Intelligent control method and system for crimping machine

Abstract

The invention relates to the technical field of crimping machine control, and discloses an intelligent control method for a crimping machine, and the method comprises the steps: obtaining a rubber hose joint parameter set; calculating an initial interval according to information such as the outer diameter, the wall thickness and the hardness, and determining a buckling interval value; deriving a target positioning coordinate based on the spacing value, generating a motor driving signal, and performing PID optimization; executing a driving signal to collect a buckling head track, and if the deviation exceeds a threshold value, correcting a target positioning coordinate; collecting pressure, deformation and temperature according to the corrected coordinates, calculating a damping coefficient and a buckling speed, and generating a real-time damping parameter set; based on the parameter set, optimizing a driving signal, executing the optimized signal, collecting monitoring data, and using gradient descent feedback to correct output until an accurate buckling head positioning result is obtained; and the outer diameter, the wall thickness, the roughness and the end face angle after machining are collected in combination with the result and compared with the parameter set to evaluate machining deviation, and a crimping machine quality evaluation result is output. The method can solve the problem that the machining precision is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of buckle press machine control, and particularly relates to an intelligent control method and system of a buckle press machine. BACKGROUND

[0002] Industrial control systems are important infrastructure in modern manufacturing and processing links, widely used in production line automation, equipment operation monitoring and process management. It is composed of sensors, actuators, controllers and human-computer interaction interface, through real-time acquisition and response to key parameters, to realize the precise control of equipment operation state. With the development of manufacturing industry to high precision and multi-species, industrial control system not only bears the role of stable production line and improves efficiency, but also needs to adapt to the parameter change and dynamic response under complex working conditions, to ensure the consistency of product quality and the safety of production process. The existing buckle press machine control technology adopts the method of setting fixed parameters to determine the buckle pressing distance and damping parameters, and relies on manual adjustment to realize control when processing rubber pipe joints. This kind of method can meet the basic production demand when dealing with standardized joints, but when facing joints of different specifications and different material characteristics, the parameter acquisition and calculation process is often not comprehensive and flexible. Especially when the joint diameter, wall thickness, material hardness and other parameters fluctuate or are non-standard, the traditional method is difficult to dynamically adapt, resulting in inaccurate calculation of buckle pressing distance and decreased processing precision.

[0003] In summary, the existing technology has the problem of decreased processing precision due to incomplete parameter acquisition. SUMMARY

[0004] The present application provides an intelligent control method and system of a buckle press machine to solve the problem of decreased processing precision.

[0005] In a first aspect, to solve the above technical problems, the present application provides an intelligent control method for a crimping machine, comprising: obtaining a set of parameters of a rubber pipe joint; generating an initial spacing value based on the set of parameters of the rubber pipe joint; calculating a target positioning coordinate based on the crimping spacing value, and generating and optimizing a motor driving signal to obtain a motor driving signal; executing the motor driving signal and collecting the actual movement trajectory of the crimping head in real time, and if the actual movement trajectory deviation exceeds a preset deviation threshold, correcting the target positioning coordinate to determine a corrected positioning coordinate; generating and dynamically adjusting a damping coefficient based on the corrected positioning coordinate to obtain a set of real-time damping parameters; optimizing the motor driving signal based on the set of real-time damping parameters to obtain an optimized motor driving signal; executing the optimized motor driving signal, collecting monitoring data in real time, and based on the monitoring data, feeding back and correcting the optimized motor driving signal until a final crimping head positioning result is obtained; and performing quality evaluation analysis based on the final crimping head positioning result to obtain a crimping machine processing quality evaluation result.

[0006] Preferably, the initial spacing value is generated based on the set of parameters of the rubber pipe joint, comprising: obtaining a material elasticity coefficient; normalizing the joint outer diameter data, wall thickness distribution value and material hardness parameter in the set of parameters of the rubber pipe joint, and generating an initial spacing value to obtain an initial spacing; monitoring the initial spacing based on the geometric shape data in the set of parameters of the rubber pipe joint, and if a non-standard joint identifier is monitored, adjusting the initial spacing based on a preset classification rule to obtain an adjusted spacing; and based on the adjusted spacing and the material elasticity coefficient, performing weighted calculation to obtain a weighted value, and if the weighted value exceeds a preset weighted threshold, iteratively adjusting the weight until the weighted value meets the weighted threshold, thereby obtaining the crimping spacing value.

[0007] Preferably, the target positioning coordinate is calculated based on the crimping spacing value, and a driving signal is generated and optimized to obtain a motor driving signal, comprising: calculating a target positioning coordinate based on the crimping spacing value to obtain a target positioning coordinate; converting the target positioning coordinate into a pulse sequence to generate a corresponding initial motor driving signal; and using a PID algorithm to correct the initial motor driving signal to obtain a motor driving signal.

[0008] Preferably, the motor drive signal is executed, and the actual movement trajectory of the buckling head is collected in real time. If the actual movement trajectory deviates beyond the preset deviation threshold, the target positioning coordinates are corrected to determine the corrected positioning coordinates, including: performing coordinate difference calculation according to the actual movement trajectory and the target positioning coordinates to obtain a coordinate difference value; if the coordinate difference value exceeds the preset deviation threshold, the target positioning coordinates are corrected using a Kalman filter algorithm to obtain the corrected positioning coordinates.

[0009] Preferably, the damping coefficient generation and dynamic adjustment are performed according to the positioning coordinates to obtain a real-time damping parameter set, including: triggering the sensor of the positioning coordinates to collect the buckling force distribution value, the joint deformation amount, and the environmental temperature; and performing standardization processing to obtain the standardized buckling force distribution value, the standardized joint deformation amount, and the standardized environmental temperature; analyzing the correlation between the standardized buckling force distribution value and the standardized joint deformation amount, combining the standardized environmental temperature, performing damping coefficient calculation, and dynamically adjusting to obtain the real-time damping parameter set.

[0010] Preferably, the motor drive signal is optimized based on the real-time damping parameter set to obtain an optimized motor drive signal, including: based on the real-time damping parameter set, the buckling force distribution value, and the joint deformation amount, performing collaborative stability calculation to obtain a collaborative stability value; if the collaborative stability value is lower than the preset stability threshold, the motor drive signal is optimized using a particle swarm optimization algorithm to obtain the optimized motor drive signal.

[0011] Preferably, the optimized motor drive signal is executed, real-time monitoring data is collected, and the optimized motor drive signal is feedback corrected based on the monitoring data until the final buckling head positioning result is obtained, including: obtaining a real-time movement trajectory, a real-time joint deformation amount, and a real-time surface roughness value; based on the real-time movement trajectory and the real-time joint deformation amount, combining a preset target trajectory, calculating a trajectory deviation value; if one of the trajectory deviation value and the real-time surface roughness value exceeds its preset precision threshold, it is determined that the precision is insufficient; when the precision is insufficient, the gradient descent algorithm is used to feedback correct the optimized motor drive signal, and the iterative optimization is continued until the trajectory deviation value and the surface roughness deviation are less than the preset precision threshold, thereby outputting the final buckling head positioning result.

[0012] Preferably, the quality evaluation analysis based on the final crimping head positioning result to obtain the crimping machine processing quality evaluation result comprises: obtaining a multi-dimensional processing data set based on the final crimping head positioning result; performing normalization processing on the multi-dimensional processing data set and calculating a processing deviation value to obtain the processing deviation value; and performing quality evaluation analysis based on the processing deviation value to obtain the crimping machine processing quality evaluation result.

[0013] In a second aspect, the present application provides an intelligent control system of a crimping machine, comprising: a data acquisition module configured to acquire a hose joint parameter set; a spacing value module configured to generate an initial spacing value based on the hose joint parameter set to obtain a crimping spacing value; a drive signal module configured to calculate a target positioning coordinate based on the crimping spacing value and generate and optimize a motor drive signal to obtain an optimized motor drive signal; a positioning coordinate module configured to execute the motor drive signal, collect a crimping head actual motion trajectory in real time, correct the target positioning coordinate if the actual motion trajectory deviation exceeds a preset deviation threshold, and determine a corrected positioning coordinate; a damping parameter set module configured to generate and dynamically adjust a damping coefficient based on the corrected positioning coordinate to obtain a real-time damping parameter set; an optimization module configured to optimize the motor drive signal based on the real-time damping parameter set to obtain the optimized motor drive signal; a final positioning module configured to execute the optimized motor drive signal, collect monitoring data in real time, and perform feedback correction on the optimized motor drive signal based on the monitoring data until a final crimping head positioning result is obtained; and an evaluation result module configured to perform quality evaluation analysis based on the final crimping head positioning result to obtain a crimping machine processing quality evaluation result.

[0014] In a third aspect, the present application further provides an electronic device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the intelligent control method of the crimping machine according to any one of the above aspects when executing the computer program.

[0015] In a fourth aspect, the present application further provides a computer readable storage medium comprising a stored computer program, wherein the computer readable storage medium controls a device where the computer readable storage medium is located to perform the intelligent control method of the crimping machine according to any one of the above aspects when the computer program runs.

[0016] Compared with the prior art, the present application has the following beneficial effects: (1) In the process of obtaining the rubber pipe joint parameter set and calculating the initial spacing, the actual characteristics of the joint can be more comprehensively reflected by collecting multi-dimensional parameters such as joint outer diameter, wall thickness, material hardness and performing normalization processing. Combined with the material elastic coefficient, weighted calculation is performed and non-standard joints are adjusted, so that the calculation of the clamping spacing is closer to the actual working condition, and the processing error caused by single or abnormal parameters is reduced; (2) In the target positioning coordinate calculation and motor driving signal generation process, the clamping spacing is converted into a target coordinate, and the initial driving signal is corrected using a PID algorithm to achieve smooth control of the motor movement trajectory. This operation can effectively reduce the speed fluctuation and overshoot phenomenon in the positioning process, and improve the positioning accuracy of the clamping head; (3) In the damping parameter generation and dynamic adjustment link, the damping coefficient is calculated by real-time collection of clamping force distribution, joint deformation and environmental temperature, and standardization processing of the data, which can dynamically correct the control parameters with the wall thickness change rate. This operation enhances the stability of the system under complex load and temperature fluctuation, and avoids stress concentration and joint damage caused by improper damping during processing; (4) In the final positioning and quality evaluation process, the clamping head movement trajectory, joint deformation and surface roughness are monitored in real time, and if the deviation exceeds the accuracy threshold, the output is adjusted by iteration correction until the accuracy requirement is met. At the same time, the deviation analysis is performed on the multi-dimensional data after processing and the quality grade report is generated, which can realize the instant judgment and traceability of the clamping result, and provide data support for subsequent process optimization. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 is the intelligent control method flow diagram of the clamping machine provided by the first embodiment of the present application; Figure 2 is the intelligent control system structure diagram of the clamping machine provided by the second embodiment of the present application. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0019] Referring to Figure 1 , the first embodiment of the present application provides an intelligent control method of a clamping machine, including the following steps: S11, obtaining a rubber pipe joint parameter set; S12, generating initial interval values according to the hose joint parameter set to obtain a crimping interval value; S13, calculating target positioning coordinates based on the crimping interval value, and generating and optimizing a motor driving signal to obtain a motor driving signal; S14, executing the motor driving signal and collecting real-time actual movement trajectories of the crimping head, and if the actual movement trajectory deviation exceeds a preset deviation threshold, correcting the target positioning coordinates to determine corrected positioning coordinates; S15, generating and dynamically adjusting a damping coefficient according to the corrected positioning coordinates to obtain a real-time damping parameter set; S16, optimizing the motor driving signal based on the real-time damping parameter set to obtain an optimized motor driving signal; S17, executing the optimized motor driving signal, collecting real-time monitoring data, and based on the monitoring data, feeding back and correcting the optimized motor driving signal until a final crimping head positioning result is obtained; S18, performing quality evaluation analysis according to the final crimping head positioning result to obtain a crimping machine processing quality evaluation result.

[0020] In step S11, a hose joint parameter set is obtained.

[0021] It is worth noting that the hose joint parameter set includes the outer diameter data, wall thickness distribution value, material hardness parameter, and joint geometric shape data of the hose joint.

[0022] The system obtains the outer diameter data of the hose joint through a laser range finder, which collects the radial distance of each point on the circumference once per second. Taking a batch of joints as an example, the collection results are three groups of data: 50.2mm, 50.3mm and 50.1mm, indicating that the outer diameter is within the allowable range. Secondly, the wall thickness distribution value is obtained by an ultrasonic thickness gauge, the sensor is close to the joint wall, and continuous measurement is performed from multiple angles to obtain wall thickness data such as 2.5mm, 2.4mm and 2.3mm. When obtaining the hardness of the hose joint, a Shore hardness tester is used for indentation rebound testing. During testing, the pressure needle of the hardness tester is vertically pressed into the surface of the hose joint, and is kept for 3 seconds under a specified load to ensure that the material reaches a stable deformation state. The hardness tester has a spring and a pointer mechanism inside, and the hardness of the material is reflected by the rebound distance of the pressure needle corresponding to the dial reading.

[0023] In a specific calculation, the corresponding relationship between the depth of the pressure pin into the material and the standard scale is obtained. For example, the scale range of the Shore A hardness tester is 0 to 100, the maximum depth of the pressure pin pressed into the material is 2.5 mm, and the scale 0 corresponds to the scale 100 when the pressure pin is not pressed at all. Assuming that the test pressure depth is 0.375 mm, the hardness value is 100-(0.375 ÷ 2.5 × 100) = 85, that is, the hardness is 85.

[0024] The extraction of the joint geometry is completed by a three-dimensional optical scanner to collect and process point cloud data. The specific steps are as follows: fix the measured rubber pipe joint on a rotatable workbench, scan the joint surface layer by layer through structured light or laser line bundle, and record the surface reflection signal to form high-density three-dimensional point cloud data. After filtering and coordinate registration of the point cloud data, a complete joint outer contour model is generated.

[0025] In step S12, according to the rubber pipe joint parameter set, the initial spacing value is generated, and the clamping spacing value is obtained, including: obtaining the material elastic coefficient; normalizing the joint outer diameter data, wall thickness distribution value and material hardness parameter in the rubber pipe joint parameter set, and generating the initial spacing value; based on the geometric shape data in the rubber pipe joint parameter set, the initial spacing is monitored, if the non-standard joint identifier is monitored, the initial spacing is adjusted according to the preset classification rule to obtain the adjusted spacing; based on the adjusted spacing combined with the material elastic coefficient, the weighted value is obtained by weighted calculation, if the weighted value exceeds the preset weighted threshold, the weight is iteratively adjusted until the weighted value meets the weighted threshold, so as to obtain the clamping spacing value.

[0026] It is worth noting that the material elastic coefficient is first obtained by uniaxial tensile test, specifically the material sample is fixed at both ends of the tensile device, the tensile force is applied at a constant speed and the corresponding relationship between stress and strain is recorded, and the elastic modulus is calculated according to the linear section of the stress-strain curve. For example, when the stress is 200 MPa and the strain is 0.001, the elastic coefficient can be determined as 200 MPa. After obtaining the elastic coefficient, the data standardization process is performed combined with the outer diameter data, wall thickness distribution value and material hardness parameter in the rubber pipe joint parameter set to ensure the comparability of different dimension data. In the standardization process, the minimum and maximum value method is adopted, the measured outer diameter such as 50.2 mm is mapped to the 0.5 interval value, the wall thickness 2.4 mm is mapped to the 0.4 interval value, and the hardness 85 is mapped to the 0.6 interval value.

[0027] After normalization, the outer diameter, wall thickness and hardness parameters of the joint are divided into intervals according to preset classification rules, so as to adjust the clamping distance according to different combinations. The rules define the judgment criteria of each parameter at the normalized value: the outer diameter normalized value is between 0.3 and 0.5, defined as medium, less than 0.3, judged as small, and greater than 0.5, judged as large; the wall thickness normalized value is less than 0.35, judged as thin wall, between 0.35 and 0.65, judged as medium wall thickness, and greater than 0.65, judged as thick wall; the hardness normalized value is less than 0.4, judged as soft material, between 0.4 and 0.7, judged as medium hardness, and greater than 0.7, judged as high hardness. Through the classification rules, various joint characteristics can be combined, such as "medium outer diameter + thin wall + high hardness", "large outer diameter + thick wall + soft material" and other different combinations.

[0028] Each combination corresponds to a different clamping distance setting, for example, the initial distance is 0.8 mm for medium outer diameter and thin wall high hardness, the distance is reduced to 0.6 mm for large outer diameter and thick wall high hardness to prevent overpressure, and the distance can be widened to 1.0 mm for small outer diameter and thin wall soft material to avoid joint loosening. Then the geometric feature is introduced into the monitoring step, if the roundness deviation obtained by three-dimensional scanning exceeds the standard limit value of 0.02 mm, it means that the joint is a non-standard type, and the initial distance needs to be adjusted. The adjustment method is to increase the compensation value based on the original distance, such as increasing 0.1 mm.

[0029] After adjustment, the material elastic coefficient obtained in the previous step is introduced for weighted calculation. The weighting formula assigns weights to the outer diameter, wall thickness, hardness and elastic coefficient, such as outer diameter weight 0.4, wall thickness weight 0.3, hardness weight 0.2, and elastic coefficient weight 0.1, and the weighted distance value is obtained by summing the product of each parameter and weight. Assuming that the weighted result is 0.88 mm, compared with the preset weighted threshold value 0.9 mm, if there is still deviation, adjust the weight of hardness or wall thickness, recalculate the weighted value until it meets the threshold value. The setting of the weighted threshold value 0.9 mm is based on the safety compression limit and sealing performance requirement of the rubber joint during clamping. When the clamping distance is controlled within 0.8-1.0 mm, the joint can meet the sealing pressure requirement of more than 2 MPa, and will not produce permanent plastic deformation or material cracks. Further, the intermediate conservative value 0.9 mm is selected as the fixed threshold value, which not only ensures sufficient safety margin under all conventional outer diameter, wall thickness and hardness combinations, but also considers the sealing stability and repeatability of processing.

[0030] Finally, the weighted result is converted into the actual clamping distance by de-masking, for example, the final clamping distance is determined as 0.9 mm.

[0031] In step S13, based on the pressing interval value, the target positioning coordinates are calculated, and the driving signal generation and optimization are performed to obtain the motor driving signal, including: according to the pressing interval value, the target positioning coordinates are calculated to obtain the target positioning coordinates; the target positioning coordinates are converted into a pulse sequence to generate a corresponding initial motor driving signal; the initial motor driving signal is corrected by using a PID algorithm to obtain the motor driving signal.

[0032] It is worth noting that when calculating the target positioning coordinates, the pressing interval, the joint outer diameter, the wall thickness and the end face angle need to be integrated into the same three-dimensional coordinate system for derivation. The joint center axis is taken as the Z axis, the end face center point is taken as the coordinate origin, the radial direction is taken as the X axis, and the tangential direction is taken as the Y axis to establish a calculation reference. First, the parameters are determined: the pressing interval is 0.9 mm, the joint outer diameter is 50.2 mm, the end face angle is 45 degrees, and the wall thickness is 2.4 mm. The joint outer diameter takes the radius of 25.1 mm as the radial basis length, and the end face angle is triangularly decomposed: the X component is 25.1*cos45°≈17.75 mm, and the Y component is 25.1*sin45°≈17.75 mm. Considering the shrinkage effect of the wall thickness on the pressing path, the half wall thickness needs to be subtracted in the radial direction, i.e. 1.2 mm is subtracted in the X and Y directions, and the corrected X≈16.55 mm and Y≈16.55 mm are obtained. The pressing interval is directly taken as the Z direction displacement, and the Z coordinate is 0.9 mm. The final target positioning point coordinates are (16.55 mm, 16.55 mm, 0.9 mm).

[0033] After the target positioning coordinates are determined, the coordinate information needs to be converted into a pulse signal executable by the motor. The pulse signal is a direct control instruction of the motor, which is often defined in terms of "pulse number and displacement correspondence", for example, 1000 pulses correspond to 1 mm of motor movement. The three-axis displacement of the target coordinates is multiplied by the corresponding pulse scaling factor to obtain the required pulse number of each axis. Assuming that the target positioning coordinates are X axis 10 mm, Y axis 5 mm and Z axis 2 mm, 10000, 5000 and 2000 pulses are required respectively. These pulses are output to the driver in time sequence to form an initial motor driving signal to drive the pressing head to move along the predetermined path.

[0034] In order to improve the stability of the movement of the pressing head and the positioning accuracy, the initial driving signal needs to be further corrected, and the proportional integral derivative method is used to optimize the movement trajectory. The optimization process starts from the real-time acquisition of the feedback signal, and the feedback signal includes the deviation of the current pressing head position and the target coordinate. First, the proportional element directly amplifies the deviation, for example, the deviation is 0.1 mm, and the correction value of 0.15 mm is calculated according to the proportional coefficient 1.5, so that the control output responds quickly. Secondly, the integral element accumulates multiple deviations to eliminate systematic errors existing for a long time, for example, the cumulative compensation amount of 0.25 mm is obtained by accumulating the deviation of 0.05 mm for 5 times. Finally, the derivative element predicts the future trend according to the rate of change of the deviation, and when the deviation increases from 0.05 mm to 0.15 mm, the derivative element will output a reverse correction amount to suppress the overshoot. The three are superimposed to obtain the final correction amount, and the pulse output frequency and quantity are adjusted in real time, so that the motor trajectory is more consistent with the target path.

[0035] In step S14, the motor driving signal is executed, and the actual movement trajectory of the pressing head is acquired in real time. If the actual movement trajectory deviation exceeds the preset deviation threshold, the target positioning coordinate is corrected, and the corrected positioning coordinate is determined, including: according to the actual movement trajectory and the target positioning coordinate, the coordinate difference value is calculated to obtain the coordinate difference value; if the coordinate difference value exceeds the preset deviation threshold, the Kalman filtering algorithm is used to correct the target positioning coordinate to obtain the corrected positioning coordinate.

[0036] It is worth noting that after executing the motor driving signal, the actual movement trajectory of the pressing head needs to be continuously monitored and compared with the target positioning coordinate, so as to judge whether there is a deviation exceeding the allowed range, and to correct according to the deviation result. The specific operation process is as follows: first, the displacement data of the pressing head is acquired in real time by the optical encoder installed on the motor shaft. The encoder outputs a position coordinate every millisecond, with an accuracy of 0.01 mm. At the same time, the motion speed information is obtained by cooperating with the speed sensor to ensure the continuity and integrity of the trajectory data. The actual trajectory coordinates collected are compared point by point with the target positioning coordinates, and the coordinate difference calculation method is used to determine the trajectory deviation. For example, the target positioning coordinate is 10.00 mm, and the real-time trajectory feedback is 10.07 mm, so the deviation is 0.07 mm. The system compares this deviation with the preset deviation threshold, if the threshold is set to 0.05 mm, it is determined that it exceeds the allowed range at this time, and needs to enter the correction step.

[0037] The correction process is completed by the Kalman filtering algorithm to optimize the target positioning coordinates, and the outer diameter and wall thickness distribution of the joint are taken as state variables during calculation. First, according to the displacement signal of the motor at the last moment and the motion equation, the outer diameter and wall thickness are predicted. For example, the outer diameter is 20.00 mm and the wall thickness is 2.20 mm at the last moment, combined with the motor cumulative displacement of 800 pulses converted to 0.8 mm, the predicted current outer diameter is still 20.00 mm and the wall thickness is 2.20 mm. After prediction, the uncertainty of the predicted value needs to be evaluated, and the new prediction covariance is obtained by accumulating the last state covariance and the process noise. The process noise reflects the error caused by the motor movement and environmental disturbance, for example, the covariance is 0.04 square millimeters, the process noise is 0.02 square millimeters, and the prediction covariance is 0.06 square millimeters after accumulation. Then the real-time measurement value of the sensor is introduced for correction, for example, the actual measured outer diameter is 20.02 mm and the wall thickness is 2.18 mm, and the Kalman gain is calculated by substituting the difference between the predicted value and the measured value into the update formula. The calculation of Kalman gain is to divide the prediction covariance by the sum of the prediction covariance and the measurement noise, for example, the measurement noise is 0.02 square millimeters, then the gain is 0.06 ÷ (0.06 + 0.02) = 0.75.

[0038] The gain is used to weight and fuse the predicted value and the measured value to obtain the corrected state estimation: the outer diameter correction value is 20.00 + (20.02-20.00) x 0.75 = 20.015 mm, and the wall thickness correction value is 2.20 + (2.18-2.20) x 0.75 = 2.185 mm. The corrected geometric parameters are substituted into the three-dimensional coordinate superposition calculation, and the outer diameter and wall thickness changes are converted into radial and axial offsets respectively and added to the original coordinates to obtain new coordinates, for example, the original positioning coordinates are 10.00 mm, and the corrected superposition obtains 10.08 mm. Through the above prediction-correction cycle, the system can real-time inhibit the positioning error caused by noise and geometric fluctuation in motion, so that the final pressing head positioning accuracy is maintained within 0.05 mm.

[0039] In step S15, according to the positioning coordinates, the damping coefficient generation and dynamic adjustment are carried out to obtain a real-time damping parameter set, including: triggering the sensor of the positioning coordinates, collecting the pressing force distribution value, the joint deformation and the environmental temperature; and performing standardization processing to obtain the standardized pressing force distribution value, the standardized joint deformation and the standardized environmental temperature; analyzing the correlation between the standardized pressing force distribution value and the standardized joint deformation, combining the standardized environmental temperature, calculating the damping coefficient, and dynamically adjusting to obtain the real-time damping parameter set.

[0040] It is worth mentioning that the sensor will trigger the acquisition process after the positioning of the pressing head is completed. The pressure sensor records the pressure distribution data of each key point on the joint surface, the laser displacement sensor synchronously obtains the deformation amount of the joint under the force state, and the thermocouple sensor records the environmental temperature. These raw data need to be standardized after inputting into the system, with the pressure unit as MPa, the deformation unit as mm, and the temperature unit as °C. Through linear normalization method, the data of different dimensions are mapped to the range of 0 to 1, so that the subsequent calculation can be directly compared.

[0041] After completing the data standardization, the system uses the S-shaped function characteristics of logistic regression to analyze the nonlinear relationship between pressure distribution and joint deformation, in order to obtain the probability value of the coupling degree between the two. Assuming that the current standardized pressure distribution value is 0.72 (corresponding to the actual pressure of about 1.8 MPa), and the standardized joint deformation is 0.60 (corresponding to the actual deformation of 0.06 mm), the output value calculated by logistic regression is 0.87, indicating that the pressure distribution has a strong influence on the joint deformation. This value is further corrected in combination with the current temperature condition, for example, when the temperature is 40°C, according to the rule that the hardness of the material decreases with the increase of temperature, the correlation of 0.87 is corrected to 0.8, and the initial damping coefficient is set to 0.3 accordingly.

[0042] Subsequently, the system analyzes the change rate of the joint wall thickness. If the measured wall thickness values of two consecutive times are 2.25 mm and 2.37 mm respectively, the change rate is (2.37−2.25) / 2.25 ≈ 5.33%, which exceeds the set 5% warning threshold, and the system will trigger the adaptive adjustment logic. The system first corrects the damping coefficient according to the preset weighted adjustment method. The specific weighted adjustment process is based on the wall thickness change rate to increase the damping coefficient, for example, from 0.30 to 0.35, to enhance the inhibition effect on the unstable state of the material. If it is detected that the pressing speed exceeds 6.0 mm / s at the same time, indicating that there is a risk of impact in the pressing process, the acceleration correction weight is superimposed, and the damping coefficient is increased again based on the previous adjustment, for example, from 0.35 to 0.38, to realize dynamic inhibition of high-speed impact state. This weighted adjustment method adjusts the damping coefficient by superimposing the correction amount of different factors in sequence, so that the damping coefficient adjustment has pertinence and precision.

[0043] The pressing speed parameter is calculated in real time by the displacement and time data fed back by the motor. The system records the spatial displacement coordinates of the pressing head in continuous sampling, and the instantaneous speed value is obtained by dividing the displacement difference of the adjacent two samplings by the time interval. For example, if the pressing head moves from 10.00 mm to 10.25 mm in 0.05 seconds, the calculated speed is (10.25-10.00) / 0.05 = 5.0 mm / s. To avoid misjudgment caused by instantaneous fluctuations, the system takes a sliding average of the speed values of multiple sampling points to obtain a more stable speed parameter, which is included in the real-time damping parameter set.

[0044] In step S16, based on the real-time damping parameter set, the motor driving signal is optimized to obtain an optimized motor driving signal, including: Based on the real-time damping parameter set, the cooperative stability value is calculated by combining the pressing force distribution value and the joint deformation amount. If the cooperative stability value is lower than the preset stability threshold, the particle swarm optimization algorithm is used to optimize the motor driving signal to obtain an optimized motor driving signal.

[0045] It is worth noting that the pressing force distribution value, joint deformation amount, damping coefficient and pressing speed parameter extracted from the real-time damping parameter set collected by the system are standardized to make all data within the same dimension range directly calculable. For example, the pressure value is unified to megapascal units, and the original pressure of 0.8 to 2.5 megapascal is mapped to the 0 to 1 interval through linear normalization; the joint deformation amount original range is 0.02 to 0.15 mm, also mapped to 0 to 1 interval; the pressing speed range is 0.1 to 1.0 mm per second, also processed by the same method. This operation eliminates the dimensional differences between different physical quantities, making the subsequent cooperative stability calculation comparable and accurate.

[0046] When calculating the cooperative stability, the system comprehensively analyzes the change trend of the damping coefficient, the standardized pressure distribution and the joint deformation amount, measures the linear relationship between the pressing speed and the deformation amount by using the Pearson correlation coefficient, and calculates the stability score combined with the change amplitude of the damping coefficient. The specific operation is as follows: first, calculate the correlation coefficient of the pressure distribution and the deformation amount, for example, when the pressure is concentrated at 1.8 megapascal, the deformation amount is 0.06 mm, when the pressure increases to 2.2 megapascal, the deformation amount increases to 0.09 mm, the correlation coefficient is calculated to be 0.88; then, combined with the current damping coefficient 0.35, the coupling relationship between the speed and the deformation amount is weighted and superimposed, and the specific weighting and superimposition is set to 0.3 and 0.7 to form the cooperative stability value, the numerical range is 0 to 1, the closer to 1 indicates the more stable.

[0047] When the calculated stability value is lower than the preset stability threshold (e.g., 0.85), the system starts the particle swarm optimization algorithm to adjust the weights of the pressure distribution. The execution of this algorithm is to take the initial weights of each sampling point in the pressure distribution as the optimization target group, and through iterative updating of the speed and position of each weight, to find the weight combination that maximizes the stability value. Taking five pressure sampling points as an example, the initial weights are all 0.2, and after iterative algorithm, the optimization result may adjust the weight of the high stress area to 0.3, the weight of the low stress area to 0.15, and the rest proportionally, so that the control of the pressure concentration area is more precise, thereby improving the overall stability.

[0048] After optimization, the system recalculates the motor driving signal using the adjusted weights and generates a new pulse sequence to control the movement trajectory of the pressing head. First, multiply the pressure value of each pressure sampling point by its optimized weight one by one, for example, the pressure values of the five sampling points are 1.8 MPa, 2.0 MPa, 2.2 MPa, 1.9 MPa and 2.1 MPa, and the corresponding optimized weights are 0.3, 0.25, 0.2, 0.15 and 0.1, respectively. The weighted pressure calculation is 1.8 x 0.3 + 2.0 x 0.25 + 2.2 x 0.2 + 1.9 x 0.15 + 2.1 x 0.1 = 1.975 MPa. Then proportionally fuse the weighted pressure with the joint deformation deviation, for example, the joint deformation deviation is 0.09 mm, and the preset proportion coefficient is 0.5, the integrated control quantity is 1.975 x 0.5 + 0.09 = 1.0775 mm / s. The integrated control quantity is superimposed and corrected with the damping coefficient and the pressing speed parameter, if the damping coefficient is 0.35 and the pressing speed is 6.0 mm / s, then the final control quantity is 1.0775 + 0.35 x 0.2 + 6.0 x 0.05 = 1.4475.

[0049] When converting the control quantity into motor pulse signals, according to the system setting that 1000 pulses correspond to 1 mm displacement, 1.77 mm displacement needs to output 1770 pulses. To realize accurate positioning in three-dimensional coordinates, the system allocates pulses according to the X, Y and Z axes of the target coordinates, for example, X axis accounts for 50%, Y axis accounts for 30%, and Z axis accounts for 20%, corresponding to 885, 531 and 354 pulse signals. At this time, perform a stability calculation again, if the value increases to 0.9 or above, it means that the optimization is successful.

[0050] In step S17, the optimized motor driving signal is executed, real-time monitoring data is collected, and the optimized motor driving signal is feedback corrected based on the monitoring data until a final press head positioning result is obtained, including: obtaining a real-time motion trajectory, a real-time joint deformation, and a real-time surface roughness value; based on the real-time motion trajectory and the real-time joint deformation, a trajectory deviation value is calculated in combination with a preset target trajectory; if one of the trajectory deviation value and the real-time surface roughness value exceeds a preset precision threshold, it is determined that the precision is insufficient; when the precision is insufficient, the gradient descent algorithm is used to feedback correct the optimized motor driving signal, and the iteration optimization is continuously performed until the trajectory deviation value and the surface roughness deviation are less than the preset precision threshold, so as to output the final press head positioning result.

[0051] It is worth noting that the actual motion trajectory is obtained by installing a high-precision optical encoder on the shaft end of the motor. The encoder records the position change of the press head in the three-dimensional coordinate system every 0.1 seconds, and the coordinate accuracy reaches 0.01 millimeters. For example, when the press head moves from the coordinates (10.00, 5.00, 2.00) millimeters to (10.05, 5.03, 2.02) millimeters, the system can accurately record the displacement of this segment. The joint deformation is obtained by a laser displacement sensor, which continuously measures the distance of key points on the joint surface and can capture micro changes in the range of 0.01 to 0.2 millimeters. The surface roughness is monitored in real time by a contact-type roughness meter, which outputs the Ra value based on the probe scanning principle, and the measurement range is 0.8 to 2.5 microns.

[0052] The collected trajectory, deformation, and roughness data are first standardized after inputting into the system, so that different physical quantities can be directly compared in subsequent calculations. The processing process includes unifying the dimension, such as keeping the displacement as millimeters and the roughness as microns, while using a linear normalization formula, and mapping various parameters to the range of 0 to 1. Taking the trajectory data as an example, if the x-coordinate of the current sampling trajectory point is 10.05 millimeters, and the preset maximum and minimum value range is 9.50 to 10.50 millimeters, then the normalized value is (10.05-9.50) / (10.50-9.50)=0.55.

[0053] After standardization, the system calculates the deviation value between the actual motion trajectory and the target trajectory. The calculation method is to calculate the Euclidean distance between the two trajectories point by point under the same time sequence, and to calculate the average deviation. For example, the target trajectory point is (10.00, 5.00, 2.00) millimeters, and the actual trajectory point is (10.05, 5.03, 2.02) millimeters, then the single-point deviation is millimeters, and the total trajectory deviation is obtained by averaging the deviations of all sampling points, and compared with the set precision threshold (such as 0.03 millimeters). If the deviation exceeds the threshold, feedback correction process is needed.

[0054] The feedback correction uses a gradient descent algorithm to iteratively optimize the motor output parameters. The basic principle is to apply a reverse adjustment to the speed and torque according to the deviation, so that the next output converges in the direction of reducing the deviation. The specific operation is as follows: first, calculate the gradient of the current output parameter, that is, the partial derivative of the deviation with respect to the speed and torque. Assuming that the current deviation changes at a rate of -0.002 mm / rev with respect to the speed and 0.001 mm / N·m with respect to the torque, then the adjustment amount is the learning rate multiplied by the corresponding gradient. If the learning rate is set to 0.5, and the current speed is 500 rpm and the torque is 10 N·m, then the next iteration output adjustment is speed 500-0.5× (-0.002)=500.001 rpm, torque 10-0.5×0.001=9.9995 N·m. The new output signal drives the crimping head to move again and collect feedback data, and the cycle continues until the trajectory deviation and roughness deviation are both within the threshold.

[0055] Taking an actual running scenario as an example, in the processing of a batch of rubber pipe joints, the initial trajectory deviation is 0.07 mm and the surface roughness deviation is 0.6 microns, both of which are higher than the preset threshold (0.03 mm and 0.5 microns). The system triggers the gradient descent correction, and after three rounds of iterative optimization, the trajectory deviation is reduced to 0.021 mm and the roughness deviation is reduced to 0.48 microns, meeting the positioning accuracy requirements. The optimized motor output signal is recorded and stored for subsequent similar batches of joints to directly call the parameter combination, achieving fast and stable control.

[0056] In step S18, according to the final crimping head positioning result, quality evaluation analysis is performed to obtain a crimping machine processing quality evaluation result, including: based on the final crimping head positioning result, a multi-dimensional processing data set is obtained; the multi-dimensional processing data set is normalized and processing deviation value calculation is performed to obtain a processing deviation value; according to the processing deviation value, quality evaluation analysis is performed to obtain a crimping machine processing quality evaluation result.

[0057] It is worth noting that after the crimping head completes the final positioning and completes the crimping process, the system performs an independent quality detection on the processed rubber pipe joint to verify whether the final product meets the preset precision requirements. This detection is different from the parameters collected earlier for controlling the crimping process, and is mainly used to determine the quality of the finished product rather than to control the process, so it is necessary to re-collect the geometric dimensions and surface state of the finished product. The core data of the detection includes outer diameter, wall thickness distribution, surface roughness and connection end face angle, which are all based on the actual state after processing.

[0058] Specifically, the outer diameter and wall thickness distribution data are obtained by a laser scanner. The laser scanner scans around the joint surface, converts the reflected signal into a high-density three-dimensional point cloud, the point cloud spacing can reach 0.01 millimeters, and the size of each position on the joint circumference is recorded in real time. Taking a batch of detections as an example, the outer diameter of the finished joint is measured to be 25.00 to 25.10 millimeters, and the single-point error is not more than 0.02 millimeters; the wall thickness distribution is between 2.50 to 2.60 millimeters, and the error is not more than 0.01 millimeters. The surface roughness is measured by an optical instrument based on the white light interference principle, represented by the Ra value, the detection range is 1.0 to 2.0 microns, for example, the Ra of a certain joint is measured to be 1.5 microns. The connecting end face angle is detected by an optical projector, the angle deviation is judged by the included angle between the end face projection and the horizontal reference line, and the measurement accuracy is 0.1°, for example, the detection result is 45.2°.

[0059] After collection is completed, the system standardizes the above multi-dimensional data to ensure that each parameter can be directly compared in subsequent deviation calculation. The standardization method is consistent with the previous one, the outer diameter and wall thickness are kept in millimeter units, the roughness is kept in micrometer units, and the angle is kept in degree units. The data is mapped to the 0 to 1 interval through a linear normalization formula. For example, the outer diameter of 25.08 millimeters is within the preset range of 25.00 to 25.10 millimeters, and its normalized value is (25.08-25.00) / (25.10-25.00)=0.8. The wall thickness of 2.58 millimeters is normalized to 0.8 within the range of 2.50 to 2.60 millimeters, the roughness of 1.5 microns is normalized to 0.5 within the range of 1.0 to 2.0 microns, and the end face angle of 45.2° is normalized to 0.7 within the range of 44.5° to 45.5°.

[0060] Subsequently, the system compares the standardized detection data with the preset target parameter set before the swaging, and calculates the processing deviation value. The calculation method is to divide the difference between the measured value and the target value by the target value to obtain the relative deviation. For example, the target outer diameter is 25.05 millimeters, and the measured outer diameter is 25.08 millimeters, then the deviation is (25.08-25.05) / 25.05≈0.12%; the target wall thickness is 2.55 millimeters, and the measured wall thickness is 2.58 millimeters, then the deviation is (2.58-2.55) / 2.55≈1.18%. Similarly, after calculating the roughness and end face angle deviations, the system compares the deviations with the preset threshold values, for example, the outer diameter deviation threshold is 0.2%, the wall thickness deviation threshold is 2%, the roughness deviation threshold is 0.5 microns, and the angle deviation threshold is 0.2°. If any deviation exceeds the limit, it is determined that the processing precision does not meet the standard.

[0061] On the basis of the deviation determination, the system classifies the machining quality using preset logical rules: when the deviations of the four indexes are all lower than 80% of the respective threshold values, it is determined as "excellent"; when any one of the deviations falls between 80% and 100% of the threshold value, i.e. close to the threshold interval, the overall is determined as "good"; when two or more deviations exceed the respective threshold values, it is determined as "unqualified". For example, if the outer diameter deviation threshold value is 0.2%, and the measured deviation is 0.18%, it belongs to the close-to-threshold value, and if the roughness and angle simultaneously exceed the threshold values, it is directly determined as "unqualified". The quality level and detailed deviation value are stored in the database, and a quality evaluation report containing numerical values, charts and distribution curves is generated.

[0062] Referring to Figure 2 The second embodiment of the present application provides an intelligent control system of a crimping machine, comprising: a data acquisition module, configured to acquire a set of parameters of a rubber pipe joint; a spacing value module, configured to generate an initial spacing value based on the set of parameters of the rubber pipe joint, to obtain a crimping spacing value; a driving signal module, configured to calculate a target positioning coordinate based on the crimping spacing value, and to generate and optimize a motor driving signal, to obtain a motor driving signal; a positioning coordinate module, configured to execute the motor driving signal, and to collect an actual movement trajectory of a crimping head in real time, and if a deviation of the actual movement trajectory exceeds a preset deviation threshold value, to correct the target positioning coordinate to determine a corrected positioning coordinate; a damping parameter set module, configured to generate and dynamically adjust a damping coefficient based on the corrected positioning coordinate, to obtain a real-time damping parameter set; an optimization module, configured to optimize the motor driving signal based on the real-time damping parameter set, to obtain an optimized motor driving signal; a final positioning module, configured to execute the optimized motor driving signal, to collect monitoring data in real time, and to perform feedback correction on the optimized motor driving signal based on the monitoring data, until a final crimping head positioning result is obtained; and an evaluation result module, configured to perform quality evaluation analysis based on the final crimping head positioning result, to obtain a crimping machine machining quality evaluation result.

[0063] It should be noted that the intelligent control system of the crimping machine provided by the embodiments of the present application is used to execute all process steps of the intelligent control method of the crimping machine of the above-mentioned embodiments, and the working principles and beneficial effects of the two are one-to-one corresponding, and thus will not be repeated.

[0064] The embodiments of the present application also provide an electronic device. The electronic device comprises a processor, a memory, and a computer program stored in the memory and executable on the processor, such as an intelligent control program of a crimping machine. The processor implements the steps in the above-mentioned various embodiments of the intelligent control method of the crimping machine when executing the computer program, such as Figure 1The step S11 is shown. Alternatively, the processor implements the functions of the modules / units in each of the above apparatus embodiments when executing the computer program, such as the final positioning module.

[0065] For example, the computer program can be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present application. The one or more modules / units can be a series of computer program instruction segments capable of completing a specific function, which are used to describe the execution process of the computer program in the electronic device.

[0066] The electronic device can be a desktop computer, a notebook computer, a palm computer, a smart tablet and the like. The electronic device can include, but is not limited to, a processor, a memory. Those skilled in the art can understand that the above components are only examples of the electronic device and do not constitute a limitation on the electronic device, and can include more or less components than the above, or combine certain components, or different components, for example, the electronic device can also include an input / output device, a network access device, a bus and the like.

[0067] The processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor and the like. The processor is the control center of the electronic device, and connects all parts of the electronic device through various interfaces and lines.

[0068] The memory can be used to store the computer program and / or modules, and the processor realizes various functions of the electronic device by running or executing the computer program and / or modules stored in the memory, and calling data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required by a function (such as a sound playing function, an image playing function, etc.), and the like; and the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), and the like. In addition, the memory can include a high-speed random access memory, and can also include a nonvolatile memory, for example, a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state memory devices.

[0069] The modules / units integrated in the electronic device, if realized in the form of software function units and sold or used as independent products, can be stored in a computer readable storage medium. Based on this understanding, all or part of the processes in the above-mentioned embodiment methods can also be completed by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. The computer program can realize the steps of the above-mentioned various method embodiments when executed by a processor. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or some intermediate forms, etc. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the contents included in the computer readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.

[0070] It should be noted that the apparatus embodiments described above are merely illustrative, and the units described as separate units can or can not be physically separate, and the units displayed as units can or can not be physical units, i.e. can be located in one place, or can be distributed to multiple network units. Part or all of the modules can be selected to achieve the purpose of the embodiment scheme according to actual needs. In addition, the connection relationship between the modules in the apparatus embodiment provided by the present application indicates that there is a communication connection between them, which can be implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement it without creative labor.

[0071] The above specific embodiments further illustrate the purpose, technical scheme and beneficial effects of the present application. It should be understood that the above description is only a specific embodiment of the present application and is not intended to limit the protection scope of the present application. It is particularly pointed out that any modification, equivalent replacement, improvement, etc. made by those skilled in the art within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. An intelligent control method of a press machine, characterized by, The method comprises the following steps: acquiring a hose joint parameter set; generating an initial interval value based on the hose joint parameter set to obtain a pressing interval value; calculating a target positioning coordinate based on the pressing interval value, and generating and optimizing a driving signal to obtain a motor driving signal; executing the motor driving signal and collecting the actual motion trajectory of the pressing head in real time; if the actual motion trajectory deviation exceeds a preset deviation threshold, the target positioning coordinate is corrected to determine the corrected positioning coordinate; generating and dynamically adjusting a damping coefficient based on the corrected positioning coordinate to obtain a real-time damping parameter set; optimizing the motor driving signal based on the real-time damping parameter set to obtain an optimized motor driving signal; executing the optimized motor driving signal, collecting monitoring data in real time, and feeding back and correcting the optimized motor driving signal based on the monitoring data until the final pressing head positioning result is obtained; and performing quality evaluation analysis based on the final pressing head positioning result to obtain a pressing machine processing quality evaluation result.

2. The intelligent control method of the buckle press machine according to claim 1, wherein, The initial interval value is generated based on the hose joint parameter set to obtain a pressing interval value, which comprises the following steps: acquiring a material elasticity coefficient; normalizing the joint outer diameter data, wall thickness distribution value and material hardness parameter in the hose joint parameter set, and generating an initial interval value to obtain an initial interval; monitoring the initial interval based on the geometric shape data in the hose joint parameter set; if a non-standard joint identifier is monitored, adjusting the initial interval based on a preset classification rule to obtain an adjusted interval; and performing weighted calculation based on the adjusted interval and the material elasticity coefficient to obtain a weighted value; if the weighted value exceeds a preset weighted threshold, iteratively adjusting the weight until the weighted value meets the weighted threshold to obtain the pressing interval value.

3. The intelligent control method of the buckle press machine according to claim 1, wherein, The target positioning coordinate is calculated based on the pressing interval value to obtain a target positioning coordinate; the target positioning coordinate is converted into a pulse sequence to generate a corresponding initial motor driving signal; and the initial motor driving signal is corrected using a PID algorithm to obtain a motor driving signal.

4. The intelligent control method of the buckle press machine according to claim 3, characterized in that, The actual motion trajectory of the pressing head is collected in real time based on the execution of the motor driving signal; if the actual motion trajectory deviation exceeds a preset deviation threshold, the target positioning coordinate is corrected to determine the corrected positioning coordinate, which comprises the following steps: calculating the coordinate difference value based on the actual motion trajectory and the target positioning coordinate to obtain a coordinate difference value; if the coordinate difference value exceeds a preset deviation threshold, the target positioning coordinate is corrected using a Kalman filtering algorithm to obtain the corrected positioning coordinate.

5. The intelligent control method of the buckle press machine according to claim 1, wherein, The damping coefficient generation and dynamic adjustment according to the positioning coordinates includes triggering the sensor of the positioning coordinates to collect the clamping pressure distribution value, the joint deformation amount and the environmental temperature, performing standardization processing to obtain the standardized clamping pressure distribution value, the standardized joint deformation amount and the standardized environmental temperature, analyzing the correlation between the standardized clamping pressure distribution value and the standardized joint deformation amount, combining the standardized environmental temperature to perform damping coefficient calculation and dynamic adjustment, and thus obtaining the real-time damping parameter set.

6. The intelligent control method of the buckle press machine according to claim 5, wherein, The optimization of the motor driving signal based on the real-time damping parameter set includes performing collaborative stability calculation based on the real-time damping parameter set, combining the clamping pressure distribution value and the joint deformation amount, and obtaining a collaborative stability value; if the collaborative stability value is lower than a preset stability threshold, a particle swarm optimization algorithm is used to optimize the motor driving signal to obtain the optimized motor driving signal.

7. The intelligent control method of the buckle press machine according to claim 1, wherein, The execution of the optimized motor driving signal, real-time collection of monitoring data and feedback correction of the optimized motor driving signal based on the monitoring data until the final clamping head positioning result is obtained include obtaining a real-time motion trajectory, a real-time joint deformation amount and a real-time surface roughness value, calculating a trajectory deviation value based on the real-time motion trajectory and the real-time joint deformation amount and combining a preset target trajectory, determining that the accuracy is insufficient if one of the trajectory deviation value and the real-time surface roughness value exceeds a preset accuracy threshold, using a gradient descent algorithm to perform feedback correction on the optimized motor driving signal when the accuracy is insufficient, and continuously iterating and optimizing until the trajectory deviation value and the surface roughness deviation are both less than the preset accuracy threshold, and thus outputting the final clamping head positioning result.

8. The intelligent control method of the push-through machine according to claim 1, wherein, The quality evaluation analysis according to the final clamping head positioning result includes obtaining a multi-dimensional processing data set based on the final clamping head positioning result, performing normalization processing on the multi-dimensional processing data set, calculating a processing deviation value, performing quality evaluation analysis according to the processing deviation value, and obtaining a clamping machine processing quality evaluation result.

9. An intelligent control system for a crimping machine, characterized in that, The data acquisition module is configured to acquire a rubber pipe joint parameter set. The distance value module is configured to generate an initial distance numerical value based on the rubber pipe joint parameter set to obtain a clamping distance value. The driving signal module is configured to calculate a target positioning coordinate based on the clamping distance value, generate and optimize a driving signal to obtain a motor driving signal. The positioning coordinate module is configured to execute the motor driving signal, collect a clamping head actual motion trajectory in real time, correct the target positioning coordinate if the actual motion trajectory deviation exceeds a preset deviation threshold, and determine a corrected positioning coordinate. The damping parameter set module is configured to generate a damping coefficient and dynamically adjust it based on the corrected positioning coordinate to obtain a real-time damping parameter set. an optimization module, configured to optimize the motor driving signal based on the real-time damping parameter set to obtain an optimized motor driving signal; a final positioning module, configured to execute the optimized motor driving signal, collect monitoring data in real time, and perform feedback correction on the optimized motor driving signal based on the monitoring data until a final die head positioning result is obtained; an evaluation result module, configured to perform quality evaluation analysis according to the final die head positioning result to obtain a die head machining quality evaluation result.

10. An electronic device, comprising: A processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, the processor executes the computer program to implement the intelligent control method of the die head machine according to any one of claims 1 to 8.

Images