Magnetic material hydraulic forming control system

Abstract

The invention discloses a magnetic material hydraulic forming control system, which adopts a first acquisition module, a second acquisition module, a third acquisition module, a fourth acquisition module and a fifth acquisition module, and is characterized in that the first acquisition module is used for acquiring dynamic parameters through a sensor array, and preprocessing the dynamic parameters by adopting a data fusion algorithm; smooth pressure data and displacement time sequence data are obtained; the second acquisition module is used for training a cooperative control model of pressure and displacement by adopting a support vector machine algorithm, determining a dynamic mapping relation of the pressure and the displacement, and obtaining an optimized control parameter combination; and the third acquisition module is used for obtaining a stable pressure application curve by adjusting the opening degree of the servo valve of the hydraulic system in real time and combining the optimized control parameter combination and correcting pressure output if the control deviation of the dynamic mapping relation between the pressure and the displacement exceeds a preset threshold value. According to the invention, the hydraulic forming precision and the product quality are obviously improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of magnetic material manufacturing, and particularly discloses a magnetic material hydraulic forming control system. BACKGROUND

[0002] Magnetic material manufacturing is an indispensable field in modern industry, widely used in motors, sensors and new energy equipment, and its product quality directly affects the performance and energy efficiency of devices. Precise forming technology, as a core link, has a decisive influence on material density, dimensional accuracy and defect control, and is the key to industry competition.

[0003] However, traditional hydraulic forming technology has significant limitations, with low pressure control accuracy, often leading to uneven product density or internal cracks, especially in the manufacturing of high-performance magnetic materials such as neodymium iron boron or iron silicon aluminum, the finished product qualification rate is difficult to meet the high-end demand. In addition, traditional equipment has high energy consumption and low mold replacement efficiency, limiting production flexibility and cost control.

[0004] In the face of these problems, the core challenge is how to achieve high-precision pressure and displacement control while considering production efficiency under complex processes. Instability in pressure control can cause uneven stress on materials during the forming process, leading to uneven density distribution and affecting the performance stability of magnetic materials. Uneven density further exacerbates the release of internal stress during demolding, easily causing micro-cracks or product deformation, especially in high-strength permanent magnet material forming. These technical problems are interrelated and jointly restrict the improvement of magnetic material forming quality.

[0005] Therefore, how to achieve precise collaborative control of pressure and displacement in high-pressure forming, while optimizing the demolding process to reduce the risk of cracks, has become a key problem in improving the forming quality and production efficiency of magnetic materials. SUMMARY

[0006] The present application provides a magnetic material hydraulic forming control system, which aims to solve at least one of the defects in the prior art.

[0007] The present application relates to a magnetic material hydraulic forming control system, comprising:

[0008] The first acquisition module is configured to acquire dynamic parameters from the hydraulic system and the mold device through a sensor array, and to preprocess the dynamic parameters using a data fusion algorithm to obtain smoothed pressure data and displacement time series data.

[0009] The second acquisition module is configured to train a collaborative control model of pressure and displacement using a support vector machine algorithm based on the smoothed pressure data and displacement time series data, determine the dynamic mapping relationship between pressure and displacement, and obtain an optimized control parameter combination.

[0010] The third acquisition module is used to adjust the servo valve opening of the hydraulic system in real time and, in combination with the optimized control parameter combination, correct the pressure output to obtain a stable pressure application curve if the control deviation of the dynamic mapping relationship between pressure and displacement exceeds a preset threshold;

[0011] The fourth acquisition module is used to predict the distribution state of material density using a neural network algorithm based on the stable pressure application curve and displacement time series data, determine whether there is a density uneven area, and obtain a density distribution prediction result;

[0012] The fifth acquisition module is used to adjust the demoulding speed and mold temperature according to the predicted results of the density distribution at the beginning of the demoulding process, and use the fuzzy control algorithm to optimize the demoulding parameters to obtain a demoulding control strategy that reduces the risk of cracks.

[0013] Furthermore, the first acquisition module includes:

[0014] A first acquisition unit is used to collect dynamic parameters from the hydraulic system and the mold equipment in real time through a sensor array to obtain an initial parameter data set;

[0015] A generating unit is used to perform denoising processing on the collected pressure information and displacement information using a data fusion algorithm based on the initial parameter data set, and generate a preliminarily processed smoothing parameter set;

[0016] A first determination unit is configured to perform outlier detection on the pressure sequence and the displacement sequence using a preset threshold range for the smoothing parameter set, and if abnormal data exceeding the threshold is detected, perform interpolation correction on the abnormal data to determine a corrected parameter sequence;

[0017] The second acquisition unit is used to obtain the corrected parameter sequence, apply the time series analysis method to extract the trend of the pressure sequence and the displacement sequence, and obtain the parameter change trend data;

[0018] The first judgment unit is used to monitor the operating status of the hydraulic system and mold equipment in real time through parameter change trend data. If the trend data deviates from the preset normal range, the abnormal status mark is triggered to determine the potential operating risk;

[0019] The third acquisition unit is used to predict the pressure and displacement trends in the future period based on the abnormal state mark and the historical time series data using the Kalman filter algorithm to obtain a predicted trend data set;

[0020] The second determination unit is used to generate a dynamic adjustment strategy for the predicted trend data set. If the predicted trend shows that the abnormality persists, the control parameters of the hydraulic system are fine-tuned to determine the optimized operating parameter configuration.

[0021] Furthermore, the dynamic parameters in the first acquisition unit cover multi-dimensional information, and the multi-dimensional information includes pressure information and displacement information.

[0022] Furthermore, in the first determination unit, the abnormality detection of the pressure data point is calculated by the following formula:

[0023]

[0024] in, Indicates the Anomaly detection identification of pressure data points, Indicates the pressure measurements, represents the mean of the pressure series, represents the standard deviation of the pressure series, Indicates the threshold multiplier coefficient;

[0025] The displacement value after interpolation correction is:

[0026]

[0027] in, Indicates the Corrected displacement value at each position represents the previous normal displacement data point, represents the next normal displacement data point, represents the interpolation correction coefficient;

[0028] The smoothing of parameter sequences by weighted averaging is achieved by the following formula:

[0029]

[0030] in, Indicates the The smoothing parameter value at each location, represents the smoothing window length, Indicates the weight coefficients, represents a data point in the original parameter sequence.

[0031] Furthermore, in the first judgment unit, the overall deviation of the hydraulic system and mold equipment parameters from the normal range is calculated using the following formula:

[0032]

[0033] in, Indicates the parameter trend deviation, represents the number of monitoring parameters, Indicates the The current value of the parameter, represents the preset normal mean of the parameter;

[0034] The risk of a single parameter deviating from the normal range is calculated using the following formula:

[0035]

[0036] in, Indicates the The risk assessment index of the parameters, Indicates the Real-time monitoring values ​​of parameters, Indicates the reference standard value of the parameter. Indicates the upper limit of the normal range of the parameter, Indicates the lower limit of the normal range of the parameter;

[0037] The abnormal status mark is triggered by the following formula:

[0038]

[0039] in, Indicates abnormal status mark signal, Indicates the number of sampling points of trend data, Indicates the Trend data value at a moment, Indicates the trend reference value under normal conditions, Indicates the anomaly trigger threshold.

[0040] Furthermore, the second acquisition module includes:

[0041] The fourth acquisition unit is used to use a data comparison tool to match the change patterns of the pressure data and displacement time series data in the time series point by point based on the acquired pressure data and displacement time series data. The matching results are compared using a preset threshold range. If the deviation exceeds the threshold range, the corresponding time point is marked to obtain a marked deviation data set.

[0042] a third determining unit configured to perform numerical correction on the marked time points using a data interpolation tool for the marked deviation data set, obtain a corrected pressure data and displacement data set, and rearrange the corrected pressure data and displacement data set in a time series using a data integration tool to determine an integrated time series data set;

[0043] The fifth acquisition unit is configured to construct a dynamic corresponding relationship between the pressure data and the displacement time series data by using a data mapping tool according to the integrated time series data set, and to obtain a characteristic mapping relationship data set by processing a nonlinear change part in the corresponding relationship by using a feature extraction tool.

[0044] The fourth determination unit is configured to compare control parameters one by one by using a parameter adjustment tool for the characteristic mapping relationship data set, and to update the parameter values iteratively if the parameter combination does not match the preset operating state, so as to determine an adjusted control parameter combination.

[0045] Further, the third acquisition module includes:

[0046] The sixth acquisition unit is configured to obtain real-time pressure data and displacement time series data from the hydraulic system, to match the pressure data and the displacement time series data point by point by using a time series tool, to determine a dynamic corresponding relationship between the pressure data and the displacement time series data in the time series, and to obtain an initial mapping data set.

[0047] The seventh acquisition unit is configured to calculate a control deviation between the pressure data and the displacement data by using a deviation calculation tool for the initial mapping data set, to mark a time point exceeding a threshold by using a marking tool if the deviation exceeds the preset threshold, and to obtain a marked deviation data set.

[0048] The fifth determination unit is configured to adjust the servo valve opening degree of the hydraulic system by using a servo valve control tool according to the marked deviation data set, to update the control parameters iteratively by using a parameter optimization tool, and to determine an adjusted servo valve opening degree parameter combination.

[0049] The eighth acquisition unit is configured to process the adjusted servo valve opening degree parameter combination by using a pressure output tool to generate corrected pressure output data, to perform smoothing processing on the corrected pressure output data by using a curve fitting tool, and to obtain a stable pressure application curve.

[0050] Further, the fourth acquisition module includes:

[0051] The ninth acquisition unit is configured to obtain corresponding data points from the stable pressure application curve and the displacement sequence, to perform point-by-point corresponding processing on a time axis by using a data mapping tool to generate an initial distribution correlation data set, to determine a dynamic relationship between the pressure application and the displacement sequence, and to obtain preliminary distribution feature data.

[0052] The tenth acquisition unit is used to extract the material characteristics in sections based on the preliminary distribution characteristic data using the state analysis tool, and compare the characteristic values ​​of each region with the regional judgment tool. If the characteristic value of a certain region deviates from the preset threshold range, the region is marked as a potential uneven region, thereby obtaining a marked regional data set;

[0053] The eleventh acquisition unit is used to use a depth prediction tool to perform detailed calculation of the density distribution of the marked regional data set, generate a corresponding density distribution prediction map, determine whether there is an area with uneven density, and obtain predicted distribution status data;

[0054] The sixth determination unit is used to perform multi-dimensional comparison on the predicted distribution status data through the distribution evaluation tool, obtain the evaluation index of each area, and perform one-by-one verification in combination with the unevenness detection tool to determine the final density distribution prediction result.

[0055] Furthermore, the fifth acquisition module includes:

[0056] The twelfth acquisition unit is used to analyze the density value of the regional data point by point using a data comparison tool based on the regional data obtained from the density distribution prediction result. If the density value exceeds a preset threshold range, it is marked as a high-risk area to obtain a marked distribution data set;

[0057] The seventh determination unit is used to associate and match the density data of the high-risk area with the initial values ​​of the demolding speed and mold temperature based on the marked distribution data set through a parameter mapping tool, generate a preliminary parameter adjustment plan, and determine the adjustment range for each area;

[0058] a thirteenth acquisition unit, configured to dynamically optimize the preliminary parameter adjustment plan using a fuzzy control tool, extract the optimal demoulding speed and mold temperature combination from the adjustment range, and obtain optimized parameter configuration data;

[0059] The second judgment unit is used to use the parameter application tool to match the optimized parameter configuration data with the actual demolding process in real time, dynamically adjust the speed and temperature according to the density distribution characteristics, determine whether the preset conditions for reducing the crack risk are met, and obtain the final control strategy data.

[0060] Furthermore, in the thirteenth acquisition unit, the parameter mapping tool adopts MATLAB / Simulink fuzzy logic toolbox.

[0061] The beneficial effects achieved by the present invention are:

[0062] The application discloses a kind of magnetic material hydraulic forming control system, adopt first acquisition module, second acquisition module, third acquisition module, fourth acquisition module and fifth acquisition module, pressure and displacement data are obtained by sensor, dynamic mapping model is established using data fusion and machine learning algorithm, real-time adjustment hydraulic system parameter to obtain stable pressure curve.Simultaneously, material density distribution is predicted using neural network, and the demolding process parameters are optimized accordingly.The method can effectively solve the problems of unstable pressure control, uneven material density and cracks in the demolding process during hydraulic forming, and realizes intelligent control of the forming process.The application significantly improves the precision and product quality of hydraulic forming through the collaborative application of various algorithms, which is of great significance to improve the automation and intelligent level of manufacturing industry.The magnetic material hydraulic forming control system disclosed by the application has the beneficial effects as follows:

[0063] I. Data preprocessing improves control base accuracy

[0064] 1. Real-time accurate acquisition of dynamic parameters: cover the hydraulic system and mold equipment with a sensor array to obtain real-time pressure, displacement and other key parameters, avoid single-point sampling errors, and ensure data integrity.

[0065] 2. Data fusion denoising and smoothing: use data fusion algorithm to preprocess dynamic parameters, eliminate signal fluctuations and noise interference, generate smooth pressure-displacement time series data, provide reliable input for subsequent control model, and improve the reliability of basic data (such as pressure fluctuation error can be reduced by more than 30%).

[0066] II. Pressure-displacement collaborative control optimizes forming process

[0067] 1. Support vector machine modeling to achieve dynamic mapping: train pressure-displacement collaborative control model through algorithm, accurately capture the nonlinear dynamic relationship between the two, break through the limitations of traditional fixed parameter control, and adapt to the needs of different material characteristics and forming stages (such as the pressure-displacement matching accuracy of complex magnetic core structure is improved by 40%).

[0068] 2. Real-time deviation correction to stabilize pressure output: when the control deviation exceeds the threshold, adjust and optimize the parameter combination through servo valve opening degree in real time to generate a stable pressure application curve, avoid uneven material deformation caused by pressure sudden change, and improve forming consistency (pressure fluctuation range can be controlled within ±2%).

[0069] III. Density distribution prediction to prevent internal defects

[0070] 1. Neural network prediction of uneven density area: based on pressure-displacement data and material characteristics, predict the spatial distribution of material density after forming using neural network algorithm, identify local loose or overpressure area in advance (such as axial density deviation warning accuracy rate is more than 90%).

[0071] 2. Prospective quality control: Predicting results through density distribution, adjusting process parameters during the forming process (rather than post-detection), reducing magnetic performance differences or structural defects caused by uneven density, and improving material performance uniformity.

[0072] Four, demolding parameter optimization to reduce the risk of cracks

[0073] 1. Demolding strategy dynamic adjustment based on density prediction: During the demolding stage, adjust the demolding speed (such as reducing the speed in high-density areas to avoid pulling) and mold temperature (local heating to relieve stress concentration) according to the density distribution results, achieving "on-demand demolding".

[0074] 2. Fuzzy control algorithm to improve demolding flexibility: Optimize the combination of demolding parameters through fuzzy logic to adapt to the complex needs of different density distribution scenarios, effectively reduce the risk of cracks caused by demolding stress (crack occurrence rate can be reduced by more than 50%), and improve product yield.

[0075] Five, system-level benefits: Intelligentization of the whole process and improvement of production efficiency

[0076] 1. Closed-loop control to improve automation level: Form a complete closed loop from parameter collection, model optimization to demolding control, reduce manual intervention, lower the operation threshold, and be suitable for batch automated production.

[0077] 2. Material and energy consumption optimization: Precise control reduces material waste (such as reducing corner loss by 25%), stable pressure curve and demolding strategy can reduce equipment energy consumption (energy consumption is reduced by 15-20% compared with the same period), with both quality and cost advantages. BRIEF DESCRIPTION OF DRAWINGS

[0078] Figure 1 is an embodiment of the function block diagram of the magnetic material hydraulic forming control system of the application;

[0079] Figure 2 is an embodiment of the function block diagram of the first acquisition module shown in Figure 1 ;

[0080] Figure 3 is an embodiment of the function block diagram of the second acquisition module shown in Figure 1 ;

[0081] Figure 4 is an embodiment of the function block diagram of the third acquisition module shown in Figure 1 ;

[0082] Figure 5 is an embodiment of the function block diagram of the fourth acquisition module shown in Figure 1 ;

[0083] Figure 6 For Figure 1 Figure 5 shows a functional module diagram of an embodiment of the fifth obtaining module shown in Figure 4.

[0084] Explanation of reference signs:

[0085] 10, first obtaining module; 20, second obtaining module; 30, third obtaining module; 40, fourth obtaining module; 50, fifth obtaining module; 11, first obtaining unit; 12, generating unit; 13, first determining unit; 14, second obtaining unit; 15, first judging unit; 16, third obtaining unit; 17, second determining unit; 21, fourth obtaining unit; 22, third determining unit; 23, fifth obtaining unit; 24, fourth determining unit; 31, sixth obtaining unit; 32, seventh obtaining unit; 33, fifth determining unit; 34, eighth obtaining unit; 41, ninth obtaining unit; 42, tenth obtaining unit; 43, eleventh obtaining unit; 44, sixth determining unit; 51, twelfth obtaining unit; 52, seventh determining unit; 53, thirteenth obtaining unit; 54, second judging unit. DETAILED DESCRIPTION

[0086] In order to better understand the above technical solutions, the above technical solutions will be described in detail below in combination with the drawings in the specification and specific embodiments.

[0087] As Figure 1As shown, the first embodiment of the present application proposes a magnetic material hydraulic forming control system, which comprises a first acquisition module 10, a second acquisition module 20, a third acquisition module 30, a fourth acquisition module 40 and a fifth acquisition module 50. The first acquisition module 10 is used to obtain dynamic parameters from the hydraulic system and the mold equipment through a sensor array, preprocess the dynamic parameters by using a data fusion algorithm, and obtain smooth pressure data and displacement time series data. The second acquisition module 20 is used to train a pressure and displacement collaborative control model by using a support vector machine algorithm according to the smooth pressure data and displacement time series data, determine the dynamic mapping relationship of pressure and displacement, and obtain an optimized control parameter combination. The third acquisition module 30 is used to correct the pressure output by adjusting the servo valve opening of the hydraulic system in real time and combining the optimized control parameter combination if the control deviation of the dynamic mapping relationship of pressure and displacement exceeds a preset threshold, and obtain a stable pressure application curve. The fourth acquisition module 40 is used to predict the distribution state of material density by using a neural network algorithm according to the stable pressure application curve and the displacement time series data, judge whether there is a density uneven area, and obtain a prediction result of density distribution. The fifth acquisition module 50 is used to adjust the demolding speed and mold temperature according to the prediction result of density distribution at the beginning of the demolding process, optimize the demolding parameters by using a fuzzy control algorithm, and obtain a demolding control strategy that reduces the risk of cracks.

[0088] In the hydraulic forming of a soft magnetic material magnetic core, the sensor array in the first acquisition module 10 collects dynamic data of the hydraulic cylinder pressure (10-200 MPa) and the ram displacement (0-50 mm) in real time. After processing by a Kalman filter fusion algorithm, the measurement noise caused by hydraulic system vibration (amplitude ±5 MPa) and mechanical clearance (±0.1 mm) can be eliminated, a smooth pressure-displacement curve can be generated, reliable input parameters can be provided for the subsequent pressure-displacement collaborative control model, and finally the density uniformity of the magnetic core can be improved by more than 15%.

[0089] In the second acquisition module 20, the support vector machine algorithm uses the regression characteristics (SVR, Support Vector Regression) of SVM (Support Vector Machine) to fit the dynamic relationship between pressure and displacement, and captures the nonlinear coupling characteristics that cannot be described by traditional linear models. The collaborative control model realizes the collaborative regulation of pressure and displacement in the forming process by modeling the time-varying mapping relationship between them, and avoids the forming defects caused by single parameter control (such as insufficient displacement when the pressure is insufficient or material damage caused by pressure overshoot).

[0090] The third obtaining module 30 is configured to determine whether the control deviation of the dynamic mapping relationship between the pressure and the displacement exceeds a preset threshold value. If the control deviation of the dynamic mapping relationship between the pressure and the displacement exceeds the preset threshold value, the servo valve opening degree of the hydraulic system is adjusted in real time, the optimized control parameter combination is combined, the pressure output is corrected, and a stable pressure application curve is obtained.

[0091] In the fourth obtaining module 40, the neural network algorithm refers to a calculation model constructed by using a plurality of nonlinear mapping units (such as a full connection layer, a convolution layer, and a cycle layer). By learning the implicit relationship between the pressure-displacement data and the material density, nonlinear mapping prediction is realized.

[0092] The density distribution state refers to the density spatial distribution of the material in the mold cavity, which is usually represented by a three-dimensional matrix (such as the density values along the mold axial direction and the radial direction). The density uneven area refers to an area in which the local density of the magnetic material deviates from the overall average value due to factors such as pressure distribution, displacement rate, or material filling during the hydraulic forming process. The deviation of the density value of the area from the overall average density of the material exceeds a preset threshold value, directly affecting the uniformity of the magnetic performance and the mechanical strength of the product. The density uneven area generally refers to an area in which the local density deviates from the average value by more than ±5%.

[0093] In the fifth obtaining module 50, the demolding control strategy for reducing the crack risk refers to a systematic method for eliminating the crack risk caused by stress concentration by dynamically adjusting the demolding speed and the mold temperature and optimizing the parameter combination by using a fuzzy control algorithm in the demolding stage of the magnetic material hydraulic forming, by analyzing the density distribution prediction results (such as the positions of the local high-density area and the low-density area) in real time. The strategy takes the density deviation data as input, generates the optimal demolding parameters through fuzzy logic mapping, and realizes the closed-loop adjustment of “prediction-control-feedback”.

[0094] Further, the magnetic material hydroforming control system provided by the embodiment further comprises a first acquisition module 10, which comprises a first acquisition unit 11, a generation unit 12, a first determination unit 13, a second acquisition unit 14, a first judgment unit 15, a third acquisition unit 16 and a second determination unit 17. The first acquisition unit 11 is configured to collect dynamic parameters from the hydraulic system and the mold equipment in real time through a sensor array to obtain an initial parameter data set. The generation unit 12 is configured to perform denoising processing on the collected pressure information and displacement information by using a data fusion algorithm according to the initial parameter data set to generate a smooth parameter set after preliminary processing. The first determination unit 13 is configured to perform outlier detection on the pressure sequence and the displacement sequence by using a preset threshold range for the smooth parameter set, and if abnormal data exceeding the threshold is detected, the abnormal data is corrected by interpolation to determine a parameter sequence after correction. The second acquisition unit 14 is configured to obtain the parameter sequence after correction, and perform trend extraction on the pressure sequence and the displacement sequence by using a time series analysis method to obtain parameter change trend data. The first judgment unit 15 is configured to perform real-time monitoring on the running state of the hydraulic system and the mold equipment by using the parameter change trend data, and if the trend data deviates from a preset normal range, a state abnormality mark is triggered to judge potential running risks. The third acquisition unit 16 is configured to predict the pressure and displacement trends in a future period of time by using a Kalman filtering algorithm according to the state abnormality mark and in combination with historical time series data to obtain a predicted trend data set. The second determination unit 17 is configured to generate a dynamic adjustment strategy for the predicted trend data set, and if the predicted trend shows that the abnormality is persistent, the control parameters of the hydraulic system are fine-tuned to determine optimized running parameter configurations.

[0095] In the real-time monitoring scene of the hydraulic system and the mold equipment, the sensor array in the first acquisition unit 11 is used to collect multi-dimensional dynamic parameters such as pressure and displacement. It is assumed that a hydraulic stamping equipment is running, and the sensor collects data once per second to obtain an initial data set, in which the pressure value ranges from 50 to 200 MPa, and the displacement value ranges from 0.5 to 5.0 mm.

[0096] In the generation unit 12, the data fusion algorithm can perform denoising processing on multi-sensor data by using a weighted average method to reduce the noise influence caused by vibration or electromagnetic interference to generate a smooth parameter set. Thus, the data reliability can be effectively improved to lay a foundation for subsequent analysis.

[0097] In the first determination unit 13, for the smoothing parameter set, a pressure threshold range of 60 to 180 MPa and a displacement threshold range of 0.8 to 4.5 mm are preset. If the pressure value detected at a certain moment is 190 MPa, exceeding the threshold, a correction value is estimated using the two preceding and following normal data points through linear interpolation, ultimately adjusting the abnormal value to 175 MPa. This correction method prevents abnormal data from interfering with subsequent trend analysis and ensures the continuity and accuracy of the parameter sequence.

[0098] The anomaly detection of pressure data points is calculated using the following formula:

[0099] (1)

[0100] In formula (1), Indicates the Anomaly detection identification of pressure data points, Indicates the pressure measurements, represents the mean of the pressure series, represents the standard deviation of the pressure series, Indicates the threshold multiplier coefficient. When the pressure value deviates from the mean by more than times the standard deviation are marked as outliers.

[0101] The displacement value after interpolation correction is:

[0102] (2)

[0103] In formula (2), Indicates the Corrected displacement value at each position represents the previous normal displacement data point, represents the next normal displacement data point, Represents the interpolation correction coefficient. Formula (2) corrects the abnormal displacement data through linear interpolation method.

[0104] The smoothing of parameter sequences by weighted averaging is achieved by the following formula:

[0105] (3)

[0106] In formula (3), Indicates the The smoothing parameter value at each location, represents the smoothing window length, Indicates the weight coefficients, represents a data point in the original parameter sequence.

[0107] After the second acquisition unit 14 acquires the modified parameter sequence, the time series analysis can extract the trend data of pressure and displacement through the sliding window method. Assuming that the pressure value presents a gradual upward trend from 70 MPa to 90 MPa in the past one hour, it may reflect an increase in the load of the hydraulic system.

[0108] The first judgment unit 15 monitors the equipment operating state in real time through the parameter change trend data. If the pressure trend exceeds the normal range of 80 to 100 MPa, a state abnormality flag is triggered, prompting a potential overload risk. This monitoring method helps to discover problems in a timely manner and reduces the probability of equipment damage.

[0109] The overall deviation degree of the hydraulic system and the mold equipment parameters from the normal range is calculated by the following formula:

[0110] (4)

[0111] In formula (4), represents the parameter trend deviation degree, represents the number of monitored parameters, represents the current value of the th parameter, represents the preset normal mean value of the parameter.

[0112] The risk degree of a single parameter deviating from the normal range is calculated by the following formula:

[0113] (5)

[0114] In formula (5), represents the risk evaluation index of the th parameter, represents the real-time monitoring value of the th parameter, represents the reference standard value of the parameter, represents the upper limit value of the parameter normal range, represents the lower limit value of the parameter normal range.

[0115] The triggering of the state abnormality flag is realized by the following formula:

[0116] (6)

[0117] In formula (6), represents the abnormal state flag signal, represents the sampling point number of the trend data, represents the trend data value at the th moment, represents the trend reference value in the normal state, Anomaly trigger threshold. Outputs 1 to trigger an anomaly flag when the average deviation of trend data exceeds a preset threshold, otherwise outputs 0 to indicate normal state.

[0118] The third acquisition unit 16 combines the state anomaly flag and historical data to predict the pressure and displacement trends for the next 30 minutes using the Kalman filter algorithm. Assuming the current pressure is 95 MPa and the historical data shows small fluctuations, the prediction result shows that the pressure may continue to rise to 105 MPa, exceeding the safe range. Kalman filtering can effectively deal with data uncertainty by dynamically adjusting the prediction model, improving prediction accuracy and providing reliable basis for subsequent decision-making.

[0119] The second determination unit 17 generates a dynamic adjustment strategy for the predicted trend data set if the pressure anomaly persists. Assuming the predicted pressure continues to be higher than 100 MPa, the output power of the hydraulic pump can be reduced by 5% to control the pressure within the safe range, and the optimized operating parameter configuration is determined. This fine-tuning strategy can effectively extend the service life of the equipment, reduce maintenance costs, while ensuring production efficiency and safety. Through the above multi-link collaborative work, from data acquisition to prediction adjustment, a closed-loop monitoring system is formed to ensure stable operation of the hydraulic system and the mold equipment.

[0120] Further, the magnetic material hydraulic forming control system provided by the embodiment, the second acquisition module 20 includes a fourth acquisition unit 21, a third determination unit 22, a fifth acquisition unit 23 and a fourth determination unit 24, wherein the fourth acquisition unit 21 is used to perform point-by-point matching on the change rule of the pressure data and the displacement time series data in the time sequence by using a data comparison tool according to the obtained pressure data and displacement time series data, and for the matching result, a preset threshold range is used for comparison, if the deviation exceeds the threshold range, the corresponding time point is marked, and a marked deviation data set is obtained; the third determination unit 22 is used to perform numerical correction on the marked time point by using a data interpolation tool for the marked deviation data set, to obtain a corrected pressure data and displacement data set, and a data integration tool is used to rearrange the corrected pressure data and displacement data set according to the time sequence to determine an integrated time series data set; the fifth acquisition unit 23 is used to construct a dynamic corresponding relationship between the pressure data and the displacement time series data by using a data mapping tool according to the integrated time series data set, and for the nonlinear change part in the corresponding relationship, a feature extraction tool is used for processing to obtain a characteristic mapping relationship data set; and the fourth determination unit 24 is used to compare the control parameters item by item by using a parameter adjustment tool for the characteristic mapping relationship data set, and if the parameter combination does not match the preset operating state, the parameter value is iteratively updated to determine the adjusted control parameter combination.

[0121] In the operation monitoring scene of hydraulic systems and mold equipment, the fourth acquisition unit 21 needs to match the change rule on the time sequence point by point for the processing of smooth pressure data and displacement data. Assuming that the pressure data and displacement data are collected once a minute during the operation of a hydraulic stamping equipment, the pressure value range is 60 to 150 megapascals, and the displacement value range is 0.5 to 4.0 millimeters. Through data comparison tools, it can be found that the pressure value at a certain time point is 140 megapascals, and the displacement value is 3.8 millimeters, which deviates greatly compared with the historical rule. Using the preset threshold range, such as pressure deviation allowed ±10 megapascals, displacement deviation allowed ±0.3 millimeters, if it exceeds, mark the time point, form the deviation data set. This point-by-point matching method helps to quickly locate abnormal fluctuations.

[0122] The third determination unit 22 is used for correcting abnormal values by using a data interpolation tool for the marked deviation data set. Assuming that the pressure value of a certain marked time point is 155 megapascals, which exceeds the upper limit of the threshold, by analyzing the pressure values of the previous and subsequent time points, which are 148 megapascals and 150 megapascals respectively, the interpolation tool estimates the correction value as 149 megapascals. The displacement data can also be adjusted by a similar method to ensure data continuity.

[0123] In the fifth acquisition unit 23, the corrected data set is rearranged by a data integration tool according to the time sequence to form an integrated time sequence data set, which provides a complete basis for subsequent analysis. For example, when constructing the dynamic correspondence relationship between pressure data and displacement data, a data mapping tool can be used. Assuming that within a certain period of time, the pressure value gradually rises from 80 megapascals to 120 megapascals, and the displacement value changes from 1.2 millimeters to 2.5 millimeters, showing a nonlinear relationship. Through a feature extraction tool, this nonlinear change part can be extracted as key feature points, such as inflection points or intervals with large change rates, to form a feature mapping relationship data set. This processing method facilitates quick identification of key change trends during subsequent parameter adjustment.

[0124] The dynamic mapping relationship function between pressure data and displacement data is:

[0125] (7)

[0126] In formula (7), represents the dynamic mapping relationship function between pressure data and displacement data, represents the value of the i-th pressure time sequence at time t, represents the value of the i-th displacement time sequence at time t, represents the value of the i-th displacement time sequence at time t, represents the value of the i-th displacement time sequence at time t, represents the value of the i-th displacement time sequence at time t, represents the value of the i-th displacement time sequence at time t, represents the value of the i-th displacement time sequence at time t, represents the value of the i-th displacement time sequence at time t, represents a linear coupling coefficient between pressure and displacement, represents a standard deviation parameter at the th time point, represents the total length of the time series.

[0127] The feature extraction function of the nonlinear change part is:

[0128] (8)

[0129] In formula (8), represents the feature extraction function of the nonlinear change part, represents the input original data variable, represents the amplitude coefficient of the th hyperbolic tangent term, represents the slope parameter of the th hyperbolic tangent term, represents the offset of the th hyperbolic tangent term, represents the amplitude coefficient of the mth sine term, represents the frequency parameter of the th sine term, represents the phase angle of the th sine term, represents the total number of hyperbolic tangent terms, represents the total number of sine terms.

[0130] The mapping relationship data set of the feature is:

[0131] (9)

[0132] In formula (9), represents the mapping relationship data set of the feature, represents the pressure feature vector of the th sample, represents the displacement feature vector of the th sample, represents the feature correlation coefficient of the th sample, represents the original pressure data of the th, represents the original displacement data of the th, represents the weight of the lth pressure feature extraction base function, represents the th pressure feature extraction base function, represents the weight of the th displacement feature extraction base function, represents the a displacement feature extraction basis function, a scaling factor representing a correlation calculation, a total number of pressure feature basis functions, a total number of displacement feature basis functions.

[0133] The fourth determination unit 24 is for the parameter adjustment tool to optimize the control parameters for the characterized mapping relationship dataset. Assuming that in the current hydraulic system operating parameter combination, the upper limit of pressure control is 130 megapascals, but according to feature data analysis, the pressure frequently approaches this value in actual operation, which may cause system instability. Through iterative updating, the upper limit is adjusted to 135 megapascals, while the related flow parameters are fine-tuned to ensure that the operating state is consistent with the preset target. The adjusted parameter combination can better adapt to the actual working conditions. Through the above multi-link collaborative processing, from data comparison to parameter adjustment, a complete analysis chain is formed. Each link is closely related to the operating requirements of the hydraulic system and the mold equipment, ensuring that each step of data processing can provide reliable support for subsequent decision-making. This approach can effectively improve the adaptability and stability of the system in practical applications.

[0134] Further, the magnetic material hydraulic forming control system provided by the embodiment, the third acquisition module 30 includes a sixth acquisition unit 31, a seventh acquisition unit 32, a fifth determination unit 33 and an eighth acquisition unit 34, wherein the sixth acquisition unit 31 is configured to obtain real-time pressure data and displacement time series data from the hydraulic system, and to determine the dynamic correspondence of the pressure data and the displacement time series data in the time series by point-by-point matching of the pressure data and the displacement time series data through a time series tool, to obtain an initial mapping dataset; the seventh acquisition unit 32 is configured to calculate the control deviation between the pressure data and the displacement data for the initial mapping dataset using a deviation calculation tool, and if the deviation exceeds a preset threshold, to mark the time points exceeding the threshold using a marking tool to obtain a marked deviation dataset; the fifth determination unit 33 is configured to adjust the servo valve opening of the hydraulic system according to the marked deviation dataset through a servo valve control tool, and to iteratively update the control parameters using a parameter optimization tool to determine an adjusted servo valve opening parameter combination; and the eighth acquisition unit 34 is configured to process the adjusted servo valve opening parameter combination through a pressure output tool to generate corrected pressure output data, and to smooth the corrected pressure output data using a curve fitting tool to obtain a stable pressure application curve.

[0135] In the context of hydraulic system operation monitoring, the real-time acquisition of pressure data and displacement time series data in the sixth acquisition unit 31 is the basis for building a dynamic control model. Hydraulic systems are commonly used in industrial stamping equipment, and the precise matching of pressure and displacement directly affects the processing precision. Assuming that pressure and displacement data are collected every second during the operation of a stamping equipment, the pressure value ranges from 50 to 160 megapascals, and the displacement value ranges from 0.2 to 3.5 millimeters. Time series tools can correspond these data one by one according to time points to form an initial mapping data set, facilitating subsequent analysis of the dynamic relationship between the two.

[0136] The seventh acquisition unit 32 applies a deviation calculation tool to the initial mapping data set, which can help identify abnormal points. Assuming that at a certain time point, the pressure value is 158 megapascals and the displacement value is 3.4 millimeters, while historical data indicates that the pressure under this displacement is usually around 150 megapascals, with a deviation of more than 10 megapascals from the preset threshold. At this time, the marking tool marks this time point as abnormal, forming a marked deviation data set. This approach facilitates quick identification of the link that needs to be adjusted.

[0137] In adjusting the hydraulic system, the fifth determination unit 33 plays a crucial role in the servo valve control tool. Based on the marked deviation data set, assuming that the current servo valve opening is 60%, resulting in a high pressure. By analyzing the data at the previous and subsequent time points, it is found that adjusting the opening to 55% may be more appropriate. Combined with the parameter optimization tool, the control parameters are iteratively updated to ultimately determine the new opening parameter combination. This adjustment method can effectively balance the running state of the system.

[0138] In the eighth acquisition unit 34, the pressure output tool processes the corrected pressure output data according to the adjusted servo valve opening parameters when generating the corrected pressure output data. Assuming that the adjusted pressure value decreases from 158 megapascals to 152 megapascals, close to the target range. Such processing helps to reduce the risk of system overload while ensuring stability during the processing process. Specifically, the curve fitting tool smoothes the corrected pressure output data to eliminate small fluctuations in the data. Assuming that the corrected pressure data shows slight oscillation over time, a smooth pressure application curve is generated by the fitting tool, making the pressure change more continuous. This smoothing process helps the device avoid the impact of sudden changes during operation, improving the overall stability of the operation. In this embodiment, from the initial data collection to the final curve generation, each link is closely related to the actual needs of the hydraulic system. For example, the determination of the dynamic correspondence provides a data basis for subsequent deviation analysis, while the deviation marking and parameter adjustment lay the foundation for the correction of the pressure output, and finally a stable control curve is formed through smoothing. This layer-by-layer progressive approach can effectively improve the adaptability and reliability of the hydraulic system in industrial applications.

[0139] Further, the magnetic material hydraulic forming control system provided by the embodiment further comprises a fourth acquisition module 40, which comprises a ninth acquisition unit 41, a tenth acquisition unit 42, an eleventh acquisition unit 43 and a sixth determination unit 44. The ninth acquisition unit 41 is configured to acquire corresponding data points from the stable pressure application curve and the displacement sequence, perform point-by-point corresponding processing on the time axis by using a data mapping tool, generate an initial distribution correlation data set, determine the dynamic relationship between the pressure application and the displacement sequence, and obtain preliminary distribution characteristic data. The tenth acquisition unit 42 is configured to perform segmented extraction on material characteristics by using a state analysis tool according to the preliminary distribution characteristic data, compare the characteristic values of each region by using a region judgment tool, mark a region as a potential uneven region if the characteristic value of the region deviates from a preset threshold range, and obtain a marked region data set. The eleventh acquisition unit 43 is configured to perform detailed calculation on the density distribution by using a deep prediction tool for the marked region data set, generate a corresponding density distribution prediction map, determine whether there is a density uneven region, and obtain predicted distribution state data. The sixth determination unit 44 is configured to perform multidimensional comparison on the predicted distribution state data by using a distribution evaluation tool, acquire an evaluation index of each region, perform one-by-one verification by using an uneven detection tool, and determine a final density distribution prediction result.

[0140] In the scene of hydraulic system operation monitoring, the ninth acquisition unit 41 acquires data points from the stable pressure application curve and the displacement sequence, which is the basis for constructing the dynamic relationship. Assuming that the pressure application curve has reached a stable state through pre-adjustment in the running process of an industrial stamping device, the pressure value fluctuates between 50 and 160 megapascals, and the displacement sequence changes in the range of 0.2 to 3.5 millimeters. The data mapping tool can correspond to these data points one by one on the time axis to form an initial distribution correlation data set. For example, when the pressure value is 120 megapascals in a certain time period, the corresponding displacement value is 2.5 millimeters. Through point-by-point corresponding processing, the dynamic relationship between the two can be preliminarily determined, and distribution characteristic data is generated to provide a basis for subsequent analysis.

[0141] The tenth acquisition unit 42 performs segmented extraction on the preliminary distribution characteristic data. Assuming that the material exhibits different stress responses in different displacement regions, the tool will divide the displacement sequence into multiple intervals and extract the characteristic data of each interval. In combination with the region judgment tool, if the characteristic value of a region deviates from the preset threshold, such as exceeding 10% of the normal range at a displacement of 2.0 millimeters, the region is marked as a potential uneven region. This segmented extraction and marking method helps to quickly locate the region that may affect the processing precision to form a marked region data set.

[0142] The eleventh acquisition unit 43 can perform detailed calculation on the density distribution when processing the marked region data set. Assuming that in the marked potential uneven density region, the tool predicts the possible change trend of the density distribution by comparing historical data and current data, and generates a density distribution prediction map. For example, the prediction map shows that in the displacement interval of 2.0 to 2.5 mm, the density distribution may deviate by 5%, and then it is judged whether there is a density uneven region. This prediction method provides intuitive data support for subsequent verification.

[0143] The sixth determination unit 44 compares the predicted distribution state data in multiple dimensions through the distribution evaluation tool to obtain the evaluation index of each region. Assuming that in the above predicted density uneven region, the evaluation index shows that the stability of this region is 15% lower than that of other regions, combined with the uneven detection tool, the final density distribution prediction result is determined by verifying one by one. This multi-dimensional comparison and verification method can improve the comprehensiveness and reliability of the analysis, and provide accurate basis for subsequent adjustment of the hydraulic system.

[0144] Further, the magnetic material hydraulic forming control system provided by the embodiment includes a fifth acquisition module 50, which includes a twelfth acquisition unit 51, a seventh determination unit 52, a thirteenth acquisition unit 53, and a second judgment unit 54. The twelfth acquisition unit 51 is configured to perform point-by-point analysis on the density values of the region data by using a data comparison tool according to the region data obtained from the density distribution prediction result. If the density value exceeds the preset threshold range, it is marked as a high-risk region to obtain a marked distribution data set. The seventh determination unit 52 is configured to associate and match the density data of the high-risk region with the initial values of the demolding speed and the mold temperature by using a parameter mapping tool for the marked distribution data set, generate a preliminary parameter adjustment scheme, and determine the adjustment range of each region. The thirteenth acquisition unit 53 is configured to dynamically optimize the preliminary parameter adjustment scheme by using a fuzzy control tool, extract the optimal demolding speed and mold temperature combination from the adjustment range, and obtain optimized parameter configuration data. The second judgment unit 54 is configured to correspond the optimized parameter configuration data with the actual demolding process in real time by using a parameter application tool, dynamically adjust the speed and temperature according to the density distribution characteristics, judge whether the preset condition of reducing the crack risk is met, and obtain the final control strategy data.

[0145] In the scenario of industrial stamping equipment operation, the density distribution prediction result in the twelfth acquisition unit 51 provides a key basis for subsequent optimization. By point-by-point analysis of the density values of the regional data through the data comparison tool, potential problem areas can be accurately identified. Assuming that in a certain stamping process, the prediction result shows that the density value of a certain area reaches 2.3 g / cm³, and the preset threshold is 2.0 g / cm³, which exceeds the threshold by 15%. In this case, the data comparison tool will mark this area as a high-risk area to form a marked distribution data set. It should be noted that the density value exceeding the standard may be due to uneven stress on the material during stamping or fluctuations in mold temperature, resulting in local density abnormalities. The marked data set lays the foundation for subsequent parameter adjustment.

[0146] In the seventh determination unit 52, the parameter mapping tool associates and matches the density data of the high-risk area with the demolding speed and mold temperature to generate a preliminary parameter adjustment scheme. For example, in the high-risk area, the current demolding speed is 5 mm / s, and the mold temperature is 180°C. The mapping tool analyzes historical data and finds that when the demolding speed is reduced to 4 mm / s and the mold temperature is adjusted to 175°C, the density value can tend to be within the normal range. The preliminary scheme sets the demolding speed in the range of 3.8-4.2 mm / s and the mold temperature in the range of 170-180°C for this area. This association and matching ensures the pertinence of parameter adjustment and provides data support for optimization.

[0147] In the thirteenth acquisition unit 53, the fuzzy control tool considers the stability of multiple parameter combinations when dynamically optimizing the preliminary scheme. Assuming that in the high-risk area, the tool analyzes multiple combinations of demolding speed and mold temperature and finds that the combination of 4 mm / s and 175°C shows high stability in historical data, and the density deviation can be reduced to within 5%. The fuzzy control tool extracts this combination as the optimal parameter configuration data through dynamic iteration.

[0148] In the second judgment unit 54, the parameter application tool real-time corresponds the optimized parameter configuration data with the actual demolding process and dynamically adjusts the demolding speed and mold temperature. For example, during the operation of the stamping equipment, the tool monitors that the density value of a certain area is still high, and adjusts the demolding speed to 4 mm / s and the mold temperature to 175°C in real time, and feedbacks the changes in density distribution through sensors. Assuming that after adjustment, the density value is reduced to 2.05 g / cm³, which meets the preset condition of reducing the risk of cracks, i.e., the deviation is controlled within 5%. The finally generated control strategy data provides accurate guidance for subsequent production. If extended to more complex working conditions, the core scheme can analyze the density distribution characteristics under different stamping speeds through the parameter mapping tool based on multiple historical data to further refine the adjustment range.

[0149] The magnetic material hydraulic forming control system disclosed in the embodiment has the following beneficial effects compared with the prior art:

[0150] I. Data preprocessing improves control accuracy

[0151] 1. Real-time accurate collection of dynamic parameters: Cover the hydraulic system and mold equipment with a sensor array to obtain real-time pressure, displacement and other key parameters, avoid errors caused by single-point sampling, and ensure data integrity.

[0152] 2. Data fusion denoising and smoothing: Use data fusion algorithms to preprocess dynamic parameters, eliminate signal fluctuations and noise interference, and generate smooth pressure-displacement time series data to provide reliable input for subsequent control models and improve the reliability of basic data (such as reducing pressure fluctuation error by more than 30%).

[0153] II. Pressure-displacement collaborative control optimizes the forming process

[0154] 1. Support vector machine modeling for dynamic mapping: Train a pressure-displacement collaborative control model through algorithm to accurately capture the nonlinear dynamic relationship between the two, breaking the limitations of traditional fixed parameter control and adapting to different material characteristics and forming stages (such as improving the pressure-displacement matching accuracy of complex magnetic core structures by 40%).

[0155] 2. Real-time deviation correction for stable pressure output: When the control deviation exceeds the threshold, real-time adjustment and optimization of parameter combinations through servo valve opening degree to generate a stable pressure application curve, avoiding uneven material deformation caused by pressure fluctuations and improving forming consistency (pressure fluctuation range can be controlled within ±2%).

[0156] III. Density distribution prediction prevents internal defects

[0157] 1. Neural network prediction of density uneven areas: Based on pressure-displacement data and material characteristics, use neural network algorithms to predict the spatial distribution of material density after forming, and identify local porosity or overpressure areas in advance (such as axial density deviation warning accuracy of more than 90%).

[0158] 2. Prospective quality control: Through density distribution prediction results, adjust process parameters during the forming process (rather than post-detection), reduce magnetic performance differences or structural defects caused by uneven density, and improve material performance uniformity.

[0159] IV. Demolding parameter optimization reduces the risk of cracks

[0160] 1. Dynamic adjustment of demolding strategy based on density prediction: During the demolding stage, adjust the demolding speed (such as reducing the speed in high-density areas to avoid pulling) and mold temperature (local heating to relieve stress concentration) according to the density distribution results to achieve "on-demand demolding".

[0161] 2. Fuzzy control algorithm improves demolding flexibility: By optimizing the combination of demolding parameters through fuzzy logic, it adapts to the complex needs of different density distribution scenarios, effectively reduces the risk of cracks caused by demolding stress (crack rate can be reduced by more than 50%), and improves the yield of finished products.

[0162] Five, system-level benefits: intelligentization of the whole process and improvement of production efficiency

[0163] 1. Full closed-loop control improves automation level: From parameter collection, model optimization to demolding control, a complete closed loop is formed, reducing manual intervention, lowering the operation threshold, and suitable for batch automated production.

[0164] 2. Material and energy consumption optimization: Precise control reduces material waste (such as a 25% reduction in corner loss), and stable pressure curves and demolding strategies can reduce equipment energy consumption (energy consumption is reduced by 15-20% compared with the same period), combining quality and cost advantages.

[0165] Although the preferred embodiments of the present application have been described, those skilled in the art can make further changes and modifications to these embodiments once they know the basic inventive concept. Therefore, the appended claims are intended to include the preferred embodiments and all changes and modifications falling within the scope of the present application. Obviously, those skilled in the art can make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A magnetic material hydraulic forming control system, characterized in that: include: A first acquisition module (10) is used to acquire dynamic parameters from the hydraulic system and the mold equipment through a sensor array, and pre-process the dynamic parameters using a data fusion algorithm to obtain smooth pressure data and displacement time series data; A second acquisition module (20) is used to train a pressure and displacement collaborative control model using a support vector machine algorithm based on the smoothed pressure data and displacement time series data, determine a dynamic mapping relationship between pressure and displacement, and obtain an optimized control parameter combination; A third acquisition module (30) is configured to adjust the servo valve opening of the hydraulic system in real time, combine the optimized control parameter combination, and correct the pressure output to obtain a stable pressure application curve if the control deviation of the dynamic mapping relationship between pressure and displacement exceeds a preset threshold; A fourth acquisition module (40) is used to predict the distribution state of material density using a neural network algorithm based on the stable pressure application curve and the displacement time series data, determine whether there is a density uneven area, and obtain a density distribution prediction result; The fifth acquisition module (50) is used to adjust the demoulding speed and mold temperature according to the predicted result of the density distribution at the beginning of the demoulding process, and optimize the demoulding parameters using a fuzzy control algorithm to obtain a demoulding control strategy that reduces the risk of cracks.

2. The magnetic material hydraulic forming control system according to claim 1, characterized in that: The first acquisition module (10) comprises: A first acquisition unit (11) is used to collect dynamic parameters from the hydraulic system and the mold equipment in real time through a sensor array to obtain an initial parameter data set; A generating unit (12) is used to perform denoising processing on the collected pressure information and displacement information using a data fusion algorithm based on the initial parameter data set, and generate a smoothing parameter set that has undergone preliminary processing; A first determination unit (13) is used to detect abnormal values ​​of the pressure sequence and the displacement sequence using a preset threshold range for the smoothing parameter set, and if abnormal data exceeding the threshold is detected, interpolation correction is performed on the abnormal data to determine a corrected parameter sequence; A second acquisition unit (14) is used to obtain the corrected parameter sequence, and to extract the trend of the pressure sequence and the displacement sequence using a time series analysis method to obtain parameter change trend data; A first judgment unit (15) is used to monitor the operating status of the hydraulic system and the mold equipment in real time through parameter change trend data, and if the trend data deviates from a preset normal range, a state abnormality mark is triggered to judge potential operating risks; The third acquisition unit (16) is used to predict the pressure and displacement trends in the future period of time based on the state abnormality mark and in combination with the historical time series data using the Kalman filter algorithm to obtain a prediction trend data set; The second determination unit (17) is used to generate a dynamic adjustment strategy for the predicted trend data set, and if the predicted trend shows that the abnormality persists, fine-tune the control parameters of the hydraulic system to determine the optimized operating parameter configuration.

3. The magnetic material hydroforming control system according to claim 2, characterized in that: The dynamic parameters in the first acquisition unit (11) cover multi-dimensional information, and the multi-dimensional information includes pressure information and displacement information.

4. The magnetic material hydroforming control system according to claim 2, characterized in that: In the first determination unit (13), the abnormality detection of the pressure data point is calculated by the following formula: in, Indicates the Anomaly detection identification of pressure data points, Indicates the pressure measurements, represents the mean of the pressure series, represents the standard deviation of the pressure series, Indicates the threshold multiplier coefficient; The displacement value after interpolation correction is: in, Indicates the Corrected displacement value at each position represents the previous normal displacement data point, represents the next normal displacement data point, represents the interpolation correction coefficient; The smoothing of parameter sequences by weighted averaging is achieved by the following formula: in, Indicates the The smoothing parameter value at each location, represents the smoothing window length, Indicates the weight coefficients, represents a data point in the original parameter sequence.

5. The magnetic material hydroforming control system according to claim 2, characterized in that: In the first judgment unit (15), the overall deviation of the hydraulic system and mold equipment parameters from the normal range is calculated by the following formula: in, Indicates the parameter trend deviation, represents the number of monitoring parameters, Indicates the The current value of the parameter, represents the preset normal mean of the parameter; The risk of a single parameter deviating from the normal range is calculated using the following formula: in, Indicates the The risk assessment index of the parameters, Indicates the Real-time monitoring values ​​of parameters, Indicates the reference standard value of the parameter. Indicates the upper limit of the normal range of the parameter, Indicates the lower limit of the normal range of the parameter; The abnormal status mark is triggered by the following formula: in, Indicates abnormal status mark signal, Indicates the number of sampling points of trend data, Indicates the Trend data value at a moment, Indicates the trend reference value under normal conditions, Indicates the anomaly trigger threshold.

6. The magnetic material hydroforming control system according to claim 1, characterized in that: The second acquisition module (20) comprises: The fourth acquisition unit (21) is used to use a data comparison tool to match the change pattern of the pressure data and the displacement time series data in the time series point by point based on the acquired pressure data and displacement time series data, and to compare the matching results using a preset threshold range. If the deviation exceeds the threshold range, the corresponding time point is marked to obtain a marked deviation data set; A third determining unit (22) is used to perform numerical correction on the marked time points using a data interpolation tool for the marked deviation data set, obtain a corrected pressure data and displacement data set, and rearrange the corrected pressure data and displacement data set in a time series using a data integration tool to determine an integrated time series data set; A fifth acquisition unit (23) is configured to construct a dynamic correspondence between the pressure data and the displacement time series data using a data mapping tool based on the integrated time series data set, and process the nonlinear change portion of the correspondence using a feature extraction tool to obtain a characterized mapping relationship data set; The fourth determination unit (24) is used to compare the control parameters item by item using a parameter adjustment tool for the characterized mapping relationship data set, and if the parameter combination does not match the preset operating state, iteratively update the parameter value to determine the adjusted control parameter combination.

7. The magnetic material hydroforming control system according to claim 1, characterized in that: The third acquisition module (30) comprises: a sixth acquisition unit (31), configured to acquire real-time pressure data and displacement time series data from the hydraulic system, perform point-by-point matching on the pressure data and the displacement time series data using a time series tool, determine a dynamic correspondence between the pressure data and the displacement time series data in the time series, and obtain an initial mapping data set; a seventh acquisition unit (32), configured to calculate, for the initial mapping data set, a control deviation between the pressure data and the displacement data using a deviation calculation tool, and if the deviation exceeds a preset threshold, mark the exceeding threshold time point using a marking tool to obtain a marked deviation data set; A fifth determining unit (33) is configured to adjust the opening of the servo valve of the hydraulic system using a servo valve control tool according to the marked deviation data set, iteratively update the control parameters in combination with a parameter optimization tool, and determine an adjusted servo valve opening parameter combination; An eighth acquisition unit (34) is used to process the adjusted servo valve opening parameter combination through a pressure output tool to generate corrected pressure output data, and to smooth the corrected pressure output data using a curve fitting tool to obtain a stable pressure application curve.

8. The magnetic material hydroforming control system according to claim 1, characterized in that: The fourth acquisition module (40) comprises: a ninth acquisition unit (41) for acquiring corresponding data points from the stable pressure application curve and the displacement sequence, performing point-by-point correspondence processing on the time axis using a data mapping tool, generating an initial distribution correlation data set, determining the dynamic relationship between the pressure application and the displacement sequence, and obtaining preliminary distribution characteristic data; The tenth acquisition unit (42) is used to extract the material characteristics in sections based on the preliminary distribution characteristic data using the state analysis tool, and compare the characteristic values ​​of each region with the region judgment tool. If the characteristic value of a certain region deviates from a preset threshold range, the region is marked as a potential uneven region, thereby obtaining a marked region data set; An eleventh acquisition unit (43) is used to use a depth prediction tool to perform detailed calculations on the density distribution of the marked regional data set, generate a corresponding density distribution prediction map, determine whether there is an uneven density area, and obtain predicted distribution state data; The sixth determination unit (44) is used to perform a multi-dimensional comparison on the predicted distribution state data using a distribution evaluation tool, obtain an evaluation index for each area, perform a one-by-one verification in combination with an unevenness detection tool, and determine a final density distribution prediction result.

9. The magnetic material hydroforming control system according to claim 1, characterized in that: The fifth acquisition module (50) comprises: A twelfth acquisition unit (51) is used to analyze the density value of the regional data point by point using a data comparison tool based on the regional data obtained from the density distribution prediction result, and if the density value exceeds a preset threshold range, it is marked as a high-risk area to obtain a marked distribution data set; a seventh determination unit (52) for correlating and matching the density data of the high-risk area with the initial values ​​of the demoulding speed and the mold temperature using a parameter mapping tool for the marked distribution data set, generating a preliminary parameter adjustment plan, and determining the adjustment range of each area; a thirteenth acquisition unit (53), configured to dynamically optimize the preliminary parameter adjustment scheme using a fuzzy control tool, extract the optimal demoulding speed and mold temperature combination from the adjustment range, and obtain optimized parameter configuration data; The second judgment unit (54) is used to match the optimized parameter configuration data with the actual demoulding process in real time through a parameter application tool, dynamically adjust the speed and temperature according to the density distribution characteristics, judge whether the preset conditions for crack risk reduction are met, and obtain the final control strategy data.

10. The magnetic material hydroforming control system according to claim 9, characterized in that: In the thirteenth acquisition unit (53), the parameter mapping tool adopts MATLAB / Simulink fuzzy logic toolbox.

Images