Automatic lubrication control method, system and storage medium for sheet metal drawing forming

Abstract

The present application relates to the technical field of sheet metal drawing forming control, and discloses an automatic lubrication control method, system and storage medium for sheet metal drawing forming. The method includes: performing zoning processing on the surface of the drawing die through a lubrication area division module and initializing the parameters of each area; collecting and preprocessing the process parameters in real time; obtaining lubrication requirement parameters through fuzzy control calculation; adjusting the pressure by using a proportional servo valve; performing online correction on the lubrication pressure curve; analyzing the lubrication parameters and storing them in a database. The present application intelligently adjusts the lubrication state of each area by monitoring and analyzing the process parameters in real time, so as to ensure the stability of the drawing forming quality.

Description

Technical Field

[0001] This application relates to the field of sheet metal drawing forming control, and particularly to an automatic lubrication control method, system and storage medium for sheet metal drawing forming. Background Art

[0002] During the sheet metal drawing forming process, the lubrication state directly affects the forming quality and die life. Traditional lubrication control methods mainly use constant pressure oil supply or simple closed-loop control to maintain a constant lubrication pressure and flow rate during the drawing process. With the improvement of industrial automation level, some adaptive lubrication control methods have been developed, such as zone oil supply control based on pressure sensor feedback, real-time control of adjusting the oil supply according to the displacement sensor signal, etc. These methods have improved the lubrication effect to a certain extent and reduced product defects.

[0003] However, the existing lubrication control methods have the following deficiencies: due to the dynamic changes of the stress state and friction conditions during the sheet metal deformation process, a single closed-loop control cannot accurately reflect the real-time lubrication requirements of each area. At the same time, traditional control methods lack in-depth analysis and excavation of process parameters and do not establish a mapping relationship between lubrication parameters and forming quality. In addition, the optimization process of control parameters often relies on empirical settings and lacks scientific data support, resulting in unstable lubrication effects and difficulty in adapting to the requirements of different working conditions. Summary of the Invention

[0004] This application provides an automatic lubrication control method, system and storage medium for sheet metal drawing forming, which is used to intelligently adjust the lubrication state of each area by real-time monitoring and analyzing process parameters, so as to ensure the stability of the drawing forming quality.

[0005] In a first aspect, the present application provides an automatic lubrication control method for sheet metal deep drawing forming. The automatic lubrication control method for sheet metal deep drawing forming includes: partitioning the surface of the deep drawing die through a lubrication area partitioning module to obtain multiple independent lubrication control areas including a flange area and a fillet area, and initializing the parameters of each lubrication control area according to the physical parameters in the workpiece material library to obtain the reference lubrication pressure value of each area; collecting the process parameters in real time according to the sensor network distributed in each lubrication control area, and performing filtering and normalization processing through a data preprocessing module to obtain a process state digital model; analyzing and calculating the stress state of each lubrication control area through a fuzzy control algorithm based on the process state digital model to obtain the real-time lubrication demand parameters of each area; based on the real-time lubrication demand parameters, using a proportional servo valve control system to perform pulsating adjustment on the lubrication pressure of each lubrication control area to form a dynamic lubrication pressure control curve; online evaluating the sheet thickness reduction rate and surface roughness, and correcting the dynamic lubrication pressure control curve according to the evaluation results to obtain optimized lubrication parameters; performing correlation analysis on the optimized lubrication parameters, establishing a lubrication parameter optimization model, and storing the lubrication parameter optimization model in the process parameter database.

[0006] In a second aspect, the present application provides an automatic lubrication control system for sheet metal deep drawing forming. The automatic lubrication control system for sheet metal deep drawing forming includes:

[0007] A partitioning module, configured to partition the surface of the deep drawing die through a lubrication area partitioning module to obtain multiple independent lubrication control areas including a flange area and a fillet area, and initialize the parameters of each lubrication control area according to the physical parameters in the workpiece material library to obtain the reference lubrication pressure value of each area;

[0008] A collection module, configured to collect the process parameters in real time according to the sensor network distributed in each lubrication control area, and perform filtering and normalization processing through a data preprocessing module to obtain a process state digital model;

[0009] A calculation module, configured to analyze and calculate the stress state of each lubrication control area through a fuzzy control algorithm based on the process state digital model to obtain the real-time lubrication demand parameters of each area;

[0010] An adjustment module, configured to perform pulsating adjustment on the lubrication pressure of each lubrication control area based on the real-time lubrication demand parameters by using a proportional servo valve control system to form a dynamic lubrication pressure control curve;

[0011] A correction module, configured to online evaluate the sheet thickness reduction rate and surface roughness, and correct the dynamic lubrication pressure control curve according to the evaluation results to obtain optimized lubrication parameters;

[0012] An analysis module for performing correlation analysis on the optimized lubrication parameters, establishing a lubrication parameter optimization model, and storing the lubrication parameter optimization model in a process parameter database.

[0013] The third aspect of the present application provides a computer-readable storage medium storing instructions that, when run on a computer, cause the computer to execute the automatic lubrication control method for sheet metal drawing forming described above.

[0014] In the technical solution provided by the present application, through the lubrication area division module, the surface of the drawing die is partitioned, realizing precise lubrication control of key parts such as the flange area and the fillet area, avoiding the problem of uneven lubrication caused by the traditional single oil supply method. At the same time, according to the physical parameters in the workpiece material library, the parameters of each lubrication control area are initialized, ensuring the scientificity and rationality of the reference lubrication pressure value. By arranging a sensor network in each lubrication control area to collect process parameters in real time, and through the data preprocessing module for filtering and standardization processing, an accurate digital model of the process state is established, providing a reliable data basis for the dynamic adjustment of lubrication parameters. Using the fuzzy control algorithm to analyze and calculate the stress state of each lubrication control area, accurately obtaining the real-time lubrication demand parameters of each area, reflecting the intelligence and self-adaptability of the control strategy. Using the proportional servo valve control system to pulsatingly adjust the lubrication pressure of each lubrication control area, forming a dynamic lubrication pressure control curve, realizing precise regulation of the lubrication pressure. By online evaluating the sheet thickness reduction rate and surface roughness, and correcting the dynamic lubrication pressure control curve according to the evaluation results, the optimized lubrication parameters are obtained, ensuring the stability of the forming quality. Finally, correlation analysis is performed on the optimized lubrication parameters, establishing a lubrication parameter optimization model and storing it in the process parameter database, realizing the continuous optimization of control parameters and experience accumulation, and providing data support for lubrication control under different working conditions. The entire control process realizes the full-process automation from parameter acquisition, data processing to control execution, significantly improving the processing quality and production efficiency of sheet metal drawing forming. Description of the Drawings

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for description in the embodiments. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0016] Figure 1 It is a schematic diagram of an embodiment of the automatic lubrication control method for sheet metal drawing forming in an embodiment of the present application;

[0017] Figure 2Schematic diagram of the influence of forced lubrication on the forming force in the embodiments of the present application;

[0018] Figure 3 Schematic diagram of an embodiment of the automatic lubrication control system for sheet metal drawing forming in the embodiments of the present application. Detailed implementation manners

[0019] The embodiments of the present application provide an automatic lubrication control method, system and storage medium for sheet metal drawing forming. Terms such as "first", "second", "third", "fourth", etc. (if any) in the description, claims and above-mentioned drawings of the present application are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments described here can be implemented in an order other than those illustrated or described here. In addition, the terms "include" or "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0020] For ease of understanding, the specific process of the embodiments of the present application will be described below. Please refer to Figure 1 One embodiment of the automatic lubrication control method for sheet metal drawing forming in the embodiments of the present application includes:

[0021] Step S101: The surface of the drawing die is partitioned by a lubrication area partitioning module to obtain multiple independent lubrication control areas including a flange area and a fillet area, and the parameters of each lubrication control area are initialized according to the physical parameters in the workpiece material library to obtain the reference lubrication pressure value of each area;

[0022] Step S102: The process parameters are collected in real time according to the sensor network distributed in each lubrication control area, and are subjected to filtering and standardization processing by a data preprocessing module to obtain a process state digital model;

[0023] Step S103: Based on the process state digital model, the stress state of each lubrication control area is analyzed and calculated by a fuzzy control algorithm to obtain the real-time lubrication demand parameters of each area;

[0024] Step S104: Based on the real-time lubrication demand parameters, the lubrication pressure of each lubrication control area is pulsatingly adjusted by a proportional servo valve control system to form a dynamic lubrication pressure control curve;

[0025] Step S105: Online evaluate the sheet thinning rate and surface roughness, and modify the dynamic lubrication pressure control curve according to the evaluation results to obtain optimized lubrication parameters;

[0026] Step S106: Conduct a correlation analysis on the optimized lubrication parameters, establish an optimized lubrication parameter model, and store the optimized lubrication parameter model in the process parameter database.

[0027] It can be understood that the execution subject of this application can be an automatic lubrication control system for sheet drawing forming, or a terminal or a server. Specifically, it is not limited here. In this embodiment of the application, the server is taken as the execution subject for illustration.

[0028] Specifically, the lubrication area division module is used to partition the surface of the drawing die, identify the areas on the surface of the drawing die according to geometric features, and divide the surface of the drawing die into a flange area and a fillet area. The flange area is located at the edge of the sheet and bears the maximum deformation, and the fillet area is located in the transition area of the die cavity. An oil circuit network is divided according to the lubrication requirements in each area, and each oil circuit is provided with an independent pressure sensor and flow sensor. Extract the friction coefficient, yield strength, and hardening index of the sheet to be processed from the workpiece material library to generate a material characteristic data set. According to the geometric features of each area and the material characteristic data set, numerically analyze the stress state of the sheet in each area, and calculate the stress distribution through finite element analysis. According to the stress distribution, use the weighted distribution method to allocate the initial pressure coefficient to each oil circuit, and calculate the reference lubrication pressure value for each area. The calculation of the reference lubrication pressure value needs to consider the deformation degree, friction state, and material characteristics of each area, and write the reference lubrication pressure value into the control parameter table corresponding to each area through the PLC control unit. When the sensor network collects the process parameters in real time, the pressure sensor collects the real-time pressure data of each area, the flow sensor monitors the flow state of the lubricating oil, the displacement sensor tracks the deformation degree of the sheet, and the force sensor measures the forming force during the drawing process. As Figure 2 shown, it is a schematic diagram of the influence of forced lubrication on the forming force in this embodiment of the application; among them, under the same process parameters such as the shape of the die and blank, and the blank holding force, when the punch displacement is the same, a smaller forming load indicates better lubrication conditions, and poor friction conditions often lead to an increase in the forming load. From Figure 2 the curve in it can be seen that in the initial stage of drawing, the deformation degree of the sheet in the flange area is small, and the influence of different lubrication conditions on the forming load is not obvious. As the sheet in the flange area flows into the center of the die cavity, the tangential compressive stress it receives becomes larger and larger, wrinkling and thickening become more and more serious, the friction environment becomes worse and worse, and the influence of different lubrication conditions on the forming load begins to become obvious. In addition, from Figure 2It can be seen that the maximum load under each lubrication condition is around 90 kN, because this is the bearing limit of the selected material in the forming with this geometric parameter. Once the load limit is exceeded, fracture will occur. Therefore, it is not scientific to simply judge the lubrication performance intuitively from the maximum load value, but it can be evaluated by comparing the load values at the same punch stroke. When the blank holder force is 20 kN and the punch stroke is 30 mm, after applying forced lubrication at 5 MPa and 9 MPa, the forming forces are reduced by 8.0% and 8.6% respectively compared with no forced lubrication; when the blank holder force is 35 kN and the punch stroke is 30 mm, after applying forced lubrication at 5 MPa and 9 MPa, the forming forces are reduced by 2.4% and 3.5% respectively compared with no forced lubrication; when the blank holder force is 50 kN and the punch stroke is 30 mm, after applying forced lubrication at 5 MPa and 9 MPa, the forming forces are reduced by 3.4% and 8.9% respectively. Under the conditions of blank holder forces of 20 kN and 50 kN, after forced lubrication, the reduction amplitude of the forming load is relatively large, reaching up to 8.9%. The test results show that applying forced lubrication during the drawing process helps to reduce the forming force, and the greater the forced lubrication pressure within the test range, the greater the reduction amplitude of the forming force.

[0029] The original data collected by the sensor is subjected to noise removal by a Butterworth filter to obtain the filtered process parameter data. The Butterworth filter has the flattest amplitude-frequency characteristic and can effectively suppress high-frequency noise by setting the cut-off frequency. The filtered process parameter data is classified according to pressure data, flow data, displacement data and force data to form a classified data group. Each type of data in the classified data group is normalized respectively to obtain the standardized process parameters. The standardized process parameters are correlated according to each lubrication control area to construct a process parameter correlation matrix. The process parameter correlation matrix is reduced in dimension by principal component analysis to obtain a process state digital model.

[0030] According to the process state digital model, the pressure data, flow data, and force data of each lubrication control area are extracted as fuzzy control input variables. The pressure data, flow data, and force data are fuzzified according to three levels: low, medium, and high to obtain fuzzy sets. The fuzzy sets are defuzzified through the weighted average method to obtain the stress state values of each lubrication control area. The stress state values are subjected to a ratio operation with the reference lubrication pressure value to form lubrication pressure deviation data. The lubrication pressure deviation data is incrementally calculated to generate a lubrication pressure compensation value. The lubrication pressure compensation value is superimposed on the reference lubrication pressure value to obtain the real-time lubrication demand parameters of each area. Based on the real-time lubrication demand parameters, the opening degrees of the proportional servo valves in each lubrication control area are calculated to obtain valve opening control data. The valve opening control data is converted into a PWM control signal to generate valve pulsation frequency and duty cycle data. The PWM control signal adjusts the output power by changing the pulse width to achieve precise control of the valve opening. The valve pulsation frequency and duty cycle data are digitally-to-analog converted to output a valve control voltage signal. The actual output pressures of the proportional servo valves in each lubrication control area are collected to form pressure feedback data. The pressure feedback data and the real-time lubrication demand parameters are subjected to a deviation calculation to generate a pressure compensation signal. The pressure compensation signal and the pressure feedback data are arranged in a time series to form a dynamic lubrication pressure control curve.

[0031] During the sheet metal drawing process, the thickness of each measurement point of the sheet is collected by an ultrasonic thickness sensor to obtain sheet thickness distribution data. The difference between the sheet thickness distribution data and the initial thickness of the sheet is calculated to obtain the thinning data of each measurement point. The thinning data is normalized to form sheet thinning rate data. The surface roughness measurement values of the sheet are collected to generate surface quality data. The sheet thinning rate data and the surface quality data are weighted and superimposed to generate a quality evaluation parameter. The dynamic lubrication pressure control curve is proportionally corrected by the quality evaluation parameter to obtain optimized lubrication parameters. When performing a correlation analysis on the optimized lubrication parameters, first, the pressure values, flow values, and time series data are extracted from the optimized lubrication parameters and grouped according to the lubrication control area. The correlation degree between the pressure value and the flow value in the grouped data is calculated through the Pearson correlation coefficient to generate a parameter correlation matrix. The parameter correlation matrix is eigen-decomposed to obtain the lubrication parameter eigenvector. The lubrication parameter eigenvector and the reference lubrication pressure value of each lubrication control area are subjected to a deviation analysis to form a pressure correction coefficient. The pressure correction coefficient is numerically fitted through the weighted average method to obtain a lubrication pressure control equation. Based on the lubrication pressure control equation, a least squares method is used to establish an optimized lubrication parameter model. The optimized lubrication parameter model and the corresponding process parameters are encoded and stored in the process parameter database.

[0032] For example: In practical applications, take the deep drawing of a certain steel plate as an example. First, divide the deep drawing die into zones. Set 8 oil circuits in the flange zone and 6 oil circuits in the fillet zone. Extract the material parameters of the steel plate: the friction coefficient is 0.15, the yield strength is 235 MPa, and the hardening index is 0.21. After calculating the stress distribution in each zone, obtain the initial pressure coefficients: 1.2 in the flange zone and 1.0 in the fillet zone. Subsequently, according to the real-time data collected by the sensors, remove the high-frequency noise through Butterworth filtering, and normalize and standardize the data. Calculate the stress states in each zone through the fuzzy control algorithm, and generate a pressure compensation value after comparing with the reference pressure. The proportional servo valve adjusts the opening according to the compensation value and is controlled by a PWM signal to achieve precise pressure regulation. After processing the data of the sheet thinning rate and surface roughness, correct the dynamic pressure curve. Establish an optimization model for lubrication parameters through correlation analysis to achieve precise control of the deep drawing process.

[0033] In the embodiment of the present application, through the lubrication zone division module, the surface of the deep drawing die is divided into zones, realizing precise lubrication control of key parts such as the flange zone and the fillet zone, avoiding the problem of uneven lubrication caused by the traditional single oil supply method. At the same time, according to the physical parameters in the workpiece material library, the parameters of each lubrication control zone are initialized to ensure the scientificity and rationality of the reference lubrication pressure value. The process parameters are collected in real time through the sensor network arranged in each lubrication control zone, and after being filtered and standardized by the data preprocessing module, an accurate digital model of the process state is established, providing a reliable data basis for the dynamic adjustment of lubrication parameters. The fuzzy control algorithm is used to analyze and calculate the stress states in each lubrication control zone, accurately obtaining the real-time lubrication demand parameters in each zone, reflecting the intelligence and self-adaptability of the control strategy. The proportional servo valve control system is used to pulsatingly adjust the lubrication pressure in each lubrication control zone to form a dynamic lubrication pressure control curve, realizing precise regulation of the lubrication pressure. By online evaluating the sheet thinning rate and surface roughness, and correcting the dynamic lubrication pressure control curve according to the evaluation results, the optimized lubrication parameters are obtained, ensuring the stability of the forming quality. Finally, perform a correlation analysis on the optimized lubrication parameters, establish an optimization model for lubrication parameters and store it in the process parameter database, realizing the continuous optimization of control parameters and the accumulation of experience, and providing data support for lubrication control under different working conditions. The entire control process realizes the full-process automation from parameter acquisition, data processing to control execution, significantly improving the processing quality and production efficiency of sheet metal deep drawing.

[0034] In a specific embodiment, the process of executing step S101 may specifically include the following steps:

[0035] (1) Identify the zones on the surface of the deep drawing die according to geometric features, and divide the surface of the deep drawing die into a flange zone and a fillet zone;

[0036] (2) Divide the oil circuit network in each area according to the lubrication requirements, and set independent pressure sensors and flow sensors for each oil circuit;

[0037] (3) Extract the friction coefficient, yield strength, and hardening index of the to-be-machined sheet from the workpiece material library to generate a material property dataset;

[0038] (4) Calculate the stress distribution in each area according to the geometric characteristics and material property dataset of each area;

[0039] (5) Based on the stress distribution, assign an initial pressure coefficient to each oil circuit, and calculate the reference lubrication pressure value for each area;

[0040] (6) Write the reference lubrication pressure value into the control parameter table corresponding to each area through the PLC control unit.

[0041] Specifically, when performing area recognition on the surface of the drawing die, a three-dimensional digital model is established, and the die surface is divided into a flange area and a fillet area through geometric feature analysis. The flange area is located at the outer edge of the sheet, mainly controlling the flow of the sheet; the fillet area is the key transition area for sheet forming; the area division adopts the curvature analysis method, and the boundary is determined by calculating the principal curvature values of each point on the die surface. A lubricating oil circuit network is set in each area, and the oil circuit spacing is determined according to the deformation gradient. The oil circuits are densely arranged in the area with large deformation, and the spacing is appropriately increased in the area with small deformation. Each oil circuit is equipped with an independent pressure sensor and a flow sensor. The measurement range of the pressure sensor is 0 - 20 MPa, the accuracy is 0.1%, and the measurement range of the flow sensor is 0 - 15 L / min. When extracting material parameters from the workpiece material library, it mainly includes three key parameters: friction coefficient, yield strength, and hardening index. The friction coefficient reflects the friction state between the material and the die, usually obtained through a slider friction test; the yield strength represents the stress value when the material starts plastic deformation, determined by a tensile test; the hardening index describes the work hardening characteristics of the material, calculated from the true stress - true strain curve. These parameters form a material property dataset, providing basic data for subsequent stress calculations.

[0042] The calculation of the stress distribution in each area is based on the finite element analysis method. A contact analysis model of the sheet and the die is established, and the parameters in the material property dataset are imported into the model. The calculation process includes steps such as establishing a geometric model, dividing grid elements, setting boundary conditions, defining contact pairs, and applying loads. Through iterative calculations, the stress distribution nephogram of each area is obtained, with a focus on the radial stress in the flange area and the equivalent stress in the fillet area.

[0043] The process of calculating the reference lubrication pressure value based on the stress distribution can be expressed as:

[0044]

[0045] Wherein: is the reference lubrication pressure value; is the lubrication pressure adjustment coefficient; is the regional deformation coefficient; is the material correction factor; is the weight coefficient of the i-th stress component; is the value of the i-th stress component; is the local strain rate coefficient; n is the number of stress components participating in the calculation.

[0046] After the PLC control unit receives the data of the reference lubrication pressure value, it first performs data format conversion, converting the floating-point number into a 16-bit integer data. Then, according to the preset storage address, the data is written into the corresponding data registers of each region. The data writing adopts the batch transfer mode, and the communication between the PLC and the host computer is realized through the Modbus-TCP protocol. In addition to the reference lubrication pressure value, the control parameter table also includes parameters such as the upper and lower pressure limits and the alarm threshold.

[0047] For example: for the deep drawing forming process of a certain automotive panel. First, establish a three-dimensional model of the mold, and divide the mold surface into three main regions through curvature analysis. 12 circular oil circuits are set in the flange region, and 8 in the fillet region. The oil circuit spacing is 30 mm in the high-stress region and 50 mm in the low-stress region. Extract the sheet metal parameters from the material library: the friction coefficient is 0.12 (measured by the slider friction test), the yield strength is 320 MPa (obtained from the tensile test), and the hardening index is 0.24 (fitted from the stress-strain curve). The finite element analysis uses quadrilateral shell elements to divide the mesh, and the element size is 3 mm to obtain the stress distribution nephogram of each region. Based on the stress distribution data, the reference lubrication pressure value in the flange region is calculated to be 12 MPa, and 15 MPa in the fillet region. After the data is format-converted, it is written into the D100 - D115 data register group of the PLC.

[0048] In a specific embodiment, the process of executing step S102 may specifically include the following steps:

[0049] (1) Collect pressure data, flow data, displacement data, and force data from the sensor network to generate the original process parameter data stream;

[0050] (2) Remove the noise from the original process parameter data stream through a Butterworth filter to obtain the filtered process parameter data;

[0051] (3) Classify the filtered process parameter data according to pressure data, flow data, displacement data, and force data to form a classified data group;

[0052] (4)Normalize the pressure data, flow data, displacement data, and force data in the classified data group respectively to obtain standardized process parameters;

[0053] (5)Associate the standardized process parameters according to each lubrication control area to construct a process parameter association matrix;

[0054] (6)Perform dimensionality reduction on the process parameter association matrix through principal component analysis to obtain a process state digital model.

[0055] Specifically, during the process of the sensor network collecting process parameters, the pressure sensor continuously collects the pressure signals of each oil circuit with a sampling frequency of 1000Hz and a measurement range of 0 - 20MPa; the flow sensor collects the flow state data of the lubricating oil with a sampling frequency of 500Hz and a range of 0 - 15L / min; the displacement sensor tracks the deformation degree of the sheet with a sampling frequency of 1000Hz and a measurement range of 0 - 300mm; the force sensor measures the forming force during the drawing process with a sampling frequency of 1000Hz and a range of 0 - 1000kN. The data collected by each sensor generates digital signals after high-speed A / D conversion, forming an original process parameter data stream. When removing noise from the original data, a Butterworth filter is used, which has the flattest amplitude-frequency characteristic. The cut-off frequency of the filter is set separately according to the characteristics of various types of data: 200Hz for pressure data, 100Hz for flow data, 200Hz for displacement data, and 200Hz for force data. The order of the filter is set to 4th order, and the original data is filtered by calculating the response function. For pressure data, the sampling signal is passed through a high-pass filter to remove the DC component and then through a low-pass filter to suppress high-frequency noise. The flow data mainly has power frequency interference and is processed using a band-stop filter. The displacement data and force data need to retain the effective signals with rapid changes while removing high-frequency noise interference.

[0056] The filtered process parameter data is classified and sorted according to different types. The pressure data contains the real-time pressure values of each oil circuit, constituting a pressure data matrix; the flow data records the flow rate changes of each oil circuit, forming a flow data matrix; the displacement data describes the deformation amounts of each measurement point of the sheet, establishing a displacement data matrix; the force data characterizes the load changes during the forming process, generating a force data matrix. The data points in each type of data matrix are aligned according to the time stamp to ensure the timeliness of the data. When normalizing the classified data, the maximum-minimum normalization method is used. First, calculate the maximum and minimum values of each type of data, and then map the data to the [0, 1] interval according to the normalization formula. The normalization of pressure data considers the upper limit of the designed pressure of each oil circuit, the normalization of flow data is based on the maximum allowable flow rate, the normalization of displacement data refers to the maximum deformation amount, and the normalization of force data is based on the upper limit value of the forming force. The normalized data eliminates the influence of dimensions and facilitates the comprehensive analysis of different types of data.

[0057] When the standardized process parameters are analyzed in relation to each lubrication control area, the corresponding relationship of the data is first determined. The pressure data, flow data, displacement data, and force data within the same area are combined to form the characteristic vector of that area. The characteristic vectors of each area constitute the process parameter correlation matrix, where the rows of the matrix represent different moments in time and the columns represent different parameter types. The correlation degree between parameters is evaluated by calculating the correlation coefficient, and the mapping relationship between parameters is established. When performing dimensionality reduction on the process parameter correlation matrix using principal component analysis, the covariance matrix of the data is first calculated, and then the eigenvalues and eigenvectors are solved. The eigenvectors are sorted according to the magnitude of the eigenvalues, and the principal components with a cumulative contribution rate of more than 85% are selected. The original high-dimensional data is projected onto the principal component space through principal component transformation to obtain the dimensionality-reduced process state digital model. This model retains the main characteristics of the original data while reducing data redundancy.

[0058] For example: During the deep drawing process of a certain automotive chassis part, the sensor network collected 50,000 groups of original data points within 10 seconds. This data includes pressure data (sampling frequency 1000Hz) of 12 oil circuits, flow data (sampling frequency 500Hz), displacement data of 16 displacement measurement points (sampling frequency 1000Hz), and force data of 4 force sensors (sampling frequency 1000Hz). The original data is processed using a fourth-order Butterworth filter. The amplitude of the high-frequency noise in the oil pressure data is reduced from ±0.5MPa to ±0.05MPa, and the fluctuation of the flow data is reduced from ±5L / min to ±0.5L / min. The filtered data is grouped by type to form 5 data matrices. Through maximum-minimum normalization, the pressure data (0 - 20MPa), flow data (0 - 15L / min), displacement data (0 - 200mm), and force data (0 - 1000kN) are mapped to the unified interval [0, 1]. A process parameter correlation matrix (50,000×44 dimensions) is established, and after dimensionality reduction by principal component analysis, a process state digital model containing 7 principal components is obtained, with a cumulative contribution rate of 87%.

[0059] In a specific embodiment, the process of executing step S103 may specifically include the following steps:

[0060] (1) Extract the pressure data, flow data, and force data of each lubrication control area from the process state digital model as the fuzzy control input variables;

[0061] (2) Fuzzify the pressure data, flow data, and force data according to three levels: low, medium, and high to obtain the fuzzy sets;

[0062] (3) Perform defuzzification operations on the fuzzy sets through the weighted average method to obtain the stress state values of each lubrication control area;

[0063] (4) Perform a ratio operation on the stress state value and the reference lubrication pressure value to form lubrication pressure deviation data;

[0064] (5) Perform an incremental calculation on the lubrication pressure deviation data to generate a lubrication pressure compensation value;

[0065] (6) Superimpose the lubrication pressure compensation value and the reference lubrication pressure value to obtain the real-time lubrication demand parameters for each region.

[0066] Specifically, when extracting data from the process state digital model, for each lubrication control region, organize the pressure data, flow data, and force data into a feature array as the input variables of fuzzy control. Among them, the pressure data includes the time-series data of the real-time pressure values of each oil circuit, the flow data records the change process of the lubricating oil flow, and the force data characterizes the load state during the deep drawing forming process. These data are aligned according to the sampling time to form a data sequence. When performing fuzzy processing on the extracted data, establish membership functions for the three linguistic variables of pressure, flow, and force. The pressure data is divided into three levels: low pressure (0 - 8 MPa), medium pressure (6 - 14 MPa), and high pressure (12 - 20 MPa) according to the actual measurement values, and the triangular membership function is used to describe the fuzzy relationship; the flow data is divided into three levels: low flow (0 - 5 L / min), medium flow (4 - 10 L / min), and high flow (8 - 15 L / min), and the trapezoidal membership function is used; the force data is divided into three levels: low load (0 - 200 kN), medium load (150 - 750 kN), and high load (700 - 1000 kN), and the Gaussian membership function is used. The membership degree values of each data point at different levels are calculated through the membership function to form a fuzzy set.

[0067] The defuzzification operation of the fuzzy set adopts the weighted average method, and its calculation formula is:

[0068]

[0069] Where: is the stress state value; is the membership degree value of the i-th level of the pressure data; is the membership degree value of the j-th level of the flow data; is the membership degree value of the k-th level of the force data; is the pressure weight coefficient; is the flow weight coefficient; is the force weight coefficient.

[0070] The ratio operation expression of the stress state value and the reference lubrication pressure value is:

[0071]

[0072] Where: is the lubrication pressure deviation; is the stress state value of the r-th region; is the reference lubrication pressure value of the r-th region; is the stress compensation coefficient; is the regional deformation coefficient; is the pressure correction factor; is the global adjustment coefficient; n is the number of lubrication control regions.

[0073] When performing incremental calculation on the lubrication pressure deviation data, the dynamic step method is used to calculate the pressure compensation increment. The calculation of the compensation value takes into account the magnitude, change rate, and cumulative amount of the deviation, and dynamically adjusts the compensation step according to different working conditions. The calculated lubrication pressure compensation value is superimposed on the reference lubrication pressure value to obtain the real-time lubrication demand parameters for each region.

[0074] For example: During the deep drawing forming process of the inner panel of an automobile door, real-time data of the flange area are extracted from the process state digital model, including the oil circuit pressure of 10 MPa, the lubricating oil flow rate of 8 L / min, and the forming force of 650 kN. These data are substituted into the fuzzy rule base for calculation to obtain the membership degrees of the pressure data in the medium pressure level of 0.7 and in the high pressure level of 0.3; the membership degrees of the flow rate data in the medium flow rate level of 0.8 and in the high flow rate level of 0.2; the membership degrees of the force data in the medium load level of 0.6 and in the high load level of 0.4. The stress state value of the flange area is calculated by the weighted average method, and its ratio operation with the reference lubrication pressure value of 12 MPa forms the lubrication pressure deviation data. The compensation value of 1.5 MPa is calculated according to the deviation data, and the real-time lubrication demand pressure of 13.5 MPa is obtained after superimposing it on the reference pressure. The entire calculation process reflects the logical relationship between the data and realizes the precise regulation of the lubrication parameters.

[0075] In a specific embodiment, the process of executing step S104 may specifically include the following steps:

[0076] (1) Calculate the opening of the proportional servo valve for each lubrication control region according to the real-time lubrication demand parameters to obtain the valve opening control data;

[0077] (2) Convert the valve opening control data into a PWM control signal to generate the valve pulsation frequency and duty ratio data;

[0078] (3) Perform digital-to-analog conversion on the valve pulsation frequency and duty ratio data and output the valve control voltage signal;

[0079] (4) Collect the actual output pressure of the proportional servo valve for each lubrication control region to form the pressure feedback data;

[0080] (5) Calculate the deviation between the pressure feedback data and the real-time lubrication demand parameters to generate a pressure compensation signal;

[0081] (6) Arrange the pressure compensation signal and the pressure feedback data in a time series to form a dynamic lubrication pressure control curve.

[0082] Specifically, for the calculation of the proportional servo valve opening, a mathematical model of the valve opening is first established using the real-time lubrication demand parameters. The valve opening calculation formula is:

[0083]

[0084] Where: is the valve opening control quantity; is the m-th lubrication demand component; is the pressure response coefficient; is the time decay factor; is the n-th flow component; is the flow weight coefficient; is the pulsation angular frequency; M and N are the numbers of pressure and flow components; t is the time variable.

[0085] The pressure deviation calculation expression is:

[0086]

[0087] Where: is the pressure compensation signal; is the i-th feedback pressure value; is the feedback gain coefficient; is the time weight factor; is the pressure feedback reference value; is the global compensation coefficient; I is the number of feedback data points.

[0088] In the actual lubrication control process of sheet metal drawing forming, when calculating the opening of the proportional servo valve in each lubrication control area according to the real-time lubrication demand parameters, the corresponding relationship between the valve opening and the flow rate is established. The opening range of the proportional servo valve is 0 - 100%, and the corresponding flow rate range is 0 - 15 L / min. The lubrication demand parameters are converted into target flow rate values through the flow characteristic curve, and then the required opening value is calculated according to the valve characteristic curve. For the case of multiple oil circuits in parallel, the pressure balance needs to be considered, and the opening of each oil circuit is calculated coordinately. When converting the valve opening control data into a PWM control signal, a PWM control method based on frequency modulation is adopted. The reference frequency of the PWM signal is set to 1 kHz, and the duty cycle range is 0 - 100%. The valve opening value is converted into a duty cycle through linear mapping, with an opening of 0% corresponding to a duty cycle of 0% and an opening of 100% corresponding to a duty cycle of 100%. The frequency of the PWM signal can be adjusted according to the dynamic characteristics of the valve. For valves with faster response, a higher frequency is used, while for valves with slower response, the frequency is reduced.

[0089] The digital-to-analog conversion of the valve pulsation frequency and duty cycle data uses a 16-bit DAC converter to convert the digital quantity into an analog voltage signal of 0 - 10 V. Voltage compensation is performed according to the control characteristics of the valve during the conversion process to ensure a linear relationship between the control signal and the valve opening. The update frequency of the DAC is set to 10 kHz to meet the requirements of the valve's fast response. The valve control voltage signal drives the proportional servo valve coil after current amplification to achieve precise control of the valve opening. The acquisition of the pressure feedback data is completed by pressure sensors installed on each oil circuit. The range of the pressure sensor is 0 - 20 MPa, the sampling frequency is 1 kHz, and the resolution is 0.01 MPa. The collected pressure signal forms a digital quantity after A / D conversion, constituting the pressure feedback data sequence. The pressure feedback data includes the real-time pressure values of each oil circuit, the acquisition time, and the channel identifier, which are used to monitor the change of the lubrication pressure in real time.

[0090] The deviation calculation between the pressure feedback data and the real-time lubrication demand parameters adopts a dynamic comparison method. The pressure feedback data is aligned according to the acquisition time, and the difference from the lubrication demand parameters is calculated. The difference data is subjected to moving average filtering to eliminate the influence of instantaneous fluctuations. According to the magnitude and change trend of the deviation, the required pressure compensation amount is calculated. The generation of the pressure compensation signal considers the dynamic response characteristics of the pressure and uses a proportional-integral-derivative (PID) control algorithm for calculation. The pressure compensation signal is temporally correlated with the pressure feedback data to establish a dynamic lubrication pressure control curve. The control curve records the change process of the pressure set value, the actual pressure value, and the compensation amount, reflecting the dynamic adjustment process of the lubrication pressure. The control curve is analyzed to extract key characteristic parameters as the basis for optimizing the lubrication control strategy.

[0091] For example, in the deep drawing of a certain automotive chassis part, the real-time lubrication required pressure set in the flange area is 15 MPa. According to this pressure value, the opening of the proportional servo valve is calculated to be 75%, generating a corresponding PWM control signal with a frequency of 1 kHz and a duty cycle of 75%. After D / A conversion, a control voltage of 7.5 V is output. The actual pressure collected by the pressure sensor is 14 MPa, with a deviation of 1 MPa from the set value. Through PID control calculation, a compensation amount of 0.8 MPa is obtained and superimposed on the original control signal. The data before and after pressure compensation form a dynamic control curve, recording the process of gradually adjusting the pressure from 14 MPa to the target value of 15 MPa. The entire control process reflects the working principle of closed-loop feedback and realizes the precise adjustment of lubrication pressure.

[0092] In a specific embodiment, the process of executing step S105 may specifically include the following steps:

[0093] (1) Collect the thickness of each measurement point of the sheet through an ultrasonic thickness sensor to obtain the sheet thickness distribution data;

[0094] (2) Calculate the difference between the sheet thickness distribution data and the initial thickness of the sheet to obtain the thinning data of each measurement point;

[0095] (3) Perform normalization operation on the thinning data to form the sheet thinning rate data;

[0096] (4) Collect the surface roughness measurement value of the sheet to generate surface quality data;

[0097] (5) Perform weighted superposition processing on the sheet thinning rate data and the surface quality data to generate a quality evaluation parameter;

[0098] (6) Perform proportional correction on the dynamic lubrication pressure control curve by the quality evaluation parameter to obtain the optimized lubrication parameter.

[0099] Specifically, when the ultrasonic thickness measurement sensor collects the thickness of the sheet, the measurement points are arranged according to a preset measurement grid. The measurement grid adopts a polar coordinate distribution method, and the measurement area is divided radially and circumferentially from the center of the sheet. Radially, it is divided into 8 measurement circles, with 12 measurement points arranged on each measurement circle, forming a total of 96 measurement points. The ultrasonic thickness measurement sensor uses a double crystal probe, with a working frequency of 10 MHz, a measurement accuracy of 0.01 mm, and a measurement range of 0.4 - 5 mm. During measurement, the probe is kept perpendicular to the surface of the sheet, and good transmission of ultrasonic waves is achieved through a coupling agent. Multiple samples are taken for each measurement point and averaged to obtain the actual thickness value of that point. The thickness data of all measurement points are stored according to the position coordinates to form the sheet thickness distribution data. When calculating the difference between the sheet thickness distribution data and the initial thickness, first read the nominal initial thickness value of the sheet and use this value as the reference thickness. Subtract the reference thickness from the actual thickness value of each measurement point to obtain the absolute thinning amount of that point. During the calculation process, the position information of the measurement point is recorded simultaneously to establish the corresponding relationship between the thinning amount and the position. For points with abnormal measurement values, interpolation correction is performed using the data of surrounding points to ensure the continuity of the thinning data.

[0100] When performing normalization calculation on the thinning data, the maximum thinning amount is used as the normalization reference. Calculate the maximum and minimum thinning amounts among all measurement points, and map the thinning amount of each measurement point to the interval [0, 1]. The normalization calculation takes into account the distribution characteristics of the thinning. For areas with concentrated thinning, piecewise linear mapping is used to improve the data resolution. The normalized data reflects the proportional relationship of each measurement point relative to the maximum thinning amount, forming the sheet thinning rate data. The surface roughness of the sheet is measured using a portable roughness meter, with a measurement range of Ra 0.05 - 10 μm, an evaluation length of 4 mm, and a sampling length of 0.8 mm. Representative areas are selected on the sheet surface for measurement, including areas with large deformation and small deformation. Multiple samples are taken at each measurement area to obtain the average roughness value of that area. After the roughness data is filtered to remove outliers, a surface quality data matrix is formed according to the measurement area.

[0101] The weighted superposition of the sheet thinning rate data and the surface quality data uses the zonal weight method. According to the process requirements, different weight coefficients are assigned to different areas. The thinning rate weight is higher in areas with large deformation, and the roughness weight is higher in areas with high surface quality requirements. The comprehensive quality evaluation parameter of each area is calculated through weighted summation. The quality evaluation parameter comprehensively reflects the thinning state and surface quality condition of the sheet.

[0102] The calculation formula for correcting the dynamic lubrication pressure control curve by the quality evaluation parameter is:

[0103]

[0104] Wherein: is the optimized lubrication parameter; is the evaluation parameter of the k-th region; is the regional hardening coefficient; is the strain rate factor; is the material yield coefficient; is the friction compensation factor; is the l-th quality eigenvalue; is the pressure correction coefficient; is the dynamic response frequency; K and L are the number of regions and the number of characteristics respectively; t is the time variable.

[0105] For example: During the deep drawing forming process of the front fender of an automobile, the workpiece is measured by ultrasonic thickness measurement. 8 measurement circles are arranged in the radial direction, with 12 points in each circle, for a total of 96 measurement points. The difference between the measured thickness data and the initial thickness of 2.0 mm is calculated to obtain the thinning amount of each point. The thinning rate distribution is obtained through normalization processing, and at the same time, the surface roughness value is measured. According to the process requirements, a weight of 0.7 is assigned to the thinning rate of the fillet region, and a weight of 0.6 is assigned to the surface quality of the flange region, and the quality evaluation parameters of each region are calculated. The quality evaluation parameters are substituted into the correction formula to correct the original lubrication pressure curve, and the optimized lubrication parameter is obtained. The entire calculation process reflects the correlation between the sheet metal forming quality and the lubrication parameter.

[0106] In a specific embodiment, the process of executing step S106 may specifically include the following steps:

[0107] (1) Extract the pressure value, flow value and time series data from the optimized lubrication parameter, and group the data according to the lubrication control region;

[0108] (2) Calculate the correlation degree between the pressure value and the flow value in the grouped data through the Pearson correlation coefficient, and generate a parameter correlation matrix;

[0109] (3) Perform eigenvalue decomposition on the parameter correlation matrix to obtain the lubrication parameter eigenvector;

[0110] (4) Perform deviation analysis on the lubrication parameter eigenvector and the reference lubrication pressure value of each lubrication control region to form a pressure correction coefficient;

[0111] (5) Numerically fit the pressure correction coefficient by the weighted average method to obtain the lubrication pressure control equation;

[0112] (6) Based on the lubrication pressure control equation, establish a lubrication parameter optimization model by the least squares method;

[0113] (7) After encoding the lubrication parameter optimization model and the corresponding process parameters, store them in the process parameter database.

[0114] Specifically, when extracting data from the optimized lubrication parameters, the pressure values, flow values, and corresponding time series data of each lubrication control region are organized into a standard format. The pressure values include the real-time pressure measurement results of each oil circuit, the flow values record the flow state of the lubricating oil, and the time series data mark the acquisition time of each group of data. The data is grouped according to the flange area and the fillet area, and the data within each area maintains a chronological correspondence. When calculating the correlation degree between the pressure value and the flow value through the Pearson correlation coefficient, for the data pairs within the same area, their covariance and standard deviation are calculated. The value range of the Pearson correlation coefficient is [-1, 1], where 1 represents a perfect positive correlation, -1 represents a perfect negative correlation, and 0 represents no correlation. The calculated correlation coefficients are organized into a matrix form, where the rows and columns of the matrix correspond to different measurement parameters, and each element represents the degree of correlation between the corresponding parameters.

[0115] When performing eigenvalue decomposition on the parameter correlation matrix, the matrix is represented as a combination of eigenvalues and eigenvectors. The eigenvalues are obtained by solving the characteristic equation, and the magnitude of the eigenvalues reflects the importance of the corresponding eigenvectors. The eigenvectors represent the main directions of data change and contain the information on the law of parameter change. The eigenvalues are sorted from largest to smallest, and the main eigenvectors are selected to form the lubrication parameter eigenvector set. When performing deviation analysis on the lubrication parameter eigenvector and the reference lubrication pressure value, the difference between the pressure distribution represented by the eigenvector and the reference pressure is calculated. The difference calculation considers both the absolute deviation and the relative deviation of the pressure value, and at the same time determines the allowable deviation range in combination with the process requirements. According to the deviation analysis results, correction coefficients are assigned to each region, and the correction coefficients reflect the direction and magnitude of pressure adjustment.

[0116] The numerical fitting of the pressure correction coefficient adopts the weighted average method to comprehensively calculate the correction coefficients of each region. The weight assignment is based on the regional importance and process sensitivity, and the fitting process uses piecewise functions to handle different working conditions. The obtained lubrication pressure control equation describes the mathematical relationship of pressure adjustment, and the equation contains the action terms of various influencing factors. When establishing the lubrication parameter optimization model using the least squares method, based on the control equation, an objective function and constraint conditions are established. The objective function reflects the optimization goal of pressure adjustment, and the constraint conditions ensure that the adjustment results meet the process requirements. By iteratively calculating to minimize the objective function, the optimized parameter values are obtained. The optimization model considers the synergistic effect of multiple lubrication regions to ensure the overall lubrication effect.

[0117] Finally, when storing the lubrication parameter optimization model in the database, data encoding and format conversion are required. The encoding rules of the process parameters include region identification, parameter type, and timestamp information to ensure the uniqueness and traceability of the data. In addition to storing the optimization model itself, the database also contains relevant process parameters and control strategies.

[0118] For example, in the processing of a deep-drawing part of a car side cover, the pressure values and flow values of each region are extracted from the optimized lubrication parameter data. In the fillet region, the Pearson correlation coefficient between the pressure value and the flow value is 0.85, indicating a strong positive correlation between pressure and flow. The eigenvectors obtained after eigenvalue decomposition show that the pressure change mainly occurs in the initial stage of deep drawing. The eigenvectors are compared with the reference pressure of 12 MPa in this region, and the correction coefficient is calculated. A pressure control equation is established by the weighted average method, and the final control parameters are optimized by the least squares method. The optimization results are encoded and stored in the database in the format of "region number_parameter type_timestamp". The whole process reflects the logic of data processing and the systematicness of parameter optimization.

[0119] In a specific embodiment, the process of performing the deviation analysis step of the lubrication parameter eigenvector and the reference lubrication pressure value of each lubrication control region may specifically include the following steps:

[0120] (1) Perform dimensionality reduction processing on the lubrication parameter eigenvector through matrix operations to obtain dimensionality-reduced feature data;

[0121] (2) Perform spectral analysis on the reference lubrication pressure value using the discrete Fourier transform to obtain frequency-domain component data;

[0122] (3) Perform numerical comparison on the dimensionality-reduced feature data and the frequency-domain component data to generate a difference coefficient;

[0123] (4) Perform linear transformation on the dimensionality-reduced feature data based on the difference coefficient to obtain normalized eigenvalues;

[0124] (5) Compare the normalized eigenvalues with the reference lubrication pressure value point by point to calculate the relative deviation value;

[0125] (6) Construct a correction factor matrix based on the relative deviation value, and extract the main components through singular value decomposition;

[0126] (7) Perform data reconstruction on the main components through bilinear interpolation to form a pressure correction coefficient.

[0127] Specifically, when performing dimensionality reduction on the lubrication parameter feature vector, the feature vector is organized into a matrix form. The rows of the matrix represent different sampling times, and the columns represent different feature components. Dimensionality reduction is performed on the matrix by the principal component analysis method. The covariance matrix of the feature vector is calculated, and the covariance matrix is subjected to eigenvalue decomposition. The main components are selected according to the eigenvalue size. Principal component analysis retains the main change characteristics of the data while reducing the data dimensionality. The dimensionality-reduced feature data retains the main information of the original data. When performing spectral analysis on the reference lubrication pressure value using the discrete Fourier transform, the pressure data sequence in the time domain is converted to the frequency domain. The Fourier transform decomposes the time-domain signal into the superposition of sine components of different frequencies and is implemented by the fast Fourier transform algorithm. Frequency-domain analysis can reflect the periodic characteristics of pressure changes and identify the main frequency components. The frequency-domain component data includes the amplitude spectrum and the phase spectrum, recording the frequency characteristics of pressure changes.

[0128] The numerical comparison between the dimensionality-reduced feature data and the frequency-domain component data uses the correlation analysis method to calculate the correlation degree of the two sets of data in different frequency bands. Correlation analysis considers the matching relationship between amplitude and phase and generates a difference coefficient reflecting the degree of data difference. The difference coefficient quantifies the deviation between the feature data and the reference data in the frequency domain and provides a basis for subsequent data processing. When performing a linear transformation on the dimensionality-reduced feature data based on the difference coefficient, a transformation matrix is constructed to map the feature data to a new feature space. The transformation process considers the weight effect of the difference coefficient and performs weighted processing on the data in different frequency bands. The data after the linear transformation is normalized to obtain the normalized eigenvalue. The normalized eigenvalue eliminates the influence of the dimension and facilitates comparison with the reference value.

[0129] When the normalized eigenvalue is compared point by point with the reference lubrication pressure value, the difference between the data at the corresponding time is calculated. The relative deviation value reflects the degree of change of the feature data relative to the reference value, and the calculation result forms a deviation sequence. The deviation sequence records the deviation change trend during the pressure regulation process and provides a basis for pressure correction. The correction factor matrix is constructed based on the relative deviation value, and the deviation data is organized into a matrix form. The correction factor matrix is decomposed by the singular value decomposition method to obtain the left singular matrix, the singular value matrix, and the right singular matrix. The singular value size reflects the importance of the corresponding component, and the main singular values and their corresponding singular vectors are selected for reconstruction. The data reconstruction of the main components uses the bilinear interpolation method to perform interpolation calculations between discrete data points. Bilinear interpolation considers the data changes in both the horizontal and vertical directions, ensuring the smoothness of the reconstructed data. The reconstructed data forms a pressure correction coefficient, which is used to adjust the control parameters of the lubrication pressure.

[0130] For example, during the deep drawing process of a car roof panel, matrix dimensionality reduction is performed on the lubrication parameter feature vector. The original data contains 32 feature components, and 8 main components are retained through principal component analysis. The fast Fourier transform is performed on the reference lubrication pressure sequence to obtain frequency domain component data, and the main frequency components are concentrated in the range of 0 - 10 Hz. The dimensionality-reduced feature data is compared with the frequency domain components to calculate the difference coefficient matrix. Based on the difference coefficient, linear transformation and normalization are performed to obtain the standardized eigenvalues. After comparison with the reference pressure value, the relative deviation sequence is obtained, and the correction factor matrix is constructed and singular value decomposition is performed. The components corresponding to the first 3 main singular values are selected for bilinear interpolation reconstruction to obtain the final pressure correction coefficient.

[0131] The automatic lubrication control method for sheet metal deep drawing in the embodiments of the present application has been described above. Next, the automatic lubrication control system for sheet metal deep drawing in the embodiments of the present application will be described. Please refer to Figure 3 , an embodiment of the automatic lubrication control system for sheet metal deep drawing in the embodiments of the present application includes:

[0132] The zoning module 201 is used to partition the surface of the drawing die through the lubrication area partitioning module to obtain multiple independent lubrication control areas including the flange area and the fillet area, and perform parameter initialization on each lubrication control area according to the physical parameters in the workpiece material library to obtain the reference lubrication pressure value of each area;

[0133] The acquisition module 202 is used to collect process parameters in real time according to the sensor network distributed in each lubrication control area, and perform filtering and standardization processing through the data preprocessing module to obtain the process state digital model;

[0134] The calculation module 203 is used to analyze and calculate the stress state of each lubrication control area through a fuzzy control algorithm based on the process state digital model to obtain the real-time lubrication demand parameters of each area;

[0135] The adjustment module 204 is used to perform pulsating adjustment on the lubrication pressure of each lubrication control area based on the real-time lubrication demand parameters by using a proportional servo valve control system to form a dynamic lubrication pressure control curve;

[0136] The correction module 205 is used to perform on-line evaluation of the sheet thinning rate and surface roughness, and correct the dynamic lubrication pressure control curve according to the evaluation results to obtain optimized lubrication parameters;

[0137] The analysis module 206 is used to perform correlation analysis on the optimized lubrication parameters, establish a lubrication parameter optimization model, and store the lubrication parameter optimization model in the process parameter database.

[0138] Through the collaborative cooperation of the above-mentioned various components, the surface of the drawing die is partitioned by the lubrication area division module, achieving precise lubrication control of key parts such as the flange area and the fillet area, avoiding the problem of uneven lubrication caused by the traditional single oil supply method. At the same time, the parameters of each lubrication control area are initialized according to the physical parameters in the workpiece material library, ensuring the scientificity and rationality of the reference lubrication pressure value. The process parameters are collected in real time through the sensor network arranged in each lubrication control area, and after being filtered and standardized by the data preprocessing module, an accurate digital model of the process state is established, providing a reliable data basis for the dynamic adjustment of lubrication parameters. The fuzzy control algorithm is used to analyze and calculate the stress state of each lubrication control area, accurately obtaining the real-time lubrication demand parameters of each area, reflecting the intelligence and self-adaptability of the control strategy. The proportional servo valve control system is used to pulsatingly adjust the lubrication pressure of each lubrication control area, forming a dynamic lubrication pressure control curve, realizing the precise regulation of the lubrication pressure. By online evaluating the sheet thinning rate and surface roughness, and correcting the dynamic lubrication pressure control curve according to the evaluation results, the optimized lubrication parameters are obtained, ensuring the stability of the forming quality. Finally, the correlation analysis of the optimized lubrication parameters is carried out, and the lubrication parameter optimization model is established and stored in the process parameter database, realizing the continuous optimization of control parameters and the accumulation of experience, providing data support for lubrication control under different working conditions. The entire control process realizes the full-process automation from parameter acquisition, data processing to control execution, significantly improving the processing quality and production efficiency of sheet drawing forming.

[0139] This application also provides a computer-readable storage medium, which can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions run on a computer, the computer is made to execute the steps of the automatic lubrication control method for sheet drawing forming.

[0140] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the above-described systems, systems and units can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0141] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The foregoing storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0142] As described above, the above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit them; although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of various embodiments of this application.

Claims

1. An automatic lubrication control method for sheet metal drawing forming, characterized in that The automatic lubrication control method for sheet metal drawing forming includes: Performing zoning treatment on the surface of the drawing die through a lubrication area division module to obtain multiple independent lubrication control areas including a flange area and a fillet area, and initializing the parameters of each lubrication control area according to the physical parameters in the workpiece material library to obtain the reference lubrication pressure values of each area; Collecting process parameters in real time according to the sensor network distributed in each lubrication control area, and performing filtering and standardization processing through a data preprocessing module to obtain a process state digital model; Based on the process state digital model, analyzing and calculating the stress state of each lubrication control area through a fuzzy control algorithm to obtain the real-time lubrication demand parameters of each area; Based on the real-time lubrication demand parameters, using a proportional servo valve control system to pulsatingly adjust the lubrication pressure of each lubrication control area to form a dynamic lubrication pressure control curve; Online evaluating the sheet thickness reduction rate and surface roughness, and correcting the dynamic lubrication pressure control curve according to the evaluation results to obtain optimized lubrication parameters; Performing correlation analysis on the optimized lubrication parameters, establishing a lubrication parameter optimization model, and storing the lubrication parameter optimization model in the process parameter database, including: extracting pressure values, flow values, and time series data from the optimized lubrication parameters, and grouping the data according to the lubrication control area; calculating the correlation degree between the pressure value and the flow value in the grouped data through the Pearson correlation coefficient to generate a parameter correlation matrix; performing eigenvalue decomposition on the parameter correlation matrix to obtain a lubrication parameter eigenvector; performing deviation analysis on the lubrication parameter eigenvector and the reference lubrication pressure value of each lubrication control area to form a pressure correction coefficient; numerically fitting the pressure correction coefficient through the weighted average method to obtain a lubrication pressure control equation; based on the lubrication pressure control equation, establishing a lubrication parameter optimization model by the least squares method; encoding the lubrication parameter optimization model and the corresponding process parameters and storing them in the process parameter database.

2. The automatic lubrication control method for sheet metal drawing forming according to claim 1, characterized in that The performing zoning treatment on the surface of the drawing die through a lubrication area division module to obtain multiple independent lubrication control areas including a flange area and a fillet area, and initializing the parameters of each lubrication control area according to the physical parameters in the workpiece material library to obtain the reference lubrication pressure values of each area includes: Identifying the areas on the surface of the drawing die according to geometric features, and dividing the surface of the drawing die into a flange area, a fillet area, and a barrel wall area; Dividing the oil circuit network according to the lubrication demand in each area, and setting an independent pressure sensor and flow sensor for each oil circuit; Extracting the friction coefficient, yield strength, and hardening index of the sheet to be processed from the workpiece material library to generate a material characteristic data set; Calculating the stress distribution of each area according to the geometric features of each area and the material characteristic data set; According to the stress distribution, assigning an initial pressure coefficient to each oil circuit, and calculating the reference lubrication pressure value of each area; Writing the reference lubrication pressure value into the control parameter table corresponding to each area through a PLC control unit.

3. The automatic lubrication control method for sheet metal drawing forming according to claim 1, wherein The process parameters are collected in real time according to the sensor network distributed in each lubrication control area, and are filtered and standardized by a data preprocessing module to obtain a process state digital model, including: Collect pressure data, flow data, temperature data, displacement data and force data from the sensor network to generate an original process parameter data stream; Remove noise from the original process parameter data stream through a Butterworth filter to obtain filtered process parameter data; Classify the filtered process parameter data according to pressure data, flow data, temperature data, displacement data and force data to form a classified data group; Perform normalization processing on the pressure data, flow data, temperature data, displacement data and force data in the classified data group respectively to obtain standardized process parameters; Associate the standardized process parameters according to each lubrication control area to construct a process parameter association matrix; Perform dimensionality reduction processing on the process parameter association matrix through principal component analysis to obtain a process state digital model.

4. The automatic lubrication control method for sheet metal drawing forming according to claim 1, wherein Based on the process state digital model, analyze and calculate the stress state of each lubrication control area through a fuzzy control algorithm to obtain real-time lubrication demand parameters for each area, including: Extract the pressure data, flow data and force data of each lubrication control area from the process state digital model as fuzzy control input variables; Perform fuzzy processing on the pressure data, flow data and force data according to three levels of low, medium and high to obtain a fuzzy set; Perform defuzzification operation on the fuzzy set through the weighted average method to obtain the stress state value of each lubrication control area; Perform a ratio operation on the stress state value and the reference lubrication pressure value to form lubrication pressure deviation data; Perform an incremental calculation on the lubrication pressure deviation data to generate a lubrication pressure compensation value; Superimpose the lubrication pressure compensation value and the reference lubrication pressure value to obtain real-time lubrication demand parameters for each area.

5. The automatic lubrication control method for sheet metal drawing forming according to claim 1, characterized in that, Based on the real-time lubrication demand parameters, use a proportional servo valve control system to pulsatingly adjust the lubrication pressure of each lubrication control area to form a dynamic lubrication pressure control curve, including: Calculate the opening of the proportional servo valve for each lubrication control area according to the real-time lubrication demand parameters to obtain valve opening control data; Convert the valve opening control data into a PWM control signal to generate valve pulsation frequency and duty cycle data; Perform digital-to-analog conversion on the valve pulsation frequency and duty cycle data and output a valve control voltage signal; Collect the actual output pressure of the proportional servo valve in each lubrication control area to form pressure feedback data; Perform a deviation calculation on the pressure feedback data and the real-time lubrication demand parameters to generate a pressure compensation signal; Arrange the pressure compensation signal and the pressure feedback data in a time series to form a dynamic lubrication pressure control curve.

6. The automatic lubrication control method for sheet metal drawing forming according to claim 1, wherein Online evaluate the sheet thinning rate and surface roughness, and correct the dynamic lubrication pressure control curve according to the evaluation results to obtain optimized lubrication parameters, including: Collect the thickness of each measurement point of the sheet through an ultrasonic thickness gauge sensor to obtain sheet thickness distribution data; Calculate the difference between the plate thickness distribution data and the initial plate thickness to obtain the thinning data at each measurement point; Perform a normalization operation on the thinning data to form the plate thinning rate data; Collect the measured values of the surface roughness of the plate to generate surface quality data; Perform a weighted superposition process on the plate thinning rate data and the surface quality data to generate a quality evaluation parameter; Perform a proportional correction on the dynamic lubrication pressure control curve based on the quality evaluation parameter to obtain the optimized lubrication parameters.

7. The automatic lubrication control method for sheet metal drawing forming according to claim 1, characterized in that, The deviation analysis of the lubrication parameter eigenvector and the reference lubrication pressure value of each lubrication control region to form a pressure correction coefficient includes: Perform a dimensionality reduction process on the lubrication parameter eigenvector through matrix operations to obtain the dimensionality reduction feature data; Perform a spectral analysis on the reference lubrication pressure value using the discrete Fourier transform to obtain the frequency domain component data; Perform a numerical comparison on the dimensionality reduction feature data and the frequency domain component data to generate a difference coefficient; Perform a linear transformation on the dimensionality reduction feature data based on the difference coefficient to obtain the normalized eigenvalue; Perform a point-to-point comparison between the normalized eigenvalue and the reference lubrication pressure value to calculate the relative deviation value; Construct a correction factor matrix based on the relative deviation value and extract the main components through singular value decomposition; Perform data reconstruction on the main components through bilinear interpolation to form a pressure correction coefficient.

8. An automatic lubrication control system for sheet metal deep drawing forming, which is used to implement the automatic lubrication control method for sheet metal deep drawing forming as described in any one of claims 1-7, is characterized in that, The automatic lubrication control system for sheet metal drawing forming includes: A zoning module for zoning the surface of the drawing die through a lubrication area division module to obtain multiple independent lubrication control areas including the flange area and the fillet area, and initializing the parameters of each lubrication control area according to the physical parameters in the workpiece material library to obtain the reference lubrication pressure value of each area; A collection module for collecting process parameters in real time according to the sensor network distributed in each lubrication control area, and performing filtering and standardization processing through a data preprocessing module to obtain a process state digital model; A calculation module for analyzing and calculating the stress state of each lubrication control area through a fuzzy control algorithm based on the process state digital model to obtain the real-time lubrication demand parameters of each area; An adjustment module for pulsatingly adjusting the lubrication pressure of each lubrication control area based on the real-time lubrication demand parameters using a proportional servo valve control system to form a dynamic lubrication pressure control curve; A correction module for online evaluating the sheet thinning rate and surface roughness, and correcting the dynamic lubrication pressure control curve according to the evaluation results to obtain the optimized lubrication parameters; An analysis module for performing correlation analysis on the optimized lubrication parameters, establishing a lubrication parameter optimization model, and storing the lubrication parameter optimization model in a process parameter database, including: extracting pressure values, flow values, and time series data from the optimized lubrication parameters, and grouping the data according to lubrication control regions; calculating the correlation degree between the pressure value and the flow value in the grouped data through the Pearson correlation coefficient to generate a parameter correlation matrix; performing eigenvalue decomposition on the parameter correlation matrix to obtain lubrication parameter eigenvectors; performing deviation analysis on the lubrication parameter eigenvectors and the reference lubrication pressure values of each lubrication control region to form a pressure correction coefficient; numerically fitting the pressure correction coefficient by the weighted average method to obtain a lubrication pressure control equation; based on the lubrication pressure control equation, establishing a lubrication parameter optimization model by the least squares method; encoding the lubrication parameter optimization model and the corresponding process parameters and storing them in the process parameter database.

9. A computer-readable storage medium having instructions stored thereon, characterized in that, When the instruction is executed by a processor, it implements the automatic lubrication control method for sheet metal drawing forming according to any one of claims 1-7.

Images