Stamping production process self-adaptive control method, stamping production line and program product

Abstract

The invention discloses a stamping production process self-adaptive control method, a stamping production line and a program product, and relates to the technical field of stamping machining. The method comprises the steps that stamping production data collected by a data collection unit are received, and the stamping production data comprise one or more of drawing inflow, die surface temperature, lubricating oil amount, closing height, blank holder force, forming force and material performance parameters; determining a quality performance prediction condition of the product based on the stamping production data; determining to-be-optimized data from the stamping production data according to the quality performance prediction condition; stamping process optimization parameters are determined according to the to-be-optimized data; and the stamping process optimization parameters are sent to a stamping controller of the stamping equipment, so that the stamping controller adjusts the stamping action of the stamping equipment according to the stamping process optimization parameters. Intelligent and automatic management of the stamping production line can be achieved, the production efficiency is improved, and the defective rate is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of stamping processing, and in particular to a stamping production process adaptive control method, a stamping production line and a program product. Background Art

[0002] High-speed stamping production line is suitable for cold stamping of low-carbon steel and low-strength aluminum alloy sheets, especially for the production and processing of large automotive panels. Stamping process parameters have a decisive influence on the quality of the cost after forming and production efficiency.

[0003] In the related art, since the process parameters are relatively complex, most of them are set based on historical experience to ensure normal production.

[0004] When defective products appear, the machine needs to be shut down to check all parameters, and various parameter combinations need to be tried continuously, wasting a lot of production time on trial and error to find the cause of the defect. This results in low production efficiency and a high rate of defective products. Summary of the invention

[0005] In view of the above-mentioned technical problems and defects, the purpose of the present invention is to provide a stamping production process adaptive control method, a stamping production line and a program product, which can realize the intelligent and automated management of the stamping production line, improve production efficiency and reduce the defective rate.

[0006] To achieve the above-mentioned purpose, in the first aspect, the present invention provides an adaptive control method for a stamping production process, which is applied to a main control unit of a stamping production line, and the stamping production line also includes a data acquisition unit and a stamping equipment respectively connected to the main control unit; the method includes: receiving stamping production data collected by the data acquisition unit, and the stamping production data includes one or more of drawing inflow, mold surface temperature, lubricating oil amount, closing height, blank holding force, forming force and material performance parameters; determining a quality performance prediction of a product based on the stamping production data, and the quality performance prediction includes at least one of a cracking prediction, a wrinkling prediction and a hidden damage prediction; determining data to be optimized from the stamping production data according to the quality performance prediction; determining stamping process optimization parameters according to the data to be optimized; and sending the stamping process optimization parameters to the stamping controller of the stamping equipment, so that the stamping controller adjusts the stamping action of the stamping equipment according to the stamping process optimization parameters.

[0007] The present invention provides accurate data support for the stamping process by collecting stamping production data in real time. Based on these data, the system can predict product quality performance, identify potential quality problems, and determine the data that needs to be optimized accordingly. By analyzing the key parameters that affect product quality, the optimization parameters of the stamping process are automatically calculated, and these parameters are sent to the controller of the stamping equipment to guide the equipment to make precise adjustments. This embodiment significantly improves production efficiency and product quality, and reduces errors and defects caused by human factors. Automated process adjustments reduce reliance on technicians' experience and intuition, making the production process more stable and reliable. In addition, through real-time monitoring and optimization, it is possible to quickly respond to changes in the production process and adjust process parameters in time to adapt to different production conditions and material properties. This not only improves production flexibility, but also helps to reduce production costs, reduce material waste, improve production efficiency, and reduce the rate of defective products.

[0008] In combination with some embodiments of the first aspect, in some embodiments, the stamping production line also includes eddy current detection equipment, and after the step of sending the stamping process optimization parameters to the stamping controller of the stamping equipment, it also includes: obtaining a surface image of the stamped product; identifying the surface image through a preset crack recognition model and a wrinkle recognition model respectively to obtain the cracking condition and wrinkling condition of the stamped product; judging whether the cracking condition and the wrinkling condition are both qualified; if so, detecting whether the stamped product has hidden damage through a preset hidden damage detection model.

[0009] The present invention adopts the above technical solution, and by introducing eddy current detection equipment, as well as preset crack recognition models and wrinkle recognition models, can quickly and accurately detect the cracking and wrinkling of products after the stamping process parameters are adjusted. This measure not only improves the real-time and accuracy of product quality detection, but also helps enterprises to promptly discover and deal with potential quality problems, thereby ensuring the quality of the final product and customer satisfaction.

[0010] In combination with some embodiments of the first aspect, in some embodiments, the stamping production line also includes eddy current detection equipment, and the step of detecting whether the stamping product has hidden damage through a preset hidden damage detection model includes: obtaining environmental data, the electrical conductivity and magnetic permeability of the stamping product, and the excitation current frequency and electrical impedance change when the eddy current detection equipment detects the stamping product; inputting the excitation current frequency, the electrical impedance change, the electrical conductivity, the magnetic permeability and the environmental data into the hidden damage detection model to determine whether the stamping product has hidden damage.

[0011] The present invention adopts the above technical solution and specifies in detail a specific method for determining whether a stamping product has hidden damage through a hidden damage detection model. This method comprehensively considers environmental data, material properties, and parameters of eddy current detection equipment, making hidden damage detection more comprehensive and accurate. This not only improves the depth of product quality detection, but also provides a more solid guarantee for product safety.

[0012] In combination with some embodiments of the first aspect, in some embodiments, the step of inputting the excitation current frequency, the electrical impedance change, the conductivity, the magnetic permeability and the environmental data into the hidden flaw detection model to determine whether the stamping product has hidden flaws includes: calculating a defect depth detection value through a defect depth estimation formula in the hidden flaw detection model, and the mathematical form of the defect depth estimation formula is: Wherein, d is the defect depth detection value, f is the excitation current frequency, α is the attenuation index related to the material properties, C is a proportional constant, σ(T, RH) is the conductivity that changes with temperature T and relative humidity RH, μ(T, RH) is the magnetic permeability that changes with temperature T and relative humidity RH, ΔZ is the change in electrical impedance, n is a power factor used to adjust the responsiveness of the formula, and β is a coefficient that indicates the degree of influence of the change in electrical impedance on the defect depth estimation; The defect depth detection value is used to determine whether the stamping product has hidden defects.

[0013] The present invention adopts the above technical solution and provides a scientific quantitative basis for hidden damage detection through the defect depth estimation formula mentioned above. Through this formula, the depth of the defect can be accurately calculated, so as to more accurately determine whether the product has hidden damage. This method not only improves the accuracy of hidden damage detection, but also provides strong support for subsequent product repair and quality control.

[0014] In combination with some embodiments of the first aspect, in some embodiments, after the step of detecting whether the stamping product has hidden defects through a preset hidden defect detection model, it also includes: if there is no hidden defect, obtaining the product parameters after the stamping process parameters are adjusted; determining the product qualification rate based on the product parameters; judging whether the product qualification rate is lower than the set value; if so, obtaining the adjusted stamping process optimization parameters.

[0015] The present invention adopts the above technical solution and introduces a real-time monitoring and evaluation mechanism for product qualification rate. By obtaining the product parameters after the stamping process parameters are adjusted and determining the product qualification rate based on these parameters, the production quality can be monitored in real time. If the product qualification rate is lower than the set value, the main control unit can obtain the adjusted stamping process optimization parameters in time. This feedback mechanism helps to quickly respond to quality problems and reduce the number of unqualified products.

[0016] In combination with some embodiments of the first aspect, in some embodiments, the step of determining a quality performance prediction of a product based on the stamping production data includes: cleaning the stamping production data; inputting the cleaned stamping production data into a preset product quality prediction model to obtain a quality performance prediction, which quality performance prediction includes at least one of a cracking prediction, a wrinkling prediction, and a hidden damage prediction.

[0017] The present invention adopts the above technical solution and introduces a data cleaning and preprocessing step, which is crucial to ensure the accuracy of the product quality prediction model. By cleaning the stamping production data, noise and outliers in the data can be eliminated and the data quality can be improved. The preprocessed data is more accurate and reliable, providing high-quality input for subsequent prediction models, making the prediction results more accurate and providing a solid data foundation for process optimization.

[0018] In combination with some embodiments of the first aspect, in some embodiments, the step of determining the stamping process optimization parameters based on the data to be optimized includes: obtaining a stamping process finite element simulation model; determining initial stamping process parameters based on the data to be optimized and the stamping process finite element simulation model; updating the initial stamping process parameters through an optimization algorithm and the stamping process finite element simulation model to obtain the stamping process optimization parameters.

[0019] The present invention adopts the above technical solution, and determines the stamping process parameters through the stamping process finite element simulation model and optimization algorithm, so that the determination of the parameters is more scientific and reasonable. This method can fully consider the material properties and production conditions, and perform calculations in a simulation environment, thereby avoiding material waste and loss in the actual production process and saving cost expenditure. At the same time, through the continuous iteration of the optimization algorithm, the enterprise can continuously optimize the production parameters and improve the quality and performance of the product.

[0020] In combination with some embodiments of the first aspect, in some embodiments, the step of determining the data to be optimized from the stamping production data based on the quality performance prediction includes: determining the degree of influence of each data in the stamping production data on the quality performance prediction; determining the data to be optimized from the stamping production data based on the degree of influence.

[0021] The present invention adopts the above technical solution, and through quantitative analysis of the impact of stamping production data on product quality performance, this step helps to identify key parameters that have a significant impact on product quality. This impact assessment not only helps determine which parameters need to be optimized, but also provides a direction for optimization, ensuring that the optimization measures can target the factors that are most likely to affect product quality, thereby improving the efficiency and effectiveness of optimization.

[0022] In the second aspect, the present invention provides a stamping production line, including a main control unit, a data acquisition unit and a stamping device, the main control unit is connected to the data acquisition unit and the stamping device respectively, the main control unit includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, the one or more processors call the computer instructions to enable the electronic device to execute the method described in the first aspect and any possible implementation method of the first aspect.

[0023] In a third aspect, the present invention provides a computer program product comprising instructions, which, when executed on a main control unit, enables the main control unit to execute the method described in the first aspect and any possible implementation of the first aspect.

[0024] In a fourth aspect, the present invention provides a computer-readable storage medium storing instructions, which, when executed on a main control unit, enables the main control unit to execute the method described in the first aspect and any possible implementation of the first aspect.

[0025] It can be understood that the stamping production line provided in the second aspect, the computer program product provided in the third aspect, and the storage medium provided in the fourth aspect are all used to execute the method provided in the present invention. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, and will not be repeated here.

[0026] One or more technical solutions provided by the present invention have at least the following technical effects or advantages: 1. Real-time quality monitoring and predictive optimization: This technical solution realizes real-time quality monitoring of the stamping production line by integrating the data acquisition unit and the main control unit. The data acquisition unit can capture key data including drawing inflow, die surface temperature, lubricating oil amount, etc., and the main control unit predicts the quality performance of the product based on these data through the preset product quality prediction model. This function not only makes the production process more transparent, but also allows intervention and adjustment before problems occur. In addition, the main control unit can automatically adjust the stamping process parameters according to the prediction results to achieve adaptive control, thereby significantly improving product quality and production efficiency.

[0027] 2. Comprehensive quality inspection and evaluation: In addition to real-time monitoring, this technical solution also introduces eddy current detection equipment and a variety of preset recognition models for comprehensive quality inspection of stamping products. Eddy current detection equipment can capture images of the product surface and quickly and accurately identify cracking and wrinkling of the product through crack recognition models and wrinkle recognition models. In addition, the hidden damage detection model further detects whether the product has hidden damage to ensure the safety of the product. This comprehensive quality inspection mechanism not only improves the product qualification rate, but also reduces the return and repair costs caused by quality problems.

[0028] 3. Intelligent parameter optimization and continuous improvement: This technical solution uses finite element simulation models and optimization algorithms to determine and update stamping process parameters. This method can set parameter values ​​scientifically and reasonably based on material properties and production conditions, avoiding waste and losses in the production process. At the same time, through continuous iteration and optimization, companies can continuously improve production parameters to adapt to changing market demands and product requirements. In addition, the solution also allows companies to further adjust and optimize production parameters based on product quality pass rate assessment results, forming a closed loop of continuous improvement, which helps companies continuously improve production efficiency and product quality and enhance market competitiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The drawings herein are incorporated into and constitute a part of the specification, showing embodiments consistent with the present invention, and together with the specification, are used to explain the principles of the present invention. Obviously, the drawings described below are only some embodiments of the present invention, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work. In the drawings: Figure 1 It is a structural schematic diagram of a stamping production line according to an embodiment of the present invention; Figure 2 It is a schematic diagram of a framework of a stamping production line according to an embodiment of the present invention; Figure 3 is a flow chart of a stamping production process adaptive control method according to an embodiment of the present invention; Figure 4 is a flow chart of another stamping production process adaptive control method according to an embodiment of the present invention; Figure 5 It is a schematic diagram of the architecture of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION

[0030] The terms used in the following embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to be limiting of the present invention. As used in the specification of the present invention, the singular expressions "a", "a", "above", "the" and "this" are intended to also include plural expressions, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in the present invention refers to any or all possible combinations comprising one or more of the listed items.

[0031] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood as implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present invention, unless otherwise specified, the meaning of "plurality" is two or more.

[0032] It should also be noted that, unless otherwise clearly specified and limited, in the embodiments of the present invention, the terms such as "setting" and "connection" should be understood in a broad sense. For example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two components; it can be a wired communication connection or a wireless communication connection. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to the specific circumstances. The embodiments of the present invention are described in detail below.

[0033] Traditional stamping process control usually relies on experience and manual operation. During the production process, technicians will set stamping parameters such as pressure, speed, die gap, etc. based on previous production data and experience. Once these parameters are set, they usually remain unchanged throughout the production batch, or are only adjusted when obvious quality problems occur. Due to the lack of real-time monitoring and dynamic adjustment mechanisms, this control method may not be able to respond to minor changes in the production process in a timely manner, resulting in unstable product quality and waste of resources.

[0034] The following is an example of a stamping process: In a metal processing manufacturing plant, the stamping process is usually operated by experienced technicians who stand next to the roaring stamping press and manually adjust the press pressure, die gap and stamping speed according to the thickness of the metal sheet and the required part shape. The technicians rely on years of experience and intuition to monitor the production process. Once defects such as wrinkling or cracking are detected in the product, they will immediately stop the machine, adjust the parameters based on experience, or collaborate with quality inspectors to make corrections. Although this method is flexible, it is inefficient and requires high skills from the technicians. It is difficult to ensure consistency and stability in the production process.

[0035] In the adaptive control technology solution for stamping production process provided by the embodiment of the present invention, the scenario is completely different. In this embodiment, the main control unit is connected to the data acquisition unit to collect key data such as drawing inflow and die surface temperature in real time. Through advanced algorithms, it is possible to predict product quality performance and automatically adjust stamping process parameters such as closing height and blank holding force to optimize the production process and ensure stamping processing accuracy.

[0036] The embodiment of the present invention realizes the intelligent and automated management of the stamping production line. By collecting stamping production data in real time, such as drawing inflow, die surface temperature, lubricating oil amount, etc., accurate data support is provided for the stamping process. Based on these data, it is possible to predict product quality performance, identify potential quality problems, and determine the data that needs to be optimized. By analyzing the key parameters that affect product quality, the optimized parameters of the stamping process are automatically calculated, and these parameters are sent to the controller of the stamping equipment to guide the equipment to make precise adjustments to ensure the stamping processing accuracy.

[0037] This embodiment significantly improves production efficiency and product quality, and reduces errors and defects caused by human factors. Automated process adjustment reduces reliance on technician experience and intuition, making the production process more stable and reliable. In addition, through real-time monitoring and optimization, it is possible to quickly respond to changes in the production process and adjust process parameters in time to adapt to different production conditions and material properties. This not only improves production flexibility, but also helps to reduce production costs, reduce material waste, achieve efficient use of resources, and improve production efficiency and reduce the rate of defective products.

[0038] The stamping production process adaptive control method of the embodiment of the present invention is applied to a stamping production line. Figure 1 As shown, the stamping production line includes a main control unit 1, a data acquisition unit 2 and a stamping device 3, wherein the main control unit 1 is connected to the data acquisition unit 2 and the stamping device 3 respectively.

[0039] The main control unit 1 is the brain of the stamping production line, responsible for the coordination and control of the entire production process, and is used to execute the stamping production process adaptive control method provided in this embodiment. It processes the received data through advanced algorithms and logic, makes decisions, and issues instructions to optimize the production process. The main control unit 1 has sufficient computing power to analyze the stamping production data transmitted by the data acquisition unit in real time, and predict product quality based on these data, automatically adjust the stamping process parameters, and ensure the efficiency of the production process and the consistency of product quality.

[0040] Data acquisition unit 2 is the sensory system of the stamping production line, responsible for collecting data on various key parameters on the production line. It monitors key indicators such as drawing inflow, die surface temperature, and lubricant volume through various sensors, and transmits these data to the main control unit 1 in real time. The accuracy and real-time performance of data acquisition unit 2 are crucial for the main control unit 1 to make correct decisions, which ensures the accuracy and integrity of data during the production process.

[0041] The stamping equipment 3 is the executive mechanism of the stamping production line, and performs specific stamping operations according to the instructions of the main control unit 1. Figure 2 As shown, it includes a punching machine 31, a die 32 and a punching controller 33. The punching equipment 3 is responsible for processing the sheet into the required shape and size. The precision and stability of the punching equipment 3 directly affect the forming quality and production efficiency of the product. The punching controller 33 receives the optimization parameters sent by the main control unit 1. The punching controller 33 can automatically adjust the punching force of the punching machine 31, the gap of the die 32, etc. to adapt to different production requirements and achieve high-quality product production.

[0042] It is understandable that the stamping production line also includes a loading mechanism and a unloading mechanism. The loading mechanism is used to transport the sheet material to the stamping equipment, and the unloading mechanism is used to remove the processed product from the stamping equipment.

[0043] The following describes the stamping production process adaptive control method of this embodiment in detail in combination with the above scenario. Figure 3 , including the following steps: Step 101, receiving stamping production data collected by the data collection unit.

[0044] The stamping production data includes one or more of drawing inflow, die surface temperature, lubricating oil quantity, closing height, blank holding force, forming force and material performance parameters.

[0045] Specifically, the draw inflow refers to the distance the material fits the die and flows toward the inner edge during the drawing process of stamping; the die surface temperature indicates the thermal state of the die during the stamping process; the amount of lubricating oil ensures proper lubrication between the die and the material to reduce friction; the closing height determines the gap when the die is closed; the clamping force affects the edge support of the material during the forming process; the forming force is directly related to the forming effect of the material; and material performance parameters, such as elastic modulus, Poisson's ratio, yield strength, etc., which determine the response of the material during the stamping process.

[0046] The data acquisition unit collects stamping production data through various sensors and measuring devices integrated in the stamping production line. These sensors may include a draw gauge to measure the draw inflow, a temperature sensor to monitor the die surface temperature, a pressure sensor to record the amount of lubricating oil and the closing height, and a force sensor to detect the blank holder force and forming force. In addition, material performance parameters such as elastic modulus and yield strength can be obtained through material testing instruments and input into the data acquisition unit. The data acquisition unit transmits this data to the main control unit in real time, providing the necessary input information for the adaptive control of the stamping process.

[0047] Step 102: Determine a predicted quality performance of the product based on the stamping production data.

[0048] Among them, the quality performance prediction includes at least one of cracking prediction, wrinkling prediction and hidden damage prediction. Based on the received stamping production data, the main control unit uses advanced data analysis technology and quality prediction models to comprehensively evaluate and predict the quality performance of the product. These data include key indicators such as drawing inflow, die surface temperature, lubricating oil volume, closing height, blank holding force, forming force and material performance parameters. Through real-time monitoring and analysis of these parameters, the main control unit can predict the quality problems that may occur in the product during the stamping process, such as cracking, wrinkling or hidden damage, thereby providing a scientific basis for process optimization and quality control. This data-driven prediction method makes the production process more accurate and controllable, helps to identify and solve potential production problems in advance, and ensures the stability and consistency of product quality.

[0049] In some embodiments, this step may specifically include: first, cleaning the stamping production data; then, inputting the cleaned stamping production data into a preset product quality prediction model to obtain a quality performance prediction. The quality performance prediction includes at least one of a crack prediction, a wrinkle prediction, and a hidden damage prediction.

[0050] Specifically, before the main control unit makes a product quality prediction, it first performs a series of cleaning steps on the collected stamping production data to ensure the accuracy and reliability of the input data. This process includes removing outliers in the data, filling missing values, standardizing the data format, and possible data smoothing, thereby eliminating noise and inconsistency and improving data quality.

[0051] The cleaned data is input into a preset trained product quality prediction model, which uses statistical analysis, machine learning or artificial intelligence technology to deeply analyze and learn the data to predict possible quality problems that may occur in the product during the stamping process.

[0052] The prediction results cover multiple aspects, including but not limited to crack prediction, which evaluates the risk of material breakage under the punching pressure; wrinkle prediction, which analyzes the possibility of wrinkles in the material during the forming process; and hidden damage prediction, which identifies potential factors that may cause internal damage to the product. Through these detailed predictions, the main control unit can fully understand the potential risks of product quality and formulate corresponding optimization strategies accordingly to improve the forming quality and overall performance of the product.

[0053] In this embodiment, the product quality prediction model is trained as follows: First, collect sample data. The sample data used for model training is a series of selected and labeled historical production records. These data include sheet metal mold parameters collected under different production conditions, as well as the corresponding product quality results (such as whether cracking, wrinkling or hidden defects have occurred); they can also include the overall qualification rate of the product. The sample data set is divided into a training set and a validation set. The training set is used to learn the mapping relationship between model learning parameters and quality results, while the validation set is used to evaluate the prediction accuracy of the model and adjust the model parameters to ensure that the model has good generalization ability on unseen data.

[0054] Next, the data is preprocessed, including cleaning, standardization, and possible feature engineering, to ensure that the data is suitable for model training.

[0055] Then, select a suitable machine learning algorithm, such as decision tree, random forest, support vector machine or neural network, divide the data set into training set and test set, use the training set to train the model, and continuously adjust the model parameters to optimize performance. After the model training is completed, use the test set to verify the prediction accuracy and generalization ability of the model.

[0056] Finally, the trained model is deployed to the main control unit, enabling it to receive new stamping production data in real time and predict potential quality problems such as cracking, wrinkling and hidden damage of the product, providing a scientific basis for the adaptive control of the stamping process.

[0057] Step 103: determining data to be optimized from the stamping production data according to the quality performance prediction.

[0058] The main control unit uses statistical methods, machine learning algorithms or expert systems to conduct a comprehensive evaluation of the data and identify key factors that may affect product quality from the stamping production data. For example, if the prediction model indicates that high temperature may cause material deformation, the main control unit will mark the mold surface temperature as data to be optimized. In addition, the main control unit will also consider the interaction between the data to ensure that the optimization measures will not affect other quality indicators. This process requires precise data analysis capabilities and a deep understanding of the production process to ensure the effectiveness and comprehensiveness of the optimization measures.

[0059] In some embodiments, the step specifically includes: First, determine the influence of each data in the stamping production data on the quality performance prediction.

[0060] The main control unit first comprehensively analyzes historical production data and real-time stamping production data, and uses statistical analysis and machine learning techniques to evaluate the impact of each data item on the predicted product quality performance. This evaluation process may include calculating the correlation coefficient between each parameter and quality defects, performing regression analysis, or applying feature selection algorithms to quantify the importance of each data item. For example, the main control unit may find that the mold surface temperature is highly correlated with the risk of material cracking, or that insufficient lubricating oil is closely related to wrinkling problems. In this way, the main control unit can identify key parameters that have a significant impact on product quality.

[0061] Then, data to be optimized is determined from the stamping production data according to the degree of influence.

[0062] Based on the evaluation results, the main control unit selects the parameters that have a significant impact on the quality performance from the stamping production data and identifies them as data to be optimized. For example, these data may include mold temperature beyond the ideal range, insufficient lubricating oil, inappropriate closing height or blank holding force, etc. The main control unit uses these data to be optimized as the target of process adjustment so that product quality can be improved by optimizing these parameters in subsequent steps. This process ensures the pertinence and effectiveness of the optimization measures, and helps to achieve continuous improvement of the production process and steady improvement of product quality.

[0063] Step 104: determining stamping process optimization parameters according to the data to be optimized.

[0064] Specifically, the main control unit can use optimization algorithms, such as gradient descent or genetic algorithm, to iteratively optimize the initial process parameters. The main control unit first sets an objective function that reflects the relationship between product quality and process parameters. Then, based on the objective function and the current process parameters, the optimal adjustment direction and amplitude are calculated. This process may require multiple iterations to gradually approach the optimal solution. In this process, the main control unit also needs to consider the actual feasibility of the process parameters and the physical limitations of the equipment to ensure that the optimization results are both scientific and practical.

[0065] In some embodiments, this step may specifically include: First, the initial stamping process parameters are determined according to the data to be optimized. Then, the initial stamping process parameters are updated through an optimization algorithm to obtain the stamping process optimization parameters.

[0066] Specifically, the main control unit will set a standard parameter set based on the current production conditions. These parameters may include die closing height, blank holder force, punching force, etc., which are key operating points in the stamping process. Then, the main control unit will analyze the relationship between the data to be optimized and these initial parameters, evaluate their specific impact on product quality, and adjust the initial parameters accordingly to form a set of process parameters that are closer to the optimal production conditions.

[0067] For example, suppose that during the stamping process, it is found that the mold surface temperature is continuously high, which has a high correlation with the problem of material cracking. The main control unit will evaluate the specific impact of this temperature parameter on product quality, and determine the extent to which the increase in mold temperature affects the ductility and formability of the material by analyzing historical data and real-time feedback. Based on this evaluation, the main control unit will adjust the initially set mold temperature parameters, which may be achieved by reducing the mold preheating temperature or increasing the efficiency of the cooling system. At the same time, the main control unit will also consider other related parameters, such as the amount of lubricating oil and the clamping force, because these parameters may also be related to the mold temperature and material cracking problems. By comprehensively adjusting these parameters, the main control unit is able to form a new set of process parameters that are more suitable for current production conditions, help reduce cracking defects, improve product quality, and thus get closer to the optimal production conditions.

[0068] Afterwards, the main control unit iteratively updates these initial stamping process parameters through the optimization algorithm to obtain more accurate stamping process optimization parameters. This process involves using gradient descent, genetic algorithm or other advanced optimization algorithms to adjust parameters according to the objective function, usually minimizing quality defects and maximizing product qualification rate. In each iteration, the main control unit calculates the gradient under the current parameters or evaluates the quality of the current solution, and updates the parameters accordingly, gradually approaching the optimal solution. In this way, the main control unit can continuously optimize the process parameters until it finds the parameter combination that can produce the highest quality products under the current production conditions. This process not only improves production efficiency, but also reduces production costs by reducing the number of trial and error, and ensures the stability and reliability of product quality.

[0069] Taking the gradient descent method as an example, the specific process of updating the initial stamping process parameters through the optimization algorithm to obtain the stamping process optimization parameters is explained, including the following steps: (1) Define the objective function f(p) based on the set product qualification rate.

[0070] When the main control unit defines the objective function f(p), it sets a function with the product qualification rate as the key indicator. For example, if the goal is to increase the product qualification rate to more than 95%, the objective function may be designed as f(p) = 1-(qualified product number / total product number), where p represents the stamping process parameter vector. The smaller the value of the function, the higher the qualification rate, which reflects the gap with the target qualification rate.

[0071] (2) Determine an initial parameter vector p0 based on the initial stamping process parameters.

[0072] After determining the objective function, the main control unit will set an initial parameter vector p0 based on the current initial stamping process parameters. Assuming that the initial parameters include mold temperature 300℃, blank holder force 2000 Newtons, etc., these initial values ​​constitute the vector p0 = [300, 2000, ...], which represents the starting state of the stamping process.

[0073] (3) Taking the initial parameter vector p0 as the starting point of the algorithm, iteratively update the parameter p k ; The calculation formula for iterative update is, in, is the objective function f(p) at the current parameter p k The corresponding gradient is η, and η is the learning rate.

[0074] Taking p0 as the starting point of the optimization algorithm, the main control unit begins the iterative process and gradually updates the parameter vector p k In each iteration, the master unit calculates the objective function f(p) at the current parameter p k The gradient below This gradient indicates how to adjust the current parameters to reduce the value of the objective function most quickly, that is, to improve the product qualification rate.

[0075] Using the gradient descent method, the master unit updates the parameter vector p k , calculate the new parameter vector Where η is the learning rate, which is a hyperparameter that controls the length of each iteration step. This process is repeated until the stopping condition is met, such as the change in the gradient is very small or the preset number of iterations is reached.

[0076] (4) The parameter p after multiple iterations is updated k+1 Determine the optimized parameters for the stamping process.

[0077] After multiple iterations, the main control unit finally determines the parameter vector p k+1As the optimized stamping process parameters. These parameters are optimized by the algorithm and are expected to significantly improve the product qualification rate, reduce defects in production, and achieve a more efficient and stable production process. For example, after optimization, the mold temperature may be adjusted to 280°C and the blank holding force increased to 2200 Newtons. These optimized parameters are used to guide the actual stamping production in order to achieve or exceed the product qualification rate target of 95%.

[0078] Step 105, sending the stamping process optimization parameters to the stamping controller of the stamping equipment, so that the stamping controller adjusts the stamping action of the stamping equipment according to the stamping process optimization parameters.

[0079] There is an efficient communication mechanism between the main control unit and the stamping controller. The main control unit sends adjustment instructions to the stamping controller, which include adjusting the stamping force, die gap, stamping speed and other stamping process optimization parameters. After receiving these instructions, the stamping controller will accurately adjust the working state of the stamping equipment to achieve the optimized process requirements. During this process, the main control unit also needs to monitor the status and feedback information of the stamping equipment in real time to ensure that the adjustment of the stamping action meets the expected effect.

[0080] In order to further illustrate the technical solution of the embodiment of the present invention, Figure 4 , to introduce the stamping production process adaptive control method of this embodiment, which specifically includes the following steps: Step 201, receiving stamping production data collected by the data collection unit.

[0081] Step 202, cleaning the stamping production data.

[0082] Step 203, input the cleaned stamping production data into a preset product quality prediction model to obtain a quality performance prediction.

[0083] Step 204 , determining the influence of each data in the stamping production data on the quality performance prediction.

[0084] Step 205: determining data to be optimized from the stamping production data according to the degree of influence.

[0085] Steps 201 - 205 refer to the contents of the aforementioned embodiment and are not described again here.

[0086] Step 206, obtaining a stamping process finite element simulation model.

[0087] Specifically, it is necessary to first establish an accurate finite element simulation model of the sheet metal and stamping equipment. This involves a detailed analysis of the geometry of the processed parts, the material properties, and the working conditions of the stamping equipment. Using CAE (Computer Aided Engineering) software, you can create a three-dimensional geometric model of the stamping process and import them into FEA (Finite element analysis) software.

[0088] Next, assign appropriate material properties to the model, such as elastic modulus, Poisson's ratio, yield strength, etc., and define boundary conditions and loading conditions. This process also needs to include meshing to ensure the accuracy and computational efficiency of the simulation. In the end, the main control unit can obtain a finite element simulation model that can simulate the actual stamping process, laying the foundation for subsequent process parameter optimization.

[0089] Step 207, determining initial stamping process parameters according to the data to be optimized and the finite element simulation model.

[0090] The main control unit combines the previously collected data to be optimized, such as drawing inflow, die surface temperature, lubricant amount, etc., with the finite element simulation model. These data provide quantitative information about key variables in the production process. With this information, initial process parameters such as punching force, speed, die gap, etc. can be set in the simulation model. By running the simulation in the finite element model and observing the results, the impact of these initial parameters on product quality can be evaluated and whether further adjustments are needed. This step is the starting point of the optimization process and provides a reference point based on the current process status.

[0091] For example, suppose that during the stamping production process, the data acquisition unit collects data such as the thickness of the sheet, the yield strength and hardness of the material, which are identified as key factors affecting product quality. According to the yield strength of the sheet, the corresponding material properties can be entered in the simulation model, and then an initial stamping force can be set. This stamping force is calculated based on the sheet thickness and material properties. Next, the stamping process is simulated in the simulation software to obtain the deformation of the material and possible problems, such as wrinkles, rebound or cracks. By analyzing the simulation results, the initial process parameters can be adjusted, such as increasing or decreasing the stamping force, adjusting the die gap or changing the stamping speed, in order to achieve better product quality in the next optimization process. This process is the starting point of iterative optimization and provides a basis for subsequent process parameter optimization.

[0092] Step 208: Update the initial stamping process parameters through the optimization algorithm and the finite element simulation model to obtain the stamping process optimization parameters.

[0093] Among them, the optimization algorithm may include but is not limited to gradient descent method, genetic algorithm, particle swarm optimization, etc., and the goal is to minimize or maximize a certain performance indicator, such as reducing product size deviation, improving material utilization or reducing production costs. In each iteration, a finite element simulation model can be used to evaluate the production results under the current process parameters, and the process parameters can be adjusted according to the simulation output. Through multiple iterations, the process parameters can be continuously improved until the preset performance target is reached or the optimization algorithm converges. The specific optimization algorithm can refer to the aforementioned embodiment and will not be repeated here.

[0094] Finally, the main control unit obtains a set of optimized stamping process parameters. These parameters have been verified through simulation and can improve production efficiency and product quality and reduce material waste.

[0095] Step 209: sending the stamping process optimization parameters to the stamping controller of the stamping equipment, so that the stamping controller adjusts the stamping action of the stamping equipment according to the stamping process optimization parameters.

[0096] Step 210, obtaining a surface image of the stamped product.

[0097] Specifically, a high-precision camera system or scanning equipment can be used to comprehensively photograph the appearance of stamped products and obtain clear surface images. These images will be used for subsequent quality inspection and analysis. In order to ensure the quality of the image and the accuracy of the analysis, it may be necessary to shoot under specific lighting conditions and use appropriate resolution settings to capture the subtle features of the product surface.

[0098] Step 211 , the surface image is identified by using a preset crack identification model and a preset wrinkle identification model to obtain cracking conditions and wrinkling conditions of the stamping product.

[0099] The crack recognition model uses image processing and pattern recognition technology to detect whether there are tiny cracks or breaks on the product surface; the wrinkle recognition model is used to identify whether the material surface is wrinkled or uneven. These models are based on machine learning algorithms and are learned and optimized through previously labeled training data to improve recognition accuracy.

[0100] Among them, the training process of the crack recognition model is as follows: The training of the crack recognition model begins with the collection of a large number of surface images of stamped products, which contain examples of various crack defects, as well as defect-free samples. These images are divided into training sets and validation sets. Image processing techniques, such as image enhancement and preprocessing, are used to improve image quality and highlight crack features. Subsequently, feature extraction algorithms are used to extract crack features from the images, such as shape, texture, and edge information. These features are then input into machine learning algorithms, such as support vector machines (SVMs), convolutional neural networks (CNNs), or other deep learning architectures to train crack recognition models. By iteratively learning on the training set and adjusting the model parameters, the model gradually learns to recognize and distinguish between images with cracks and images without cracks. During the training process, the model is evaluated using the validation set to monitor its performance and avoid overfitting.

[0101] The training process of the wrinkle recognition model is as follows: The training process of the wrinkle recognition model is similar to that of the crack recognition model. First, images of the stamped product surface with and without wrinkles need to be collected. These images are preprocessed to remove noise and uneven lighting issues, and then image segmentation techniques are used to separate wrinkles from the background. The feature extraction step focuses on the geometric characteristics of wrinkles, such as length, width, depth, and distribution pattern. The extracted features are then used to train a classification model that is able to distinguish between images with and without wrinkles. During the training process, deep learning techniques may be used, especially convolutional neural networks, as they perform well in image recognition tasks. The wrinkle recognition model is trained with a large amount of labeled data, and the network weights are adjusted to minimize the classification error. Techniques such as cross-validation are used to evaluate the generalization ability of the model and ensure that the model can accurately identify wrinkle defects on unseen data.

[0102] Step 212, determining whether both the cracking condition and the wrinkling condition are qualified.

[0103] The cracking and wrinkling conditions identified in step 211 can be compared with preset quality standards. If the cracking and wrinkling conditions of the product are within an acceptable range, that is, they meet the quality standards, the product is considered qualified at this stage.

[0104] If both are judged to be qualified, the process proceeds to step 213; if at least one of the splitting condition and the wrinkling condition is judged to be unqualified, the product can be judged as an unqualified product.

[0105] Step 213, using a preset hidden damage detection model to detect whether the stamping product has hidden damage. If yes, the product is determined to be a substandard product; if no, proceed to step 214.

[0106] For products that are qualified for both surface cracking and wrinkling, further in-depth testing is required using a preset hidden damage detection model. The hidden damage detection model may include eddy current testing, ultrasonic testing or other non-destructive testing technologies that can detect potential defects inside the product, such as microcracks or other invisible damage. If the hidden damage test results show that the product has no internal defects, then the product can be finally judged to be qualified. If hidden damage is found, the product may need to be reworked or scrapped.

[0107] Taking eddy current detection as an example, the stamping production line in this embodiment may also include eddy current detection equipment. This step may specifically include: first, obtaining environmental data, the electrical conductivity and magnetic permeability of the stamping product, and the excitation current frequency and electrical impedance change when the eddy current detection equipment detects the stamping product; then inputting the excitation current frequency, the electrical impedance change, the electrical conductivity, the magnetic permeability and the environmental data into the hidden damage detection model to determine whether the stamping product has hidden damage.

[0108] Among them, eddy current testing equipment is based on the principle of electromagnetic induction. It generates a high-frequency alternating magnetic field on the surface of the material to induce eddy currents, which in turn generate their own magnetic field and affect the distribution of the original magnetic field. The sensors in the eddy current testing equipment can detect these changes and convert them into amplitude and phase change signals of electrical impedance. By analyzing these signals, the operator can evaluate the integrity of the material. Eddy current testing equipment can be configured with a variety of probes and frequency settings to meet different testing needs, including inspections of parts of specific materials, shapes or sizes. Its automation functions and data acquisition systems improve detection efficiency and accuracy, and are widely used in industries such as aerospace, automotive manufacturing, energy and medical equipment to ensure product quality and safety.

[0109] In this embodiment, the main control unit collects and analyzes key production data, including environmental parameters such as temperature and humidity, which may affect the conductivity and magnetic permeability of the material, and thus affect the propagation of eddy currents. At the same time, the main control unit can obtain the conductivity and magnetic permeability data of stamping products of different materials through prior material testing, which are indispensable material characteristic parameters in eddy current testing. During the eddy current testing process, the main control unit sets and adjusts the frequency of the excitation current, while monitoring the resulting changes in electrical impedance, which are key indicators for evaluating the internal condition of the material.

[0110] The collected excitation current frequency, impedance change, conductivity, permeability, and environmental data are integrated into the flaw detection model. The flaw detection model is an advanced data analysis system that uses machine learning algorithms, combined with eddy current testing principles and material science knowledge, to conduct in-depth analysis of the input data. The model evaluates the pattern of impedance change, considers the impact of conductivity and permeability on eddy current testing, and also considers the potential impact of environmental conditions on material properties. Through these comprehensive analyses, the flaw detection model can determine whether the stamped product has internal damage, such as cracks, holes, or other defects, thereby providing an accurate basis for product quality control.

[0111] In some embodiments, the defect depth detection value can be calculated by the defect depth estimation formula in the hidden flaw detection model. The mathematical form of the defect depth estimation formula is: Where d is the defect depth detection value, f is the excitation current frequency, α is the attenuation index related to the material properties, C is a proportional constant, σ(T, RH) is the conductivity that varies with temperature T and relative humidity RH, μ(T, RH) is the magnetic permeability that varies with temperature T and relative humidity RH, ΔZ is the change in electrical impedance, n is a power factor used to adjust the responsiveness of the formula, and β is a coefficient that represents the degree of influence of the change in electrical impedance on the defect depth estimation.

[0112] In the defect depth estimation formula of this embodiment, the excitation current frequency f and the attenuation index α take into account the penetration ability of the eddy current and the sensitivity to surface defects, wherein the higher the frequency, the more sensitive the eddy current is to the detection of surface defects.

[0113] The electrical conductivity σ(T, RH) and magnetic permeability μ(T, RH) vary with environmental conditions and directly affect the generation and propagation of eddy currents. By incorporating them into the formula, the impact of environmental factors on the test results can be corrected.

[0114] The proportionality constant C and the power factor n provide flexibility in the model, allowing the response of the formula to be adjusted for specific materials or test conditions.

[0115] The change in electrical impedance ΔZ is a parameter directly measured in eddy current testing, which reflects the change in the internal structure of the product material. The exponential function exp(-β·ΔZ) is used to quantify the impact of this change on the defect depth estimation.

[0116] The defect depth estimation formula aims to describe the complex physical phenomena in the eddy current testing process through a unified mathematical model, so as to achieve accurate estimation of the potential defect depth in stamping products. In addition, the design of the formula allows parameter optimization and calibration through experimental data to adapt to different testing conditions and material properties, enhancing the generalization ability and practicality of the model.

[0117] After calculating the defect depth detection value through the above formula, the main control unit determines whether the stamping product has hidden defects based on the defect depth detection value.

[0118] Specifically, the main control unit will use the preset evaluation criteria or thresholds to analyze this detection value. If the calculated defect depth value is less than or equal to the maximum allowable defect depth threshold and does not exceed the product specification requirements, the main control unit will determine that there is no hidden damage in the stamping product, and the defect depth is relatively shallow, which should be manifested on the outer surface of the product, such as cracks or peeling. However, the crack recognition model and the wrinkle recognition model did not recognize it in the previous steps, which indicates that the recognition accuracy of the crack recognition model and the wrinkle recognition model may need to be further improved, so this situation can be recorded, and the surface image of this stamping product can be provided as sample data to the crack recognition model and the wrinkle recognition model.

[0119] On the contrary, if the defect depth detection value exceeds the preset threshold, indicating that there may be internal damage that affects the integrity and performance of the product, the main control unit will determine that the stamping product has hidden damage and may trigger an alarm or automatically mark the product for further inspection or rejection. This decision-making process is a key link in quality control, ensuring that only high-quality products that meet standards can enter the market.

[0120] Alternatively, if the detected defect depth value is equal to 0 or close to 0, it can be considered that the stamped product has no defects such as hidden scratches, cracks or peeling.

[0121] Step 214, obtaining product parameters after the stamping process parameters are adjusted.

[0122] After the stamping process parameters are adjusted, the main control unit will monitor and collect the parameters of the produced products in real time. These parameters may include key indicators such as product dimensional accuracy, consistency of material thickness, and surface quality after forming. The main control unit accurately captures this data through high-precision sensors and measuring tools, and records it for further analysis.

[0123] Step 215, determining the product qualification rate based on the product parameters.

[0124] After obtaining the adjusted product parameters, the main control unit determines the product qualification rate based on these data. The qualification rate is the proportion of defect-free products.

[0125] Step 216, determining whether the product qualification rate is lower than a set value.

[0126] The master control unit compares the calculated product pass rate with the pre-set target pass rate. This target pass rate is set based on customer needs, industry standards or internal quality goals of the company. For example, if the set target pass rate is 99%, and the actual pass rate calculated by the master control unit is 97%, then further process optimization is required.

[0127] If the product qualification rate is lower than the set value, the process returns to step 208 to re-optimize the stamping process parameters to obtain adjusted stamping process optimization parameters and send them to the stamping controller.

[0128] If the product qualification rate is not lower than the set value, the process returns to step 214 to continue monitoring the qualification rate of the next product and continue to execute the stamping process optimization parameters.

[0129] For example, if it is found that the 97% pass rate is due to defects in some products, the main control unit may adjust the die drawing inflow, forming force or stamping speed to reduce this deviation, and restart the optimization algorithm to update the process parameters to obtain the re-adjusted stamping process optimization parameters. Then, the re-adjusted stamping process optimization parameters are sent to the stamping controller. If it is detected that the product pass rate is still not up to standard, return to step 208 again to re-optimize the stamping process parameters.

[0130] Repeat the above process N times, that is, after sending the stamping process optimization parameters adjusted for the Nth time to the stamping controller, determine whether the current product qualification rate is lower than the set value; if so, send a stop command to the stamping equipment; if not, continue to execute the stamping process optimization parameters adjusted for the Nth time, and continue to monitor the product qualification rate.

[0131] Specifically, assuming that N=3, that is, after adjusting the stamping process optimization parameters for three consecutive times, the product qualification rate is still lower than the set value, indicating that there are still quality problems in the production process, and further intervention and adjustment are required. In this case, the main control unit will take decisive measures to send a stop command to the stamping equipment to prevent the production of more unqualified products. For example, suppose that in a production run, the main control unit finds that after the third parameter adjustment, the product qualification rate is only 95%, which does not reach the target qualification rate of 98%. The main control unit will immediately send a stop signal to the stamping equipment to suspend production to avoid waste of resources and potential market risks.

[0132] At the same time as sending the stop command, the main control unit will start the problem diagnosis program to analyze why the current process parameters have not achieved the expected results. It may be necessary to review the data provided by the data acquisition unit to check whether there are data acquisition errors or equipment failures. In addition, the main control unit will also consider whether the optimization algorithm needs to be adjusted or whether the stamping equipment needs to be maintained and calibrated. Through this feedback and adjustment mechanism, the main control unit can ensure continuous improvement of the production process and ultimately achieve high-quality product output.

[0133] In some embodiments, the stamping equipment can mark the stamped product with an identification mark when performing stamping, and the identification mark can be marked on the edge of the product. This not only enhances product traceability, but also does not affect the product appearance because of its relatively close position, providing a safe and effective internal marking method for the product.

[0134] When the product is processed, the camera system or scanning equipment can take a comprehensive picture of the appearance of the stamped product, and then identify and extract the identification mark, and confirm which product has a quality defect based on this identification mark.

[0135] The technical solution of this embodiment brings significant technical effects to the stamping production line by integrating multiple functions such as data acquisition, real-time monitoring, quality prediction, automatic optimization and comprehensive detection. First, by collecting key production data in real time and combining it with a preset prediction model, the technical solution can accurately predict product quality performance and intervene and adjust before problems occur, thereby significantly improving product quality and production efficiency. Secondly, the introduction of eddy current detection equipment and a variety of identification models realizes comprehensive quality inspection of stamping products and ensures product safety and pass rate. In addition, by using finite element simulation models and optimization algorithms, the technical solution can scientifically and reasonably set and adjust stamping process parameters, avoiding waste and losses in the production process, while supporting the continuous improvement and optimization of production parameters.

[0136] In summary, this technical solution not only improves the automation and intelligence level of the stamping production line, but also significantly improves product quality and production efficiency, bringing considerable economic benefits and market competitiveness to the enterprise.

[0137] In some embodiments, the embodiments of the present invention may also implement fault simulation and response strategy generation.

[0138] First, the main control unit must establish a comprehensive fault database that collects detailed information on all historical fault cases, including fault type, time, affected equipment or production line part, fault cause, detection method and repair measures.

[0139] Based on the fault database, the main control unit uses data mining technology to identify fault patterns and trends. This involves using statistical analysis techniques to identify the frequency of faults, using clustering algorithms to find similarities between fault cases, or using time series analysis to predict when faults will occur. Through these analyses, the main control unit can understand which factors are most likely to cause faults and how faults develop over time.

[0140] Next, this information can be used to deploy fault simulation models on the master control unit. These models use computer simulation technology to reproduce the conditions under which faults occur and simulate their impact on the production line. Simulations can include everything from simple component failures to complex system-level failures and their potential impact on production efficiency, product quality and delivery time.

[0141] Once the simulation is complete, the master control unit will enter the response strategy generation phase. In this phase, the master control unit evaluates different response measures and predicts their effectiveness in mitigating or repairing the failure. This may involve considering the availability of spare parts, the scheduling of maintenance personnel, the reconfiguration of the production line, or the adjustment of the production plan. The master control unit uses optimization algorithms to determine the most effective response strategy, taking into account cost, time, resource constraints and production goals.

[0142] In addition, the master control unit also needs to consider the implementation of the response strategy. This includes integration with the existing production management system and enterprise resource planning (ERP) system to ensure that the response strategy can be seamlessly integrated into the production process. The strategy generated by the master control unit needs to be understood and executed by the production line staff, so it may be necessary to develop a user-friendly interface and instruction manual.

[0143] After implementing the response strategy, the main control unit will continue to monitor its effect and collect feedback information. This information will be used to update the fault database and optimize the fault simulation model, forming a continuous improvement cycle. In this way, the main control unit can not only improve its response to faults, but also reduce the probability of future faults.

[0144] Finally, the master control unit also needs to have self-learning capabilities, which means that it can learn from each fault handling and optimize its algorithms. Through machine learning and artificial intelligence technology, the master control unit can continuously improve its prediction accuracy and the effectiveness of its response strategy.

[0145] In summary, this embodiment combines data analysis, simulation technology, optimization algorithms and artificial intelligence to achieve rapid response and effective management of faults. Through this innovative approach, the reliability and efficiency of the stamping production line have been significantly improved, and the company's ability to adapt to complex production environments has also been improved.

[0146] In some embodiments, the present invention can also implement intelligent diagnosis and suggestions, a process involving multiple links such as real-time monitoring, data analysis, fault detection, cause analysis, suggestion generation and feedback learning.

[0147] First, the main control unit is connected to the sensors and data acquisition system on the production line to collect real-time status data and production parameters of various equipment, such as temperature, pressure, speed, vibration, current, voltage, etc. These data provide basic information for intelligent diagnosis.

[0148] Next, the main control unit uses data processing techniques such as signal processing, feature extraction, and data cleaning to pre-process the collected raw data to improve the quality and usability of the data. The main control unit then uses statistical analysis and machine learning algorithms such as cluster analysis, principal component analysis, time series analysis, support vector machines, neural networks, etc. to conduct in-depth analysis of the pre-processed data to identify abnormal patterns and trends in equipment operation.

[0149] When an abnormal situation is detected, the main control unit will trigger the intelligent diagnosis module to conduct an in-depth analysis of the cause of the abnormality. This analysis process may involve the use of causal inference, fault tree analysis, decision tree, logistic regression and other methods, combined with the working principle of the equipment, historical fault data and maintenance experience, to infer the possible cause of the fault and the scope of impact.

[0150] After completing the fault cause analysis, the main control unit will further perform suggestion generation to provide operators with suggestions for solving abnormal situations. These suggestions may include adjusting process parameters, replacing parts, performing equipment maintenance, optimizing production plans, improving operating procedures, etc. The main control unit will use multi-objective optimization algorithms such as genetic algorithms and simulated annealing algorithms to generate one or more solutions based on the urgency of the fault, the scope of impact, resource availability, and production goals, and evaluate their feasibility and effectiveness.

[0151] In addition, the master control unit will integrate the results of intelligent diagnosis and recommendations with the existing production management system and notification system to ensure that relevant information can be communicated to relevant staff and managers on the production line in a timely manner. This may involve developing user-friendly interfaces, generating visual reports, and sending automatic notifications and alarms.

[0152] After implementing the recommendations, the master control unit will continue to monitor their effects and collect feedback information. This information will be used to update the fault database, optimize the intelligent diagnosis model, and adjust the recommendation generation algorithm, forming a continuous improvement cycle. In this way, the master control unit can not only improve its responsiveness to abnormal situations, but also reduce the probability of future failures.

[0153] Finally, the master control unit also needs to be self-learning, meaning it is able to learn from each diagnosis and recommendation and optimize its algorithms. Through machine learning and artificial intelligence technology, the master control unit can continuously improve the accuracy of its diagnoses and the effectiveness of its recommendations.

[0154] In summary, this embodiment combines multiple links such as real-time monitoring, data analysis, fault detection, cause analysis, suggestion generation and feedback learning to achieve rapid response and effective management of abnormal situations in the production line. Through this innovative method, the reliability and efficiency of the production line have been significantly improved, and the company's ability to adapt to complex production environments has also been improved.

[0155] The method provided in the above embodiment is executed by a main control unit, which is an electronic device. The following describes the electronic device from the perspective of hardware processing. Figure 5 , is a schematic diagram of a physical device structure of an electronic device in an embodiment of the present invention.

[0156] It should be noted that Figure 5 The structure of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0157] like Figure 5 As shown, the electronic device includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303, such as executing the method described in the above embodiment. In RAM 303, various programs and data required for system operation are also stored. CPU 301, ROM 302 and RAM 303 are connected to each other through bus 304. Input / output (I / O) interface 305 is also connected to bus 304.

[0158] The following components are connected to the I / O interface 305: an input section 306 including an audio input device, a button switch, etc.; an output section 307 including a liquid crystal display (LCD) and an audio output device, an indicator light, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read therefrom is installed into the storage section 308 as needed.

[0159] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication section 309, and / or installed from a removable medium 311. When the computer program is executed by a central processing unit (CPU) 301, various functions defined in the present invention are performed.

[0160] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0161] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings.

[0162] Specifically, the electronic device of this embodiment includes a processor and a memory, the memory is coupled to one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and one or more processors call the computer instructions to enable the electronic device to execute the method provided by the above embodiment.

[0163] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiment; or may exist independently without being assembled into the electronic device. The above storage medium carries one or more computer programs, and when the above one or more computer programs are executed by a processor of the electronic device, the electronic device implements the method provided in the above embodiment.

[0164] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention.

[0165] As used in the above embodiments, the term "when..." may be interpreted to mean "if..." or "after..." or "in response to determining..." or "in response to detecting...", depending on the context. Similarly, the phrases "upon determining..." or "if (the stated condition or event) is detected" may be interpreted to mean "if determining..." or "in response to determining..." or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)", depending on the context.

[0166] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

Claims

1. A stamping production process adaptive control method, characterized in that: A main control unit applied to a stamping production line, the stamping production line further comprising a data acquisition unit and a stamping device respectively connected to the main control unit; the method comprising: receiving stamping production data acquired by the data acquisition unit, the stamping production data comprising one or more of a drawing inflow, a die surface temperature, a lubricating oil amount, a closing height, a blank holding force, a forming force and a material performance parameter; Determine a quality performance prediction of the product based on the stamping production data, wherein the quality performance prediction includes at least one of a cracking prediction, a wrinkling prediction, and a hidden damage prediction; Determining data to be optimized from the stamping production data according to the quality performance prediction; Determine the stamping process optimization parameters according to the data to be optimized; The stamping process optimization parameters are sent to a stamping controller of the stamping equipment, so that the stamping controller adjusts the stamping action of the stamping equipment according to the stamping process optimization parameters.

2. The method according to claim 1, characterized in that The stamping production line further includes an eddy current detection device, and after the step of sending the stamping process optimization parameters to the stamping controller of the stamping device, further includes: Acquire surface images of stamping products; Respectively identifying the surface image by using a preset crack recognition model and a wrinkle recognition model to obtain the cracking condition and wrinkling condition of the stamping product; Determining whether the cracking condition and the wrinkling condition are both qualified; If so, the preset hidden damage detection model is used to detect whether the stamping product has hidden damage.

3. The method according to claim 2, characterized in that The stamping production line further includes eddy current detection equipment, and the step of detecting whether the stamping product has hidden damage by using a preset hidden damage detection model includes: Acquiring environmental data, electrical conductivity and magnetic permeability of stamping products, and changes in excitation current frequency and electrical impedance when the eddy current detection device detects stamping products; The excitation current frequency, the electrical impedance change, the electrical conductivity, the magnetic permeability and the environmental data are input into the hidden damage detection model to determine whether the stamping product has hidden damage.

4. The method according to claim 3, characterized in that The step of inputting the excitation current frequency, the electrical impedance change, the electrical conductivity, the magnetic permeability and the environmental data into the hidden damage detection model to determine whether the stamping product has hidden damage includes: The defect depth detection value is calculated by the defect depth estimation formula in the hidden flaw detection model. The mathematical form of the defect depth estimation formula is: Wherein, d is the defect depth detection value, f is the excitation current frequency, α is the attenuation index related to the material properties, C is a proportional constant, σ(T, RH) is the conductivity that changes with temperature T and relative humidity RH, μ(T, RH) is the magnetic permeability that changes with temperature T and relative humidity RH, ΔZ is the change in electrical impedance, n is a power factor used to adjust the responsiveness of the formula, and β is a coefficient that indicates the degree of influence of the change in electrical impedance on the defect depth estimation; It is determined whether the stamping product has hidden defects based on the defect depth detection value.

5. The method according to claim 2, characterized in that: After the step of detecting whether the stamping product has hidden damage by using a preset hidden damage detection model, the method further includes: If there is no hidden damage, obtain the product parameters after the stamping process parameters are adjusted; Determine the product qualification rate based on the product parameters; Determine whether the qualified rate of the product is lower than a set value; If so, the adjusted stamping process optimization parameters are obtained.

6. The method according to any one of claims 1 to 5, characterized in that: The step of determining a predicted quality performance of a product based on the stamping production data comprises: Cleaning the stamping production data; The cleaned stamping production data is input into the preset product quality prediction model to obtain the quality performance prediction.

7. The method according to claim 1, characterized in that The step of determining the stamping process optimization parameters according to the data to be optimized comprises: Obtain the finite element simulation model of stamping process; Determining initial stamping process parameters according to the data to be optimized and the stamping process finite element simulation model; The initial stamping process parameters are updated through the optimization algorithm and the stamping process finite element simulation model to obtain the stamping process optimization parameters.

8. The method according to claim 1, characterized in that The step of determining the data to be optimized from the stamping production data according to the quality performance prediction comprises: Determining the influence of each data in the stamping production data on the quality performance prediction; Data to be optimized are determined from the stamping production data according to the degree of influence.

9. A stamping production line, characterized in that: It includes a main control unit, a data acquisition unit and a stamping device, wherein the main control unit is connected to the data acquisition unit and the stamping device respectively, and the main control unit includes one or more processors and memories; The memory is coupled to the one or more processors, and the memory is used to store computer program codes, wherein the computer program codes include computer instructions, and the one or more processors call the computer instructions to enable the main control unit to execute the method according to any one of claims 1 to 8.

10. A computer program product comprising instructions, characterized in that When the computer program product is run on an electronic device, the electronic device is enabled to execute the method according to any one of claims 1 to 8.

Images