A parameter control method and system for friction stir welding process

Abstract

The present application provides a parameter control method and system for a friction stir welding process, relating to the technical field of welding equipment for metal materials. The method comprises: before friction stir welding begins, inputting the working condition information of the workpiece to be welded into a welding process simulation model for virtual test welding, and screening multiple sets of standard process parameter combinations that meet preset welding quality requirements; during the friction stir welding process, determining the change trend of each process parameter based on the real-time process parameter combination within a first preset time period; if the change trend determines that the current welding state has a risk of deviation within a second preset time period in the future, then determining the standard process parameter combination in the standard process parameter library with the greatest similarity to the real-time process parameter combination as the target process parameter combination, and performing parameter control and adjustment on the welding equipment. Implementing this method can address welding defects caused by sudden changes in the process window, improving the stability of the welding process and the consistency of weld quality.

Description

Technical Field

[0001] The present application relates to the technical field of welding equipment for metal materials, and in particular to a parameter control method and system for a friction stir welding process. Background Art

[0002] As an efficient and environmentally friendly solid-state joining process, friction stir welding (FSW) has gained widespread application in aerospace, rail transit, automotive, and other fields due to its superior weld quality and low energy consumption. As engineering requirements for the mechanical performance and reliability of welded structural components continue to increase, the refinement and intelligence of FSW process control are becoming increasingly important developments in the industry. Improving the stability of the welding process and the consistency of welds, particularly in complex parts and high-volume production scenarios, has become a pressing technical challenge.

[0003] In related technologies, in order to achieve precise control of the friction stir welding process, key process parameters such as welding temperature, stirring head speed, axial pressure, welding speed, etc. are generally collected in real time through sensors, and the collected data is fed back to the control system in real time. The control system adjusts the parameters of the welding equipment according to the preset process window and control strategy to maintain the process parameters within the target range. For example, when a change in welding temperature or downward pressure is detected, the control system can automatically adjust the stirring head speed or feed speed to ensure the stable operation of the welding process and the controllability of the weld quality. This type of method can better cope with the fluctuations of parameters in conventional production processes and meet the process requirements of most application scenarios.

[0004] However, the dynamic parameter adjustment methods based on real-time detection in related technologies primarily rely on the process parameter information collected at the current moment for immediate adjustment. This makes it difficult to address the impact of these coupled changes on the process window in complex working conditions where multiple factors, including material properties, structural parameters, welding environment, and equipment status, vary simultaneously. When factors such as material batch changes, sudden structural morphology changes, drastic fluctuations in ambient temperature, or abnormal equipment status combine, nonlinear changes in process parameters can occur, making it difficult for existing real-time adjustment strategies to adapt to these sudden changes in a timely and accurate manner. This can lead to undesirable phenomena such as sudden changes in the process window, increased welding defects, and unstable welding quality during the welding process. Summary of the Invention

[0005] The present application provides a parameter control method and system for a friction stir welding process, which is used to address the problem that changes in multiple factors such as material properties, structural parameters, welding environment, and equipment status during the friction stir welding process may cause sudden changes in the process window, thereby causing welding defects and unstable welding quality.

[0006] In a first aspect, the present application provides a parameter control method for a friction stir welding process, which is applied to a friction stir welding control system. The method comprises:

[0007] Before friction stir welding begins, the working condition information of the workpiece to be welded is input into the welding process simulation model for virtual test welding. Multiple sets of standard process parameter combinations that meet the preset welding quality requirements are screened out to obtain a standard process parameter library. The working condition information includes the material properties, structural parameters, welding environment information, and welding equipment status parameters of the workpiece to be welded.

[0008] During the friction stir welding process, process parameter information is collected in real time to obtain a real-time process parameter combination;

[0009] Determining a change trend of each process parameter based on the real-time process parameter combination within a first preset time period;

[0010] If it is determined based on the change trend that the current welding state has a risk of deviation within a second preset time period in the future, the standard process parameter combination in the standard process parameter library that has the greatest similarity to the real-time process parameter combination is determined as the target process parameter combination, and the target process parameter combination is used to perform parameter control and adjustment on the welding equipment.

[0011] Through the above-described embodiments, the system simulates virtual test welds for different working conditions before welding, establishes a standard process parameter library, and collects process parameters in real time during the welding process. By combining parameter change trends to predict future working conditions, the system can promptly identify the risk of deviation from the welding state and dynamically select the optimal parameter combination for control and adjustment. This approach overcomes the limitations of traditional methods that rely on real-time parameter adjustment and struggle to cope with complex, multi-factor coupled changes. It can address welding defects caused by sudden changes in the process window, improving the stability of the welding process and the consistency of weld quality.

[0012] In some embodiments, the step of inputting the working condition information of the workpiece to be welded into the welding process simulation model to perform virtual test welding and screening out multiple groups of standard process parameter combinations that meet preset welding quality requirements specifically includes:

[0013] Determine the fluctuation range of each working condition parameter based on the working condition information and historical production data of workpieces of the same type as the working condition information;

[0014] Divide multiple operating condition parameter combinations within the fluctuation range to obtain multiple groups of derived operating condition information;

[0015] Multiple groups of derived working condition information are input into the welding process simulation model respectively, and a standard process parameter combination that meets the preset welding quality requirements under each derived working condition information is screened out.

[0016] Through the above-described embodiment, the system analyzes operating condition information and historical production data to define operating condition parameter fluctuation ranges and screens multiple sets of standard process parameter combinations that meet quality requirements within the simulation model. This step expands the coverage of process parameters and enhances the representativeness of the parameter library. The resulting standard process parameter library can better adapt to complex operating conditions such as different batches of materials and structural variations in actual production, supporting parameter adjustment and quality assurance in subsequent welding processes.

[0017] In some embodiments, after the step of inputting the plurality of sets of derived working condition information into the welding process simulation model and screening out the standard process parameter combinations that meet the preset welding quality requirements under each derived working condition information, the method further includes:

[0018] Obtaining a first quality score corresponding to each standard process parameter combination, where the first quality score is calculated based on a weighted distance between each process parameter and a corresponding indicator in the preset welding quality requirement;

[0019] Adjusting the first quality score according to the importance weight corresponding to each derived working condition information to obtain a second quality score corresponding to each standard process parameter combination;

[0020] The standard process parameter library is constructed by selecting a standard process parameter combination with the largest second quality score that meets a corresponding preset quantity ratio from among multiple standard process parameter combinations corresponding to each derived working condition information.

[0021] Through the above-mentioned implementation, the system performs a multi-dimensional quality score on standard process parameter combinations and performs secondary optimization based on the importance weight of working condition information. Ultimately, it selects highly reliable and adaptable parameter combinations for inclusion in the parameter library. This approach not only improves the accuracy of parameter screening but also dynamically adjusts the parameter library structure based on actual working conditions, helping to improve the quality consistency and stability of the welding process.

[0022] In some embodiments, the step of determining the standard process parameter combination having the greatest similarity to the real-time process parameter combination in the standard process parameter library as the target process parameter combination specifically includes:

[0023] Calculating the time required for parameter adjustment between each standard process parameter combination in the standard process parameter library and the real-time process parameter combination based on the real-time process parameter combination;

[0024] Screening the standard process parameter library for standard process parameter combinations whose parameter adjustment time is less than or equal to a preset time threshold to obtain a first candidate parameter combination set;

[0025] Screening out standard process parameter combinations whose second quality scores are greater than a preset score threshold from the first candidate parameter combination set to obtain a second candidate parameter combination set;

[0026] The standard process parameter combination with the shortest required parameter adjustment time in the second candidate parameter combination set is determined as the target process parameter combination.

[0027] Through the above-described embodiment, the system uses multiple screening conditions, such as calculating the time required for parameter adjustment, setting time thresholds, and quality score thresholds, to ensure that the selected target parameter combination is not only highly similar to the real-time process during the actual welding process, but also that the adjustment can be completed within a limited time, ensuring the timely and efficient parameter switching. This multi-level, multi-constrained screening mechanism improves response efficiency and parameter adaptation accuracy during the welding process, reducing the risk of welding defects caused by slow parameter switching.

[0028] In some embodiments, after the step of determining the standard process parameter combination having the greatest similarity to the real-time process parameter combination in the standard process parameter library as the target process parameter combination, the method further includes:

[0029] Adjusting the welding process simulation model according to current working condition information;

[0030] inputting the target process parameter combination into the adjusted welding process simulation model to obtain a new first quality score;

[0031] Determining whether the new first quality score is less than a preset score threshold;

[0032] If it is detected that the new first quality score is less than the preset score threshold, the standard process parameter combination with the second highest similarity is input into the adjusted welding process simulation model to re-obtain a new first quality score for re-judgment.

[0033] Through the above-described embodiment, the system achieves closed-loop optimization of parameter adjustment by adjusting the simulation model in real time based on current working conditions and performing quality scoring verification on the target parameter combination. If the score falls short of the target, the system automatically switches to the suboptimal parameter for re-evaluation. This dynamic feedback mechanism enhances the adaptability and intelligence of parameter selection, ensuring that each parameter adjustment is verified by simulation, maximizing the reliability of the welding process and the final weld quality.

[0034] In some embodiments, after the step of determining the standard process parameter combination having the greatest similarity to the real-time process parameter combination in the standard process parameter library as the target process parameter combination, the method further includes:

[0035] Obtaining a proportion of target process parameters with a deviation risk in the real-time process parameter combination;

[0036] If it is detected that the ratio value exceeds a preset ratio threshold, all process parameters are adjusted as a whole using the target process parameter combination;

[0037] If it is detected that the ratio value does not exceed the preset ratio threshold, the adjustment value of the process parameter with deviation risk is determined based on historical production data, and local adjustment is performed according to the adjustment value.

[0038] Through the above examples, the system proposes a control strategy that combines global and local adjustments based on the varying degrees of parameter deviation risk. When the deviation risk is high, global parameter adjustments can be made quickly to avoid widespread quality issues. When the risk is low, specific parameters are fine-tuned locally based on historical data to achieve more refined process control. This hierarchical adjustment strategy enhances the flexibility and targeted nature of parameter control, not only improving the adaptability of welding production but also effectively reducing the difficulty of human intervention and operation.

[0039] In some embodiments, the step of determining the adjustment value of the process parameter with a risk of deviation based on historical production data and performing local adjustment according to the adjustment value specifically includes:

[0040] Retrieving historical production data whose similarity to the operating condition information is less than a preset threshold to obtain target historical production data;

[0041] Extracting historical process parameter values ​​and adjustment responses corresponding to process parameters with deviation risks from the target historical production data to obtain a historical parameter data set, wherein the adjustment response includes historical adjustment values ​​and corresponding historical first quality scores;

[0042] Based on the operating condition information and the historical parameter data set, determining, by an optimization algorithm, an adjustment value corresponding to the process parameter with a risk of deviation;

[0043] The process parameters with the risk of deviation are locally adjusted according to the adjustment value.

[0044] Through the above-described embodiment, the system efficiently retrieves and extracts historical parameters and adjustment responses similar to the current working conditions, and combines this with an optimization algorithm to calculate the optimal adjustment value, enabling precise fine-tuning of parameters at risk of deviation. This method leverages the value of historical data, making parameter adjustments more scientific and traceable, enhancing the intelligence of the welding process and the consistency of welding quality, and helping to ensure welding stability under complex working conditions.

[0045] In a second aspect, the present application provides a friction stir welding control system, the friction stir welding control system comprising: one or more processors and a memory;

[0046] The memory is coupled to the one or more processors, and the memory is used to store computer program code, wherein the computer program code includes computer instructions. The one or more processors call the computer instructions so that the friction stir welding control system can implement a parameter control method for a friction stir welding process provided in the above embodiment, which will not be repeated here.

[0047] In a third aspect, the present application provides a computer-readable storage medium comprising instructions. When the instructions are executed on a friction stir welding control system, the friction stir welding control system can implement a parameter control method for a friction stir welding process provided in the above embodiment, which will not be described in detail here.

[0048] In a fourth aspect, the present application provides a computer program product. When the computer program product is run on a friction stir welding control system, the friction stir welding control system can implement a parameter control method for a friction stir welding process provided in the above embodiment, which will not be repeated here.

[0049] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0050] 1. Through working condition information simulation, parameter trend prediction, and dynamic parameter matching, this solution proactively identifies and promptly responds to welding state deviation risks. Compared to traditional passive adjustments that rely solely on real-time feedback, this solution improves welding process stability and weld quality consistency in complex and changing production environments, addressing the risk of defects caused by sudden changes in process windows.

[0051] 2. Through the hierarchical quality scoring and weight adjustment mechanism, a target process parameter combination that is both representative and highly adaptable is selected, thereby improving the coverage and response capabilities of the standard process parameter library to abnormal working conditions and complex environments.

[0052] 3. An optimization algorithm that combines parameter adjustment time, quality scoring, multi-level candidate screening, and historical data drives the implementation of rapid and accurate matching and hierarchical adjustment of target parameters. Specifically, when assessing parameter deviation risk levels, global or local adjustments can be selected based on the risk level. Historical data feedback is used to optimize the adjustment value in a closed-loop manner, ensuring a scientific and effective adjustment plan. This multi-level, dynamic closed-loop control mechanism improves the welding process's response speed and adjustment accuracy to sudden anomalies and complex working conditions, ensuring consistent and reliable welding quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 This is a flow chart of a parameter control method for a friction stir welding process according to an embodiment of the present application;

[0054] Figure 2 This is another flow chart of a parameter control method for a friction stir welding process according to an embodiment of the present application;

[0055] Figure 3 This is a flow chart of a friction stir welding control system for adjusting process parameters in an embodiment of the present application;

[0056] Figure 4 This is a schematic diagram of the structure of a physical device of the friction stir welding control system in the embodiment of the present application. DETAILED DESCRIPTION

[0057] The terms used in the following examples of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification and appended claims of this application, the singular expressions "a," "an," "said," "above," "the," and "this" are intended to include plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in this application refers to any or all possible combinations comprising one or more of the listed items.

[0058] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood to imply or suggest relative importance or implicitly indicate the number of the technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of this application, unless otherwise specified, "plurality" means two or more.

[0059] For ease of understanding, the following describes the process of the method provided by this implementation. Figure 1 , which is a flow chart of a parameter control method for a stir friction welding process in an embodiment of the present application.

[0060] S101. Before friction stir welding begins, input working condition information of the workpiece to be welded into a welding process simulation model to perform virtual test welding, screen out multiple groups of standard process parameter combinations that meet preset welding quality requirements, and obtain a standard process parameter library.

[0061] Among them, working condition information refers to a collection of various parameters directly related to the welding process, including material properties (such as material, hardness, thermal conductivity), structural parameters (such as plate thickness, groove form, butt gap), welding environment information (such as ambient temperature, humidity, gas protection conditions) and welding equipment status parameters (such as stirring head wear degree, spindle motor power); the welding process simulation model is used to represent a computer model established based on the physical mechanism of welding (such as frictional heat generation and plastic metal flow). By inputting working condition information, it simulates the welding process and predicts results such as weld formation, temperature field distribution, stress and strain; the standard process parameter combination represents a combination of parameters such as stirring head speed, welding speed, axial pressure, etc. that meet the preset welding quality requirements (such as no cracks, incomplete penetration, porosity and other defects, and mechanical properties meet the standards).

[0062] Specifically, during the welding preparation phase, the operator first collects complete working condition information of the workpiece to be welded, including the chemical composition of the material, geometric dimensions, temperature and humidity data of the welding environment, and the current status of the welding equipment (such as the wear of the stirring head and the working status of the cooling system). Subsequently, this information is input into a pre-trained welding process simulation model (such as a model based on finite element analysis or a machine learning model). The model uses an algorithm to simulate the welding process under different process parameter combinations and outputs weld quality prediction results (such as weld nugget size, hardness distribution, and defect probability). The system screens out all parameter combinations that meet the requirements based on preset quality standards (such as industry specifications or internal corporate standards) and stores them in the standard process parameter library for subsequent welding process calls.

[0063] Optionally, the system can use commercial welding simulation software (such as Simufact Welding, ANSYS Workbench) to build a simulation model, input the working condition information, and then perform meshing, boundary condition setting, and solution calculations; it can also use machine learning models (such as neural networks) to train historical working condition information and corresponding qualified process parameters, establish a working condition-parameter mapping relationship, and automatically generate parameter combinations that meet the requirements; or through the orthogonal experimental design method, generate multiple groups of test combinations within the fluctuation range of the working condition parameters, and input them one by one into the simulation model to screen out qualified parameters. There is no limitation here.

[0064] S102. During the friction stir welding process, process parameter information is collected in real time to obtain a real-time process parameter combination.

[0065] Among them, process parameter information refers to process parameters that directly affect welding quality, including stirring head speed, welding speed, axial pressure, welding temperature, torque, etc.

[0066] Specifically, the system uses an integrated sensor network (such as speed sensors, pressure sensors, and temperature sensors) to collect raw data on various process parameters in real time. After signal conditioning (such as filtering and amplification) and analog-to-digital conversion, the data is transmitted to the control system's central processing unit (CPU) or digital signal processor (DSP). The processor combines the values ​​of each parameter at the same moment into a real-time process parameter combination and stores it in the system memory or database for subsequent analysis.

[0067] S103 : Determine a change trend of each process parameter based on a combination of real-time process parameters within a first preset time period.

[0068] Specifically, the system extracts data points within a first preset time period (e.g., 300 data points within the past 30 seconds) from the historical data of the real-time process parameter combination and performs trend analysis on each process parameter (e.g., speed, temperature). For example, for the speed parameter, the system uses the least squares method to fit the time-speed curve and calculates the slope to determine whether the speed is increasing, decreasing, or remaining stable. For the temperature parameter, the system uses the moving average method to smooth the data and observe whether the fluctuation range is gradually expanding. The analysis results are output as trend vectors (e.g., speed change rate +5 rpm / s, temperature fluctuation range ±10°C) for subsequent deviation risk assessment.

[0069] S104. If it is determined based on the change trend that the current welding state has a deviation risk within a second preset time period in the future, the standard process parameter combination with the greatest similarity to the real-time process parameter combination in the standard process parameter library is determined as the target process parameter combination.

[0070] Among them, deviation risk indicates that the welding state may exceed the preset process window (such as parameters exceeding the qualified range), resulting in the risk of welding defects (such as lack of fusion and excessive flash). Trend analysis is used to predict whether the parameters will reach the risk threshold within the second preset time period in the future (such as 5 seconds or 10 seconds).

[0071] Specifically, the system predicts the values ​​of each process parameter within the second preset time period in the future based on the changing trends of the process parameters (such as through linear extrapolation or model prediction), and compares them with the preset process window boundaries (such as the allowable speed range of 800-1200rpm, the allowable temperature range of 400-500℃). If the predicted value exceeds the boundary, it is determined that there is a risk of deviation. At this time, the system calls the similarity calculation algorithm to compare the real-time process parameter combination with all combinations in the standard process parameter library, calculates the distance (such as Euclidean distance) or similarity coefficient (such as cosine similarity) between each standard combination and the real-time combination, and selects the combination with the smallest distance or the largest similarity as the target process parameter combination, and then uses the target process parameter combination to adjust the parameters of the welding equipment.

[0072] Optionally, the system can also calculate the time required for each standard process parameter combination in the standard process parameter library to switch to the real-time parameters based on the real-time process parameter combination through the dynamic model or historical data of the welding equipment, for example, calculate the speed adjustment time, pressure adjustment delay, etc. according to the motor response curve to obtain the time required for parameter adjustment of each combination; then compare these times with the preset time threshold, filter out combinations with adjustment time less than or equal to the threshold, form a first candidate parameter combination set, and exclude combinations that cannot be adjusted in time; then extract the second quality score of each combination from the first candidate set, compare it with the preset score threshold, retain the combinations with scores greater than the threshold, and obtain the second candidate parameter combination set, ensuring that the filtered combinations have both timeliness and quality assurance; finally, sort the combinations in the second candidate set in ascending order according to the time required for parameter adjustment, select the combination with the shortest time as the target process parameter combination, and if the time is the same, further compare the quality scores, and give priority to the combination with the higher score, thereby achieving a fast and high-quality parameter adjustment response.

[0073] In the above-mentioned embodiment, the system simulates virtual test welds for different working conditions before welding, establishes a standard process parameter library, and collects process parameters in real time during the welding process. By combining parameter change trends to predict future working conditions, the system can promptly identify the risk of deviation from the welding state and dynamically select the optimal parameter combination for control and adjustment. This approach overcomes the limitations of traditional methods that rely on real-time parameter adjustments and struggle to cope with complex, multi-factor coupled changes. It can address welding defects caused by sudden changes in the process window, improving the stability of the welding process and the consistency of weld quality.

[0074] The following is a more detailed description of the process of the method provided by this implementation. Figure 2 , is another flow chart of a parameter control method for a stir friction welding process in an embodiment of the present application.

[0075] S201 , determining the fluctuation range of each working condition parameter based on the working condition information and historical production data of workpieces of the same type as the working condition information, and dividing the working condition parameters into multiple combinations to obtain multiple groups of derived working condition information.

[0076] Among them, the same type of workpiece refers to welded workpieces with similar material properties and structural parameters (such as plate thickness and groove form) to the workpiece to be welded, such as different specifications of aluminum alloy profiles of the same material; the working condition parameter fluctuation range refers to the possible variation range of each working condition parameter (such as material hardness and ambient temperature) in actual production, for example, the thickness fluctuation range of aluminum alloy plate is 2-4mm, and the ambient temperature fluctuation range is 15-35℃; derived working condition information is used to represent multiple groups of simulated working conditions generated by parameter combination expansion based on the original working condition information. For example, the original working condition is a plate thickness of 3mm and a temperature of 25℃, and the derived working conditions may include combinations such as plate thickness 2.5mm / temperature 20℃ and plate thickness 3.5mm / temperature 30℃.

[0077] This step is performed before the virtual test welding in step S101 and is applicable to scenarios where workpiece material batches are unstable, the production environment changes frequently, or the equipment status fluctuates. The purpose is to expand the working condition coverage by analyzing historical data and improve the robustness of the standard process parameter library.

[0078] Specifically, the system first retrieves workpiece data of the same type as the current working condition information (e.g., welding records with the same material and similar structure) from the historical database and extracts the actual value range of each working condition parameter (e.g., minimum plate thickness of 2.1mm, maximum of 3.9mm). Combining the current workpiece's design tolerance (e.g., nominal plate thickness of 3mm±0.5mm) with process experience, the final fluctuation range of each parameter is determined. Subsequently, a parameter space partitioning algorithm (e.g., uniform sampling, Latin hypercube sampling) is used to generate multiple working condition parameter combinations within the fluctuation range. Each combination contains specific values ​​for material properties, structural parameters, environmental information, and equipment status, forming a derived working condition information set.

[0079] S202, inputting multiple sets of derived working condition information into the welding process simulation model respectively, and screening out standard process parameter combinations that meet preset welding quality requirements under each derived working condition information.

[0080] Among them, the preset welding quality requirements refer to the pre-set welding quality evaluation criteria, including weld formation indicators (such as weld nugget width ≥8mm, flash height ≤0.5mm), mechanical property indicators (such as tensile strength ≥200MPa, elongation ≥15%) and defect levels (such as porosity ≤1%).

[0081] The system sequentially inputs each set of derived working condition information into the welding process simulation model. The model then simulates the welding process based on the working condition parameters and outputs a weld quality prediction. Each set of simulation results is then verified against pre-set quality requirements, such as whether the weld nugget size meets the standard and whether crack risk is predicted. If the simulation results for a given process parameter combination meet all quality criteria, it is marked as qualified and included in the candidate set of standard process parameter combinations. If not, the parameters are adjusted and the simulation is repeated, or the combination is eliminated.

[0082] In the above-mentioned embodiment, the system analyzes operating condition information and historical production data to define operating parameter fluctuation ranges and screens multiple sets of standard process parameter combinations that meet quality requirements within the simulation model. This step expands the coverage of process parameters and enhances the representativeness of the parameter library. The resulting standard process parameter library can better adapt to complex operating conditions such as different batches of materials and structural variations in actual production, supporting parameter adjustment and quality assurance in the subsequent welding process.

[0083] S203: Obtain a first quality score corresponding to each standard process parameter combination.

[0084] Specifically, the system establishes a quality assessment model for each qualified standard process parameter combination. For each process parameter (such as stir head speed and welding speed), the absolute distance from the corresponding target value in the preset quality index is calculated and normalized to the interval [0,1]. (For example, if the allowable deviation is ±200 rpm and the actual deviation is 100 rpm, the normalized value is 0.5.) Using a pre-set parameter weight matrix (such as temperature weighting higher than pressure weighting), the normalized distances of each parameter are weighted and summed to obtain a first quality score. For example, if the speed, temperature, and pressure scores of a combination are 0.8, 0.9, and 0.7, respectively, and the weights are 0.3, 0.4, and 0.3, respectively, the first quality score is 0.8 × 0.3 + 0.9 × 0.4 + 0.7 × 0.3 = 0.81.

[0085] S204 , adjusting the first quality score according to the importance weight corresponding to each derived working condition information to obtain a second quality score corresponding to each standard process parameter combination.

[0086] The system assigns an importance weight to each set of derived operating condition information (e.g., a weight of 1.0 for common operating conditions and 0.6 for rare operating conditions). This weight reflects the priority of that operating condition in actual production. The system then multiplies the first quality score of each standard process parameter combination by the weight of the corresponding derived operating condition to obtain a second quality score. For example, if a combination corresponds to a rare operating condition (weight 0.6) with a first quality score of 0.8, the second quality score is 0.8 × 0.6 = 0.48. Another combination corresponds to a common operating condition (weight 1.0) with a first quality score of 0.75, the second quality score is 0.75 × 1.0 = 0.75. The latter combination, because the operating condition is more common, receives a higher score.

[0087] It should be noted that the importance weights of derived operating condition information represent the probability of occurrence or impact of different derived operating conditions in actual production. For example, a high-humidity environment (a rare operating condition) has a lower weight, while a normal room temperature environment (a common operating condition) has a higher weight. The weights can be determined through historical production data statistics or process risk assessments and are not limited here.

[0088] S205 , selecting a standard process parameter combination with the largest second quality score that meets a corresponding preset quantity ratio from a plurality of standard process parameter combinations corresponding to each derived working condition information to construct a standard process parameter library.

[0089] The system ranks the standard process parameter combinations for each derived working condition from highest to lowest according to the second quality score, and selects the top N combinations based on a preset ratio (e.g., 20%) (N = total number of combinations × ratio). For example, if there are 50 qualifying combinations for a given working condition and the preset ratio is 20%, the 10 highest-scoring combinations will be selected and stored. The system also checks the parameter differences between the stored combinations for each working condition to ensure that combinations within the same working condition cover different parameter adjustment options (e.g., both high-speed-low-speed and low-speed-high-speed combinations) to address the diverse adjustment needs of actual welding.

[0090] In the above example, the system performs a multi-dimensional quality score on standard process parameter combinations and performs secondary optimization based on the importance weight of working condition information. Ultimately, it selects highly reliable and adaptable parameter combinations for inclusion in the parameter library. This approach not only improves the accuracy of parameter screening but also dynamically adjusts the parameter library structure based on actual working conditions, helping to improve the quality consistency and stability of the welding process.

[0091] S206. After determining the target process parameter combination, adjust the welding process simulation model according to the current working condition information, and input the target process parameter combination into the adjusted welding process simulation model to obtain a new first quality score.

[0092] The system collects real-time operating condition information during the current welding process and compares it with the original operating condition information input before welding, identifying any parameters that have changed (such as ambient temperature and equipment wear). The system then adjusts the input parameters or boundary conditions of the welding process simulation model based on the changed operating condition parameters. Once the adjustments are complete, the target process parameter combination is input into the adjusted model, and the weld quality prediction results (such as temperature field distribution and stress values) are recalculated. A new first-level quality score is then calculated based on the distance-weighted calculation of the preset quality indicators.

[0093] S207: Determine whether the new first quality score is less than a preset score threshold.

[0094] The system compares the newly calculated first quality score with a preset threshold. For example, if the preset threshold is 0.75 and the new score is 0.82, the product is considered acceptable; if the new score is 0.70, the product is considered unacceptable. The threshold is based on process standards and historical data and is typically set slightly below the average score of high-quality parameter combinations to provide a safety margin; this threshold is not specified here.

[0095] S208: Input the standard process parameter combination with the second highest similarity into the adjusted welding process simulation model to re-obtain a new first quality score.

[0096] Specifically, when the system determines that the new first quality score is less than a preset threshold, it immediately retrieves the standard combination with the second highest similarity to the real-time process parameter combination from the standard process parameter library. (If the original combination with the highest similarity score does not meet the standard, the second closest combination is selected.) This combination is then input into the adjusted welding process simulation model (model parameters have been updated based on the current working conditions) to recalculate its first quality score. If the new score meets the standard, this combination is used as the new target parameter combination. If it still does not meet the standard, the third highest similarity combination is retrieved for verification until a qualified combination is found or a no valid solution alarm is issued.

[0097] S209: Parameter control and adjustment of the welding equipment is performed based on the target process parameter combination.

[0098] The system converts the values ​​of each parameter in the target process parameter combination (e.g., rotational speed 1000 rpm, welding speed 60 mm / min, axial pressure 2.5 kN) into control signals (e.g., analog voltage or digital pulse signals) recognizable by the equipment. This signal is then transmitted via an industrial bus to the welding equipment's actuators (e.g., servo motors and pressure controllers). Upon receiving these signals, the equipment gradually adjusts the actual operating parameters using a closed-loop control system (e.g., PID control) until the target values ​​are achieved. The system also continuously monitors real-time data during the parameter adjustment process to ensure a smooth adjustment process and avoid welding defects caused by sudden parameter changes.

[0099] In the above embodiment, the system achieves closed-loop optimization of parameter adjustment by adjusting the simulation model in real time based on current working conditions and performing a quality score verification on the target parameter combination. If the score falls short of the target, the system automatically switches to the suboptimal parameters for re-evaluation. This dynamic feedback mechanism enhances the adaptability and intelligence of parameter selection, ensuring that each parameter adjustment is validated by simulation, maximizing the reliability of the welding process and the quality of the final weld.

[0100] The following is a more detailed description of the process of the method provided by this implementation. Figure 3 , which is a flow chart of process parameter adjustment of the friction stir welding control system in an embodiment of the present application.

[0101] S301. Obtain the proportion of target process parameters with deviation risks in the real-time process parameter combination.

[0102] Specifically, the system first extracts all process parameters (e.g., n parameters) from the real-time process parameter combination. Then, based on the parameter change trends determined in step S103, it determines whether each parameter has a deviation risk (i.e., whether the predicted value exceeds the process window). The number of parameters with deviation risk, m, is counted, and the ratio is calculated as m / n × 100%. For example, if the real-time process parameter combination includes five parameters: speed, temperature, pressure, welding speed, and torque, and the speed, temperature, and pressure are predicted to exceed the process window, the ratio is 60%.

[0103] S302: Whether the ratio value exceeds a preset ratio threshold.

[0104] Specifically, the system compares the ratio calculated in step S301 with a preset ratio threshold. For example, if the preset threshold is 50%, a ratio ≥ 50% indicates a high risk of deviation, triggering the overall adjustment process in step S303. If the ratio is < 50%, the risk of deviation is determined to be low, triggering the local adjustment process from steps S304 to S306. The threshold setting should be based on process stability requirements and historical data. For example, in aerospace applications with extremely high welding quality requirements, the threshold could be set to 40% to trigger more stringent adjustment measures in advance. This is not a limitation here.

[0105] S303: Use the target process parameter combination to adjust all process parameters as a whole.

[0106] This step is the same as step S209 and will not be repeated here.

[0107] S304 , searching for historical production data whose similarity with the operating condition information is greater than a preset threshold, and obtaining target historical production data.

[0108] Specifically, the system first extracts key features from the current operating condition (such as material type, plate thickness, ambient temperature, and equipment wear). It then retrieves all historical operating condition records from the historical production database and calculates the similarity between each record and the current operating condition. Based on a preset threshold (e.g., similarity > 80%), the system selects historical production data with a similarity greater than that threshold and selects them as the target historical production data.

[0109] S305 . Extract historical process parameter values ​​and adjustment responses corresponding to process parameters with deviation risks from the target historical production data to obtain a historical parameter data set.

[0110] Specifically, based on the list of deviation parameters (such as speed and temperature) determined in step S301, the system traverses each record in the target historical production data and extracts the historical values ​​of these parameters in each record (for example, a record shows a speed of 900 rpm and a temperature of 450°C). Simultaneously, the system extracts information about adjustment operations for these parameters in the record, such as the adjustment value (for example, if the speed is adjusted from 900 rpm to 1000 rpm, the adjustment value is +100 rpm) and the adjusted quality score (for example, the first quality score is 0.85). This information is organized into a structured dataset, for example, stored in a table format, with columns such as parameter name, historical value, adjustment value, and quality score, and rows representing each historical record.

[0111] S306: Based on the working condition information and the historical parameter data set, the adjustment value corresponding to the process parameter with deviation risk is determined by the optimization algorithm and local adjustment is performed.

[0112] Specifically, the system inputs current operating condition information (such as material properties, structural parameters, etc.) and historical parameter data sets into the optimization algorithm model. Through training or calculation, the model analyzes the adjustment patterns of deviating parameters under different operating conditions and outputs the optimal adjustment value for the current deviating parameter. For example, a random forest model is trained on historical data, inputting the current operating condition characteristics and the current value of the deviating parameter to predict the optimal adjustment amount (e.g., a predicted adjustment value of -8°C when the temperature deviates). The system then converts the adjustment value into equipment control instructions, adjusting only parameters at risk of deviation. For example, using a PID controller to gradually adjust the temperature from 460°C to 452°C (current value + adjustment value = 460-8 = 452°C) while keeping other parameters (such as speed and pressure) unchanged.

[0113] In the above example, the system proposes a control strategy that combines global and local adjustments based on the degree of parameter deviation risk. When the deviation risk is high, global parameter adjustments can be made quickly to avoid widespread quality issues. When the risk is low, specific parameters are fine-tuned locally based on historical data to achieve more refined process control. This hierarchical adjustment strategy enhances the flexibility and targeted nature of parameter control, not only improving the adaptability of welding production but also effectively reducing human intervention and operational difficulty.

[0114] The friction stir welding control system of the embodiment of the present invention is applied to electronic equipment. Figure 4 A schematic diagram of the architecture of an electronic device suitable for implementing an embodiment of the present invention is shown.

[0115] It should be noted that Figure 4 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0116] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments can be accomplished by instructions (computer programs) or by controlling related hardware through instructions (computer programs), and the instructions can be stored in a computer-readable storage medium and loaded and executed by a processor. The electronic device of this embodiment includes a storage medium and a processor, wherein the storage medium stores a plurality of instructions, which can be loaded by the processor to execute any step of the method provided in the embodiment of the present invention.

[0117] Specifically, the storage medium and the processor are electrically connected directly or indirectly to achieve data transmission or interaction. For example, these elements can be electrically connected to each other via one or more signal lines. The storage medium stores computer-executable instructions for implementing the data access control method, including at least one software function module that can be stored in the storage medium in the form of software or firmware. The processor executes various functional applications and data processing by running the software programs and modules stored in the storage medium. The storage medium can be, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc. The storage medium is used to store programs, and the processor executes the programs after receiving the execution instructions.

[0118] Furthermore, the software programs and modules in the above-mentioned storage medium may also include an operating system, which may include various software components and / or drivers for managing system tasks (such as memory management, storage device control, power management, etc.), and may communicate with various hardware or software components to provide an operating environment for other software components. The processor may be an integrated circuit chip having signal processing capabilities. The above-mentioned processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc., which may implement or execute the various methods, steps, and logic flow diagrams disclosed in this embodiment. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0119] Since the instructions stored in the storage medium can execute the steps of any method provided in the embodiments of the present invention, the beneficial effects of any method provided in the embodiments of the present invention can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0120] The above description is merely a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A parameter control method for a friction stir welding process, applied to a friction stir welding control system, characterized in that: The method comprises: Before friction stir welding begins, the working condition information of the workpiece to be welded is input into the welding process simulation model for virtual test welding. Multiple sets of standard process parameter combinations that meet the preset welding quality requirements are screened out to obtain a standard process parameter library. The working condition information includes the material properties, structural parameters, welding environment information, and welding equipment status parameters of the workpiece to be welded. During the friction stir welding process, process parameter information is collected in real time to obtain a real-time process parameter combination; Determining a change trend of each process parameter based on the real-time process parameter combination within a first preset time period; If it is determined based on the change trend that the current welding state has a risk of deviation within a second preset time period in the future, the standard process parameter combination in the standard process parameter library that has the greatest similarity to the real-time process parameter combination is determined as the target process parameter combination, and the target process parameter combination is used to perform parameter control and adjustment on the welding equipment.

2. The method according to claim 1, characterized in that The step of inputting the working condition information of the workpiece to be welded into the welding process simulation model to perform virtual test welding and screen out multiple groups of standard process parameter combinations that meet the preset welding quality requirements specifically includes: Determine the fluctuation range of each working condition parameter based on the working condition information and historical production data of workpieces of the same type as the working condition information; Divide multiple operating condition parameter combinations within the fluctuation range to obtain multiple groups of derived operating condition information; Multiple groups of derived working condition information are input into the welding process simulation model respectively, and a standard process parameter combination that meets the preset welding quality requirements under each derived working condition information is screened out.

3. The method according to claim 2, characterized in that After the step of inputting the plurality of groups of derived working condition information into the welding process simulation model respectively and screening out the standard process parameter combination that meets the preset welding quality requirements under each derived working condition information, the method further includes: Obtaining a first quality score corresponding to each standard process parameter combination, where the first quality score is calculated based on a weighted distance between each process parameter and a corresponding indicator in the preset welding quality requirement; Adjusting the first quality score according to the importance weight corresponding to each derived working condition information to obtain a second quality score corresponding to each standard process parameter combination; The standard process parameter library is constructed by selecting a standard process parameter combination with the largest second quality score that meets a corresponding preset quantity ratio from among multiple standard process parameter combinations corresponding to each derived working condition information.

4. The method according to claim 3, characterized in that The step of determining the standard process parameter combination having the greatest similarity to the real-time process parameter combination in the standard process parameter library as the target process parameter combination specifically includes: Calculating the time required for parameter adjustment between each standard process parameter combination in the standard process parameter library and the real-time process parameter combination based on the real-time process parameter combination; Screening the standard process parameter library for standard process parameter combinations whose parameter adjustment time is less than or equal to a preset time threshold to obtain a first candidate parameter combination set; Screening out standard process parameter combinations whose second quality scores are greater than a preset score threshold from the first candidate parameter combination set to obtain a second candidate parameter combination set; The standard process parameter combination with the shortest required parameter adjustment time in the second candidate parameter combination set is determined as the target process parameter combination.

5. The method according to claim 1, wherein After the step of determining the standard process parameter combination having the greatest similarity to the real-time process parameter combination in the standard process parameter library as the target process parameter combination, the method further includes: Adjusting the welding process simulation model according to current working condition information; inputting the target process parameter combination into the adjusted welding process simulation model to obtain a new first quality score; Determining whether the new first quality score is less than a preset score threshold; If it is detected that the new first quality score is less than the preset score threshold, the standard process parameter combination with the second highest similarity is input into the adjusted welding process simulation model to re-obtain a new first quality score for re-judgment.

6. The method according to claim 1, characterized in that After the step of determining the standard process parameter combination having the greatest similarity to the real-time process parameter combination in the standard process parameter library as the target process parameter combination, the method further includes: Obtaining a proportion of target process parameters with a deviation risk in the real-time process parameter combination; If it is detected that the ratio value exceeds a preset ratio threshold, all process parameters are adjusted as a whole using the target process parameter combination; If it is detected that the ratio value does not exceed the preset ratio threshold, the adjustment value of the process parameter with deviation risk is determined based on historical production data, and local adjustment is performed according to the adjustment value.

7. The method according to claim 6, characterized in that The step of determining the adjustment value of the process parameter with a deviation risk based on the historical production data and performing local adjustment according to the adjustment value specifically includes: Retrieving historical production data whose similarity to the operating condition information is greater than a preset threshold to obtain target historical production data; Extracting historical process parameter values ​​and adjustment responses corresponding to process parameters with deviation risks from the target historical production data to obtain a historical parameter data set, wherein the adjustment response includes historical adjustment values ​​and corresponding historical first quality scores; Based on the operating condition information and the historical parameter data set, determining, by an optimization algorithm, an adjustment value corresponding to the process parameter with a risk of deviation; The process parameters with the risk of deviation are locally adjusted according to the adjustment value.

8. A friction stir welding control system, characterized in that: The friction stir welding control system includes: one or more processors and memories; The memory is coupled to the one or more processors, and is configured to store computer program codes, wherein the computer program codes include computer instructions. The one or more processors call the computer instructions to enable the friction stir welding control system to execute the method according to any one of claims 1 to 7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on a friction stir welding control system, the friction stir welding control system is caused to execute the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product is run on a friction stir welding control system, the friction stir welding control system is enabled to perform the method according to any one of claims 1 to 7.

Images