Metal plate forming real-time regulation and control system and method based on cloud parameter self-adaptive control

Abstract

The invention provides a sheet metal forming real-time regulation and control system and method based on cloud parameter adaptive control, and relates to the technical field of real-time regulation and control, material parameters of a target sheet metal part are obtained, a digital prediction model is constructed based on the material parameters, and an initial cracking risk is obtained according to the digital prediction model; working condition vectors in the forming process of the target sheet metal part are collected in real time, quality detection is conducted on the forming process of the target sheet metal part according to the working condition vectors, a sheet metal quality index is obtained, and a sheet metal cracking coefficient is determined according to the sheet metal quality index and the initial cracking risk; performing stage screening on the sheet metal cracking coefficient based on historical cracking data to obtain a cracking risk stage, and determining a cracking stress index according to the cracking risk stage; and generating a sheet metal regulation strategy through the cracking stress index. According to the method, the digital prediction model and the historical data can be fused, self-adaptive quantitative evaluation and active regulation and control of the cracking risk of the sheet metal part are realized, and thus the production accuracy and stability are improved.

Description

Technical Field

[0001] This application relates to the field of real-time control technology, and more specifically, to a real-time control system and method for sheet metal forming based on cloud-based parameter adaptive control. Background Technology

[0002] Currently, the existing technology system in the sheet metal forming field mainly comprises three levels: First, in the process design stage, computer-aided engineering (CAE) simulation technology based on material parameters is widely used to predict material flow and potential defects during the forming process by constructing finite element models; second, in the production execution stage, sensor networks installed on equipment and molds are used to collect real-time data on stamping speed, blank holder force, and other operating conditions to monitor process status and issue alarms for exceeding limits; third, at the experience accumulation level, a knowledge base of experience is formed by systematically recording and analyzing the correlation between material batches, process parameters, and defects in historical production data to guide process optimization. These technologies together constitute the main means by which the industry currently controls the forming process.

[0003] However, while existing technologies can perform pre-production simulation and post-production statistics, they still face significant bottlenecks in actual production. On the one hand, offline CAE simulation is disconnected from real-time production conditions, failing to dynamically respond to on-site variables such as material performance fluctuations and mold wear. On the other hand, sensor monitoring is mostly limited to threshold alarms, lacking the ability to quantitatively assess and warn of risk evolution patterns under multiple coupled operating conditions. Simultaneously, historical data is fragmented from real-time decision-making, making it difficult to directly translate experience bases into online control commands, resulting in process adjustments relying on manual experience and exhibiting delayed responses. Therefore, how to integrate digital prediction models and historical data to achieve adaptive quantitative assessment and proactive control of sheet metal part cracking risks, thereby improving production accuracy and stability, is a challenge facing the industry. Summary of the Invention

[0004] This application provides a real-time control system and method for sheet metal forming based on cloud-based parameter adaptive control. It can integrate digital prediction models and historical data to achieve adaptive quantitative assessment and proactive control of the cracking risk of sheet metal parts, thereby improving production accuracy and stability.

[0005] In a first aspect, this application provides a real-time control method for sheet metal forming based on cloud-based parameter adaptive control, the control method comprising the following steps: Obtain the material parameters of the target sheet metal part, construct a digital prediction model of the forming process of the target sheet metal part based on the material parameters, predict the forming process of the target sheet metal part according to the digital prediction model, and then obtain the initial cracking risk of each forming stage in the forming process of the target sheet metal part. The working condition vector of the target sheet metal part forming process is collected in real time. The quality inspection of the target sheet metal part forming process is carried out based on the working condition vector to obtain the sheet metal quality index of each forming stage. The sheet metal cracking coefficient of the target sheet metal part in each forming stage is determined based on the sheet metal quality index of each forming stage and the corresponding initial cracking risk. Historical cracking data of the sheet metal forming process is obtained. Based on the historical cracking data, the sheet metal cracking coefficient of each forming stage is screened to obtain each cracking risk stage. The cracking stress index is determined according to each cracking risk stage. The cracking stress index is used to generate a sheet metal control strategy.

[0006] In this embodiment, the material parameters of the target sheet metal part are obtained by acquiring the physical parameters and mechanical property parameters of the target sheet metal part from the material database of the target sheet metal part, and then using the physical parameters and mechanical property parameters of the target sheet metal part as material parameters.

[0007] In this embodiment, constructing a digital prediction model for the forming process of the target sheet metal part based on the material parameters specifically includes: A 3D model is built based on the material parameters of the target sheet metal part; A mesh is generated from the 3D model to obtain a sheet metal mesh model; The sheet metal mesh model is imported into the simulation platform to obtain a digital prediction model of the forming process of the target sheet metal part.

[0008] In this embodiment, the quality inspection of the forming process of the target sheet metal part is performed based on the working condition vector, and the sheet metal quality index of each forming stage is obtained, specifically including: Initialize the reference force-stroke curve; The baseline deviation is determined based on the aforementioned working condition vector and the reference force-stroke curve. Determine the offset of feature points at each forming stage; The sheet metal quality index for each forming stage is determined based on the baseline deviation and the corresponding feature deviation point.

[0009] In this embodiment, determining the sheet metal cracking coefficient of the target sheet metal part at each forming stage based on the sheet metal quality index and the corresponding initial cracking risk specifically includes: For the sheet metal quality index at each forming stage, the risk direction of the sheet metal quality index is unified to obtain the sheet metal quality risk. Based on the sheet metal quality risk and the corresponding initial cracking risk, risk fusion is performed to obtain the sheet metal cracking coefficient for the corresponding forming stage, and then the sheet metal cracking coefficient of the target sheet metal part at each forming stage is obtained.

[0010] In this embodiment, the sheet metal cracking coefficient is a coefficient used to quantify the risk of cracking in sheet metal parts during the forming stage.

[0011] In this embodiment, determining the cracking stress index based on each cracking risk stage specifically includes: The weights of each risk stage are determined based on the historical cracking data. The basic stress component is determined based on the sheet metal cracking coefficient and the corresponding risk stage weight for each cracking risk stage. Risk gradients are extracted by using the sheet metal cracking coefficients corresponding to each cracking risk stage to obtain the trend stress component. The cracking stress index is obtained by fusing the basic stress component and the trend stress component.

[0012] In this embodiment, the cracking stress index is used to quantify the severity of the overall cracking threat faced by sheet metal parts during the forming process.

[0013] In this embodiment, the sheet metal control strategy generated by the cracking stress index specifically includes: Initialize each stress threshold interval; The sheet metal control strategy is determined by the cracking stress index and various stress threshold ranges.

[0014] Secondly, this application provides a real-time control system for sheet metal forming based on cloud-based adaptive parameter control, used to execute a real-time control method for sheet metal forming based on cloud-based adaptive parameter control, the control system comprising: The parameter acquisition module is used to acquire the material parameters of the target sheet metal part, construct a digital prediction model of the forming process of the target sheet metal part based on the material parameters, predict the forming process of the target sheet metal part according to the digital prediction model, and thus obtain the initial cracking risk of each forming stage in the forming process of the target sheet metal part. The crack detection module is used to collect the working condition vector of the forming process of the target sheet metal part in real time, perform quality inspection on the forming process of the target sheet metal part based on the working condition vector, obtain the sheet metal quality index of each forming stage, and determine the sheet metal cracking coefficient of the target sheet metal part at each forming stage based on the sheet metal quality index of each forming stage and the corresponding initial cracking risk. The coefficient fusion module is used to acquire historical cracking data of the historical sheet metal forming process, perform stage filtering on the sheet metal cracking coefficient of each forming stage based on the historical cracking data, obtain each cracking risk stage, and determine the cracking stress index according to each cracking risk stage. The sheet metal control module is used to generate a sheet metal control strategy based on the cracking stress index.

[0015] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects: The process involves: acquiring material parameters of the target sheet metal part; constructing a digital prediction model for the forming process of the target sheet metal part based on these parameters; predicting the forming process of the target sheet metal part using the digital prediction model to obtain the initial cracking risk at each forming stage; collecting the working condition vector of the forming process of the target sheet metal part in real time; performing quality inspection on the forming process of the target sheet metal part based on the working condition vector to obtain the sheet metal quality index at each forming stage; determining the sheet metal cracking coefficient of the target sheet metal part at each forming stage based on the sheet metal quality index of each forming stage and the corresponding initial cracking risk; acquiring historical cracking data of historical sheet metal forming processes; performing stage filtering on the sheet metal cracking coefficient of each forming stage based on the historical cracking data to obtain each cracking risk stage; determining the cracking stress index based on each cracking risk stage; and generating a sheet metal control strategy based on the cracking stress index.

[0016] Therefore, this application demonstrates that, firstly, by constructing a digital prediction model using material parameters, it can identify the potential initial cracking risk at each forming stage, achieving early warning of defects and laying a precise risk baseline for subsequent real-time monitoring and control. Secondly, by calculating the sheet metal quality index at each stage through real-time acquisition of working condition vectors, and then combining it with the initial cracking risk predicted by the digital model, the sheet metal cracking coefficient for each forming stage is dynamically generated. This avoids the theoretical bias that may exist in a single model and compensates for the lag of simple detection, achieving dynamic and accurate quantification of cracking risk in the forming process, providing a basis for subsequent risk stage identification and process control. This provides a real-time, reliable data foundation. Furthermore, by introducing historical cracking data, the cracking coefficients of sheet metal at each stage calculated in real time are verified and screened, effectively identifying cracking risk stages strongly correlated with defects. Based on the cracking stress index determined for each cracking risk stage, the overall risk level is comprehensively reflected, making risk assessment more accurate and reliable, and providing a decision-making basis for finally formulating precise process control strategies. Finally, by matching the obtained cracking stress index with the preset process parameter control logic, corresponding sheet metal control strategies can be intelligently generated, thereby effectively improving the adaptability and intelligence level of the production line.

[0017] In summary, the technical solution adopted in this application can integrate digital prediction models and historical data to achieve adaptive quantitative assessment and proactive control of the cracking risk of sheet metal parts, thereby improving production accuracy and stability. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only for this embodiment of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is an exemplary flowchart of the real-time control method for sheet metal forming based on cloud-based parameter adaptive control provided in this application; Figure 2 This is a flowchart illustrating the process for determining the sheet metal cracking coefficient of a target sheet metal part at each forming stage, based on the information provided in this application. Figure 3 This is a flowchart illustrating the process for determining the cracking stress index provided in this application; Figure 4 This is a module structure diagram of the real-time control system for sheet metal forming based on cloud-based parameter adaptive control provided in this application. Detailed Implementation

[0020] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0021] This application provides a real-time control system and method for sheet metal forming based on cloud-based parameter adaptive control. The core of this system involves: acquiring the material parameters of a target sheet metal part; constructing a digital prediction model of the forming process based on these parameters; predicting the forming process of the target sheet metal part using the digital prediction model to obtain the initial cracking risk at each forming stage; real-time acquisition of the working condition vector of the forming process; quality inspection of the forming process based on the working condition vector to obtain the sheet metal quality index at each forming stage; determining the sheet metal cracking coefficient at each forming stage based on the sheet metal quality index and the corresponding initial cracking risk; acquiring historical cracking data of the historical sheet metal forming process; performing stage filtering on the sheet metal cracking coefficient at each forming stage based on the historical cracking data to obtain each cracking risk stage; determining the cracking stress index based on each cracking risk stage; and generating a sheet metal control strategy using the cracking stress index.

[0022] Example 1: To better understand the above technical solution, the following will provide a detailed description of the technical solution in conjunction with the accompanying drawings and specific implementation methods. (Refer to...) Figure 1 As shown in the figure, this is an exemplary flowchart of a real-time control method for sheet metal forming based on cloud-based parameter adaptive control according to this embodiment of the present application. The control method includes the following steps: In step S1, the material parameters of the target sheet metal part are obtained, a digital prediction model of the forming process of the target sheet metal part is constructed based on the material parameters, and the forming process of the target sheet metal part is predicted according to the digital prediction model, thereby obtaining the initial cracking risk of each forming stage in the forming process of the target sheet metal part.

[0023] In this embodiment, the material parameters of the target sheet metal part are obtained by acquiring the physical and mechanical property parameters of the target sheet metal part from the material database of the target sheet metal part, and then using the physical and mechanical property parameters of the target sheet metal part as material parameters. Specifically, the physical and mechanical property parameters of the target sheet metal part, such as thickness, density, elastic modulus, yield strength, tensile strength, strain hardening index and thickness anisotropy index, can be extracted from the material database and used as material parameters of the target sheet metal part.

[0024] In this embodiment, the construction of a digital prediction model for the forming process of the target sheet metal part based on the material parameters can be achieved through the following steps: A 3D model is built based on the material parameters of the target sheet metal part; A mesh is generated from the 3D model to obtain a sheet metal mesh model; The sheet metal mesh model is imported into the simulation platform to obtain a digital prediction model of the forming process of the target sheet metal part.

[0025] In practical implementation, a 3D model is established based on the material parameters of the target sheet metal part. That is, the material parameters of the target sheet metal part can be used to create a 3D model using CAD software. Then, a mesh can be generated from the 3D model to obtain a sheet metal mesh model. Specifically, shell elements can be selected, and the mesh can be set according to the physical parameters of the target sheet metal part to obtain a sheet metal mesh model. Finally, the sheet metal mesh model can be imported into a simulation platform to obtain a digital prediction model of the forming process of the target sheet metal part. That is, the sheet metal mesh model can be imported into a CAE simulation platform, the mechanical property parameters of the target sheet metal part can be input into the material definition, and the complete process type can be set to obtain a digital prediction model of the forming process of the target sheet metal part.

[0026] In practical implementation, the forming process of the target sheet metal part is predicted based on the digital prediction model, thereby obtaining the initial cracking risk of each forming stage in the forming process of the target sheet metal part. That is, each forming stage of the target sheet metal part can be preset in the digital prediction model, such as: the pressure ring closes, the sheet metal is initially bent; the material begins to flow into the die fillet; the side wall is completely attached to the die; the bottom of the part is completely formed. Then, the timestamps of each forming stage are recorded, and the distribution cloud map data of the principal strain field and the secondary strain field and the thickness distribution field data are extracted for each forming stage. For each forming stage, the top ten grid cells with the largest principal strain in the forming stage are selected as candidate risk points. For each candidate risk point, the principal strain of the candidate risk point is divided by the ultimate principal strain corresponding to the candidate risk point, and the result is used as the candidate risk value. Thus, all candidate risk values ​​of each grid cell in the forming stage are obtained. The maximum value among all candidate risk values ​​is used as the initial cracking risk of the forming stage, thereby obtaining the initial cracking risk of each forming stage in the forming process of the target sheet metal part.

[0027] In step S2, the working condition vector of the target sheet metal part forming process is collected in real time. The quality of the target sheet metal part forming process is inspected based on the working condition vector to obtain the sheet metal quality index of each forming stage. The sheet metal cracking coefficient of the target sheet metal part in each forming stage is determined based on the sheet metal quality index of each forming stage and the corresponding initial cracking risk.

[0028] In practical implementation, the working condition vector of the target sheet metal part forming process is collected in real time. The total forming force and total forming stroke of the target sheet metal part can be detected in real time by sensors pre-installed on the forming machine tool of the target sheet metal part, so as to use the total forming force and total forming stroke of the target sheet metal part as the working condition vector of the forming process of the target sheet metal part.

[0029] In this embodiment, the quality inspection of the forming process of the target sheet metal part based on the working condition vector, and the obtaining of the sheet metal quality index at each forming stage, can be achieved by the following steps: Initialize the reference force-stroke curve; The baseline deviation is determined based on the aforementioned working condition vector and the reference force-stroke curve. Determine the offset of feature points at each forming stage; The sheet metal quality index for each forming stage is determined based on the baseline deviation and the corresponding feature deviation point.

[0030] In practical implementation, firstly, a reference force-stroke curve can be initialized. This is achieved by extracting qualified working condition vectors from multiple qualified sheet metal parts based on historical production data, thereby constructing individual force-stroke curves. Each force-stroke curve is then aligned on the stroke axis, and each force-stroke curve is resampled at the same stroke interval to obtain a data point sequence. For each data point, the mean and standard deviation of the forming force of all qualified sheet metal parts at that point are calculated, thus obtaining the reference force-stroke curve. The reference force-stroke curve is a curve composed of the mean forming force of all qualified sheet metal parts. Then, the baseline deviation can be determined based on the working condition vectors and the reference force-stroke curve. That is, a real-time force-stroke curve can be constructed based on the working condition vectors, and the real-time force-stroke curve is aligned with the reference force-stroke curve. The baseline deviation can then be obtained using the following formula:

[0031] in, Indicates baseline deviation; Indicates the total number of data points; This represents the forming force at the j-th data point in the real-time force-stroke curve; This represents the forming force at the j-th point in the reference force stroke curve. Furthermore, the feature point offset for each forming stage can be determined. That is, for each forming stage of the target sheet metal part, the peak force stroke and peak force value when the forming force reaches its maximum value are extracted from the reference force stroke curve and real-time force stroke curve corresponding to the forming stage, respectively. The peak force value of the real-time force stroke curve is subtracted from the peak force value of the reference force stroke curve, and the absolute value of the result is taken. The result is then divided by three times the standard deviation of the reference force stroke curve, and the result is used as the peak force offset. The peak force stroke of the real-time force stroke curve is subtracted from the peak force stroke of the reference force stroke curve, and the absolute value of the result is taken. The result is then divided by three times the stroke interval, and the result is used as the peak force stroke offset. The peak force offset is multiplied by the peak force stroke offset, and the result is used as the feature point offset for that forming stage, thus obtaining the feature point offset for each forming stage.

[0032] In addition, in practical implementation, the sheet metal quality index of each forming stage can be determined based on the baseline deviation and the corresponding feature deviation point. That is, the mean of the reference force stroke curve can be added to 3 times the standard deviation, and then the baseline deviation can be divided by the result to obtain the standardized baseline deviation. For each forming stage, the feature point deviation corresponding to the forming stage is added to the standardized baseline deviation, the result is divided by 2, and then the result is subtracted by 1. The result is used as the sheet metal quality index of that forming stage, thus obtaining the sheet metal quality index of each forming stage. The sheet metal quality index is used to evaluate the quality status of sheet metal parts in the forming stage in real time.

[0033] Preferably, in this embodiment, the sheet metal cracking coefficient of the target sheet metal part at each forming stage is determined based on the sheet metal quality index and the corresponding initial cracking risk at each forming stage, with reference to... Figure 2 As shown in the figure, this is a flowchart illustrating the process of determining the sheet metal cracking coefficient of a target sheet metal part at each forming stage in some embodiments of this application. In this embodiment, the determination of the sheet metal cracking coefficient of the target sheet metal part at each forming stage can be achieved by the following steps: In step S21, for the sheet metal quality index of each forming stage, the risk direction of the sheet metal quality index is unified to obtain the sheet metal quality risk. In step S22, risk fusion is performed based on the sheet metal quality risk and the corresponding initial cracking risk to obtain the sheet metal cracking coefficient of the corresponding forming stage, and then the sheet metal cracking coefficient of the target sheet metal part at each forming stage is obtained.

[0034] In practice, firstly, for the sheet metal quality index of each forming stage, the risk direction of the sheet metal quality index is unified to obtain the sheet metal quality risk. That is, for the sheet metal quality index of each forming stage, the risk direction of the sheet metal quality index of the forming stage is unified, and the sheet metal quality risk of that forming stage can be obtained by the following formula:

[0035] in, This indicates the sheet metal quality risk at this forming stage; This represents the sheet metal quality index at this forming stage. Then, risk fusion can be performed based on the sheet metal quality risk and the corresponding initial cracking risk to obtain the sheet metal cracking coefficient for the corresponding forming stage. This leads to the sheet metal cracking coefficient of the target sheet metal part at each forming stage. In other words, the sheet metal quality risk can be multiplied by the corresponding initial cracking risk, and the result can be used as the sheet metal cracking coefficient for that forming stage. Thus, the sheet metal cracking coefficient for each forming stage can be obtained. It should be noted that the sheet metal cracking coefficient is a coefficient used to quantify the risk of cracking of sheet metal parts during the forming stage.

[0036] It should be noted that by collecting working condition vectors in real time to calculate the sheet metal quality index at each stage, and then combining it with the initial cracking risk predicted by the digital model, the sheet metal cracking coefficient for each forming stage is dynamically generated. This avoids the theoretical deviation that may exist in a single model, and also makes up for the lag of simple detection. It realizes the dynamic and accurate quantification of cracking risk in the forming process, and provides a real-time and reliable data foundation for subsequent risk stage identification and process control.

[0037] In step S3, historical cracking data of the historical sheet metal forming process is obtained. Based on the historical cracking data, the sheet metal cracking coefficient of each forming stage is screened to obtain each cracking risk stage. The cracking stress index is determined according to each cracking risk stage.

[0038] In practice, historical cracking data of the historical sheet metal forming process can be obtained by retrieving relevant production data from the past 6 months from the historical sheet metal forming database. This includes the sheet metal cracking coefficients of all cracked sheet metal parts at each forming stage and the sheet metal cracking coefficients of all qualified sheet metal parts at each forming stage. The number of qualified sheet metal parts extracted should be 1.5 times the number of cracked sheet metal parts. Thus, the sheet metal cracking coefficients of all cracked sheet metal parts at each forming stage and the sheet metal cracking coefficients of all qualified sheet metal parts at each forming stage are used as historical cracking data of the historical sheet metal forming process.

[0039] In practical implementation, the sheet metal cracking coefficients of each forming stage can be screened based on historical cracking data to obtain each cracking risk stage. That is, for each forming stage in the historical cracking data, the sheet metal cracking coefficients of the forming stage in the historical cracking data are divided into a cracked group and a qualified group. The mean and standard deviation of the cracked group and the qualified group are calculated separately. The difference between the means of the two groups is used as the mean difference. A random test is used to mix the two groups of data, redistribute them, maintain the original sample size, and calculate the mean difference between the two groups again to obtain the random mean difference. The random test process is repeated 1000-10000 times, and all the times when the random mean difference is greater than the mean difference are recorded. The number of times the random mean difference is greater than the mean difference is divided by the total number of random test processes, and the result is used as the data difference for that forming stage. The combined difference can be calculated based on the standard deviation of the two groups using the following formula:

[0040] in, Indicates the difference between the merged and merged parts; This represents the total number of data points in the crack group; This represents the standard deviation of the crack group; This represents the total number of data points in the qualified groups; The standard deviation of the qualified group is represented by the difference between the means of the two groups divided by the combined difference. The result is taken as the effect size of the forming stage. It should be noted that the effect size is used to quantify the degree of cracking difference in the forming stage. The difference between the two groups is taken as the logarithm to the base 10, the result is then negative, and the result is multiplied by the degree of cracking difference in the forming stage. The result is taken as the stage score of the forming stage. Based on the above steps, the stage scores of each forming stage can be obtained. All stage scores are sorted from largest to smallest, and the forming stages corresponding to the top three stage scores are extracted. Each extracted forming stage is taken as a risk stage. Thus, each risk stage in the forming process of the current target sheet metal part is taken as a cracking risk stage.

[0041] Preferably, in this embodiment, the cracking stress index is determined according to each cracking risk stage, with reference to... Figure 3 As shown in the figure, this is a schematic flowchart of determining the crack stress index in some embodiments of this application. In this embodiment, the crack stress index can be determined by the following steps: In step S31, the weights of each risk stage are determined based on the historical cracking data; In step S32, the basic stress component is determined based on the sheet metal cracking coefficient and the corresponding risk stage weight for each cracking risk stage. In step S33, risk gradient is extracted by using the sheet metal cracking coefficient corresponding to each cracking risk stage to obtain the trend stress component; In step S34, component fusion is performed based on the basic stress component and the trend stress component to obtain the cracking stress index.

[0042] In practical implementation, firstly, the weights of each risk stage can be determined based on historical cracking data. That is, the stage scores of each cracking risk stage are summed, and for each cracking risk stage, the stage score is divided by the summation result. The result is used as the risk stage weight for that cracking risk stage, thus obtaining the weights of each risk stage. Then, the basic stress component can be determined based on the sheet metal cracking coefficient and the corresponding risk stage weight for each cracking risk stage. That is, the sheet metal cracking coefficient for each cracking risk stage is multiplied by the corresponding risk stage weight, and the multiplication results are summed. The result is used as the basic stress component. It should be noted that the basic stress component is used to quantify the cracking risk level faced by the sheet metal part. Furthermore, risk gradients can be extracted using the sheet metal cracking coefficients corresponding to each cracking risk stage to obtain the trend stress component. The quantity, namely, for each cracking risk stage, subtracts the sheet metal cracking coefficient of the next adjacent cracking risk stage from the sheet metal cracking coefficient of the cracking risk stage, and uses the result as the stress negative trend, thus obtaining each stress negative trend. The negative values ​​of all stress negative trends are extracted, and the results are summed. The summation result is divided by the total number of all extracted data points, and the result is then negative, and the result is used as the trend stress component. The trend stress component is used to quantify the changing trend of risk. Finally, the basic stress component and the trend stress component can be fused to obtain the cracking stress index. That is, the basic stress component and the trend stress component can be summed, and the result can be divided by 2, and the result is used as the cracking stress index. It should be noted that the cracking stress index is used to quantify the severity of the overall cracking threat faced by the sheet metal part during the forming process.

[0043] It should be noted that by introducing historical cracking data, the cracking coefficients of sheet metal at each stage calculated in real time are verified and screened, effectively identifying the cracking risk stages that are strongly correlated with defects. Based on the cracking stress index determined at each cracking risk stage, the overall risk level is comprehensively reflected, making the risk assessment more accurate and reliable, and providing a decision-making basis for the final formulation of precise process control strategies.

[0044] In step S4, a sheet metal control strategy is generated using the cracking stress index.

[0045] In this embodiment, the sheet metal control strategy generated by the cracking stress index can be implemented through the following steps: Initialize each stress threshold interval; The sheet metal control strategy is determined by the cracking stress index and various stress threshold ranges.

[0046] In practice, firstly, each stress threshold range is initialized, that is, each stress threshold range can be preset based on historical data statistics; then, the sheet metal control strategy can be determined by the cracking stress index and each stress threshold range, that is, the cracking stress index can be compared with each stress threshold range to obtain the sheet metal control strategy. For example: when the cracking stress index is less than 0.45, the sheet metal control strategy is stable production; when the cracking stress index is greater than 0.45 and less than 0.75, the sheet metal control strategy is early warning, and process parameters are adjusted, with the blank holder force ±5%-8%; when the cracking stress index is greater than 0.75, the sheet metal control strategy is to immediately stop the machine to prevent cracking, and remove the current part for destructive testing; thus, the sheet metal control strategy is obtained.

[0047] Therefore, this application demonstrates that, firstly, by constructing a digital prediction model using material parameters, it can identify the potential initial cracking risk at each forming stage, achieving early warning of defects and providing a key theoretical basis for process design. This shortens the trial-and-error cycle traditionally reliant on experience and lays a precise risk baseline for subsequent real-time monitoring and control. Secondly, by collecting working condition vectors in real time to calculate the sheet metal quality index at each stage, and then combining it with the initial cracking risk predicted by the digital model, the sheet metal cracking coefficient for each forming stage is dynamically generated. This effectively establishes a correlation between theoretical prediction and real-time production status, avoiding potential theoretical biases from a single model and compensating for the lag in simple detection. It achieves dynamic and precise quantification of cracking risk in the forming process, providing a real-time and reliable data foundation for subsequent risk stage identification and process control. Furthermore, by introducing historical cracking data, the actual... The calculated sheet metal cracking coefficients at each stage are verified and screened to effectively identify cracking risk stages strongly correlated with defects. Based on the cracking stress index determined for each cracking risk stage, the overall risk level under the coupling of multiple stages and factors is comprehensively reflected. This achieves a focus and improvement from scattered stage indicators to global risk assessment, making risk judgment more accurate and reliable. It provides a scientific and efficient decision-making basis for the final formulation of precise process control strategies. Finally, by matching the obtained cracking stress index with the preset process parameter control logic, the corresponding sheet metal control strategy can be intelligently generated. This realizes a closed-loop transformation from risk quantification assessment to production execution intervention, freeing process control from excessive reliance on human experience and making it more timely, accurate, and automated. This effectively inhibits cracking, stabilizes product quality, and improves the adaptability and intelligence level of the production line.

[0048] In summary, the technical solution adopted in this application can integrate digital prediction models and historical data to achieve adaptive quantitative assessment and proactive control of the cracking risk of sheet metal parts, thereby improving production accuracy and stability.

[0049] Example 2: This application provides a real-time control system for sheet metal forming based on cloud-based parameter adaptive control, referencing... Figure 4 As shown in the figure, this is a module structure diagram of a real-time control system for sheet metal forming based on cloud-based parameter adaptive control according to this embodiment of the present application. The control system includes: The parameter acquisition module 100 is used to acquire the material parameters of the target sheet metal part, construct a digital prediction model of the forming process of the target sheet metal part based on the material parameters, predict the forming process of the target sheet metal part according to the digital prediction model, and then obtain the initial cracking risk of each forming stage in the forming process of the target sheet metal part. The crack detection module 200 is used to collect the working condition vector of the forming process of the target sheet metal part in real time, perform quality inspection on the forming process of the target sheet metal part based on the working condition vector, obtain the sheet metal quality index of each forming stage, and determine the sheet metal cracking coefficient of the target sheet metal part in each forming stage based on the sheet metal quality index of each forming stage and the corresponding initial cracking risk. The coefficient fusion module 300 is used to acquire historical cracking data of the historical sheet metal forming process, perform stage screening on the sheet metal cracking coefficient of each forming stage based on the historical cracking data, obtain each cracking risk stage, and determine the cracking stress index according to each cracking risk stage. The sheet metal control module 400 is used to generate a sheet metal control strategy based on the cracking stress index.

[0050] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0051] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, including read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-Erasable Programmable Read-Only Memory (EEPROM), compactdisc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0052] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

Claims

1. A real-time control method for sheet metal forming based on cloud-based parameter adaptive control, characterized in that, The control method includes the following steps: Obtain the material parameters of the target sheet metal part, construct a digital prediction model of the forming process of the target sheet metal part based on the material parameters, predict the forming process of the target sheet metal part according to the digital prediction model, and then obtain the initial cracking risk of each forming stage in the forming process of the target sheet metal part. The working condition vector of the target sheet metal part forming process is collected in real time. The quality inspection of the target sheet metal part forming process is carried out based on the working condition vector to obtain the sheet metal quality index of each forming stage. The sheet metal cracking coefficient of the target sheet metal part in each forming stage is determined based on the sheet metal quality index of each forming stage and the corresponding initial cracking risk. Historical cracking data of the sheet metal forming process is obtained. Based on the historical cracking data, the sheet metal cracking coefficient of each forming stage is screened to obtain each cracking risk stage. The cracking stress index is determined according to each cracking risk stage. The cracking stress index is used to generate a sheet metal control strategy.

2. The real-time control method for sheet metal forming based on cloud-based parameter adaptive control as described in claim 1, characterized in that, Obtaining the material parameters of the target sheet metal part involves retrieving the physical and mechanical properties of the target sheet metal part from its material database, and then using these physical and mechanical properties as the material parameters.

3. The real-time control method for sheet metal forming based on cloud-based parameter adaptive control as described in claim 1, characterized in that, Constructing a digital prediction model for the forming process of the target sheet metal part based on the aforementioned material parameters specifically includes: A 3D model is built based on the material parameters of the target sheet metal part; A mesh is generated from the 3D model to obtain a sheet metal mesh model; The sheet metal mesh model is imported into the simulation platform to obtain a digital prediction model of the forming process of the target sheet metal part.

4. The real-time control method for sheet metal forming based on cloud-based parameter adaptive control as described in claim 1, characterized in that, Based on the aforementioned working condition vector, the quality of the target sheet metal part forming process is inspected, and the sheet metal quality index for each forming stage is obtained, specifically including: Initialize the reference force-stroke curve; The baseline deviation is determined based on the aforementioned working condition vector and the reference force-stroke curve. Determine the offset of feature points at each forming stage; The sheet metal quality index for each forming stage is determined based on the baseline deviation and the corresponding feature deviation point.

5. The real-time control method for sheet metal forming based on cloud-based parameter adaptive control as described in claim 1, characterized in that, The sheet metal cracking coefficient of the target sheet metal part at each forming stage is determined based on the sheet metal quality index and the corresponding initial cracking risk at each forming stage. Specifically, this includes: For the sheet metal quality index at each forming stage, the risk direction of the sheet metal quality index is unified to obtain the sheet metal quality risk. Based on the sheet metal quality risk and the corresponding initial cracking risk, risk fusion is performed to obtain the sheet metal cracking coefficient for the corresponding forming stage, and then the sheet metal cracking coefficient of the target sheet metal part at each forming stage is obtained.

6. The real-time control method for sheet metal forming based on cloud-based parameter adaptive control as described in claim 1, characterized in that, The sheet metal cracking coefficient is a coefficient used to quantify the risk of cracking in sheet metal parts during the forming stage.

7. The real-time control method for sheet metal forming based on cloud-based parameter adaptive control as described in claim 1, characterized in that, The cracking stress index is determined based on each stage of cracking risk, specifically including: The weights of each risk stage are determined based on the historical cracking data. The basic stress component is determined based on the sheet metal cracking coefficient and the corresponding risk stage weight for each cracking risk stage. Risk gradients are extracted by using the sheet metal cracking coefficients corresponding to each cracking risk stage to obtain the trend stress component. The cracking stress index is obtained by fusing the basic stress component and the trend stress component.

8. The real-time control method for sheet metal forming based on cloud-based parameter adaptive control as described in claim 1, characterized in that, The cracking stress index is used to quantify the severity of cracking threats faced by sheet metal parts during the forming process.

9. The real-time control method for sheet metal forming based on cloud-based parameter adaptive control as described in claim 1, characterized in that, The sheet metal control strategy generated by the cracking stress index specifically includes: Initialize each stress threshold interval; The sheet metal control strategy is determined by the cracking stress index and various stress threshold ranges.

10. A real-time control system for sheet metal forming based on cloud-based adaptive parameter control, used to execute the real-time control method for sheet metal forming based on cloud-based adaptive parameter control as described in any one of claims 1 to 9, characterized in that, The control system includes: The parameter acquisition module is used to acquire the material parameters of the target sheet metal part, construct a digital prediction model of the forming process of the target sheet metal part based on the material parameters, predict the forming process of the target sheet metal part according to the digital prediction model, and thus obtain the initial cracking risk of each forming stage in the forming process of the target sheet metal part. The crack detection module is used to collect the working condition vector of the forming process of the target sheet metal part in real time, perform quality inspection on the forming process of the target sheet metal part based on the working condition vector, obtain the sheet metal quality index of each forming stage, and determine the sheet metal cracking coefficient of the target sheet metal part at each forming stage based on the sheet metal quality index of each forming stage and the corresponding initial cracking risk. The coefficient fusion module is used to acquire historical cracking data of the historical sheet metal forming process, perform stage filtering on the sheet metal cracking coefficient of each forming stage based on the historical cracking data, obtain each cracking risk stage, and determine the cracking stress index according to each cracking risk stage. The sheet metal control module is used to generate a sheet metal control strategy based on the cracking stress index.

Images