A method and system for controlling the temperature distribution of an edge-reinforced blow molding panel

Abstract

The present invention discloses a method and system for controlling the temperature distribution of an edge-reinforced blow-molded panel, which relates to the technical field of plastic production, and includes: predicting the true die temperature field that the die will present in the future after blow-molding the panel blank according to a pre-trained first machine learning model; calling a pre-configured genetic algorithm to obtain the ideal temperature field that the die should present after blow-molding the panel blank; judging whether the panel blank meets the conversion condition for entering the next cooling link according to the average true die temperature and the average target die temperature; when the conversion condition is not met, obtaining at least one target temperature-adjusting partition and the temperature adjustment amount corresponding to the target temperature-adjusting partition from all partitions; after performing a heating or cooling operation on the target temperature-adjusting partition according to the temperature adjustment amount, blow-molding the panel blank; the present invention is beneficial to accurately adjusting the die to ensure the production quality and yield rate of the panel finished product.

Description

Technical Field

[0001] The present invention relates to the technical field of plastic production, and particularly relates to a method and system for controlling the temperature distribution of an edge-reinforced blow-molded panel. Background Art

[0002] In the blow molding process of a hollow plastic panel, the temperature distribution of the mold has a significant impact on the final shape, thickness distribution, and structural strength of the product; in order to achieve local differential temperature control, the prior art usually divides the mold into multiple heating / cooling zones and separately configures temperature control units to adjust each zone.

[0003] However, the existing mold temperature control methods mainly rely on unified heating or regular temperature control strategies, lacking the ability to model and predict the actual evolution trend of the temperature field. In actual production, due to being far from the main heat source or having a complex cooling path in the edge area of the mold, there are often problems such as low temperature and control lag, which easily lead to defects such as insufficient thickness, warping, and streaks in the edge area of the panel, seriously affecting the consistency and mechanical properties of the finished product.

[0004] In addition, there is an obvious thermal coupling effect between the temperature control zones of the mold, that is, the adjustment of the temperature in one zone often affects the temperature distribution in other zones through heat conduction or structural coupling; most of the existing temperature adjustment strategies do not fully consider this factor, resulting in inaccurate temperature adjustment effects and even causing temperature offsets in other areas, affecting the overall temperature control stability.

[0005] Meanwhile, the traditional temperature control scheme lacks a systematic optimization mechanism, unable to select the most suitable temperature control zone according to the actual temperature difference and thermal coupling relationship, nor able to quantify the temperature adjustment amount, and often relies on manual experience setting, with large limitations in both adjustment efficiency and accuracy. Summary of the Invention

[0006] The purpose of the present invention is to provide a method and system for controlling the temperature distribution of an edge-reinforced blow-molded panel to solve the problems in the above background art.

[0007] To achieve the above purpose, the present invention provides the following technical solutions:

[0008] In the first aspect, the present invention provides a method for controlling the temperature distribution of an edge-reinforced blow-molded panel, including:

[0009] In the blow molding process, according to the pre-trained first machine learning model, predict the true mold temperature field that the mold will present in the future after blow molding the panel blank, and the true mold temperature field includes the true average mold temperature of R zones on the mold after blow molding , where R is a positive integer;

[0010] Call the pre-configured genetic algorithm to obtain the ideal temperature field that the mold should present after blow molding the panel blank, where the ideal temperature field includes the target average mold temperature of R partitions on the mold after blow molding. ;

[0011] According to the actual average mold temperature and the target average mold temperature , determine whether the panel blank meets the conversion conditions for entering the next cooling stage; the conversion conditions are the preset temperature difference tolerance interval ΔT and the regional quantity interval Δ S ;

[0012] When the conversion conditions are not met, obtain at least one target temperature adjustment partition and the temperature adjustment amount corresponding to the target temperature adjustment partition from all partitions;

[0013] After performing a heating or cooling operation on the target temperature adjustment partition according to the temperature adjustment amount, blow mold the panel blank to complete the blow molding stage.

[0014] Furthermore, the method for obtaining the actual mold temperature field is as follows:

[0015] Obtain the initial average mold temperature of R partitions and obtain the second characteristic data, where the second characteristic data includes the attribute data of the panel blank, the basic data of the mold, and the parameter data of the blow molding process;

[0016] Among them, the attribute data includes the initial blank temperature, material type, blank viscosity, specific heat capacity, and blank volume / mass of the panel blank; the basic data includes the heat conduction coefficient of the mold, mold material, number of partitions R, and partition distance of each partition; the parameter data includes blowing pressure, blowing duration, and blowing flow rate;

[0017] Input the second characteristic data and the initial average mold temperature of R partitions into the first machine learning model to obtain the actual mold temperature field that the mold will present in the future after blow molding the panel blank;

[0018] Among them, the training method of the first machine learning model is as follows:

[0019] Obtain historical temperature detection training data, and divide the historical temperature training data into a temperature detection training set and a temperature detection test set. The historical temperature detection training data includes the first characteristic data and its corresponding actual mold temperature field, that is, the actual average mold temperature of R partitions on the mold;

[0020] Among them, the first characteristic data includes the second characteristic data and the initial average mold temperature of R partitions;

[0021] Construct a recurrent neural network, use the first feature data in the temperature detection training set as the input of the recurrent neural network, and use the true mold temperature field as the output to train the recurrent neural network to obtain an initial recurrent neural network;

[0022] Use the temperature detection test set to verify the model of the initial recurrent neural network, and output the initial recurrent neural network with a value less than or equal to the preset test error threshold as the trained first machine learning model.

[0023] Further, the method for obtaining the ideal temperature field is as follows:

[0024] a1: Initialize the population: Randomly generate an original population, where the original population contains x individuals, each individual represents a test mold temperature field, and includes the average temperature of the test mold with R partitions. x is an integer greater than zero;

[0025] a2: Fitness evaluation: Under each individual, obtain the thickness distribution data of the panel blank in the mold; input the thickness distribution data into the pre-constructed fitness function to calculate the fitness of each individual. The thickness distribution data is the thickness of the panel blank in each partition of the mold;

[0026] a3: Selection: Use the roulette wheel method to select two individuals with high fitness in the original population as the male parent and the female parent;

[0027] a4: Crossover: Perform a crossover operation on the male parent and the female parent to generate new individuals;

[0028] a5: Mutation: Perform a mutation operation on the new individuals to obtain Y new individuals, combine the Y new individuals into a new population, replace the original population with the new population, and return to step a2;

[0029] a6: Repeat the above steps a2 - a5 until the fitness of the individuals in the original population or the new population is greater than or equal to the preset fitness threshold, or the number of iterations is greater than or equal to the preset maximum iteration threshold, and output the test mold temperature field represented by the corresponding individual as the ideal temperature field, that is, obtain the target mold average temperature of the R partitions on the mold after blow molding.

[0030] Further, the thickness distribution data of the panel blank in the mold includes:

[0031] Obtain the average temperature of the test mold in R partitions, and obtain the second feature data at the average temperature of the test mold;

[0032] Input the average temperature of the test mold in R partitions and the second feature data into the pre-trained second machine learning model to obtain the thickness distribution data of the panel blank;

[0033] Among them, the training method of the second machine learning model is as follows:

[0034] Obtain historical thickness detection training data, and divide the historical thickness training data into a thickness detection training set and a thickness detection test set. The historical thickness detection training data includes third feature data and its corresponding thickness distribution data;

[0035] Among them, the third feature data includes second feature data and the average temperature of the test molds in R partitions;

[0036] Construct a recurrent neural network, use the third feature data in the thickness detection training set as the input of the recurrent neural network, and use the thickness distribution data as the output, and train the recurrent neural network to obtain an initial recurrent neural network;

[0037] Use the thickness detection test set to verify the initial recurrent neural network, and output the initial recurrent neural network whose value is less than or equal to the preset test error threshold as the trained second machine learning model.

[0038] Furthermore, determining whether the panel blank meets the conversion condition for entering the next cooling link includes:

[0039] Extract the target mold average temperature in R partitions after blow molding according to the ideal temperature field ;

[0040] For each partition, calculate its actual mold average temperature and the target mold average temperature The absolute difference between them is marked as the temperature deviation ;

[0041] Compare the temperature deviation with the preset temperature difference tolerance interval ΔT;

[0042] If , then mark the corresponding partition as a qualified partition; if , then mark the corresponding partition as an unqualified partition;

[0043] Count the number of all unqualified partitions , and compare it with the preset area number interval ΔS;

[0044] If , it is determined that the panel blank meets the conversion condition, that is, it means that the panel blank meets the condition for entering the next cooling link;

[0045] If , it is determined that the panel blank does not meet the conversion condition, that is, it means that the panel blank does not meet the condition for entering the next cooling link.

[0046] Further, the obtaining of at least one target temperature control zone and the temperature adjustment amount corresponding to the target temperature control zone includes:

[0047] b1: For each zone, calculate the deviation vector composed of all of its , and call the established thermal influence coefficient matrix , indicating the temperature change amount generated in the i-th zone due to heat conduction or structural coupling when the temperature in the j-th zone rises by 1 °C;

[0048] b2: Based on the temperature deviation and the thermal influence coefficient matrix , calculate the thermal control contribution degree of each zone. The specific calculation formula is: ;

[0049] b3: Sort all zones in descending order according to the value to form a thermal control contribution degree sorted list Q;

[0050] b4: Generate a target temperature control zone set S and initialize it as an empty set. Set an error tolerance threshold , and initialize the zone selection index r as 1;

[0051] b5: Iteratively select target temperature control zones and fit the solution of the temperature adjustment amount to obtain at least one target temperature control zone and the temperature adjustment amount of the target temperature control zone.

[0052] Further, the iteratively selecting target temperature control zones and fitting the solution of the temperature adjustment amount includes:

[0053] b51: Obtain the r-th zone number from the sorted list Q and add it to the target temperature control zone set S to obtain the updated target temperature control zone set S: , where r is a positive integer;

[0054] b52: According to the updated target temperature control zone set S, extract the columns corresponding to S from the thermal influence matrix H to form a submatrix ;

[0055] b53: Based on the deviation vector E and the submatrix , and solve the temperature adjustment amount of the target temperature control zone by the least squares method. The calculation formula is: ; In the formula: , representing the temperature adjustment amounts of each target temperature control zone in S, is the transpose matrix of , that is, the zones that have been added to the updated set of target temperature control zones;

[0056] b54: According to the obtained , calculate the fitted deviation vector ;

[0057] b55: Calculate the fitting residual, ;

[0058] b56: Determine whether the fitting residual meets the error tolerance threshold . If , let r = r + 1, and return to step b41 to continue selecting the next zone number from Q; if , terminate the iteration and output the updated set of target temperature control zones S and its corresponding temperature adjustment amount .

[0059] In a second aspect, the present invention provides an edge-reinforced blow molding panel temperature distribution control system, which is implemented based on the above-mentioned edge-reinforced blow molding panel temperature distribution control method, and includes:

[0060] The first acquisition module is used to predict the true die temperature field that the die will present in the future after blow molding the panel blank according to the pre-trained first machine learning model during the blow molding process. The true die temperature field includes the true average die temperature of R zones on the die after blow molding , where R is a positive integer;

[0061] The second acquisition module is used to call the pre-configured genetic algorithm to obtain the ideal temperature field that the die should present after blow molding the panel blank. The ideal temperature field includes the target average die temperature of R zones on the die after blow molding ;

[0062] The judgment module is used to judge whether the panel blank meets the conversion condition for entering the next cooling process according to the true average die temperature and the target average die temperature . The conversion condition is the preset temperature difference tolerance interval ΔT and the region number interval Δ S ;

[0063] The analysis module is used to obtain at least one target temperature control zone and the temperature adjustment amount corresponding to the target temperature control zone from all zones when the conversion condition is not met;

[0064] The control module is used to perform heating or cooling operations on the target temperature control zone according to the temperature adjustment amount, and then blow mold the panel blank to complete the blow molding process.

[0065] In a third aspect, the present invention provides an electronic device, including a memory, a processor, and a computer program stored on the memory and running on the processor. When the processor executes the computer program, the method for controlling the temperature distribution of the edge-reinforced blow molding panel described in any one of the above is implemented.

[0066] In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed, the method for controlling the temperature distribution of the edge-reinforced blow molding panel described in any one of the above is implemented.

[0067] In the above technical solution, the technical effects and advantages provided by the present invention are as follows:

[0068] By constructing a first machine learning model and based on multi-source data such as the physical properties of the panel blank, the mold structure characteristics, and the blow molding process conditions, the present invention realizes the accurate prediction of the temperature field of the mold after blow molding, overcomes the problem of lag in temperature control response caused by the lack of thermal field evolution trend modeling in the prior art, and significantly improves the forward-looking and timeliness of the temperature control strategy.

[0069] Furthermore, by introducing a thermal influence coefficient matrix, combining the deviation vector and the evaluation of the thermal control contribution degree, a selection mechanism for the temperature regulation zone is established, and the least squares method is used to solve the temperature adjustment amount, fully considering the thermal coupling relationship between different parts of the mold, and solving the problems in the prior art such as the temperature regulation process relying on experience, ignoring thermal interference, and low adjustment accuracy.

[0070] By jointly optimizing the ideal temperature field through the genetic algorithm and the thickness prediction model and performing differential temperature regulation operations based on the deviation determination, the present invention can strengthen the temperature control of the edge area of the mold, effectively avoid forming defects such as warping, bubbles, and stripes caused by insufficient or excessive temperature, and significantly improve the edge forming quality, thickness uniformity, and overall yield rate of the blow molding panel. Description of the Drawings

[0071] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0072] Figure 1 It is a flowchart of a method for controlling the temperature distribution of an edge-reinforced blow molding panel according to the present invention;

[0073] Figure 2 It is a framework diagram of a system for controlling the temperature distribution of an edge-reinforced blow molding panel according to the present invention;

[0074] Figure 3Schematic structural diagram of an electronic device provided by the present invention. Detailed implementation manners

[0075] Example embodiments will now be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that this disclosure will be more thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. The drawings are merely schematic illustrations of this disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repeated description will be omitted.

[0076] In addition, the described features, structures, or characteristics can be combined in any suitable manner in one or more example embodiments. In the following description, numerous specific details are provided to give a thorough understanding of the example embodiments of this disclosure. However, those skilled in the art will realize that one or more of the specific details can be omitted in practicing the technical solutions of this disclosure, or other methods, components, steps, etc. can be adopted. In other cases, well-known structures, methods, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this disclosure.

[0077] Example 1

[0078] As Figure 1 shown, this example embodiment discloses and provides a method for controlling the temperature distribution of an edge-reinforced blow-molded panel, including:

[0079] S101: In the blow molding process, according to a pre-trained first machine learning model, predict the true mold temperature field that the mold will present in the future after blow molding the panel blank. The true mold temperature field includes the true average mold temperature of R zones on the mold after blow molding, where R is a positive integer; , R is a positive integer;

[0080] In implementation, the true mold temperature field is obtained as follows:

[0081] Obtain the initial average mold temperature of R zones, and obtain second feature data, where the second feature data includes the attribute data of the panel blank, the basic data of the mold, and the parameter data of the blow molding process;

[0082] Among them, the initial mold temperature uniformity represents the average temperature within the partition, which is obtained by collecting through temperature sensors. The attribute data includes but is not limited to the initial blank temperature of the panel blank (obtained by collecting through temperature sensors), material type (such as PET, HDPE, PP, etc.), blank viscosity (which can be measured by the rotation method), specific heat capacity, and blank volume / mass (determined according to the manually input data); the basic data includes but is not limited to the heat conduction coefficient of the mold (determined according to the mold type. For example, the heat conduction coefficient of steel is 43 W / m·K), mold material (such as aluminum, steel), the number of partitions R, and the partition distance of each partition (which refers to the spatial distance between each partition and the panel blank inlet, and is determined according to the historical input data); the parameter data includes but is not limited to the blowing pressure, blowing duration, and blowing flow rate, all of which are monitored by various sensors, including but not limited to pressure sensors, timers, and flow sensors;

[0083] Input the second feature data and the initial mold temperature uniformity of the R partitions into the first machine learning model to obtain the true mold temperature field presented by the mold in the future after blow molding the panel blank;

[0084] Among them, the training method of the first machine learning model is as follows:

[0085] Obtain historical temperature detection training data, and divide the historical temperature training data into a temperature detection training set and a temperature detection test set. The historical temperature detection training data includes the first feature data and its corresponding true mold temperature field, that is, the true mold temperature uniformity of the R partitions on the mold;

[0086] Among them, the first feature data includes the second feature data and the initial mold temperature uniformity of the R partitions;

[0087] It should be understood that the R partitions on the mold are determined in advance by technicians according to different mold specifications (dimensions), and all partition sizes are the same; for example, for a mold of a 500×300 hollow panel, it is evenly divided into 3×3, a total of 9 equal-range partitions according to the horizontal and vertical coordinates;

[0088] It should be noted that a corresponding temperature control unit is provided on the outer surface of each partition to adjust the temperature change of the corresponding partition. The temperature control unit includes but is not limited to components composed of a resistive heating tape (or an infrared heating unit) and a water cooling channel (or a thermoelectric cooler (TEC));

[0089] It should be noted that the first feature data and the true mold temperature field in the historical temperature detection training data are actually collected and recorded by technicians according to experiments or historical real situations;

[0090] Construct a recurrent neural network, use the first feature data in the temperature detection training set as the input of the recurrent neural network, and use the true mold temperature field as the output to train the recurrent neural network to obtain an initial recurrent neural network;

[0091] Use the temperature detection test set to verify the model of the initial recurrent neural network, and output the initial recurrent neural network whose error is less than or equal to the preset test error threshold as the trained first machine learning model;

[0092] By predicting the true average mold temperature of the R partitions on the mold according to the second feature data and the initial average mold temperature of the R partitions, it is beneficial to avoid the temperature control lag problem caused by the lack of temperature evolution trend modeling in the traditional temperature control strategy.

[0093] S102: Call the pre-configured genetic algorithm to obtain the ideal temperature field that the mold should present after blow molding the panel blank. The ideal temperature field includes the target average mold temperature of the R partitions on the mold after blow molding ;

[0094] In implementation, the method for obtaining the ideal temperature field is as follows:

[0095] a1: Initialize the population: Randomly generate the original population, which contains x individuals. Each individual represents a test mold temperature field, that is, a set of test average mold temperatures, including the test average mold temperatures of the R partitions. x is an integer greater than zero;

[0096] a2: Fitness evaluation: For each individual (i.e., each test mold temperature field in the original population), obtain the thickness distribution data of the panel blank in the mold; input the thickness distribution data into the pre-constructed fitness function to calculate the fitness of each individual. The thickness distribution data is the thickness of the panel blank in each partition of the mold;

[0097] In the genetic algorithm, fitness evaluation is one of the core steps, which is used to determine the fitness of each individual, that is, to determine how well each individual performs in a given problem; the design of the fitness function directly affects the efficiency of the algorithm and the quality of the final solution;

[0098] In implementation, the thickness distribution data of the panel blank in the mold includes:

[0099] Obtain the test average mold temperatures of the R partitions, and obtain the second feature data at the test average mold temperatures;

[0100] Input the test average mold temperatures of the R partitions and the second feature data into the pre-trained second machine learning model to obtain the thickness distribution data of the panel blank;

[0101] Among them, the training method of the second machine learning model is as follows:

[0102] Obtain historical thickness detection training data, and divide the historical thickness training data into a thickness detection training set and a thickness detection test set. The historical thickness detection training data includes third feature data and its corresponding thickness distribution data;

[0103] Among them, the third feature data includes second feature data and the average temperature of the test dies in R partitions;

[0104] It should be noted that the third feature data and the thickness distribution data in the historical thickness detection training data are actually collected and recorded by technicians according to experiments or historical real situations;

[0105] Construct a recurrent neural network, use the third feature data in the thickness detection training set as the input of the recurrent neural network, and use the thickness distribution data as the output, and train the recurrent neural network to obtain an initial recurrent neural network;

[0106] Use the thickness detection test set to verify the initial recurrent neural network model, and output the initial recurrent neural network with a value less than or equal to the preset test error threshold as the trained second machine learning model;

[0107] It should be understood that: the first (second) machine learning model is preferably a recurrent neural network (RNN) for fitting the non-linear mapping relationship between features and prediction results. However, although RNN is used as an example, other machine learning models (such as multi-layer perceptron MLP, convolutional neural network CNN, ensemble learning model, etc.) can also be used to achieve similar effects, and can be flexibly selected according to the training effect and actual deployment requirements;

[0108] Among them, the calculation formula of the pre-constructed fitness function is:

[0109] ;

[0110] In the formula: is the fitness, is the thickness of the panel blank in the i-th partition, is the number of partitions, is a (very small arbitrary) positive real number used to avoid singularities;

[0111] a3: Selection: Use the roulette wheel method to select two individuals with high fitness in the original population as the father and mother;

[0112] The roulette wheel method is a commonly used selection method, which is used in genetic algorithms to select individuals with higher fitness to enter the next generation. It simulates the process of roulette, and each individual obtains a corresponding "roulette wheel" area according to its fitness. The higher the fitness of the individual, the larger the corresponding area, and the higher the probability of being selected.

[0113] a4: Crossover: Perform crossover operation on the father and mother to produce new individuals;

[0114] It should be noted that the crossover operation on the paternal parent and the maternal parent is implemented based on a crossover operation, and the crossover operation includes but is not limited to one of a single-point crossover, a uniform crossover or a sequential crossover, etc.;

[0115] a5: Mutation: Perform mutation operation on the new individuals to obtain Y new individuals, combine the Y new individuals into a new population, replace the original population with the new population, and return to step a2;

[0116] In genetic algorithms, mutation operations are used to introduce genetic diversity and prevent the algorithm from falling into a local optimum. The mutation operation on new individuals is implemented by uniform mutation or Gaussian mutation.

[0117] a6: Repeat the above steps a2 to a5 until the fitness of the individuals in the original population or the new population is greater than or equal to the preset fitness threshold, or the number of iterations is greater than or equal to the preset maximum number of iterations threshold, and output the test mold temperature field represented by the corresponding individual as the ideal temperature field, that is, the target mold average temperature of the R partitions on the mold after blow molding is obtained;

[0118] For example, assuming that the maximum number of iterations is 100, the individual with the highest fitness in the current population and its fitness value are recorded after each iteration; if it is found that the fitness value has not changed significantly in a certain generation, it is considered that the convergence condition is met, the iteration is stopped, and the test mold temperature field represented by the corresponding individual is output as the ideal temperature field;

[0119] Determining the ideal temperature field through preconfigured genetic algorithms is conducive to constructing the optimal target distribution of mold zone temperature control, achieving molding thickness control and defect suppression in the panel edge area; at the same time, it improves the system's intelligent optimization capabilities and temperature control accuracy, thereby improving finished product consistency and production yield.

[0120] S103: According to the actual mold temperature and target mold temperature , determine whether the panel blank meets the conversion conditions for entering the next cooling stage; the conversion conditions are the preset temperature difference tolerance interval ΔT and the area number interval Δ S ;

[0121] In implementation, determining whether the panel blank meets the conversion conditions for entering the next cooling stage includes:

[0122] Extracting the target die average temperature of R zones after blow molding according to the ideal temperature field ;

[0123] For each zone, calculating its actual die average temperature and the target die average temperature and marking the absolute difference between them as the temperature deviation amount ;

[0124] Comparing the temperature deviation amount with the preset temperature difference tolerance interval ΔT;

[0125] wherein, , Tmin represents the minimum value of the temperature difference, and Tmax represents the maximum value of the temperature difference;

[0126] If , then mark the corresponding zone as a qualified zone; if , then mark the corresponding zone as an unqualified zone;

[0127] Count the number of all unqualified zones , and compare it with the preset zone number interval Δ S ;

[0128] wherein, , Smin represents the minimum value of the zone number, and Smax represents the maximum value of the zone number;

[0129] If , then determine that the panel blank meets the conversion conditions, that is, it means the panel blank meets the conditions for entering the next cooling stage;

[0130] If , then determine that the panel blank does not meet the conversion conditions, that is, it means the panel blank does not meet the conditions for entering the next cooling stage;

[0131] It should be understood that the prior art usually adopts an isothermal strategy to control the temperature of R partitions on the mold during the blow molding process, that is, the same temperature is adopted for the R partitions on the mold. However, due to a series of reasons such as inconsistent thermal conductivity of the mold material and the relatively long distance from the mold edge to the blow molding area, there will be a certain temperature difference between the edge area and the central area when the isothermal strategy is adopted, resulting in uneven distribution of the true mold temperature field of the mold. Therefore, if entering the cooling process under such circumstances, it will cause uneven thickness of the panel blanks in the edge area and the central area, and defects such as warping, bubbles, and stripes will appear in the edge area, seriously affecting the product quality. Therefore, accurately controlling the temperature distribution of the panel during the blow molding stage is crucial for improving the qualification rate of blow molded products.

[0132] S104: When the conversion condition is not met, obtain at least one target temperature adjustment partition and the temperature adjustment amount corresponding to the target temperature adjustment partition from all partitions;

[0133] In implementation, the obtaining of at least one target temperature adjustment partition and the temperature adjustment amount corresponding to the target temperature adjustment partition includes:

[0134] b1: For each partition, calculate all of its constituted deviation vector , call the established thermal influence coefficient matrix , represents the temperature change amount (in degrees Celsius) generated in the i-th partition due to heat conduction or structural coupling when the temperature of the j-th partition rises by 1°C, The value of can be obtained through experimental data, finite element simulation, or historical monitoring data during the actual production process;

[0135] It should be noted that: the thermal influence coefficient matrix is obtained by means such as the heat conduction experiment method or the finite element thermal simulation modeling method; for example, in the finite element thermal simulation modeling method, a three-dimensional heat conduction finite element simulation software (such as ANSYS, COMSOL Multiphysics) is used to establish a heat conduction model of the mold. The specific steps include: constructing a thermal simulation model including parameters such as the mold partition structure, material properties (such as thermal conductivity, specific heat capacity), and boundary conditions (such as heat flux, cooling channels, air convection); applying a 1°C temperature perturbation to the j-th partition in the simulation model; observing the steady-state or transient temperature change response ΔTi of other partitions; taking ΔTi as estimated value and filling it into the matrix H , repeating the above operations for j = 1 to R, and obtaining the complete H , that is, the thermal influence coefficient matrix;

[0136] Exemplarily, assume that a certain mold is divided into R = 4 temperature-controlled zones with equal areas (denoted as Z1, Z2, Z3, and Z4), and the distribution is as follows: , due to structural coupling and heat conduction, when adjusting the temperature of one zone, the temperatures of other adjacent or structurally connected zones will also be affected. Assume that using the ANSYS heat conduction simulation platform, the specific effects are as shown in Table 1 below:

[0137] Table 1: Thermal Influence Data Table

[0138]

[0139] According to Table 1 above, a thermal influence coefficient matrix is generated ;

[0140] b2: Based on the temperature deviation amount and the thermal influence coefficient matrix calculate the thermal control contribution degree of each zone. The specific calculation formula is: ;

[0141] It should be understood that: represents the potential regulation influence intensity of the j-th zone on the overall temperature deviation correction; its calculation method comprehensively considers the temperature deviation amount required for fitting the target mold temperature and the thermal coupling path intensity , and is used to evaluate to what extent adjusting the temperature of the j-th zone can affect the temperature compensation of other zones, so as to guide the selection order of the priority temperature adjustment zones;

[0142] b3: Sort all zones in descending order according to the value to form a thermal control contribution degree sorted list Q, which is expressed as: Q = [q1, q2,..., qR], where q1 represents the zone number with the highest thermal control contribution degree, q2 is the second highest, and so on;

[0143] b4: Generate a target temperature adjustment zone set S and initialize it as an empty set. Set an error tolerance threshold (unit: degree Celsius) to control the acceptance range of the overall temperature difference fitting result, and initialize the zone selection index r as 1;

[0144] It should be understood that: The error tolerance threshold is an overall fitting error tolerance used to evaluate whether the predicted temperature adjustment amount can effectively fit the current temperature deviation vector E during the least squares fitting process; it is empirically set based on the statistical relationship between the historical fitting error and the actual product defect rate, or set by backtracking from the target temperature fitting accuracy;

[0145] b5: Iteratively select the target temperature control zones and fit the solution of the temperature adjustment amount to obtain at least one target temperature control zone and the temperature adjustment amount of the target temperature control zone;

[0146] Specifically, the iterative selection of the target temperature control zones and fitting the solution of the temperature adjustment amount includes:

[0147] b51: Obtain the r-th zone number from the sorted list Q , and add it to the set S of target temperature control zones to obtain the updated set S of target temperature control zones: , where r is a positive integer;

[0148] b52: According to the updated set S of target temperature control zones, extract the columns corresponding to S from the heat influence matrix H to form a sub-matrix ;

[0149] Exemplarily, continuing the assumption, the heat influence coefficient matrix ; where the rows represent the temperature response zone numbers i = 1, 2, 3, 4; the columns represent the temperature rise in a certain zone j = 1, 2, 3, 4; and assuming the updated set S of target temperature control zones is S = {2, 4}, that is, the temperatures of the 2nd and 4th zones are to be adjusted, then extract the sub-matrix from the 2nd and 4th zones to obtain , which means extracting the 2nd and 4th columns (keeping all rows) from H , where has a dimension of R×|S| = 4×2, and each column represents the heat influence of adjusting the 2nd or 4th zone on each zone;

[0150] b53: Based on the deviation vector E and the sub-matrix , and solve the temperature adjustment amount of the target temperature control zone by the least squares method. The calculation formula is: ; In the formula: , represents the temperature adjustment amounts of the target temperature control zones in S, is the transpose matrix, , that is, the zones that have been added to the updated set of target temperature control zones;

[0151] It can be understood that: the essence of this least squares method solving process is to find a set of minimum temperature adjustment increments in the error space, so that the heat response after temperature adjustment can approximate the expected temperature difference correction value as much as possible, thereby minimizing the error;

[0152] b54: According to the obtained , calculate the fitted deviation vector ;

[0153] b55: Calculate the fitting residual error, ;

[0154] b56: Judge the fitting residual error whether it meets the error tolerance threshold , if , then let r = r + 1, and return to step b41 to continue selecting the next partition number from Q; if , then terminate the iteration and output the updated target temperature control partition set S and its corresponding temperature adjustment amount ;

[0155] In an optional embodiment, when the panel blank meets the conversion condition, the next cooling link is executed to cool the panel blank in the mold;

[0156] It can be understood that when the panel blank meets the conversion condition, it means that the true mold average temperature presented by the panel blank on each partition of the mold approaches or is equivalent to the target mold average temperature. Therefore, no temperature adjustment is required, and after the panel blank at this temperature enters the cooling link for cooling treatment, there will be no or only a small amount of warping, bubbles, stripes and other defects in the edge area of the panel blank, so that the formed panel meets the factory standards.

[0157] S105: After performing the heating or cooling operation on the target temperature control partition according to the temperature adjustment amount, blow the panel blank to complete the blow molding link;

[0158] Performing the heating or cooling operation on the target temperature control partition can be achieved by controlling the temperature control unit corresponding to the partition. Specifically, if , then control the resistance heating belt or the infrared heating device to turn on; if , then turn on the water cooling channel or the thermoelectric cooler for cooling;

[0159] It can be understood that there are heating or cooling operations in temperature adjustment because, near the inlet of the panel blank, due to being close to the heat source, the temperature is relatively high, and usually cooling treatment is required, while in the edge area of the mold, due to being far from the heat source, the temperature is relatively low, and usually heating treatment is required; compared with the average temperature strategy, the present invention takes into account the influence of actual various factors on the mold average temperature, and realizes the true mold average temperature consistency through the differential temperature control method of the partition temperature control method, which is beneficial to ensuring the structural quality and strength of the edge area of the formed panel.

[0160] Embodiment 2

[0161] As Figure 2As shown, the parts not detailed in this embodiment are as shown in Embodiment 1. This embodiment publicly provides an edge-reinforced blow-molded panel temperature distribution control system, including:

[0162] A first acquisition module 201, configured to, in the blow molding process, according to a pre-trained first machine learning model, predict the true mold temperature field that the mold will present in the future after blow molding the panel blank, where the true mold temperature field includes the true average mold temperature of R partitions on the mold after blow molding, and R is a positive integer; , R is a positive integer;

[0163] A second acquisition module 202, configured to call a pre-configured genetic algorithm to obtain an ideal temperature field that the mold should present after blow molding the panel blank, where the ideal temperature field includes the target average mold temperature of R partitions on the mold after blow molding; ;

[0164] A judgment module 203, configured to judge whether the panel blank meets the conversion condition for entering the next cooling process according to the true average mold temperature and the target average mold temperature ; the conversion condition is a preset temperature difference tolerance interval ΔT and a region quantity interval Δ S ;

[0165] An analysis module 204, configured to, when the conversion condition is not met, obtain at least one target temperature adjustment partition and the temperature adjustment amount corresponding to the target temperature adjustment partition from all partitions;

[0166] A control module 205, configured to perform a heating or cooling operation on the target temperature adjustment partition according to the temperature adjustment amount, and then blow mold the panel blank to complete the blow molding process.

[0167] Embodiment 3

[0168] Please refer to Figure 3 As shown, this embodiment publicly provides an electronic device, including a memory, a processor, and a computer program stored on the memory and running on the processor. When the processor executes the computer program, it implements the edge-reinforced blow-molded panel temperature distribution control method provided by any one of the above methods.

[0169] Since the electronic device introduced in this embodiment is the one used to implement the edge-enhanced blow molding panel temperature distribution control method in the embodiments of the present application, based on the edge-enhanced blow molding panel temperature distribution control method introduced in the embodiments of the present application, those skilled in the art can understand the specific implementation manners and various variations of the electronic device in this embodiment. Therefore, the specific implementation of how this electronic device implements the method in the embodiments of the present application will not be described in detail here. As long as those skilled in the art implement the electronic device used in the edge-enhanced blow molding panel temperature distribution control method in the embodiments of the present application, it falls within the scope of protection of the present application.

[0170] Embodiment 4

[0171] This embodiment publicly provides a computer-readable storage medium, including a memory, a processor, and a computer program stored on the memory and running on the processor. When the processor executes the computer program, it implements the edge-enhanced blow molding panel temperature distribution control method provided by any one of the above methods.

[0172] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to obtain a formula that is closest to the actual situation. The selection of the preset parameters, weights, and thresholds in the formulas is set by those skilled in the art according to the actual situation.

[0173] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired network or a wireless network. The computer-readable storage medium can be any available medium that the computer can access or a data storage device such as a server or a data center that includes one or more collections of available media. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, or a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0174] Only some exemplary embodiments of the present invention have been described by way of illustration. Without doubt, for those of ordinary skill in the art, the described embodiments can be modified in various different ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and description are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A method for controlling the temperature distribution of an edge-strengthened blow-molded panel, characterized in that: include: In the blow molding process, the real mold temperature field of the mold after blow molding of the panel blank is predicted based on the pre-trained first machine learning model. The real mold temperature field includes the real mold average temperature of R partitions on the mold after blow molding. , R is a positive integer; The method for obtaining the real mold temperature field is as follows: Obtaining the initial average mold temperature of the R partitions, and obtaining second characteristic data, wherein the second characteristic data includes attribute data of the panel blank, basic data of the mold, and parameter data of the blow molding process; Among them, the attribute data includes the initial blank temperature, material type, blank viscosity, specific heat capacity and blank volume / mass of the panel blank; the basic data includes the thermal conductivity coefficient of the mold, the mold material, the number of partitions R and the partition distance of each partition; the parameter data includes the blowing pressure, blowing time and blowing flow rate; The second feature data and the initial mold average temperatures of the R partitions are input into the first machine learning model to obtain the real mold temperature field that the mold will present in the future after the panel blank is blow-molded; The training method of the first machine learning model is as follows: Acquire historical temperature detection training data, and divide the historical temperature detection training data into a temperature detection training set and a temperature detection test set, wherein the historical temperature detection training data includes the first feature data and its corresponding real mold temperature field, that is, the real mold average temperature of R partitions on the mold; Wherein, the first characteristic data includes the second characteristic data and the initial mold average temperature of R partitions; Constructing a recurrent neural network, taking the first feature data in the temperature detection training set as the input of the recurrent neural network, and taking the real mold temperature field as the output, training the recurrent neural network to obtain an initial recurrent neural network; The temperature detection test set is used to verify the model of the initial recurrent neural network, and the initial recurrent neural network with a value less than or equal to the preset test error threshold is output as the trained first machine learning model; Call the preconfigured genetic algorithm to obtain the ideal temperature field that the mold should present after blow molding the panel blank, and the ideal temperature field includes the target mold average temperature of R partitions on the mold after blow molding. ; According to the actual mold temperature and target mold temperature , judging whether the panel blank meets the conversion conditions for entering the next cooling link; the conversion conditions are the preset temperature difference tolerance interval ΔT and the area quantity interval ΔS; When the conversion condition is not met, obtaining at least one target temperature adjustment zone and the temperature adjustment amount corresponding to the target temperature adjustment zone from all zones; After heating or cooling the target temperature adjustment zone according to the temperature adjustment amount, the panel blank is blow-molded to complete the blow-molding process.

2. The edge-strengthened blow-molded panel temperature distribution control method according to claim 1, characterized in that: The method for obtaining the ideal temperature field is as follows: a1: Initialize the population: randomly generate an original population, which contains x individuals, each of which represents a test mold temperature field, including the average temperature of the test mold in R partitions, and x is an integer greater than zero; a2: Fitness evaluation: Under each individual, obtain the thickness distribution data of the panel blank in the mold; input the thickness distribution data into the pre-built fitness function to calculate the fitness of each individual, wherein the thickness distribution data is the thickness of the panel blank in each partition of the mold; a3: Selection: Use the roulette method to select two individuals with high fitness in the original population as the father and mother; a4: Crossover: Perform crossover operation on the father and mother to produce new individuals; a5: Mutation: Perform mutation operation on the new individuals to obtain Y new individuals, combine the Y new individuals into a new population, replace the original population with the new population, and return to step a2; a6: Repeat steps a2 to a5 above until the fitness of individuals in the original population or the new population is greater than or equal to the preset fitness threshold, or the number of iterations is greater than or equal to the preset maximum number of iterations threshold, and output the test mold temperature field represented by the corresponding individual as the ideal temperature field, that is, the target mold average temperature of the R partitions on the mold after blow molding is obtained.

3. The edge-strengthened blow-molded panel temperature distribution control method according to claim 2, characterized in that: The thickness distribution data of the panel blank in the mold includes: Obtaining the average temperature of the test mold of the R partitions, and obtaining the second characteristic data under the average temperature of the test mold; Input the average temperature of the test mold of R partitions and the second characteristic data into the pre-trained second machine learning model to obtain the thickness distribution data of the panel blank; The training method of the second machine learning model is as follows: Acquire historical thickness detection training data, and divide the historical thickness detection training data into a thickness detection training set and a thickness detection test set, wherein the historical thickness detection training data includes the third feature data and its corresponding thickness distribution data; Wherein, the third characteristic data includes the second characteristic data and the average temperature of the test mold in R partitions; Constructing a recurrent neural network, taking the third feature data in the thickness detection training set as the input of the recurrent neural network, and taking the thickness distribution data as the output, training the recurrent neural network to obtain an initial recurrent neural network; The initial recurrent neural network is model verified using the thickness detection test set, and an initial recurrent neural network with an output value less than or equal to a preset test error threshold is used as the trained second machine learning model.

4. The edge-strengthened blow-molded panel temperature distribution control method according to claim 1, characterized in that: The step of judging whether the panel blank meets the conversion conditions for entering the next cooling stage includes: Extract the target mold average temperature of R partitions after blow molding based on the ideal temperature field ; For each zone, calculate the actual average mold temperature and target mold temperature The absolute difference between ; The temperature deviation Compare with the preset temperature difference tolerance interval ΔT; like , then mark the corresponding partition as a qualified partition; if , then the corresponding partition is marked as a non-compliant partition; Count the number of all partitions that do not meet the standard , and compare it with the preset area quantity interval ΔS; like , it is determined that the panel blank meets the conversion conditions, which means that the panel blank meets the requirements for entering the next cooling stage; like , it is determined that the panel blank does not meet the conversion conditions, which means that the panel blank does not meet the requirements for entering the next cooling stage.

5. The edge-strengthened blow-molded panel temperature distribution control method according to claim 4, characterized in that: The obtaining of at least one target temperature adjustment zone and a temperature adjustment amount corresponding to the target temperature adjustment zone includes: b1: For each partition, calculate all The deviation vector , call the established thermal influence coefficient matrix , It indicates the temperature change of the ith partition due to heat conduction or structural coupling when the temperature of the jth partition rises by 1°C; b2: Based on temperature deviation and the thermal influence coefficient matrix Calculate the thermal control contribution of each partition. The specific calculation formula is: ; b3: For all partitions The values ​​are sorted from large to small to form a ranking list Q of thermal control contribution; b4: Generate the target temperature control partition set S, initialize it to an empty set, and set the error tolerance threshold , initialize the partition to select index r as 1; b5: Iteratively select a target temperature adjustment partition and fit the solution of the temperature adjustment amount to obtain at least one target temperature adjustment partition and the temperature adjustment amount of the target temperature adjustment partition.

6. The edge-strengthened blow-molded panel temperature distribution control method according to claim 5, characterized in that: The iterative selection of the target temperature adjustment partition and the fitting of the solution of the temperature adjustment amount include: b51: Get the rth partition number from the sorted list Q , and add it to the target temperature control partition set S to obtain the updated target temperature control partition set S: , r is a positive integer; b52: According to the updated target temperature control partition set S, from the heat influence matrix H Extract the columns corresponding to S to form a submatrix ; b53: Based on the bias vector E and the submatrix , and solve the temperature adjustment amount of the target temperature adjustment partition by the least squares method , the calculation formula is: ; Where: , represents the temperature adjustment amount of each target temperature adjustment partition in S, for The transposed matrix of , that is, the partitions added to the updated target temperature control partition set; b54: According to the obtained , calculate the deviation vector of the fit ; b55: Calculate the fitting residuals, ; b56: Determine the fitting residual Whether the error tolerance threshold is met ,like , then let r=r+1, and return to step b41 to continue selecting the next partition number from Q; if , the iteration is terminated, and the updated target temperature adjustment partition set S and its corresponding temperature adjustment amount are output .

7. A temperature distribution control system for edge-strengthened blow-molded panels, implemented based on the temperature distribution control method for edge-strengthened blow-molded panels according to any one of claims 1 to 6, characterized in that: include: The first acquisition module is used to predict the real mold temperature field of the mold after blow molding the panel blank according to the pre-trained first machine learning model in the blow molding process, and the real mold temperature field includes the real mold average temperature of R partitions on the mold after blow molding. , R is a positive integer; The second acquisition module is used to call the preconfigured genetic algorithm to obtain the ideal temperature field that the mold should present after blow molding the panel blank. The ideal temperature field includes the target mold average temperature of R partitions on the mold after blow molding. ; Judgment module, used to determine the actual mold temperature and target mold temperature , determine whether the panel blank meets the conversion conditions for entering the next cooling stage; the conversion conditions are the preset temperature difference tolerance interval ΔT and the area number interval Δ S ; An analysis module, used for obtaining at least one target temperature adjustment zone and a temperature adjustment amount corresponding to the target temperature adjustment zone from all zones when the conversion condition is not met; The control module is used to blow-mold the panel blank after performing a heating or cooling operation on the target temperature adjustment zone according to the temperature adjustment amount to complete the blow-molding process.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the edge reinforced blow-molded panel temperature distribution control method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed, the method for controlling the temperature distribution of an edge-reinforced blow-molded panel according to any one of claims 1 to 6 is implemented.

Images