A method for online quality monitoring during sheet metal stamping process

Abstract

The present application provides a method for online quality monitoring during sheet metal stamping, which relates to the technical field of intelligent manufacturing. The method comprises: collecting the real-time pressing speed and real-time pressing amount of the stamping equipment for the target component; inputting the real-time pressing speed and real-time pressing amount into a quality prediction model to obtain the real-time strain rate and real-time stress of each part of the target component; judging whether the stamping equipment causes cracking or wrinkling of the target component based on the real-time strain rate, and judging whether the component strength of the target component meets the preset strength standard based on the real-time stress; if it is determined that the stamping equipment causes cracking or wrinkling of the target component, or the component strength of the target component does not meet the preset strength standard, adjusting the parameters of the stamping equipment. The present application can achieve real-time monitoring of the quality of components during the stamping process.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent manufacturing, and specifically to a method for online quality monitoring during sheet metal stamping forming. Background Art

[0002] Sheet metal stamping is a metalworking technique widely used in the manufacturing industry. It primarily involves shaping sheet metal into specific geometries using dies and presses. This method is commonly used in the automotive, aerospace, appliance, and construction industries, enabling the rapid and cost-effective production of large quantities of complex metal parts. During the stamping process, the sheet metal undergoes plastic deformation under pressure, and various stamping operations such as drawing, bending, shearing, and punching are performed to form the desired part shape. This process places high demands on the material's properties, requiring precise control of process parameters to ensure product quality and structural integrity.

[0003] With the rapid development of the aerospace and automotive industries, lightweighting has become one of the development trends in the transportation sector, and the proportion of lightweight materials such as high-strength steel, aluminum alloys, and titanium alloys is increasing. The stamping process of sheet metal is an important component processing process. During the stamping process, the sheet metal is prone to defects such as cracking, wrinkling, and insufficient strength, resulting in an increased scrap rate. The quality of the component during the stamping process is often directly related to the material flow. Therefore, it is important to monitor the material flow in real time during the stamping process and achieve feedback control. However, stamping dies are often closed, so visual monitoring is not possible. The die often operates under high temperature and high stress conditions, making it difficult to arrange sensors inside. Therefore, real-time detection of material flow in the stamping process faces huge challenges. Summary of the Invention

[0004] The present application provides a method for online monitoring of the quality of a sheet metal stamping process, which can realize real-time monitoring of the quality of components during the stamping process.

[0005] In a first aspect of the present application, a method for online quality monitoring during a sheet metal stamping process is provided, the method comprising:

[0006] Collect the real-time pressing speed and real-time pressing amount of the stamping equipment for the target component;

[0007] Inputting the real-time pressing speed and the real-time pressing amount into a quality prediction model to obtain the real-time strain rate and real-time stress of each part of the target component;

[0008] Determining whether the stamping equipment causes cracking or wrinkling of the target component based on the real-time strain rate, and determining whether the component strength of the target component meets a preset strength standard based on the real-time stress;

[0009] If it is determined that the stamping equipment causes the target component to crack or wrinkle, or the component strength of the target component does not meet the preset strength standard, the parameters of the stamping equipment are adjusted.

[0010] Based on the above technical solution, preferably, before inputting the real-time pressing speed and the real-time pressing amount into the quality prediction model to obtain the real-time strain rate and real-time stress of each part of the target component, the method further includes:

[0011] Component BP neural network model, in which the pressing speed and pressing amount are used as input nodes of the input layer, and the strain rate and stress are used as output nodes of the output layer;

[0012] Obtain a preset data set, and divide the data set into a training set, a validation set, and a test set;

[0013] Using the training set to train the BP neural network model, using the validation set to adjust the parameters of the BP neural network model, and using the test set to evaluate the performance of the BP neural network model to obtain the quality prediction model;

[0014] The quality prediction model is integrated into the monitoring system of the production line, and the collected pressing speed and pressing amount are input in real time, and the predicted strain rate and stress are output.

[0015] On the basis of the above technical solution, preferably, before the component BP neural network is constructed, the method further comprises:

[0016] Establish a three-dimensional model of sheet metal stamping;

[0017] Setting boundary conditions for the sheet metal stamping, wherein the boundary conditions include sheet metal material properties, pressing speed range, pressing amount range, and friction conditions;

[0018] Running a simulation on the three-dimensional model after setting the boundary conditions, recording the stress rate and stress distribution of the stamping component under different process conditions, as well as the pressing amount and pressing speed under different process conditions;

[0019] The stress rate, stress distribution, pressing amount and pressing speed are output to obtain the data set.

[0020] On the basis of the above technical solution, preferably, the real-time pressing speed and the real-time pressing amount are input into the quality prediction model to obtain the real-time strain rate and real-time stress of each part of the target component, which are specifically calculated by the following formula:

[0021]

[0022] σ(ε ′ ,ε,T)=σ y (ε ′ ,T)+(K(T)·ε n )·(1+C·log(ε ′ ))

[0023] Wherein, ε is the real-time strain rate, H is the thickness change rate of the target component per unit time, h is the current thickness of the target component, v is the real-time pressing speed, σ(ε',ε,T) is the real-time stress, σ y (∈,T) is the yield stress, K(T) is the hardening coefficient, ∈ is the accumulated strain, n is the hardening exponent, C is the rate sensitivity coefficient, and T is the material temperature.

[0024] On the basis of the above technical solution, preferably, judging whether the stamping forming equipment causes the target component to crack or wrinkle based on the real-time strain rate specifically includes:

[0025] determining a critical strain rate of the target component;

[0026] It is determined whether the real-time strain rate is greater than or equal to the critical strain rate. If it is determined that the real-time strain rate is greater than or equal to the critical strain rate, it is determined that the stamping equipment will cause the target component to crack or wrinkle.

[0027] On the basis of the above technical solution, judging whether the component strength of the target component reaches a preset strength standard according to the real-time stress specifically includes:

[0028] Determining a stress threshold corresponding to a preset strength standard of the target component based on the yield strength and tensile strength of the target component;

[0029] It is determined whether the real-time stress is greater than or equal to the stress threshold; if it is determined that the real-time stress is greater than or equal to the stress threshold, it is determined that the component strength of the target component reaches the preset strength standard.

[0030] Based on the above technical solution, preferably, if it is determined that the stamping equipment causes the target component to crack or wrinkle, or the component strength of the target component does not meet the preset strength standard, the parameters of the stamping equipment are adjusted, specifically including:

[0031] Determining a component yield rate of the target component according to a stamping simulation result for the target component;

[0032] Determining whether the component yield rate is greater than or equal to a preset yield rate;

[0033] If it is determined that the component yield is less than the preset yield, the pressure distribution of the stamping equipment is adjusted according to the material properties and thickness of the target component to make the pressure distribution of the stamping equipment uniform.

[0034] In a second aspect of the present application, a device for online monitoring of quality during a sheet metal stamping process is provided, the device comprising an acquisition module, a processing module, and a judgment module, wherein:

[0035] The acquisition module is used to collect the real-time pressing speed and real-time pressing amount of the stamping forming equipment for the target component;

[0036] The processing module is used to input the real-time pressing speed and the real-time pressing amount into a quality prediction model to obtain the real-time strain rate and real-time stress of each part of the target component;

[0037] The judgment module is configured to judge whether the stamping equipment causes cracking or wrinkling of the target component based on the real-time strain rate, and to judge whether the component strength of the target component meets a preset strength standard based on the real-time stress;

[0038] The processing module is configured to adjust parameters of the stamping equipment if it is determined that the stamping equipment causes cracking or wrinkling of the target component, or that the component strength of the target component does not meet a preset strength standard.

[0039] On the basis of the above technical solution, preferably, the processing module is used to construct a BP neural network model, wherein the pressing speed and pressing amount are used as input nodes of the input layer, and the strain rate and stress are used as output nodes of the output layer;

[0040] The acquisition module is used to acquire a preset data set and divide the data set into a training set, a validation set and a test set;

[0041] The processing module is configured to train the BP neural network model using the training set, adjust parameters of the BP neural network model using the validation set, and evaluate the performance of the BP neural network model using the test set to obtain the quality prediction model;

[0042] The processing module is used to integrate the quality prediction model into the monitoring system of the production line, input the collected pressing speed and pressing amount in real time, and output the predicted strain rate and stress.

[0043] On the basis of the above technical solution, preferably, the processing module is used to establish a three-dimensional model of the sheet metal stamping;

[0044] The processing module is used to set the boundary conditions of the plate stamping, wherein the boundary conditions include the plate material properties, the pressing speed range, the pressing amount range and the friction conditions;

[0045] The processing module is used to run a simulation on the three-dimensional model after setting the boundary conditions, and record the stress rate and stress distribution of the stamping component under different process conditions, as well as the pressing amount and pressing speed under different process conditions;

[0046] The processing module is used to output the stress rate, stress distribution, pressing amount and pressing speed to obtain the data set.

[0047] Based on the above technical solution, preferably, the processing module is used to input the real-time pressing speed and the real-time pressing amount into a quality prediction model to obtain the real-time strain rate and real-time stress of each part of the target component, specifically calculated by the following formula:

[0048]

[0049] σ(ε ′ ,ε,T)=σ y (ε ′ ,T)+(K(T)·ε n )·(1+C·log(ε ′ ))

[0050] Wherein, ε is the real-time strain rate, H is the thickness change rate of the target component per unit time, h is the current thickness of the target component, v is the real-time pressing speed, σ(ε',ε,T) is the real-time stress, σ y (∈,T) is the yield stress, K(T) is the hardening coefficient, ∈ is the accumulated strain, n is the hardening exponent, C is the rate sensitivity coefficient, and T is the material temperature.

[0051] On the basis of the above technical solution, preferably, the processing module is used to determine the critical strain rate of the target component;

[0052] The judgment module is used to judge whether the real-time strain rate is greater than or equal to the critical strain rate. If it is determined that the real-time strain rate is greater than or equal to the critical strain rate, it is determined that the stamping forming equipment will cause the target component to crack or wrinkle.

[0053] On the basis of the above technical solution, preferably, the processing module is used to determine a stress threshold corresponding to a preset strength standard of the target component based on the yield strength and tensile strength of the target component;

[0054] The judgment module is used to judge whether the real-time stress is greater than or equal to the stress threshold. If it is determined that the real-time stress is greater than or equal to the stress threshold, it is determined that the component strength of the target component reaches the preset strength standard.

[0055] On the basis of the above technical solution, preferably, the processing module is used to determine the component yield rate of the target component according to the stamping simulation result of the target component;

[0056] The judging module is configured to judge whether the component yield rate is greater than or equal to a preset yield rate;

[0057] The processing module is used to adjust the pressure distribution of the stamping equipment according to the material properties and thickness of the target component to make the pressure distribution of the stamping equipment uniform if it is determined that the component yield is less than the preset yield.

[0058] In the third aspect of the present application, an electronic device is provided, including a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes any one of the methods described above.

[0059] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores instructions, and when the instructions are executed, any one of the methods described above is executed.

[0060] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0061] 1. This application can achieve real-time monitoring of component quality during the stamping process by integrating real-time data acquisition, dynamic model analysis and instant quality assessment methods. First, by installing sensors to collect real-time information about the pressing speed and pressing amount of the target component, these data directly reflect the dynamic conditions of the stamping process. By inputting these data into a pre-trained quality prediction model, the strain rate and stress of each part of the target component can be calculated in real time, which provides a scientific basis for evaluating whether the component will crack, wrinkle or fail to reach the required strength during the production process. By analyzing these real-time calculation results, the system can promptly identify quality problems and automatically adjust the parameters of the stamping equipment before problems occur, such as changing the pressing speed or adjusting the pressure distribution, thereby preventing defects and ensuring component quality.

[0062] 2. By building and applying a quality prediction model based on a BP neural network, it is possible to effectively monitor and control component quality in real time during the stamping process. By using real-time data on pressing speed and pressing amount as input, the model can predict component strain rate and stress, thereby proactively identifying risks that could lead to cracking, wrinkling, or substandard strength. This significantly reduces trial-and-error costs, optimizes the production process, reduces scrap rates, and improves overall production efficiency.

[0063] 3. Integrating intelligent predictive models into the production line's monitoring system enables automatic adjustments to the manufacturing process before potential problems are discovered, ensuring product quality meets preset standards and enhancing the reliability and stability of the manufacturing process. Furthermore, this helps reduce labor and time costs by reducing reliance on continuous monitoring by professionals and enabling highly automated production control.

[0064] 4. The stress model disclosed in this application combines the material's yield stress, hardening coefficient, and strain rate sensitivity coefficient to accurately reflect the stress response under different process conditions. Furthermore, by using a neural network model to predict and adjust process parameters, machine settings can be automatically adjusted to optimize product quality without intervening in the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 This is a flow chart of a method for online quality monitoring during a sheet metal stamping forming process disclosed in an embodiment of the present application;

[0066] Figure 2 This is a module diagram of a method for online quality monitoring during a sheet metal stamping forming process disclosed in an embodiment of the present application;

[0067] Figure 3 This is a schematic structural diagram of an electronic device disclosed in an embodiment of the present application.

[0068] Explanation of the reference numerals: 201, acquisition module; 202, processing module; 203, judgment module; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0069] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0070] In the description of the embodiments of this application, words such as "for example" or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "for example" or "for instance" in the embodiments of this application should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "for example" or "for instance" is intended to present the relevant concepts in a concrete manner.

[0071] In the description of the embodiments of the present application, the term "multiple" means two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0072] Sheet metal stamping is a key metal processing technology widely used in the automotive, aviation, home appliance and construction industries. It mainly uses dies and presses to shape metal sheets into specific geometric shapes. With the increasing use of lightweight materials such as high-strength steel, aluminum alloys and titanium alloys, the importance of stamping has become increasingly prominent. However, during the stamping process, the sheet metal is prone to defects such as cracking and wrinkling. These problems are usually directly related to material flow. However, due to the closed and high-temperature and high-stress environment of the stamping die, real-time monitoring of material flow through traditional vision or internal sensors is extremely challenging. Therefore, the development of an effective real-time monitoring and feedback control system is crucial to improving component quality and reducing scrap rates.

[0073] This embodiment discloses a method for online monitoring of quality during sheet metal stamping. Figure 1 , including the following steps S110-S140:

[0074] S110, collecting the real-time pressing speed and real-time pressing amount of the stamping forming equipment for the target component.

[0075] The embodiment of the present application discloses an online quality monitoring method for a sheet metal stamping process, which is applied to a server. The server includes, but is not limited to, electronic devices such as mobile phones, tablet computers, wearable devices, and PCs (personal computers), and can also be a background server running the online quality monitoring method for a sheet metal stamping process. The server can be implemented as a standalone server or a server cluster consisting of multiple servers.

[0076] Acquiring real-time data on the speed and amount of pressure applied to a target component by a stamping machine is crucial for ensuring production efficiency and product quality. Measuring these speeds and amounts requires the selection of appropriate sensors. Position sensors measure the position of the die or punch, thereby calculating the amount of pressure applied. Velocity sensors directly measure the speed of the punch. While pressure sensors primarily measure pressure, they can also indirectly infer velocity and displacement from pressure changes.

[0077] Position sensors are typically installed between a moving part (such as a slide or punch) and a fixed part (such as the press bed). Velocity sensors can be installed on the moving part of the punch to monitor its speed in real time. Pressure sensors are installed where the greatest forces may be applied, such as near the die contact point.

[0078] Configure the data acquisition system to receive, store, and process signals from sensors. Then, process and analyze the collected data to support production decisions. This includes data filtering and smoothing, applying digital filtering techniques to eliminate noise and interference and improve data quality. Extract key features from time series data, such as maximum pressing speed, average speed, and total pressing volume.

[0079] S120 , inputting the real-time pressing speed and the real-time pressing amount into the quality prediction model to obtain the real-time strain rate and real-time stress of each part of the target component.

[0080] In one possible embodiment, before inputting the real-time pressing speed and the real-time pressing amount into the quality prediction model to obtain the real-time strain rate and real-time stress of each part of the target component, the method also includes: a component BP neural network model, wherein the pressing speed and the pressing amount are used as input nodes of the input layer, and the strain rate and stress are used as output nodes of the output layer; obtaining a preset data set, and dividing the data set into a training set, a validation set, and a test set; using the training set to train the BP neural network model, using the validation set to adjust the parameters of the BP neural network model, and using the test set to evaluate the performance of the BP neural network model to obtain a quality prediction model; integrating the quality prediction model into the monitoring system of the production line, inputting the collected pressing speed and pressing amount in real time, and outputting the predicted strain rate and stress.

[0081] Specifically, in the stamping process, the use of BP neural network model for quality prediction is an advanced technical means to improve production efficiency and product quality. In the stamping process, the use of BP neural network model for quality prediction is an advanced technical means to improve production efficiency and product quality. Input layer design, the number of nodes in the input layer should correspond to the number of variables affecting the prediction. In this case, there are two input nodes, corresponding to the real-time pressing speed and the real-time pressing amount respectively. The number of nodes and the number of layers in the hidden layer are usually determined based on the complexity of the problem and the characteristics of the data. The optimal hidden layer structure and number of nodes can be selected by experiment or by using heuristic methods such as cross-validation. The number of nodes in the output layer should correspond to the number of results to be predicted, namely strain rate and stress, so there should be two output nodes.

[0082] Obtain the dataset for neural network training and perform appropriate preprocessing. First, collect historical production data, including records of press speed, press amount, strain rate, and stress. Perform data cleaning (remove outliers and missing values) and standardize or normalize the input and output data to improve the efficiency and effectiveness of network training. Divide the entire dataset into training, validation, and test sets. A common ratio is 70% training, 15% validation, and 15% test.

[0083] Train and tune the neural network model using the training and validation sets. Train the BP neural network using the training set. During training, adjust network weights to minimize prediction error (e.g., mean squared error (MSE)). Use the validation set to adjust model parameters, such as the learning rate and batch size, and use early stopping to avoid overfitting. Use the test set to evaluate model performance. Analyze the model's prediction accuracy and stability, and perform iterative optimization as needed.

[0084] Integrate the trained model into the production line's monitoring system to achieve real-time quality prediction. Integrate the BP neural network model into the existing production monitoring system. Ensure the model can receive real-time input data and quickly output prediction results. The system receives real-time data on the press speed and press load of the stamping equipment, uses the model to predict strain rate and stress, and displays this information for operator monitoring. Based on the predictions, production parameters can be adjusted, such as adjusting the press speed or changing the die settings, to optimize product quality.

[0085] In one possible embodiment, before the component BP neural network, the method also includes: establishing a three-dimensional model of sheet metal stamping; setting boundary conditions for sheet metal stamping, the boundary conditions including sheet metal material properties, pressing speed range, pressing amount range and friction conditions; running simulation on the three-dimensional model after setting the boundary conditions, recording the stress rate and stress distribution of the stamped component under different process conditions, as well as the pressing amount and pressing speed under different process conditions; outputting the stress rate, stress distribution, pressing amount and pressing speed to obtain a data set.

[0086] Specifically, before using the BP neural network model to predict the quality of sheet metal stamping, establishing a three-dimensional model of the sheet metal and performing numerical simulation are key steps. These steps provide the necessary data sets for training the neural network. First, it is necessary to use suitable computer-aided engineering (CAE) software such as Abaqus, ANSYS or SolidWorks to establish a three-dimensional model of sheet metal stamping. Draw the precise three-dimensional geometry of the sheet metal and mold to ensure that all details such as stamping location, thickness and shape accurately reflect the design intent. Mesh the three-dimensional model to facilitate finite element analysis. The density and type of the mesh (such as tetrahedron or hexahedron) have an important impact on simulation accuracy and calculation time.

[0087] Enter the sheet material properties, such as elastic modulus, yield strength, and Poisson's ratio. These properties can typically be obtained from material handbooks. Set the speed and amount of force used in the simulation. These parameters should reflect actual production conditions. Set the friction coefficient based on the actual contact conditions between the stamping die and the sheet.

[0088] CAE software was then used to run simulations to analyze stress and strain rates under varying process parameters. Simulations were run under defined boundary conditions, recording the stress rate and stress distribution throughout the stamping process. The simulations were repeated with varying press speed and press load to observe how these changes affected the stamping results.

[0089] After the simulation is complete, collect and output the required data sets. This data will be used to train the BP neural network model. Extract data such as stress rate, stress distribution, pressure amount, and pressure velocity from the CAE software. Format the extracted data, such as saving it as a CSV or Excel file, for subsequent processing and analysis.

[0090] The real-time pressing speed and real-time pressing amount are input into the quality prediction model to obtain the real-time strain rate and real-time stress of each part of the target component, which are calculated using the following formula:

[0091]

[0092] σ(ε ′,ε,T)=σ y (ε ′ ,T)+(K(T)·ε n )·(1+C·log(ε ′ ))

[0093] Among them, ε is the real-time strain rate, H is the thickness change rate of the target component per unit time, h is the current thickness of the target component, v is the real-time pressing speed, σ(ε',ε,T) is the real-time stress, σ y (∈,T) is the yield stress, K(T) is the hardening coefficient, ∈ is the accumulated strain, n is the hardening exponent, C is the rate sensitivity coefficient, and T is the material temperature.

[0094] The strain rate (∈) is the rate of change of material deformation per unit time and is defined as the ratio of the thickness change rate (H) to the current thickness (h). In the actual stamping process, the real-time downward pressure velocity (v) of the punch can be approximately equivalent to the thickness change rate (H).

[0095] The stress model adopts a classic plastic hardening model with an additional term for strain rate sensitivity. In this model, the yield stress σ y It can be determined through experimental data and is usually related to the strain rate and temperature of the material. The hardening coefficient K(T) describes the hardening behavior of the material after plastic deformation and usually needs to be obtained through material testing. The hardening exponent n describes the degree of nonlinearity of the hardening behavior. The Clog(∈′) term takes into account the rate dependence of the material, that is, how the stress response of the material changes with changes in the deformation rate. By integrating these physical models and material parameters, the material stress state during the stamping process can be accurately predicted, thereby achieving better quality control and optimization in the production process.

[0096] S130: Determine whether the stamping equipment causes cracking or wrinkling of the target component based on the real-time strain rate, and determine whether the component strength of the target component meets the preset strength standard based on the real-time stress.

[0097] In one possible embodiment, whether the stamping equipment causes cracking or wrinkling of the target component is determined based on the real-time strain rate, specifically including: determining the critical strain rate of the target component; determining whether the real-time strain rate is greater than or equal to the critical strain rate; if it is determined that the real-time strain rate is greater than or equal to the critical strain rate, it is determined that the stamping equipment will cause cracking or wrinkling of the target component.

[0098] Specifically, it is a key quality control process to determine whether the stamping equipment will cause the target component to crack or wrinkle based on the judgment of real-time strain rate. The critical strain rate refers to the maximum allowable deformation rate at which the component begins to crack or wrinkle during the stamping process. Material mechanics tests (such as tensile tests) can be used to measure the behavior of materials at different strain rates under controlled experimental conditions. Observe at which strain rate the material begins to show signs of cracking or wrinkling. Or analyze the data recorded in previous production, especially those cases known to cause cracking or wrinkling, to estimate the critical strain rate. It is also possible to combine material science and engineering experience to determine a safe strain rate range to avoid cracking and wrinkling.

[0099] Once real-time strain rate data and a predetermined critical strain rate are available, a comparison can be made. Warning thresholds can be set in the monitoring system to issue a warning when the real-time strain rate reaches or exceeds the critical strain rate. The system can also be configured to automatically take action, such as slowing down the press or pausing the operation, to prevent component damage when an excessively high strain rate is detected.

[0100] In one possible embodiment, determining whether the component strength of the target component meets a preset strength standard based on the real-time stress specifically includes: determining a stress threshold corresponding to the preset strength standard of the target component based on the yield strength and tensile strength of the target component; and determining whether the real-time stress is greater than or equal to the stress threshold. If it is determined that the real-time stress is greater than or equal to the stress threshold, determining that the component strength of the target component meets the preset strength standard.

[0101] Specifically, during the stamping process, it is crucial to ensure that the strength of the target component meets the preset standard. This requires a series of steps to monitor real-time stress and compare it with the preset strength standard. First, the preset strength standard is determined based on the material properties of the target component, such as yield strength and tensile strength. Through material mechanics tests, such as standard tensile tests, the yield strength (that is, the lowest stress at which the material begins to permanently deform) and tensile strength (that is, the maximum stress that the material can withstand before breaking) of the material are obtained. Based on the yield strength and tensile strength obtained, a safe stress threshold is determined. Usually, this threshold is set below the yield strength to ensure that the component does not undergo permanent deformation during operation.

[0102] Analyze the collected real-time stress data and compare it with a preset stress threshold. Real-time monitoring software or systems continuously compare the monitored stress data with the preset stress threshold. If the monitored stress data is greater than or equal to the preset stress threshold, the system should issue a warning, indicating that the component strength has reached or exceeded the preset standard, posing a potential safety risk. Once the real-time stress exceeds the preset standard, immediate measures are taken to prevent possible component damage or failure.

[0103] S140: If it is determined that the stamping equipment causes cracking or wrinkling of the target component, or the component strength of the target component does not meet the preset strength standard, the parameters of the stamping equipment are adjusted.

[0104] In one possible embodiment, if it is determined that the stamping equipment causes cracking or wrinkling of the target component, or the component strength of the target component does not meet the preset strength standard, the parameters of the stamping equipment are adjusted, specifically including: determining the component yield of the target component based on the stamping simulation results for the target component; judging whether the component yield is greater than or equal to the preset yield; if it is determined that the component yield is less than the preset yield, adjusting the pressure distribution of the stamping equipment based on the material properties and thickness of the target component to make the pressure distribution of the stamping equipment uniform.

[0105] Specifically, a stamping simulation is performed using computer-aided engineering (CAE) software. Based on the design of the target component, an accurate 3D model is created, and material properties and thickness data are input. The initial conditions for the simulation are configured, including pressure distribution, punch speed, die temperature, etc. The simulation is performed to predict the material behavior during the stamping process, focusing particularly on stress, strain, and possible defect areas (such as cracking or wrinkling).

[0106] Use simulation results to assess component yield, i.e., the proportion of defect-free components. Analyze the simulation results in detail to determine the component's yield under the current pressure distribution. Compare the simulated yield to the pre-set yield standard.

[0107] If the simulated yield is lower than the preset standard, the pressure distribution needs to be adjusted to improve the quality of the component. Based on the problem areas found in the simulation, identify the causes of uneven pressure distribution, such as improper mold design, uneven material thickness, or inappropriate pressing speed. Adjust the mold structure or change the settings of the stamping equipment as needed, such as adjusting the alignment of the punch, changing the punch speed, or optimizing the lubrication conditions. Use software tools to redesign the pressure distribution to ensure that the force applied to the component is more uniform. This may involve adjusting the geometry of the punch, changing the buffer material, or adjusting the support structure of the mold. After adjusting the pressure distribution, rerun the stamping simulation to check how the new pressure distribution affects the stress state and yield of the component. Analyze the simulation results after the improvement measures to confirm whether the yield meets or exceeds the preset standard.

[0108] This embodiment also discloses an online quality monitoring device for the plate stamping process, referring to Figure 2 The device includes an acquisition module 201, a processing module 202 and a judgment module 203, wherein:

[0109] The acquisition module 201 is used to collect the real-time pressing speed and real-time pressing amount of the stamping forming equipment for the target component.

[0110] The processing module 202 is used to input the real-time pressing speed and the real-time pressing amount into the quality prediction model to obtain the real-time strain rate and real-time stress of each part of the target component.

[0111] The judgment module 203 is used to judge whether the stamping equipment causes cracking or wrinkling of the target component based on the real-time strain rate, and to judge whether the component strength of the target component meets the preset strength standard based on the real-time stress.

[0112] The processing module 202 is configured to adjust parameters of the stamping equipment if it is determined that the stamping equipment causes cracking or wrinkling of the target component, or that the component strength of the target component does not meet a preset strength standard.

[0113] In a possible implementation, the processing module 202 is used to construct a BP neural network model, wherein the pressing speed and pressing amount are used as input nodes of the input layer, and the strain rate and stress are used as output nodes of the output layer.

[0114] The acquisition module 201 is used to acquire a preset data set and divide the data set into a training set, a validation set, and a test set.

[0115] The processing module 202 is used to train the BP neural network model using the training set, adjust the parameters of the BP neural network model using the validation set, and evaluate the performance of the BP neural network model using the test set to obtain a quality prediction model.

[0116] The processing module 202 is used to integrate the quality prediction model into the monitoring system of the production line, input the collected pressing speed and pressing amount in real time, and output the predicted strain rate and stress.

[0117] In a possible implementation, the processing module 202 is used to establish a three-dimensional model of sheet metal stamping.

[0118] The processing module 202 is used to set the boundary conditions for sheet metal stamping, which include sheet metal material properties, pressing speed range, pressing amount range, and friction conditions.

[0119] The processing module 202 is used to run a simulation on the three-dimensional model after setting the boundary conditions, and record the stress rate and stress distribution of the stamping component under different process conditions, as well as the pressing amount and pressing speed under different process conditions.

[0120] The processing module 202 is used to output the stress rate, stress distribution, pressing amount and pressing speed to obtain a data set.

[0121] In one possible implementation, the processing module 202 is configured to input the real-time pressing speed and the real-time pressing amount into the quality prediction model to obtain the real-time strain rate and real-time stress of each part of the target component, specifically calculated using the following formula:

[0122]

[0123] σ(ε ′ ,ε,T)=σ y (ε ′ ,T)+(K(T)·ε n )·(1+C·log(ε ′ ))

[0124] Among them, ε is the real-time strain rate, H is the thickness change rate of the target component per unit time, h is the current thickness of the target component, v is the real-time pressing speed, σ(ε',ε,T) is the real-time stress, σ y (∈,T) is the yield stress, K(T) is the hardening coefficient, ∈ is the accumulated strain, n is the hardening exponent, C is the rate sensitivity coefficient, and T is the material temperature.

[0125] In one possible implementation, the processing module 202 is configured to determine a critical strain rate of a target component.

[0126] The judgment module 203 is used to judge whether the real-time strain rate is greater than or equal to the critical strain rate. If it is determined that the real-time strain rate is greater than or equal to the critical strain rate, it is determined that the stamping forming equipment will cause the target component to crack or wrinkle.

[0127] In a possible implementation, the processing module 202 is configured to determine a stress threshold corresponding to a preset strength standard of the target component based on the yield strength and tensile strength of the target component.

[0128] The judgment module 203 is used to judge whether the real-time stress is greater than or equal to the stress threshold. If it is determined that the real-time stress is greater than or equal to the stress threshold, it is determined that the component strength of the target component reaches a preset strength standard.

[0129] In a possible implementation, the processing module 202 is configured to determine a component yield rate of the target component based on a stamping simulation result for the target component.

[0130] The judgment module 203 is used to judge whether the component yield rate is greater than or equal to a preset yield rate.

[0131] The processing module 202 is used to adjust the pressure distribution of the stamping equipment according to the material properties and thickness of the target component to make the pressure distribution of the stamping equipment uniform if it is determined that the component yield is less than the preset yield.

[0132] It should be noted that the above embodiments provide devices that implement their functions using only the division of the above functional modules as examples. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiments are based on the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0133] This embodiment also discloses an electronic device, referring to Figure 3 The electronic device may include: at least one processor 301 , at least one communication bus 302 , a user interface 303 , a network interface 304 , and at least one memory 305 .

[0134] The communication bus 302 is used to implement the connection and communication between these components.

[0135] The user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0136] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0137] The processor 301 may include one or more processing cores. The processor 301 utilizes various interfaces and lines to connect various parts of the entire server. By running or executing instructions, programs, code sets, or instruction sets stored in the memory 305, and calling data stored in the memory 305, the processor 301 performs various server functions and processes data. Optionally, the processor 301 may be implemented in at least one hardware form of a digital signal processing (DSP), a field-programmable gate array (FPGA), or a programmable logic array (PLA). The processor 301 may integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU primarily processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display; and the modem is used to handle wireless communications. It is understood that the modem may not be integrated into the processor 301 and may be implemented separately on a single chip.

[0138] Among them, the memory 305 may include a random access memory (RAM) or a read-only memory (ROM). Optionally, the memory includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may also be at least one storage device located away from the aforementioned processor 301. The memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface 303 module and an application for an online quality monitoring method during sheet metal stamping forming.

[0139] exist Figure 3 In the electronic device shown, the user interface 303 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 301 can be used to call an application program stored in the memory 305 for an online quality monitoring method in a sheet metal stamping process. When executed by one or more processors 301, the electronic device executes one or more methods as in the above-mentioned embodiments.

[0140] It should be noted that for the aforementioned method embodiments, for simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for this application.

[0141] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0142] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely schematic, such as the division of units, which is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interface, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0143] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0144] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0145] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory 305 and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory 305 includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a magnetic disk, or an optical disk.

[0146] The present application also discloses a computer-readable storage medium storing instructions, which, when executed by one or more processors 301, enable an electronic device to execute one or more of the methods described in the above embodiments.

[0147] The above is only an exemplary embodiment of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, those skilled in the art will easily think of other embodiments of the present disclosure. This application is intended to cover any variation, use or adaptive change of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art that are not recorded in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A method for online quality monitoring during sheet metal stamping, characterized in that: The method comprises: Collect the real-time pressing speed and real-time pressing amount of the stamping equipment for the target component; Inputting the real-time pressing speed and the real-time pressing amount into a quality prediction model to obtain the real-time strain rate and real-time stress of each part of the target component; Determining whether the stamping equipment causes cracking or wrinkling of the target component based on the real-time strain rate, and determining whether the component strength of the target component meets a preset strength standard based on the real-time stress; If it is determined that the stamping and forming equipment causes the target component to crack or wrinkle, or the component strength of the target component does not meet the preset strength standard, adjusting the parameters of the stamping and forming equipment; Before inputting the real-time pressing speed and the real-time pressing amount into a quality prediction model to obtain the real-time strain rate and real-time stress of each part of the target component, the method further includes: Component BP neural network model, in which the pressing speed and pressing amount are used as input nodes of the input layer, and the strain rate and stress are used as output nodes of the output layer; Obtain a preset data set, and divide the data set into a training set, a validation set, and a test set; Using the training set to train the BP neural network model, using the validation set to adjust the parameters of the BP neural network model, and using the test set to evaluate the performance of the BP neural network model to obtain the quality prediction model; Integrate the quality prediction model into the production line's monitoring system, input the collected pressing speed and pressing amount in real time, and output the predicted strain rate and stress; The real-time pressing speed and the real-time pressing amount are input into the quality prediction model to obtain the real-time strain rate and real-time stress of each part of the target component, which are specifically calculated by the following formula: ； ； Wherein, ε is the real-time strain rate, H is the thickness change rate of the target component per unit time, h is the current thickness of the target component, v is the real-time pressing speed, σ(ε',ε,T) is the real-time stress, σ y (ε,T) is the yield stress, K(T) is the hardening coefficient, ε is the accumulated strain, n is the hardening exponent, C is the rate sensitivity coefficient, and T is the material temperature.

2. The method for online monitoring of quality during sheet metal stamping according to claim 1, characterized in that: Before the component BP neural network is constructed, the method further includes: Establish a three-dimensional model of sheet metal stamping; Setting boundary conditions for the sheet metal stamping, wherein the boundary conditions include sheet metal material properties, pressing speed range, pressing amount range, and friction conditions; Running a simulation on the three-dimensional model after setting the boundary conditions, recording the stress rate and stress distribution of the stamping component under different process conditions, as well as the pressing amount and pressing speed under different process conditions; The stress rate, stress distribution, pressing amount and pressing speed are output to obtain the data set.

3. The method for online monitoring of quality during sheet metal stamping according to claim 1, characterized in that: The determining, based on the real-time strain rate, whether the stamping equipment causes the target component to crack or wrinkle specifically includes: determining a critical strain rate of the target component; It is determined whether the real-time strain rate is greater than or equal to the critical strain rate. If it is determined that the real-time strain rate is greater than or equal to the critical strain rate, it is determined that the stamping equipment will cause the target component to crack or wrinkle.

4. The method for online monitoring of quality during sheet metal stamping according to claim 1, characterized in that: The determining, based on the real-time stress, whether the component strength of the target component reaches a preset strength standard specifically includes: Determining a stress threshold corresponding to a preset strength standard of the target component based on the yield strength and tensile strength of the target component; It is determined whether the real-time stress is greater than or equal to the stress threshold; if it is determined that the real-time stress is greater than or equal to the stress threshold, it is determined that the component strength of the target component reaches the preset strength standard.

5. The method for online monitoring of quality during sheet metal stamping according to claim 1, characterized in that: If it is determined that the stamping equipment causes the target component to crack or wrinkle, or the component strength of the target component does not meet the preset strength standard, the parameters of the stamping equipment are adjusted, specifically including: Determining a component yield rate of the target component according to a stamping simulation result for the target component; Determining whether the component yield rate is greater than or equal to a preset yield rate; If it is determined that the component yield is less than the preset yield, the pressure distribution of the stamping equipment is adjusted according to the material properties and thickness of the target component to make the pressure distribution of the stamping equipment uniform.

6. An online quality monitoring device for sheet metal stamping process, characterized in that: The device is used to execute the method according to any one of claims 1 to 5, and comprises an acquisition module (201), a processing module (202), and a judgment module (203), wherein: The acquisition module (201) is used to collect the real-time pressing speed and real-time pressing amount of the stamping equipment for the target component; The processing module (202) is used to input the real-time pressing speed and the real-time pressing amount into a quality prediction model to obtain the real-time strain rate and real-time stress of each part of the target component; The judgment module (203) is used to judge whether the stamping equipment causes the target component to crack or wrinkle based on the real-time strain rate, and to judge whether the component strength of the target component reaches a preset strength standard based on the real-time stress; The processing module (202) is used to adjust the parameters of the stamping equipment if it is determined that the stamping equipment causes the target component to crack or wrinkle, or the component strength of the target component does not meet the preset strength standard.

7. An electronic device, characterized in that: The electronic device comprises a processor (301), a communication bus (302), a user interface (303), a network interface (304) and a memory (305), wherein the memory (305) is used to store instructions, the user interface (303) and the network interface (304) are both used to communicate with other devices, and the processor (301) is used to execute the instructions stored in the memory (305) so that the electronic device executes the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 5 is executed.

Images