allowing the device's status to be presented to the user in an intuitive manner. For example, if a device's trend value indicates a low wear rate and its status value shows that the force fluctuation remains within a stable range, the device can be classified as "normal." However, if the trend value is high and the status value indicates abnormal fluctuations, the device is classified as "heavy wear" and requires timely maintenance. Ultimately, the equipment status report will provide the current operating status of the equipment, predicted wear trends, and corresponding maintenance recommendations based on the results of cluster analysis, so that users can develop reasonable maintenance plans, optimize the service life of the equipment, and improve the stability of the production process.

[0103] In step S14, the material data and a preset force prediction model are combined to obtain an initial predicted force, including:

[0104] Analyzing hardness data and thickness data in the material data, and determining whether the hardness data and the thickness data meet preset hardness requirements and preset thickness requirements, respectively;

[0105] When the hardness data and the thickness data meet the preset hardness requirement and the preset thickness requirement respectively, obtaining the material elastic modulus, the material cross-sectional area and the original length of the material from the material data;

[0106] Get the current deformation detected by the sensor;

[0107] The elastic modulus of the material, the cross-sectional area of ​​the material, the current deformation and the original length of the material are input into a preset force prediction model to obtain an initial predicted force.

[0108] The force prediction model includes a physical calculation submodule based on material mechanics, specifically the deformation formula of Hooke's law:

[0109] The calculation formula of the initial prediction strength is expressed as:

[0110]

[0111] Where, F physicalRepresents the initial predicted force, E represents the elastic modulus of the material, A represents the cross-sectional area of ​​the material, ΔL represents the current deformation, and L0 represents the original length of the material.

[0112] First, to predict the optimal rivet force, the system requires comprehensive calculation and evaluation of speed, position, environmental, and material data based on multidimensional data analysis. Hardness and thickness data within the material data are key factors influencing rivet force, as the hardness and thickness of different materials determine the force required during the riveting process. Hardness data reflects a material's resistance to deformation, while thickness data determines the area of ​​force applied and the degree of deformation. Therefore, the system first analyzes the real-time hardness and thickness data and compares them with the preset hardness and thickness requirements to determine whether the material meets the established riveting process standards. For example, if the preset hardness requirements for an aluminum alloy are 90 HRC and 5 mm thickness, but the real-time data collected shows a hardness of 95 HRC and a thickness of 6 mm, the system will determine that the material does not meet the preset requirements and will need to adjust the force prediction model to ensure the stability and accuracy of the riveting process. Conversely, if both the hardness and thickness data meet the preset requirements, the system can proceed to the next step of analysis and calculation.

[0113] In a specific embodiment, when the hardness data and thickness data of the material meet the preset requirements, the system will obtain the material elastic modulus, material cross-sectional area and original length of the material from the material data. The material data can be obtained from the manual or system library. The elastic modulus, cross-sectional area and original length of the material are inherent or initial properties of the material and structure. The current deformation can be collected by a displacement sensor, such as a laser displacement sensor. The unit of the elastic modulus E is Pascal (Pa = N / m 2 ), the unit of cross-sectional area A is square meter (m 2 ), strain ΔL / L0 is dimensionless. This linear formula based on Hooke's law is suitable for small deformation scenarios (such as metal riveting and structural component design). It has high prediction accuracy within the elastic range of the material and provides a benchmark for subsequent corrections.

[0114] In step S15, determining a comprehensive correction coefficient based on the speed data, the position data, and the environmental data in combination with a preset dynamic coupling factor model includes:

[0115] According to the speed data, the attenuation effect of time on the data is simulated by an exponential decay function to obtain a time attenuation coefficient;

[0116] Calculating a spatial weight based on the Euclidean distance between the location data and the target location;

[0117] Normalizing the temperature and humidity in the environmental data and weighting them to obtain an environmental coupling factor;

[0118] The product of the time attenuation coefficient, the spatial weight and the environmental coupling factor is calculated as a comprehensive correction coefficient.

[0119] Specifically, adjusting the initial predicted strength according to the comprehensive correction coefficient to obtain the predicted optimal strength includes:

[0120] Calculating the product of the comprehensive correction coefficient and the initial predicted strength to obtain the predicted optimal strength;

[0121] The calculation formulas for the initial prediction strength and the optimal prediction strength are expressed as follows:

[0122]

[0123] F pred =α·F physical

[0124] Where, F physical represents the initial predicted force, E represents the elastic modulus of the material, A represents the cross-sectional area of ​​the material, ΔL represents the current deformation, L0 represents the original length of the material; α represents the comprehensive correction coefficient, F pred Indicates the best prediction strength.

[0125] It should be noted that using an exponential decay function to simulate the decaying effect of time on data can emphasize the contribution of recent velocity data and weaken the influence of historical data. Spatial weights are calculated based on the Euclidean distance between the current location and the target location. The closer the distance to the target, the greater the spatial weight (approaching 1), while the opposite weight decreases (approaching 0). This can spatially enhance the weight of data close to the target and weaken data farther away. Environmental parameters are converted into dimensionless data through normalization and then subjected to weighted linear combinations. For example, the contributions of temperature (weight 0.5) and humidity (weight 0.3) are dynamically coupled, reflecting the comprehensive impact of the environment on the fusion factor. Finally, the fusion factor combines the effects of time decay, spatial weight, and environmental coupling to dynamically adjust the predicted value, ensuring the system's adaptive performance under temporal, spatial, and environmental changes.

[0126] Exemplarily, the specific implementation process of the dynamic coupling factor model includes:

[0127]

[0128] The function is named spatiotemporal_fusion and takes speed, position, and env_data as parameters. It contains three main components: a temporal decay coefficient, a spatial weight, and an environmental coupling factor. The temporal decay component uses np.exp(-0.1*np.arange(len(speed)))). np.arange generates an array starting at 0 and equal to the length of speed. Each element is then multiplied by -0.1 and exponentially calculated. This calculates the temporal decay coefficient; earlier data has a lower weight. The spatial weight is calculated by dividing 1 by (1 plus the norm of the distance between the current and target positions). Position and target_pos are used here to calculate the distance from the current position to the target; the farther the distance, the smaller the weight. The environmental coupling factor is 0.5 times the temperature plus 0.3 times the humidity. env_data contains both temperature and humidity data. This comprehensively accounts for the impact of environmental factors on the results, with temperature and humidity having different weights. The return value is the product of the temporal decay coefficient, spatial weight, and environmental factor. These three factors are combined to form a comprehensive fusion factor, which serves as a comprehensive correction factor.

[0129] In step S16, it is necessary to determine whether the equipment parameters need to be adjusted based on the predicted optimal force and the stable force data, obtain a determination result, and adjust the riveting equipment based on the determination result and the equipment status report, including:

[0130] Calculating a relative difference between the predicted optimal force and the stable force data;

[0131] When the relative difference is greater than a preset relative difference, the equipment parameters are adjusted to obtain updated rivet parameters;

[0132] Analyze potential process problems of the equipment based on the equipment status report and obtain optimal working conditions;

[0133] The optimal working conditions and the updated riveting parameters are applied to the riveting equipment.

[0134] In a specific embodiment, the system needs to calculate the relative difference between the predicted optimal force and the stable force data. The relative difference is used to measure the gap between the predicted result and the actual data. The calculation formula is: relative difference = | predicted optimal force - stable force data | / stable force data × 100%. For example, if the predicted optimal force is 1500N and the stable force data is 1450N, the relative difference is = 3.45%. The relative difference reflects the difference between the predicted force and the stable force in actual operation. If this difference exceeds the preset relative difference threshold, the system determines that the equipment parameters need to be adjusted. The preset relative difference is set according to the equipment accuracy and production requirements, and is set between 1% and 5%. A reasonable threshold is set according to different specific application scenarios.

[0135] In one specific embodiment, when the calculated relative difference exceeds a preset relative difference, the system dynamically adjusts key equipment parameters, including pressure, speed, and operation time, based on this difference to ensure that the actual force during the riveting process matches the predicted optimal force as closely as possible. During operation, the system first determines the adjustment strategy based on the magnitude of the relative difference. If the difference is small, the system may moderately increase the equipment's pressure, adjust the operation time, or slightly increase the equipment's speed to ensure that the force approaches the optimal predicted value. For example, if the relative difference is 6%, the system may increase the equipment's pressure by 5% to compensate for the deviation. If the relative difference is large, indicating a significant discrepancy between the predicted and actual force, the system may make larger adjustments, increasing the pressure amplitude or speed, or even extending the operation time to ensure a more complete riveting process and avoid unsatisfactory connections. For each adjustment, the system can make real-time fine-tuning adjustments based on the material characteristics and equipment response during the riveting process. For example, when riveting soft materials, the system may reduce the pressure adjustment amplitude to prevent excessive damage to the material; while when riveting harder materials, the pressure and speed may need to be increased to achieve the ideal riveting effect. Furthermore, operation times can be adjusted based on actual needs to ensure that riveting operations are completed within the correct timeframe, avoiding situations where excessive or short operation times could affect force accuracy. Through these dynamic adjustment strategies, the system can effectively address fluctuations in actual operations, ensuring that each riveting operation consistently meets the set process standards, thereby improving production efficiency and ensuring consistent and reliable product quality.

[0136] In a specific embodiment, the system analyzes potential process problems of the equipment based on the equipment status report and derives the optimal working conditions from it. The equipment status report contains multiple status information of the equipment, such as the wear of the equipment, the temperature, humidity, pressure changes of the current operating environment, and the characteristics of the materials. This information is crucial for determining the operating status of the equipment. The system will first identify potential problems with the equipment based on the wear information in the equipment status report, combined with the equipment's service life, maintenance history, and operating intensity. For example, if the equipment status report shows that the equipment has slight wear, the system will determine that the equipment has performance degradation, and then analyze whether it is necessary to increase the force in the riveting operation, or adjust the speed and pressure of the equipment to ensure that the operation is not affected.

[0137] Furthermore, if the report includes data on environmental factors (such as temperature and humidity), the system will incorporate this information for further analysis. For example, if a high ambient temperature causes performance degradation in certain equipment components, such as reduced hydraulic efficiency or thermal expansion of materials, the system will simulate operating conditions under different environmental conditions using a process model. The system will then analyze and calculate the equipment's optimal operating range under different ambient temperatures to minimize the impact of temperature fluctuations on equipment performance and riveting quality.

[0138] Specifically, based on identifying potential equipment issues, the system will provide optimization suggestions, such as adjusting the equipment's operating temperature range, optimizing the service life of worn parts, or restoring the equipment to optimal working condition through regular maintenance and component replacement. For example, if excessive wear is detected on equipment, the system may recommend shortening the component's service life or replacing certain key components to prevent equipment failure. If environmental conditions affect equipment efficiency, the system may recommend adjusting production plans to avoid high-load operations in extreme environments.

[0139] In one specific embodiment, the system automatically applies the obtained optimal operating conditions and updated riveting parameters to the riveting equipment's operating control system. During this process, the equipment's control system adjusts the equipment's operating parameters, such as pressure, speed, and operating time, based on the new operating conditions to ensure the equipment performs riveting operations in optimal conditions. Specifically, once the updated parameters are set, the system automatically transmits these parameters to the equipment's control system to ensure the equipment operates according to the new settings. For example, if the aforementioned analysis indicates that the equipment's pressure parameters need to be increased to match the new operating conditions, the system automatically adjusts the equipment's pressure settings. The equipment's pressure control system then monitors the pressure sensor data in real time to ensure that the pressure value during actual operation is consistent with the new standard. If the monitored pressure value exceeds the predetermined range, the control system immediately adjusts it to prevent the equipment from experiencing poor riveting quality or damage due to excessive or insufficient pressure.

[0140] The system also monitors other key equipment parameters in real time. For example, the equipment's speed and position sensors verify that the equipment is operating within the specified speed and position accuracy. If speed fluctuations occur during operation, the system promptly detects and adjusts speed parameters to ensure stable operation and maintain accurate riveting.

[0141] Specifically, after the equipment parameters are updated and start running, the system will continue to track the actual operation of the equipment, monitor all key parameters (such as pressure, speed, temperature, etc.) and compare them with the set values. If it is found that the equipment fails to achieve the set goals in actual operation, the system will provide feedback and adjustments in real time. For example, during the production process, if the equipment wears out or the environment changes, causing the actual working status to be inconsistent with expectations, the system will automatically optimize the parameter settings through algorithms to ensure that the riveting process is always maintained in the best working condition, thereby improving the riveting quality, reducing the risk of equipment failure, and extending the service life of the equipment.

[0142] In summary, the present invention discloses a material-environment coupled adaptive rivet parameter optimization method, which improves the stability of the rivet operation and optimizes the equipment maintenance efficiency by real-time rivet force prediction and adjustment, combined with long-term data analysis to identify equipment wear and material changes. The present invention uses multi-dimensional data analysis (including force, speed, position, environment and material data) to predict the optimal force in real time to ensure the accuracy of each rivet operation; by performing fluctuation pattern analysis on stable force data, the working status of the equipment is effectively monitored, and potential equipment wear and material change problems are discovered in a timely manner. In addition, historical rivet data is trained through the support vector regression (SVR) algorithm to construct an accurate force prediction model, which improves the accuracy of the prediction and the response speed of the equipment adjustment. The present invention can improve the stability of the rivet operation and the efficiency of equipment maintenance by real-time rivet force prediction and adjustment, combined with long-term data analysis to identify equipment wear and material changes.

[0143] Reference Figure 2 The second embodiment of the present invention provides a material-environment coupled adaptive rivet parameter optimization system, comprising:

[0144] A data acquisition module is used to obtain force data, speed data, position data, environmental data and material data during the riveting process;

[0145] A parameter adjustment module is used to adjust the parameters of the riveting equipment when the force data is greater than a preset force threshold to obtain stable force data;

[0146] a fluctuation analysis module for performing a fluctuation pattern analysis on the stability force data based on the material data to obtain a device status report;

[0147] A force prediction module, configured to combine the material data with a preset force prediction model to obtain an initial predicted force;

[0148] a force adjustment module, configured to determine a comprehensive correction coefficient based on the speed data, the position data, and the environmental data in combination with a preset dynamic coupling factor model, and adjust the initial predicted force based on the comprehensive correction coefficient to obtain a predicted optimal force;

[0149] The equipment adjustment module is used to determine whether equipment parameters need to be adjusted based on the predicted optimal force and the stable force data, obtain a judgment result, and adjust the riveting equipment based on the judgment result and the equipment status report.

[0150] It should be noted that the material-environment coupled adaptive rivet parameter optimization system provided in an embodiment of the present invention is used to execute all the process steps of the material-environment coupled adaptive rivet parameter optimization method of the above embodiment. The working principles and beneficial effects of the two correspond one to one, so they will not be repeated here.

[0151] An embodiment of the present invention further provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a force prediction program. When the processor executes the computer program, the steps in the above-mentioned embodiments of the adaptive rivet parameter optimization method for material-environment coupling are implemented, such as Figure 1 Alternatively, when the processor executes the computer program, the functions of the modules / units in the above-mentioned device embodiments are realized, such as the fluctuation analysis module.

[0152] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program in the electronic device.

[0153] The electronic device may be a computing device such as a desktop computer, notebook, PDA, or smart tablet. The electronic device may include, but is not limited to, a processor and memory. Those skilled in the art will appreciate that the aforementioned components are merely examples of electronic devices and do not constitute a limitation of the electronic device. The electronic device may include more or fewer components than those described above, or a combination of certain components, or different components. For example, the electronic device may also include input / output devices, network access devices, buses, and the like.

[0154] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the electronic device, connecting various parts of the entire electronic device using various interfaces and lines.

[0155] The memory can be used to store the computer programs and / or modules, and the processor realizes various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created based on the use of the mobile phone (such as audio data, a phone book, etc.). In addition, the memory can include a high-speed random access memory and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0156] Wherein, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the process in the above-mentioned embodiment method, and can also be completed by a computer program to instruct the relevant hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, it can implement the steps of each of the above-mentioned method embodiments. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0157] It should be noted that the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed across multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. In addition, in the drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art can understand and implement the present invention without inventive effort.

[0158] The specific embodiments described above further illustrate the objectives, technical solutions, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included within the scope of protection of the present invention for those skilled in the art.

Claims

1. A material-environment coupled adaptive rivet parameter optimization method, characterized in that include: Obtain force data, speed data, position data, environmental data and material data during the riveting process; When the force data is greater than a preset force threshold, adjusting the parameters of the riveting equipment is performed to obtain stable force data; performing a fluctuation pattern analysis on the stability force data based on the material data to obtain a device status report; Combining the material data with a preset force prediction model to obtain an initial predicted force; Determining a comprehensive correction coefficient based on the speed data, the position data, and the environmental data in combination with a preset dynamic coupling factor model, and adjusting the initial predicted force based on the comprehensive correction coefficient to obtain a predicted optimal force; Based on the predicted optimal force and the stable force data, it is determined whether equipment parameters need to be adjusted, a determination result is obtained, and the riveting equipment is adjusted based on the determination result and the equipment status report.

2. The adaptive rivet parameter optimization method based on material-environment coupling according to claim 1 is characterized in that: When the force data is greater than a preset force threshold, adjusting the riveting equipment parameters to obtain stable force data includes: When the force data is greater than a preset force threshold, calculating the difference between the force data and the preset force threshold to obtain an abnormality degree; Calculating the pressure adjustment amount and the speed adjustment amount based on the abnormality and the preset adjustment coefficient; Applying the pressure adjustment amount and the speed adjustment amount to the device pressure value and the device speed value respectively to perform force adjustment to obtain adjustment force data; When the adjusted force data is less than or equal to a preset force threshold, the adjusted force data is determined as stable force data.

3. The adaptive rivet parameter optimization method based on material-environment coupling according to claim 1, characterized in that: The method of performing a fluctuation pattern analysis on the stable force data based on the material data to obtain a device status report includes: Extracting fluctuation characteristics of the stability force data to obtain a fluctuation value; Performing periodic identification and abnormal fluctuation analysis on the fluctuation value to obtain a mode value; Analyze the potential trend of equipment wear based on the material data and the mode value to obtain a trend value and a status value; A clustering algorithm is used to classify the trend value and the status value to obtain a device status report.

4. The adaptive rivet parameter optimization method based on material-environment coupling according to claim 1, characterized in that: Combining the material data with a preset force prediction model to obtain an initial predicted force includes: Analyzing hardness data and thickness data in the material data, and determining whether the hardness data and the thickness data meet preset hardness requirements and preset thickness requirements, respectively; When the hardness data and the thickness data meet the preset hardness requirement and the preset thickness requirement respectively, obtaining the material elastic modulus, the material cross-sectional area and the original length of the material from the material data; Get the current deformation detected by the sensor; The elastic modulus of the material, the cross-sectional area of ​​the material, the current deformation and the original length of the material are input into a preset force prediction model to obtain an initial predicted force.

5. The adaptive rivet parameter optimization method based on material-environment coupling according to claim 4, characterized in that: The determining of the comprehensive correction coefficient based on the speed data, the position data, and the environmental data in combination with a preset dynamic coupling factor model includes: According to the speed data, the attenuation effect of time on the data is simulated by an exponential decay function to obtain a time attenuation coefficient; Calculating a spatial weight based on the Euclidean distance between the location data and the target location; Normalizing the temperature and humidity in the environmental data and weighting them to obtain an environmental coupling factor; The product of the time attenuation coefficient, the spatial weight and the environmental coupling factor is calculated as a comprehensive correction coefficient.

6. The adaptive rivet parameter optimization method based on material-environment coupling according to claim 5, characterized in that: The adjusting the initial predicted strength according to the comprehensive correction coefficient to obtain the predicted optimal strength includes: Calculating the product of the comprehensive correction coefficient and the initial predicted strength to obtain the predicted optimal strength; The calculation formulas for the initial prediction strength and the optimal prediction strength are expressed as follows: F pred =α·F physical Where, F physical represents the initial predicted force, E represents the elastic modulus of the material, A represents the cross-sectional area of ​​the material, Δl represents the current deformation, L0 represents the original length of the material; α represents the comprehensive correction coefficient, F pred Indicates the best prediction strength.

7. The adaptive rivet parameter optimization method based on material-environment coupling according to claim 1, characterized in that: The method of determining whether equipment parameters need to be adjusted based on the predicted optimal force and the stable force data, obtaining a determination result, and adjusting the riveting equipment based on the determination result and the equipment status report includes: Calculating a relative difference between the predicted optimal force and the stable force data; When the relative difference is greater than a preset relative difference, the equipment parameters are adjusted to obtain updated rivet parameters; Analyze potential process problems of the equipment based on the equipment status report and obtain optimal working conditions; The optimal working conditions and the updated riveting parameters are applied to the riveting equipment.

8. A material-environment coupled adaptive rivet parameter optimization system, characterized in that: include: A data acquisition module is used to obtain force data, speed data, position data, environmental data and material data during the riveting process; A parameter adjustment module is used to adjust the parameters of the riveting equipment when the force data is greater than a preset force threshold to obtain stable force data; a fluctuation analysis module for performing a fluctuation pattern analysis on the stability force data based on the material data to obtain a device status report; A force prediction module, configured to combine the material data with a preset force prediction model to obtain an initial predicted force; a force adjustment module, configured to determine a comprehensive correction coefficient based on the speed data, the position data, and the environmental data in combination with a preset dynamic coupling factor model, and adjust the initial predicted force based on the comprehensive correction coefficient to obtain a predicted optimal force; The equipment adjustment module is used to determine whether equipment parameters need to be adjusted based on the predicted optimal force and the stable force data, obtain a judgment result, and adjust the riveting equipment based on the judgment result and the equipment status report.

9. An electronic device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the adaptive rivet parameter optimization method for material-environment coupling according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the material-environment coupled adaptive rivet parameter optimization method according to any one of claims 1 to 7.

Images