Process parameter optimization method for inhibiting cold forging springback of aluminum material
By monitoring and optimizing process and environmental parameters during the cold forging of aluminum materials, and using a PID controller to adjust the equipment output power, the problem of springback in cold forging of aluminum materials was solved, and the processing accuracy and stability were improved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-01-04
- Publication Date
- 2026-04-03
AI Technical Summary
During the cold forging of aluminum, the process parameters are out of sync with the actual processing and production, making it difficult to effectively suppress springback, which affects forming accuracy and performance.
By monitoring the process and environmental parameters during the cold forging of aluminum, analyzing the deviation fluctuations and correlations, and using a PID controller to optimize the process parameters, the output power of the cold forging equipment is adjusted in real time to suppress springback.
It improves the process stability of cold forging of aluminum materials, ensures the dimensional accuracy and shape stability of products, effectively suppresses springback, and improves processing quality.
Smart Images
Figure CN121785101A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of cold forging technology, specifically to a method for optimizing process parameters to suppress springback in cold forging of aluminum materials. Background Technology
[0002] Cold forging of aluminum is a process in which high pressure is applied to an aluminum billet through a die at room temperature to achieve plastic deformation. However, the inherent low elastic modulus and significant work hardening effect of aluminum cause the workpiece to spring back after the forming force is removed, resulting in deviations in the shape and size of the formed workpiece, which affects the accuracy of subsequent product assembly and performance.
[0003] In traditional aluminum cold forging, automatic processing is mainly achieved by setting process parameters. However, in actual processing, the performance differences between different batches of aluminum billets and the differences in the actual operating conditions of cold forging equipment are ignored, which affect the actual production. At the same time, there is a strong dynamic coupling relationship between different process parameters, resulting in a large deviation between the actual process parameters and the set process parameters. This causes the parameter control in the aluminum processing process to be disconnected from the actual production, affecting the stability of the springback suppression effect of aluminum cold forging and making it difficult to effectively guarantee the processing quality of aluminum cold forging. Summary of the Invention
[0004] To address the aforementioned technical problems, a method for optimizing process parameters to suppress springback in cold forging of aluminum is provided, thereby resolving the existing issues.
[0005] The solution to the technical problem of this application is to provide a method for optimizing process parameters to suppress the springback of aluminum materials during cold forging, including the following steps: Data on each monitoring parameter during the cold forging process of aluminum materials at different times in each processing cycle are obtained. The monitoring parameters include process parameters and environmental parameters. For each processing cycle, the deviation volatility, which characterizes the fluctuation deviation state of the monitoring parameter itself, is determined based on the degree of deviation and volatility of each monitoring parameter. Based on the evolution differences in the deviation fluctuations of monitoring parameters between different processing cycles, and the instability of the correlation between monitoring parameters, the cumulative interference impact on the processing process is assessed, and the interference assessment degree of each processing cycle is obtained. If the interference assessment degree of the current processing cycle meets the preset conditions, the process parameter optimization strategy is activated, and the strategy includes: By analyzing the trend of the deviation fluctuation of the same process parameter between the current processing cycle and other processing cycles, and the contribution of the deviation fluctuation of the process parameter to the overall processing deviation, the influence of the process parameter on the process instability is characterized. The process influence of each process parameter in the current processing cycle is determined to predict the process parameter. Using the prediction results, the process parameter is optimized and controlled by a PID controller.
[0006] Preferably, the environmental parameters include ambient temperature, ambient humidity, and dust concentration.
[0007] Preferably, the process for determining the deviation fluctuation is as follows: Calculate the relative error between the data of each monitoring parameter at each time point and the preset command value under each processing cycle; Calculate the degree of dispersion of all relative errors for each monitoring parameter in each processing cycle; Calculate the average of the absolute values of all relative errors for each monitoring parameter in each processing cycle; The deviation volatility is the result of a positive fusion of the average value and the degree of dispersion.
[0008] Preferably, the specific process of positive fusion is as follows: the product of the average value and the degree of dispersion is used as the deviation fluctuation.
[0009] Preferably, obtaining the interference assessment degree for each processing cycle includes: The correlation of any two monitoring parameters under each processing cycle is used to form a correlation vector; the correlation between each processing cycle and the correlation vector of each previous processing cycle is calculated and negatively mapped. The difference in the deviation fluctuation of all monitoring parameters between each processing cycle and its previous processing cycles is taken as the fluctuation difference; The interference assessment degree is the result of positively fusing the fluctuation differences between each processing cycle and all previous processing cycles, as well as the negative mapping.
[0010] Preferably, the step of determining whether the interference assessment degree of the current processing cycle meets the preset conditions and controlling the activation of the process parameter optimization strategy includes: if the interference assessment degree of the current processing cycle is greater than the preset threshold, then the process parameter optimization strategy is activated; otherwise, the process parameters are maintained for processing and production.
[0011] Preferably, determining the process influence of each process parameter within the current processing cycle includes: Obtain the trend statistics of the deviation fluctuation of the same process parameter in the current processing cycle and all previous processing cycles; Calculate the ratio between the deviation fluctuation of each process parameter in the current processing cycle and the sum of the deviation fluctuations of all monitored parameters, and use it as the deviation contribution value; The process influence degree, trend statistics, and deviation contribution value are all positively correlated.
[0012] Preferably, the process of calculating the process influence is as follows: the product of the result of positive mapping of the trend statistic and the deviation contribution value is used as the process influence.
[0013] Preferably, the prediction of process parameters includes: The process influence of each process parameter in the current processing cycle is normalized and used as the smoothing coefficient for each process parameter in the current processing cycle. Based on the smoothing coefficient, the exponential smoothing algorithm is used to predict the data of each process parameter at the current time and within the preset time period before it, and to obtain the prediction result of each process parameter at the next time.
[0014] Preferably, the step of optimizing the process parameters using a PID controller includes: calculating the average of the data for each process parameter at the current moment and the predicted result at the next moment, using the difference between this average and the preset command value as the predictive control deviation, and adjusting the output power of the cold forging equipment using the PID controller to optimize the process parameters.
[0015] This application has at least the following beneficial effects: This application analyzes the fluctuations and levels of deviations in monitored parameters, calculating the deviation volatility. Its advantage lies in considering the inherent fluctuations of individual monitored parameters, reflecting the instability of these parameters within the processing cycle. It also obtains the interference assessment degree for each processing cycle, which considers the cross-cycle evolution differences in deviation volatility, reveals the time-varying accumulation trend of interference, analyzes the instability of the correlation between monitored parameters, and reveals abnormal changes in multi-parameter coupling effects, thus assessing the overall process drift caused by the accumulation of multi-source interference in each processing cycle. If the interference assessment degree of the current processing cycle exceeds the control range, the process parameters for the processing cycle are optimized to determine the process influence of each process parameter in the current processing cycle. Its advantage lies in considering the inherent fluctuations of the process parameters themselves. The study investigates the deteriorating trend of process deviation and the contribution of individual process parameter deviations to the overall processing cycle deviation, reflecting the process instability caused by the deviation of process parameters and its potential impact on the stress distribution and springback of cold forging. It aims to predict process parameters and use the prediction results to optimize the control of process parameters through a PID controller. The beneficial effect lies in using the process influence degree as a smoothing coefficient in an exponential smoothing algorithm to predict process parameters, closely tracking their latest changes, accurately capturing potential deteriorating trends that could lead to process instability, and proactively responding to feedback to optimize process parameters. This improves the process stability during aluminum cold forging, effectively suppresses aluminum springback, and ensures that the final product's dimensional accuracy meets design requirements. Attached Figure Description
[0016] The following section, in conjunction with the accompanying drawings, provides a more detailed explanation of a method for optimizing process parameters to suppress springback in cold forging of aluminum materials according to this application.
[0017] Figure 1 A flowchart illustrating the steps of a method for optimizing process parameters to suppress springback in cold forging of aluminum, as provided in this application embodiment; Figure 2 A flowchart illustrating the steps of the method for obtaining the process influence degree provided in the embodiments of this application. Detailed Implementation
[0018] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description, in conjunction with the accompanying drawings and embodiments, provides a method for optimizing process parameters to suppress springback in cold forging of aluminum materials. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.
[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.
[0020] Please see Figure 1 The diagram illustrates a flowchart of a method for optimizing process parameters to suppress springback in cold forging of aluminum, according to an embodiment of this application. The method includes the following steps: Step 1: Obtain data for each monitoring parameter at different times during each processing cycle in the cold forging process of aluminum materials. The monitoring parameters include process parameters and environmental parameters.
[0021] Cold forging of aluminum is an advanced net-forming process that uses a die to apply high pressure to a blank at room temperature, causing plastic deformation to obtain precision parts. During the cold forging of aluminum, improper process parameters can lead to springback. When the external forming force is removed, the elastic strain energy stored within the material is released instantaneously, causing springback. Springback refers to the deviation of the workpiece's dimensions and shape from the design target due to the material's elastic recovery characteristics after cold forging, severely affecting product assembly accuracy and batch production consistency. To suppress springback, the process parameters during cold forging are optimized to effectively control the plastic deformation process, reduce the storage of elastic strain, and improve the dimensional accuracy and shape stability of the product.
[0022] Based on the above analysis, in the cold forging process of a batch of aluminum workpieces using forming machine tools, multiple monitoring parameters at different times are obtained. The processing time of a single aluminum workpiece is taken as a processing cycle, and data of each monitoring parameter at different times within each processing cycle are obtained. The monitoring parameters include process parameters and environmental parameters. Among them, process parameters include billet forming temperature and pressing parameters. The billet forming temperature includes, but is not limited to, billet preheating temperature and die working temperature. The pressing parameters include, but are not limited to, pressing amount and pressing rate. The environmental parameters include, but are not limited to, ambient temperature, ambient humidity and dust concentration. In this embodiment, the billet forming temperature is collected by an infrared thermometer, the pressing amount and pressing rate are collected by a displacement sensor and a speed sensor, respectively, and the ambient temperature, ambient humidity and dust concentration are collected by a temperature sensor, a humidity sensor and a dust concentration sensor, respectively. Secondly, the data acquisition time interval is 0.1s. As other implementation methods, the implementer can set it according to the actual situation.
[0023] The collected data is subjected to anomaly detection, and abnormal data is removed. Missing values are filled in, and the data is normalized using the maximum-minimum normalization method.
[0024] In this embodiment, the Laida criterion is used for anomaly detection, and a linear interpolation algorithm is used for missing value filling. Both the Laida criterion and the linear interpolation algorithm are well-known technologies and will not be described in detail here.
[0025] Thus, data for each monitoring parameter at different times within each processing cycle are obtained.
[0026] Step 2: For each processing cycle, determine the deviation volatility based on the degree of deviation and volatility of each monitoring parameter to characterize the fluctuation deviation state of the monitoring parameter itself; based on the evolution difference of the deviation volatility of the monitoring parameters between different processing cycles and the instability of the correlation between the monitoring parameters, assess the cumulative interference impact on the processing process and obtain the interference assessment degree for each processing cycle.
[0027] In the cold forging of aluminum workpieces, the combined influence of multiple factors leads to problems such as data jumps, accuracy deviations, and signal attenuation in the collected process parameters. For example, the temperature and humidity in the workshop are easily affected by the start and stop of the ventilation system and changes in outdoor weather, which in turn affects the temperature of the billet and the die. Metal chips generated during the cold forging process are easily attached to the sensor detection end face, resulting in inaccurate data collected by the sensor, which affects the precise control of process parameters during the cold forging process and makes it difficult to effectively suppress springback.
[0028] Secondly, due to interference from multiple sources, process parameters may fluctuate. Therefore, it is necessary to periodically monitor and optimize the process parameters. The purpose is to capture the cumulative characteristics of parameter deviations caused by multi-source interference in real time, and then dynamically correct the process parameters to control the fluctuations of the process parameters within the allowable range of springback suppression, so as to ensure the dimensional accuracy of batch-processed aluminum workpieces and avoid the problem of poor springback stability of cold forging of batch-produced aluminum materials.
[0029] During batch cold forging, the deviation of monitoring parameters from target values is analyzed to assess the fluctuation of these parameters and calculate the degree of deviation fluctuation. Specifically: Calculate the relative error between the data of each monitoring parameter at each time point and the preset command value under each processing cycle; In this embodiment, the relative error is calculated as follows: the difference between the data of each monitoring parameter at each moment in each processing cycle and the preset instruction value is taken as the ratio of the difference to the preset instruction value, and this ratio is used as the relative error. For process parameters, the preset target value refers to the value corresponding to the processing process parameter curve that changes over time and is preset during the process design stage of the cold forging process. For environmental parameters, the preset instruction value is the optimal environmental temperature, optimal environmental humidity, and optimal dust concentration corresponding to the optimal environment for the cold forging process. The optimal environmental parameters are set according to the relevant environmental requirements for cold forging in the actual production process. In this embodiment, the optimal environmental temperature is set to 25°C, the optimal environmental humidity is set to 50%, and the optimal dust concentration is set to 10mg / m³. In other implementation methods, the implementer can set these parameters according to the actual situation.
[0030] Calculate the degree of dispersion of all relative errors for each monitoring parameter in each processing cycle; In this embodiment, the degree of dispersion is measured by calculating the standard deviation of the relative error of each monitoring parameter at all times in each processing cycle. As an alternative implementation, the implementer may use other methods of the prior art, such as variance, etc. This embodiment does not impose any special restrictions on this.
[0031] Calculate the average of the absolute values of all relative errors for each monitoring parameter in each processing cycle; The product of the average value and the degree of dispersion is used as the deviation fluctuation of each monitoring parameter in each processing cycle; It should be noted that, in order to avoid the dispersion level being equal to 0, a parameter tuning factor is added to the dispersion level. In this embodiment, the parameter tuning factor is set to 1. In other implementation methods, the implementer can set it according to the actual situation.
[0032] It should be noted that the greater the dispersion, the more drastic and unstable the monitoring parameter fluctuates throughout the entire processing cycle, reflecting strong dynamic interference or control failure in the processing and production process. The larger the average value, the more the monitoring parameter continuously deviates from the preset ideal target throughout the entire processing cycle. The greater the deviation fluctuation, the more the monitoring parameter not only continuously deviates from the target, but also experiences drastic fluctuations in its deviation, reflecting the instability of the monitoring parameter during this processing cycle and its greater susceptibility to interference.
[0033] Secondly, different monitoring parameters are coupled with the springback of aluminum. For example, excessively high billet temperature reduces the yield strength and elastic modulus of the material, potentially leading to a decrease in springback. The coupling effect of different monitoring parameters can influence the suppression of springback. Therefore, analyzing the correlation between different monitoring parameters and constructing a correlation vector is crucial. The correlation vector is formed by analyzing the correlation between any two monitoring parameters under each processing cycle. In this embodiment, the degree of correlation is measured by calculating the Pearson correlation coefficient of any two monitoring parameters under each processing cycle. The calculation of the Pearson correlation coefficient is a well-known technique and will not be described in detail here. As other implementation methods, implementers may use other methods of the prior art, such as Spearman correlation coefficient, etc. This embodiment does not impose any special restrictions on this.
[0034] It should be noted that the elements in the correlation vectors between different processing cycles are arranged in the same way, that is, the elements in the same position in the two correlation vectors reflect the same degree of correlation between the two monitoring parameters; secondly, the larger the absolute value of the correlation, the higher the correlation between the two monitoring parameters.
[0035] Furthermore, by analyzing the differences in the correlation between monitoring parameters and the trends in deviation fluctuations across different processing cycles, the interference assessment degree is calculated to reflect the cumulative effect of multi-source interference in continuous production cycles and the evolution of parameter fluctuation patterns. Specifically: Calculate the correlation between each processing cycle and its previous processing cycles using the correlation vector, and perform a negative mapping on them; In this embodiment, the relevance is measured by calculating the cosine similarity of the association vectors between each processing cycle and its previous processing cycles. The calculation of cosine similarity is a well-known technique and will not be elaborated upon here. Secondly, the specific process of negative mapping is as follows: negative mapping is performed using an exponential function. Assume the relevance of the association vectors between each processing cycle and its previous processing cycles is denoted as... Then The value of is used as the result of the negative mapping, where For an exponential function with the natural constant as the base, the negative mapping process is used to make the result of the negative mapping range greater than 0 and less than or equal to 1.
[0036] The difference in the deviation fluctuation of all monitoring parameters between each processing cycle and its previous processing cycles is taken as the fluctuation difference; In this embodiment, the DTW distance of the deviation fluctuation of all monitoring parameters between each processing cycle and each previous processing cycle is taken as the fluctuation difference. The calculation of the DTW distance is a well-known technique and will not be described in detail here. As other implementation methods, implementers may use other methods of the prior art, such as Euclidean distance, etc. This embodiment does not impose any special restrictions on this.
[0037] The fluctuation differences between each processing cycle and all previous processing cycles, as well as the results of negative mapping, are positively integrated to serve as the interference assessment degree for each processing cycle. In this embodiment, the mean of the product of the fluctuation difference of each processing cycle with all previous processing cycles and the result of the negative mapping is used as the interference evaluation degree of each processing cycle. In other implementations, the implementer may calculate the sum of the products of the fluctuation difference of each processing cycle with all previous processing cycles and the result of the negative mapping as the interference evaluation degree of each processing cycle.
[0038] It should be noted that the larger the negative mapping result, the smaller the similarity of the coordinated changes of the monitoring parameters between the two processing cycles, reflecting a significant change in the coordinated relationship of the monitoring parameters under this processing cycle; the larger the fluctuation difference, the more significant the difference in the trend of the deviation fluctuation of the monitoring parameters between the two processing cycles; the larger the obtained interference assessment degree, the more significant the fluctuation characteristics and correlation of the monitoring parameters under this processing cycle, reflecting a more significant cumulative impact of the interference, and a greater impact on the rebound suppression effect.
[0039] Thus, the interference assessment degree for each processing cycle is obtained.
[0040] Step 3: Determine if the interference assessment degree of the current processing cycle meets the preset conditions, and initiate the process parameter optimization strategy. The strategy includes: characterizing the influence of process parameters on process instability by analyzing the changing trend of the deviation fluctuation of the same process parameter between the current processing cycle and other processing cycles, and the contribution of the deviation fluctuation of process parameters to the overall processing deviation; determining the process influence degree of each process parameter under the current processing cycle to predict the process parameters; and using the prediction results to optimize the control of process parameters through a PID controller.
[0041] Furthermore, based on the interference assessment degree, the cumulative deviation of the processing cycle is evaluated to determine the control of process parameters, specifically: The batches of aluminum workpieces that meet the design requirements after cold forging are selected from historical periods as historical benchmark batches. The monitoring parameters of all processing cycles of the aluminum workpieces in the historical benchmark batch during cold forging are compiled into a historical reference set. Following the above process, the interference evaluation value of all processing cycles in the historical reference set is calculated, and the maximum interference evaluation value in the historical reference set is selected as the preset threshold.
[0042] If the interference assessment degree of the current processing cycle is greater than the preset threshold, the process parameter optimization strategy is activated; otherwise, the process parameters are maintained for processing and production. It should be noted that the maximum interference assessment value reflects the maximum level of interference that the processing and production process can withstand, provided that the springback of the workpiece meets the design requirements. In subsequent processing and production, if the interference assessment value of the current processing cycle exceeds the preset threshold, it indicates that the overall fluctuation of the processing cycle has exceeded the safe range of the historical benchmark, and the risk of uncontrolled springback has increased significantly. Conversely, if the interference assessment value does not exceed the preset threshold, it indicates that the overall fluctuation of the monitoring parameters of the processing cycle has not exceeded the controllable range. At this time, there is no need to make significant adjustments to the process parameters, and the current production process parameters can be maintained to continue batch processing.
[0043] To address situations where the interference assessment level exceeds a preset threshold, and to reduce the impact of accumulated interference on the suppression of springback in batch cold forging production, it is necessary to optimize and control the process parameters of the processing cycle. Therefore, by analyzing the changing trend of the deviation fluctuation of the same process parameter in the current processing cycle and all previous processing cycles, and the proportion of the deviation fluctuation of the corresponding process parameter among all monitored parameters, the process influence degree is calculated. This assesses the potential impact of each process parameter on the processing process in the current processing cycle. The flowchart of the process influence degree acquisition method provided in this application embodiment is shown below. Figure 2 As shown, it specifically includes: Obtain the trend statistics of the deviation fluctuation of the same process parameter in the current processing cycle and all previous processing cycles; In this embodiment, the MK (Mann-Kendall) trend test algorithm is used to obtain trend statistics. The MK trend test algorithm is a well-known technology and will not be described in detail here.
[0044] It should be noted that the trend statistics reflect the direction and trend of the deviation of the process parameters in a continuous processing cycle. The value is positive and the larger the value, the more the deviation of the process parameter shows a continuous increasing trend.
[0045] Calculate the ratio between the deviation fluctuation of each process parameter in the current processing cycle and the sum of the deviation fluctuations of all monitored parameters, and use it as the deviation contribution value of each process parameter in the current processing cycle. It should be noted that, to avoid the denominator being zero when calculating the ratio, a parameter tuning factor is added to the denominator. The range of values for the parameter tuning factor is [range missing]. In this embodiment, the parameter tuning factor is set to 1. In other implementation methods, the implementer can set it according to the actual situation.
[0046] The product of the positive mapping result of the trend statistics and the deviation contribution value is used as the process influence degree of each process parameter in the current processing cycle. In this embodiment, the positive mapping process is as follows: An exponential function is used for positive mapping. Let the trend statistic be denoted as... ,but The result is taken as the result of the positive mapping, where, This represents an exponential function with the natural constant as its base, through a positive mapping process, such that the result of the positive mapping is greater than or equal to 0.
[0047] It should be noted that the larger the deviation contribution value, the more prominent the contribution of the process parameter to the overall process fluctuation of the processing cycle, and the more critical the factor causing the overall parameter fluctuation, the greater the need for control over it; the greater the process influence, the greater the potential impact of the process parameter on the stress distribution and springback of cold forging. If not controlled, the fluctuation of the process parameter may lead to a large springback, affecting product quality.
[0048] Furthermore, by predicting the changing trends of process parameters and analyzing the deviation between the predicted results and preset command values, the process parameters can be adjusted and controlled in advance. When using the exponential smoothing algorithm for prediction, the smoothing coefficient is used to control the algorithm's trust allocation between new and historical data. The larger the smoothing coefficient, the higher the weight the algorithm assigns to recent data, the more sensitive the prediction results are to the latest changes in parameters, and the faster the response. The smaller the smoothing coefficient, the more the algorithm relies on the average of long-term historical data, and the smoother and more stable the prediction results.
[0049] The process influence reflects the abnormal, unstable, or rapidly deviating state of the process parameter in the recent period, indicating that the process parameter has a significant impact on the final processing technology. Therefore, a large smoothing coefficient needs to be set to capture the deterioration trend of the process parameter so that the subsequent control efforts can be increased.
[0050] The process influence of each process parameter in the current processing cycle is normalized and used as the smoothing coefficient for each process parameter in the current processing cycle. In this embodiment, the normalization process is as follows: calculate the sum of the process influence of all process parameters in the current processing cycle, and use the ratio of the process influence of each process parameter in the current processing cycle to the sum as the smoothing coefficient.
[0051] Based on the smoothing coefficient of the processing cycle to which the current moment belongs, the exponential smoothing algorithm is used to predict the data of each process parameter in the current moment and the preset time period before it, and to obtain the prediction result of each process parameter in the next moment. In this embodiment, the duration of the preset time period includes all moments within the three processing cycles. As for other implementation methods, the implementer can set it according to the actual situation.
[0052] The average of the data for each process parameter at the current moment and the predicted result at the next moment is calculated. The difference between this average and the preset command value is taken as the predictive control deviation. Based on the predictive control deviation, the PID controller in the PLC control system adjusts the output power of the cold forging equipment to optimize the process parameters.
[0053] For example, when the forming temperature is predicted to deviate from the preset command value, it means that the output power corresponding to the preset command value will cause the forming temperature to be too high or too low. The output power should be adjusted. Therefore, in order to make the forming temperature at the next moment close to the ideal target, the original set command value should be compensated, and the PID controller should be controlled to reduce or increase the power of the heating device to reduce the cumulative impact of multi-source interference in batch production and ensure the strengthening and springback suppression effect of cold forged parts.
[0054] It should be noted that the purpose of averaging the data at the current moment with the predicted results at the next moment is to balance the current actual state of the process parameters with the future fluctuation trend, thereby avoiding drastic fluctuations or overly aggressive control actions based on the predicted results, and improving the stability of process parameter adjustments.
[0055] It should be understood that, although Figure 1 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 1 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.
[0056] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0057] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application. Therefore, any simple modifications, equivalent changes, and alterations made to the above embodiments based on the technical essence of this application, without departing from the content of the technical solution of this application, shall fall within the protection scope of the technical solution of this application.
Claims
1. A method for optimizing process parameters to suppress springback in cold forging of aluminum materials, characterized in that, The method includes the following steps: Data on each monitoring parameter during the cold forging process of aluminum materials at different times in each processing cycle are obtained. The monitoring parameters include process parameters and environmental parameters. For each processing cycle, the deviation volatility, which characterizes the fluctuation deviation state of the monitoring parameter itself, is determined based on the degree of deviation and volatility of each monitoring parameter. Based on the evolution differences in the deviation fluctuations of monitoring parameters between different processing cycles, and the instability of the correlation between monitoring parameters, the cumulative interference impact on the processing process is assessed, and the interference assessment degree of each processing cycle is obtained. If the interference assessment degree of the current processing cycle meets the preset conditions, the process parameter optimization strategy is activated, and the strategy includes: By analyzing the trend of the deviation fluctuation of the same process parameter between the current processing cycle and other processing cycles, and the contribution of the deviation fluctuation of the process parameter to the overall processing deviation, the influence of the process parameter on the process instability is characterized. The process influence of each process parameter in the current processing cycle is determined to predict the process parameter. Using the prediction results, the process parameter is optimized and controlled by a PID controller.
2. The method for optimizing process parameters to suppress springback in cold forging of aluminum as described in claim 1, characterized in that, The environmental parameters include ambient temperature, ambient humidity, and dust concentration.
3. The method for optimizing process parameters to suppress springback in cold forging of aluminum as described in claim 1, characterized in that, The process for determining the deviation fluctuation is as follows: Calculate the relative error between the data of each monitoring parameter at each time point and the preset command value under each processing cycle; Calculate the degree of dispersion of all relative errors for each monitoring parameter in each processing cycle; Calculate the average of the absolute values of all relative errors for each monitoring parameter in each processing cycle; The deviation volatility is the result of a positive fusion of the average value and the degree of dispersion.
4. The method for optimizing process parameters to suppress springback in cold forging of aluminum as described in claim 3, characterized in that, The specific process of positive fusion is as follows: the product of the average value and the degree of dispersion is used as the deviation volatility.
5. The method for optimizing process parameters to suppress springback in cold forging of aluminum as described in claim 1, characterized in that, The obtained interference assessment degree for each processing cycle includes: The correlation of any two monitoring parameters under each processing cycle is used to form a correlation vector; the correlation between each processing cycle and the correlation vector of each previous processing cycle is calculated and negatively mapped. The difference in the deviation fluctuation of all monitoring parameters between each processing cycle and its previous processing cycles is taken as the fluctuation difference; The interference assessment degree is the result of positively fusing the fluctuation differences between each processing cycle and all previous processing cycles, as well as the negative mapping.
6. The method for optimizing process parameters to suppress springback in cold forging of aluminum as described in claim 1, characterized in that, The step of determining whether the interference assessment degree of the current processing cycle meets the preset conditions and controlling the activation of the process parameter optimization strategy includes: if the interference assessment degree of the current processing cycle is greater than the preset threshold, then the process parameter optimization strategy is activated; otherwise, the process parameters are maintained for processing and production.
7. The method for optimizing process parameters to suppress springback in cold forging of aluminum as described in claim 1, characterized in that, The determination of the process influence of each process parameter in the current processing cycle includes: Obtain the trend statistics of the deviation fluctuation of the same process parameter in the current processing cycle and all previous processing cycles; Calculate the ratio between the deviation fluctuation of each process parameter in the current processing cycle and the sum of the deviation fluctuations of all monitored parameters, and use it as the deviation contribution value; The process influence degree, trend statistics, and deviation contribution value are all positively correlated.
8. The method for optimizing process parameters to suppress springback in cold forging of aluminum as described in claim 7, characterized in that, The process of calculating the process influence is as follows: the product of the result of positive mapping of the trend statistic and the deviation contribution value is used as the process influence.
9. The method for optimizing process parameters to suppress springback in cold forging of aluminum as described in claim 1, characterized in that, The prediction of process parameters includes: The process influence of each process parameter in the current processing cycle is normalized and used as the smoothing coefficient for each process parameter in the current processing cycle. Based on the smoothing coefficient, the exponential smoothing algorithm is used to predict the data of each process parameter at the current time and within the preset time period before it, and to obtain the prediction result of each process parameter at the next time.
10. The method for optimizing process parameters to suppress springback in cold forging of aluminum as described in claim 9, characterized in that, The process parameters are optimized and controlled by a PID controller, which includes: calculating the average of the data of each process parameter at the current time and the predicted result at the next time, taking the difference between the average and the preset command value as the predictive control deviation, and adjusting the output power of the cold forging equipment through the PID controller to optimize the process parameters.