A method and system for controlling properties of a composite material

Abstract

The embodiment of the specification provides a composite material performance control method and system, the method comprises selecting raw materials in a preset proportion and mixing, the raw materials include at least one of polyethyleneimine, soluble polytetrafluoroethylene, metal powder and metal oxide powder; wherein, the preset proportion includes: the mass percentage of polyethyleneimine is 55%-65%, the mass percentage of soluble polytetrafluoroethylene is 35%-45%, and the mass percentage of metal powder and / or metal oxide powder is 0-5%; based on the preset temperature and the preset current, the forming device is controlled to warm, pressurize and extrude the mixture after mixing to obtain a composite material.

Description

Technical Field

[0001] This specification relates to the field of composite material preparation, and in particular to a method and system for controlling the properties of composite materials. Background Technology

[0002] The dielectric constant characterizes a material's ability to store electrical energy. The higher the dielectric constant, the higher the capacitance of the dielectric material. When used in high-capacitance electronic and electrical applications, insulating materials with higher dielectric constants are often required. Currently, in the preparation of composite materials with high dielectric constants, there is a problem that may lead to serious loss of other properties of the composite material.

[0003] To address the aforementioned issues, CN101885886B proposes a method for preparing high-dielectric polyvinylidene fluoride (PVDF) composite materials. This method utilizes a magnetic field to control the distribution of Ni powder, achieving a percolation effect even when the Ni filler content is far below the percolation threshold, thus preparing a PVDF / Ni high-dielectric composite material. However, this method only addresses the preparation of composite materials with high dielectric properties and cannot intelligently control the dielectric constant during the composite material production process according to different application scenarios.

[0004] Therefore, it is desirable to provide a composite material performance control system and method that can help to intelligently monitor and control the dielectric constant of composite materials. Summary of the Invention

[0005] This specification provides one or more embodiments of a composite material performance control method. The method is processor-based and includes: selecting and mixing raw materials in a preset proportion, wherein the raw materials include at least one of polyethyleneimine, soluble polytetrafluoroethylene, metal powder, and metal oxide powder; wherein the preset proportion includes: polyethyleneimine accounting for 55%-65% by mass, soluble polytetrafluoroethylene accounting for 35%-45% by mass, and metal powder and / or metal oxide powder accounting for 0-5% by mass; and controlling a molding device to heat, pressurize, and extrude the mixed mixture into granules based on a preset temperature and a preset current to obtain a composite material.

[0006] This specification provides one or more embodiments of a composite material performance control system, the system comprising: a mixing module for selecting and mixing raw materials in a preset proportion, the raw materials including at least one of polyethyleneimine, soluble polytetrafluoroethylene, metal powder, and metal oxide powder; wherein the preset proportion includes at least: polyethyleneimine by mass of 55%-65%, soluble polytetrafluoroethylene by mass of 35%-45%, and metal powder and / or metal oxide powder by mass of 0-5%; and a control module for controlling a molding device to heat, pressurize, and extrude the mixed mixture into granules based on a preset temperature and a preset current to obtain a composite material.

[0007] This specification provides one or more embodiments of a composite material performance control device, the device including at least one processor and at least one memory; the at least one memory is used to store computer instructions; the at least one processor is used to execute at least a portion of the computer instructions to implement the composite material performance control method.

[0008] This specification provides one or more embodiments of a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions from the storage medium, the computer executes the composite material performance control method. Attached Figure Description

[0009] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting; in these embodiments, the same reference numerals denote the same structures, wherein:

[0010] Figure 1 This is an exemplary flowchart of a composite material performance control method according to some embodiments of this specification;

[0011] Figure 2A This is an exemplary flowchart illustrating the determination of magnetization parameters according to some embodiments of this specification;

[0012] Figure 2B This is an exemplary schematic diagram illustrating the determination of a predicted dielectric constant value according to some embodiments of this specification;

[0013] Figure 3 This is an exemplary schematic diagram illustrating the determination of whether a composite material is qualified, based on some embodiments of this specification. Detailed Implementation

[0014] To more clearly illustrate the technical solutions of the embodiments in this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this specification. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0015] It should be understood that the terms “system,” “device,” “unit,” and / or “module” used herein are one way to distinguish different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0016] As indicated in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not specifically refer to the singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of expressly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0017] Flowcharts are used in this specification to illustrate the operations performed by the system according to embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0018] Currently, most composite materials rely on preset parameters during production, resulting in relatively uniform dielectric constant values. When the application scenario changes, manual adjustments are required, indicating a low level of automation. CN101885886B only involves the preparation of materials with specific high dielectric constants, but does not involve the intelligent control of the dielectric constant of the materials.

[0019] Therefore, some embodiments of this specification provide a way to obtain reasonable magnetization parameters based on the preparation of composite materials, and to monitor the magnetization process in real time to obtain accurate dielectric constant values, thereby obtaining qualified composite materials and improving production quality and efficiency.

[0020] In some embodiments, the composite material performance control system may include a mixing module and a control module.

[0021] In some embodiments, the mixing module can be used to select and mix raw materials in a preset ratio, the raw materials including at least one of polyethyleneimine, soluble polytetrafluoroethylene, metal powder, and metal oxide powder; wherein the preset ratio includes at least: 55%-65% by mass of polyethyleneimine, 35%-45% by mass of soluble polytetrafluoroethylene, and 0-5% by mass of metal powder and / or metal oxide powder.

[0022] In some embodiments, the control module can be used to control the molding device to heat, pressurize, and extrude the mixed mixture into granules based on a preset temperature and a preset current to obtain a composite material.

[0023] In some embodiments, the composite material performance control system may further include a magnetization module, which can be used to place the composite material into a heated and magnetized environment to perform at least one stage of magnetization treatment on the composite material with corresponding magnetization parameters; the magnetization parameters include at least one of magnetic field strength and magnetization treatment time.

[0024] In some embodiments, the magnetization module may be further configured to: determine the target magnetization parameters for the first stage of magnetization processing based on the composition ratio of the raw materials and the target performance parameters; generate at least one set of candidate magnetization parameter combinations based on the target magnetization parameters of at least one completed stage; predict the estimated dielectric constant value corresponding to at least one set of candidate magnetization parameter combinations based on the target magnetization parameters of at least one completed stage, the sensing data of at least one completed stage, and at least one set of candidate magnetization parameter combinations; determine the target magnetization parameter combination based on at least one estimated dielectric constant value; and determine the target magnetization parameters for magnetization processing outside the first stage based on the target magnetization parameter combination.

[0025] In some embodiments, the magnetization module may be further configured to measure the intermediate dielectric constant value of the composite material by means of a dielectric constant measuring device at at least one preset time point in the preparation of the composite material, wherein the at least one preset time point includes the time point at which the composite material is obtained; and in response to the intermediate dielectric constant value of the composite material meeting a preset requirement, the composite material is determined to be qualified.

[0026] In some embodiments, the hybrid module, control module, and magnetization module can be integrated into the processor, as described below. Figure 1 Process 100 in the process can be considered as being executed by the processor.

[0027] Figure 1 This is an exemplary flowchart of a composite material performance control method according to some embodiments of this specification.

[0028] In some embodiments, process 100 can be implemented based on a composite material performance control system. For example... Figure 1 As shown, process 100 includes the following steps:

[0029] Step 110: Select raw materials in a preset ratio and mix them.

[0030] Raw materials refer to the raw materials used in the production of composite materials.

[0031] In some embodiments, the raw materials include at least one or any combination of polyetherimide (PEI), soluble polytetrafluoroethylene (PFA), metal powder, and metal oxide powder. The metal powder may be nickel powder, etc. The metal oxide may be titanium dioxide, barium titanate, etc.

[0032] A preset ratio refers to the pre-defined proportion of different types of raw materials when they are mixed. For example, a preset ratio can be the mass ratio of various raw materials, such as PEI:PFA:metal powder = a:b:c.

[0033] In some embodiments, the preset proportions include at least: 55%-65% by mass of PEI, 35%-45% by mass of PFA, and 0-5% by mass of metal powder and / or metal oxide powder.

[0034] In some embodiments, the processor can obtain the preset ratio in various ways. For example, the preset ratio can be a manually preset value, a default value, a preset value based on experience, or any combination thereof. The preset ratio can also be determined according to actual needs.

[0035] Mixing refers to the process of dispersing different types of raw materials to achieve a certain degree of uniformity.

[0036] In some embodiments, the processor can control the raw material mixing device to mix the raw materials according to a preset ratio to obtain a mixture.

[0037] A raw material mixing device refers to a device or equipment used to mix raw materials. For example, a raw material mixing device may include, but is not limited to, a high-speed mixer.

[0038] Step 120: Based on preset temperature and preset current, the molding device is used to heat, pressurize, and extrude the mixed mixture into granules to obtain a composite material.

[0039] A mixture refers to a mixture obtained by mixing different types of raw materials in a predetermined proportion. For example, a mixture can be a mixture of PEI, PFA, metal powder, etc., in a predetermined proportion.

[0040] A molding device is a piece of equipment that heats, pressurizes, and extrudes a mixture into granules according to production parameters. For example, a molding device can be a plastic molding machine.

[0041] Production parameters can refer to the operating parameters of the molding equipment during the production of composite plastics. For example, production parameters may include preset temperature, preset pressure, preset current, etc.

[0042] The preset temperature is a parameter used by the molding apparatus to heat the mixture to a molten state. In some embodiments, the preset temperature can be 350-400°C.

[0043] The preset pressure is a parameter used by the molding device to apply pressure when heating the mixture.

[0044] Preset temperature and pressure can be determined in several ways. For example, preset temperature and pressure can be determined manually. Alternatively, preset temperature and pressure can be set according to the actual scenario and different types of raw materials.

[0045] In some embodiments, the preset temperature can be determined by the processor and sent to the molding apparatus.

[0046] The preset current is a parameter used by the molding device to cool and extrude the molten mixture. For example, different preset currents correspond to different extrusion pressures, extrusion temperatures, and extrusion rates of the molding device.

[0047] The preset current can be determined in various ways. For example, the processor can determine it based on the characteristics of the molten mixture. These characteristics can refer to information that reflects the properties of the molten mixture. For example, the molten mixture may include image features (such as color, luminosity, etc.) of various regions of the molten mixture. In some embodiments, the processor can acquire an image of the molten mixture and determine its characteristics based on image recognition.

[0048] In some embodiments, the processor can retrieve historical images of molten mixtures that meet similarity criteria from a preset table based on the molten mixture image, and associate these images with historical preset currents stored in the table as the current preset current. The similarity criteria can be that the image similarity is greater than a preset threshold, which can be manually set or a system default.

[0049] In some embodiments, preset parameters may be determined by the processor and sent to the molding apparatus.

[0050] Heating and pressurizing refer to the operation of heating or pressurizing a mixture to a molten state.

[0051] Extrusion granulation refers to the operation of cooling, pressing, and cutting a molten mixture into granules.

[0052] In some embodiments, the processor can generate corresponding control commands based on production parameters and send them to the molding device to control the operation of the molding device, heat and pressurize the mixture, and extrude it into granules to obtain a composite material.

[0053] In some embodiments, the process 100 further includes step 130.

[0054] Step 130: Place the composite material in a heated and magnetized environment and perform at least one stage of magnetization treatment on the composite material with the corresponding magnetization parameters.

[0055] The heated and magnetized environment (hereinafter referred to as the magnetized environment) refers to the environment in which composite materials are subjected to heat preservation and magnetization treatment based on the set magnetization parameters.

[0056] In some embodiments, the processor can generate control instructions based on magnetization parameters to control the operation of the magnetization device and enable it to generate a magnetization environment.

[0057] Magnetizing equipment refers to a device that generates a magnetizing environment to magnetize composite materials. For example, magnetizing equipment can be a high-temperature magnetic field annealing furnace.

[0058] Magnetization parameters refer to the parameters used when magnetizing composite materials. For example, magnetization parameters may include any one or a combination of magnetic field strength, magnetic field direction, magnetization time, holding temperature, and set vacuum level.

[0059] Magnetization intensity and magnetic field direction refer to the magnitude and direction of the magnetic field in a magnetized environment.

[0060] Magnetization time refers to the duration of magnetization treatment on the composite material. In some embodiments, the magnetization treatment can be divided into multiple stages, and the magnetization time can include the magnetization time of each stage and the total magnetization time of all stages. The magnetization time for each stage can be different. For more information on the magnetization time of each stage, please refer to [link to relevant documentation]. Figure 2A Related descriptions.

[0061] The holding temperature refers to the parameter value or range that maintains the temperature within the magnetized environment.

[0062] The vacuum level is set to characterize the vacuum level of the magnetization environment during magnetization treatment.

[0063] In some embodiments, the magnetization parameters may include target magnetization parameters for each stage of the magnetization process. In some embodiments, the magnetization parameters may be represented by a vector ((b1, y1), (b2, y2)...), where the vector indicates that the target magnetization parameter for stage b1 is y1, the target magnetization parameter for stage b2 is y1, and so on.

[0064] Magnetization parameters can be determined in several ways. For example, the processor can obtain magnetization parameters randomly. Alternatively, the magnetization parameters can be parameters preset by the user. Or, the magnetization parameters can be parameters used in the last magnetization process.

[0065] In some embodiments, for the first-stage magnetization process, the processor can determine the target magnetization parameters for the first stage based on the component ratio of the raw materials and the target performance parameters; for magnetization processes other than the first stage, the processor can determine the target magnetization parameters for the non-first-stage magnetization processes based on the combination of target magnetization parameters. For more details on this embodiment, please refer to [link to relevant documentation]. Figure 2A Related descriptions.

[0066] In some embodiments, the processor can magnetize the composite material by setting the magnetization environment to a strong magnetic field, high vacuum, and high temperature environment based on magnetization parameters.

[0067] In some embodiments of this specification, by magnetizing the composite material with appropriate magnetization parameters, the quality and efficiency of magnetization can be improved, thereby obtaining a dielectric constant value with higher accuracy.

[0068] In some embodiments of this specification, by presetting the temperature and presetting the current, the molding device is controlled to heat, pressurize, and extrude the mixed mixture into granules. This can improve the accuracy and efficiency of the control, realize the intelligent regulation of the molding device, and facilitate the subsequent acquisition of a higher accuracy dielectric constant value.

[0069] It should be noted that the above description of the process is for illustrative purposes only and does not limit the scope of this specification. Those skilled in the art can make various modifications and changes to the process under the guidance of this specification. However, these modifications and changes remain within the scope of this specification.

[0070] Figure 2A This is an exemplary flowchart illustrating the determination of magnetization parameters according to some embodiments of this specification.

[0071] In some embodiments, process 200 may be executed by a processor of the composite material performance control system. For example... Figure 2A As shown, process 200 includes the following steps:

[0072] In some embodiments, such as Figure 2A As shown, the processor can determine the magnetization parameters for at least one stage of the magnetization process based on steps S21-S24.

[0073] Step S21: For the first stage of magnetization treatment, the target magnetization parameters for the first stage are determined based on the composition ratio of the raw materials and the target performance parameters.

[0074] For more information on raw materials, please refer to [link / reference]. Figure 1 Related descriptions.

[0075] In some embodiments, the processor can divide the time period during which the composite material is magnetized into multiple time intervals, with different time intervals corresponding to different stages.

[0076] The division can be based on a preset time length, equal intervals, or other methods.

[0077] The first stage corresponds to the first time interval.

[0078] A period of time has a certain length, such as 12 hours or 24 hours. During the period of magnetization treatment of composite materials based on magnetization parameters, the dielectric constant of the composite material will change.

[0079] In some embodiments, a period of time is divided into multiple time intervals, each time interval can correspond to a magnetization process, for example, the first interval corresponds to the first magnetization process, the second interval corresponds to the second magnetization process, and so on. After the first stage corresponding to the first magnetization process, the processor can perform a second magnetization process on the composite material, and after the second stage corresponding to the second magnetization process, the composite material can perform a third magnetization process, and so on.

[0080] In some embodiments, a time interval has a certain duration, such as 1 hour, 2 hours, etc. In some embodiments, the durations of multiple time intervals may be the same or different.

[0081] The composition ratio of raw materials is information related to different types of raw materials and their proportions. The composition ratio can be the mass proportion, volume proportion, etc. of different types of raw materials. In some embodiments, the composition ratio of raw materials can be represented by a vector ((a1, x1), (a2, x2)...), which indicates that the proportion of raw material a1 is x1, the proportion of raw material a2 is x2, and so on.

[0082] Target performance parameters are those related to the final composite material itself. For example, target performance parameters may include the composite material's mechanical and electrical properties. "Finally" refers to completing all stages of magnetization treatment.

[0083] Mechanical property parameters reflect the ability of the final composite material to resist deformation under external forces. For example, mechanical property parameters may include impact strength, flexural strength, tensile strength, etc.

[0084] Electrical performance parameters are used to reflect the electrical properties of composite materials under voltage or current. For example, electrical performance parameters may include dielectric constant, dielectric loss, etc.

[0085] The dielectric constant is a parameter that characterizes a material's ability to store charge in an electric field.

[0086] Dielectric loss is a measure of the energy lost due to heat generation in composite materials.

[0087] In some embodiments, the target performance parameters can be represented by a vector as (A1, A2, A3, ...), where A1, A2, and A3 represent the mechanical and electrical performance parameters of the composite material, respectively.

[0088] Target performance parameters can be obtained in several ways. For example, they can be obtained based on a production plan. Alternatively, they can be determined through manual input.

[0089] The target magnetization parameters refer to the magnetization parameters used in each stage of the magnetization process. For example, the target magnetization parameters can be the magnetization parameters for the first stage, the magnetization parameters for the second stage, and so on.

[0090] For more information on magnetization parameters, please refer to [link / reference]. Figure 1 Related descriptions.

[0091] The target magnetization parameter can be determined in various ways. In some embodiments, the processor can determine the target magnetization parameter based on the ingredient ratio of the raw materials. For example, the processor can generate a first retrieval vector based on the ingredient ratio of the raw materials, search a historical database based on the first retrieval vector, determine reference vectors that meet the matching conditions, determine the reference vectors that meet the matching conditions as the target vector, and determine the target magnetization parameter of the first historical stage corresponding to the target vector as the target magnetization parameter of the first stage. The matching conditions can refer to the judgment conditions used to determine the target vector. Matching conditions may include vector distance from the first retrieval vector being less than a distance threshold, minimum vector distance, etc. There are various methods for calculating vector distance, such as Euclidean distance, cosine distance, Mahalanobis distance, Chebyshev distance, Manhattan distance, etc.

[0092] In some embodiments, when there are multiple target vectors, the processor can determine the relationship between the dielectric constant range corresponding to the target vector and the dielectric constant value of the target performance parameter, select one or more target vectors that meet the preset conditions, randomly select one target vector from the one or more target vectors, and determine the target magnetization parameter of the historical first stage corresponding to it as the target magnetization parameter of the first stage.

[0093] The dielectric constant range refers to all values ​​between two specific dielectric constant values. These specific dielectric constant values ​​can be system default values ​​or manually preset values.

[0094] Preset conditions refer to the criteria used to evaluate the target vector. For example, preset conditions may include conditions such as the dielectric constant value being within a certain range.

[0095] A historical database is a database used to store, index, and query vectors. A historical database can store multiple reference vectors and their corresponding associated vectors.

[0096] In some embodiments, the historical database can be constructed based on historical magnetization processing data. For example, the reference vector is a vector composed of the composition ratios of historical raw materials, etc.; the correlation vector is a vector composed of the magnetization parameters of the historical raw materials corresponding to the reference vector at various stages in chronological order.

[0097] In some embodiments, the correlation vector also includes the dielectric constant range of the final composite material made from historical raw materials. The dielectric constant range of the final composite material can be determined by experimental measurement.

[0098] It should be noted that different raw materials correspond to different numbers of stages in the historical magnetization data. During the construction of the historical database based on this data, the processor can pre-set the number of stages. When the number of magnetization stages corresponding to a raw material is less than the preset number, the target magnetization parameters corresponding to the missing stages can be replaced with default values. For example, the default value is zero. The preset number of stages can be set based on actual needs.

[0099] Step S22: For magnetization processes that are not in the first stage, the processor can determine the target magnetization parameter combinations for each non-first stage through the following steps S222-S224.

[0100] Step S222: Generate at least one set of candidate magnetization parameter combinations based on the target magnetization parameters of at least one completed stage.

[0101] The non-first stage is the stage corresponding to the time interval following the first time interval. For example, the stage corresponding to the second time interval, the stage corresponding to the third time interval, etc.

[0102] In some embodiments, the non-first stage can be the remaining stages, that is, all subsequent stages of the currently completed stage.

[0103] The term "at least one stage that has been completed" refers to the stage of magnetization that was completed before the current moment.

[0104] Candidate magnetization parameter combinations are used to determine the target magnetization parameter combination. For example, a candidate magnetization parameter combination can be a sequence of target magnetization parameters for the remaining stages. For instance, if a time period includes four magnetization processes, and the first stage of magnetization has been completed, then the candidate magnetization parameter combination is a sequence of target magnetization parameters for the second, third, and fourth stages in chronological order.

[0105] It should be noted that the number of target magnetization parameters included in the candidate magnetization parameter combinations varies depending on the number of remaining stages. For example, when there are two remaining stages, the candidate magnetization parameter combinations will contain target magnetization parameters for two stages.

[0106] Candidate magnetization parameter combinations can be determined in several ways. For example, the processor can determine the candidate magnetization parameter combinations by random generation. Alternatively, the processor can determine the current candidate magnetization parameter combinations as those used in the previous production of the composite material.

[0107] In some embodiments, the processor can also determine at least one set of candidate magnetization parameter combinations by matching against a historical database based on the target magnetization parameters, raw material composition ratios, and target performance parameters of one or more currently completed stages. For more details on this embodiment, please refer to [link to relevant documentation]. Figure 2B Related descriptions.

[0108] Step S224: Based on the target magnetization parameters of at least one completed stage, the sensing data of at least one completed stage, and at least one set of candidate magnetization parameter combinations, predict the estimated dielectric constant value corresponding to at least one set of candidate magnetization parameter combinations.

[0109] Sensing data can refer to temperature information on the surface of a composite material. For example, sensing data can be a sequence of temperatures at different locations on the surface of a composite material.

[0110] Sensing data can be acquired in various ways. In some embodiments, the processor can acquire it using one or more sensors deployed within a preset range of the material in the magnetic field space. The preset range can refer to a region centered on the composite material at a preset distance. The preset distance can be set according to actual needs; for example, the preset distance can be zero, indicating that the sensor is in close contact with the composite material. Exemplary sensors may include temperature sensors, infrared image sensors, etc. The magnetic field space refers to the region in the magnetic field environment where a magnetic field is applied.

[0111] In some embodiments, when the sensor is an infrared image sensor, the processor can also acquire infrared images based on the infrared sensor and determine the surface temperature of the composite material by the image color of the area where the composite material is located in the acquired infrared image (i.e., the color of the composite material).

[0112] The estimated dielectric constant refers to the predicted dielectric constant of the composite material. For example, the estimated dielectric constant can be the final dielectric constant of the composite material obtained after subsequent magnetization treatment using a certain candidate combination of magnetization parameters.

[0113] The estimated dielectric constant can be obtained in a variety of ways. In some embodiments, the processor can process the target magnetization parameters of at least one completed stage, the sensing data of at least one completed stage, and the candidate combinations of magnetization parameters based on mathematical fitting, machine learning models, etc., to obtain the estimated dielectric constant.

[0114] In some embodiments, the processor may further process the target magnetization parameters of at least one completed stage, the sensing data of at least one completed stage, and candidate combinations of magnetization parameters predicted by a first prediction model to obtain an estimated dielectric constant value corresponding to the candidate combination of magnetization parameters. For further details on this embodiment, please refer to... Figure 2B Related descriptions.

[0115] Step S23: Determine the target magnetization parameter combination based on at least one estimated dielectric constant value.

[0116] The target magnetization parameter combination refers to the combination of target magnetization parameters used in the remaining stage magnetization process.

[0117] In some embodiments, the processor may select an estimated dielectric constant value that is equal to or similar to the dielectric constant value in the target performance parameters, and determine the candidate magnetization parameter combination corresponding to the estimated dielectric constant value as the target magnetization parameter combination.

[0118] Step S24: Based on the target magnetization parameter combination, determine the target magnetization parameters for magnetization processing other than the first stage.

[0119] In some embodiments, the processor may use the target magnetization parameters of each stage in the target magnetization parameter combination as the target magnetization parameters for the remaining stages of magnetization processing.

[0120] In some embodiments, the processor may redetermine and update the target magnetization parameter combination after each stage of magnetization processing is completed, and determine the target magnetization parameters for the remaining stages of magnetization processing based on the target magnetization parameter combination.

[0121] In this way, as the magnetization process continues, the processor can adjust and update the magnetization parameters of subsequent magnetization processes in real time, thereby improving the accuracy of magnetization.

[0122] In some embodiments of this specification, by retrieving candidate combinations of magnetization parameters from a historical database, and then determining the target magnetization parameters for all stages of the magnetization process, the accuracy of the magnetization parameters can be improved, thereby improving the magnetization precision and ensuring that the dielectric constant of the final produced composite material meets production requirements.

[0123] Figure 2B This is an exemplary schematic diagram illustrating the determination of a predicted dielectric constant value according to some embodiments of this specification.

[0124] In some embodiments, such as Figure 2BAs shown, the processor can determine at least one set of candidate magnetization parameter combinations 215 by matching in the historical database 213 based on the target magnetization parameters 214, the raw material composition ratio 211, and the target performance parameters 212 of one or more currently completed stages.

[0125] In some embodiments, the processor may construct a second retrieval vector based on the target magnetization parameters 214 of one or more currently completed stages and the raw material composition ratio 211, retrieve reference vectors that meet the same or similar conditions in the historical database 213, and determine one or more candidate magnetization parameter combinations 215 based on the magnetization parameter sequence subsequently used in one or more reference vectors that meet the same or similar conditions.

[0126] For more information on historical databases, please refer to [link / reference]. Figure 2A Related descriptions.

[0127] The same or similar conditions refer to the judgment conditions used to determine the candidate magnetization parameter combination 215.

[0128] In some embodiments, the same or similar conditions may include a first condition and a second condition.

[0129] The first condition is a judgment condition related to the magnetization parameter. For example, the first condition may include that the similarity between the second search vector and the reference vector is greater than a first preset threshold. Similarity can be used to measure how close two vectors are numerically. In some embodiments, the processor can calculate the similarity between vectors by calculating the Euclidean norm or cosine similarity, etc.

[0130] The second condition is a judgment condition related to the dielectric constant value. For example, the second condition may include the dielectric constant value corresponding to the second search vector being located within the dielectric constant range corresponding to the reference vector.

[0131] In some embodiments, the processor may search the historical database 213 based on the second retrieval vector and determine one or more reference vectors that satisfy the first condition as the first vector; select vectors that satisfy the second condition from the first vectors and determine them as the second vectors; for each of the second vectors, form a candidate magnetization parameter combination 215 using the target magnetization parameters used by the vector in the remaining stages.

[0132] In some embodiments, the first preset threshold may be a manually preset value, a system default value, etc.

[0133] In some embodiments, when matching in the historical database 213, a first preset threshold is related to the magnetization processing time of each magnetization process that has been completed so far.

[0134] In some embodiments, the first preset threshold may be negatively correlated with the total magnetization processing time. For example, the larger the total magnetization processing time, the smaller the first preset threshold. The total magnetization processing time refers to the sum of the magnetization processing times of each stage that has been completed so far.

[0135] In some embodiments of this specification, as the magnetization time increases, the internal magnetic distribution of the composite material gradually stabilizes, and the magnetization parameters in subsequent magnetization processes have little impact on the dielectric constant value. By reducing the first preset threshold, the calculation efficiency can be improved while ensuring accuracy.

[0136] In some embodiments, the sum of the magnetization times for each stage that has been completed can be obtained by arithmetic addition or by weighted summation.

[0137] In some embodiments, the sum of magnetization processing times for each stage refers to the weighted sum of the magnetization processing times for each stage.

[0138] In some embodiments, during weighted summation, the weight of the magnetization time in each stage can be negatively correlated with the holding temperature of the corresponding magnetization stage. For example, the higher the holding temperature, the smaller the weight.

[0139] In some embodiments of this specification, the higher the temperature, the more intense the molecular motion inside the composite material. Therefore, the magnetization effect of the magnetization treatment time at high temperature is more obvious. By determining the weight by temperature, the sum of the magnetization treatment times can more accurately reflect the effect of the magnetization treatment and improve the accuracy of subsequently determining the first preset threshold.

[0140] In some embodiments, such as Figure 2B As shown, the processor can process the target magnetization parameter 214 of the at least one completed stage, the sensing data 216 of the at least one completed stage, and the candidate magnetization parameter combination 215 based on the prediction of the first prediction model 220 to obtain the estimated dielectric constant value 230 corresponding to the candidate magnetization parameter combination 215. The first prediction model 220 is a machine learning model.

[0141] In some embodiments, the first prediction model 220 may be a machine learning model such as a deep neural network.

[0142] In some embodiments, the first prediction model 220 can be trained based on multiple first training samples with first labels. For example, multiple first training samples with first labels are input into an initial first prediction model, a loss function is constructed using the first labels and the output of the initial first prediction model, and the parameters of the initial first prediction model are iteratively updated based on the loss function using gradient descent or other methods until training is completed when a preset condition is met, resulting in a trained first prediction model 220. The preset condition may be that the loss function converges, the number of iterations reaches a threshold, etc.

[0143] In some embodiments, the first training sample may include at least the target magnetization parameters of the sample composite material at various stages, sample sensing data, and candidate magnetization parameter combinations. The first label for training may be the actual dielectric constant value of the final sample composite material corresponding to the candidate magnetization parameter combination. The first training sample may be determined based on historical data. The first label may be obtained based on processor or manual annotation.

[0144] During the magnetization process, the internal particles of the composite material are affected by the magnetic field, resulting in heat release or absorption phenomena, either overall or locally. This causes changes in the surface temperature of the composite material, thus affecting the set holding temperature in the magnetization parameters. Obtaining the temperature sequence of the composite material surface helps to more accurately predict the estimated dielectric constant value, thereby improving magnetization accuracy.

[0145] In some embodiments, the inputs to the first prediction model 220 also include intermediate dielectric constant values ​​217 measured at time points during the magnetization process of the composite material in one or more stages, and the surface temperature 218 of the composite material at each time point.

[0146] For more information on intermediate dielectric constant values ​​obtained from time-point measurements during one or more stages of magnetization treatment of composite materials, please refer to [link to relevant documentation]. Figure 3 Related descriptions.

[0147] In some embodiments, when the input to the first prediction model 220 includes intermediate dielectric constant values ​​217 measured at time points during the magnetization process of the composite material in one or more stages, and the surface temperature 218 of the composite material at each time point, the first training sample may further include historical dielectric constant values ​​measured at time points during the magnetization process of the composite material in one or more stages, and historical surface temperatures of the composite material at each time point. Each time point is a historical time point.

[0148] In some embodiments of this specification, by considering the dielectric constant values ​​measured during the magnetization process of the composite material in one or more stages, and the surface temperature of the composite material at each time point, a machine learning model can be trained based on a large number of extensive features using the real dielectric constant values ​​at each time point. This can make the predicted dielectric constant values ​​more accurate and closer to the actual situation.

[0149] Figure 3 This is an exemplary schematic diagram illustrating the determination of whether a composite material is qualified, based on some embodiments of this specification.

[0150] In some embodiments, the processor can measure the intermediate dielectric constant value 321 of the composite material at at least one preset time point 310 during the preparation of the composite material using a dielectric constant measuring device; in response to the intermediate dielectric constant value 321 of the composite material meeting a preset requirement, the composite material is determined to be qualified 360.

[0151] The intermediate dielectric constant value 321 refers to the dielectric constant value during the production process of composite materials. For example, the intermediate dielectric constant value 321 can include the dielectric constant value during the magnetization process, such as the dielectric constant value of the first stage magnetization process, the dielectric constant value of the second stage magnetization process, etc.

[0152] For more information on dielectric constant values, please refer to [link / reference]. Figure 2A Related descriptions.

[0153] The preset time point 310 refers to a time point in the process of preparing the composite material. For example, the preset time point 310 may include time points in processes such as mixing, heating, pressurizing, extrusion granulation, and magnetization.

[0154] In some embodiments, the preset time point may also include the time point at which the final composite material is obtained.

[0155] For more information on mixing, heating, pressurizing, and extrusion granulation, please refer to [link to relevant documentation]. Figure 1 Related descriptions.

[0156] For more information on magnetization, please refer to [link / reference]. Figure 2A Related descriptions.

[0157] In some embodiments, at least one preset time point 310 may also include a time point in the magnetization process of the composite material in at least one stage.

[0158] For each stage, the time point in the magnetization process can be any point in the magnetization process of that stage, or it can be a specified point in the magnetization process of that stage. The specified time point can be determined by manual selection, system default, or other methods.

[0159] In some embodiments, the processor can obtain the time points in each stage of the magnetization process by random selection.

[0160] The intermediate dielectric constant 321 can be measured in various ways. In some embodiments, the processor can measure the intermediate dielectric constant 321 of the composite material at a preset time point during composite material preparation using methods such as capacitance, microwave, impedance, and frequency methods. In some embodiments, the processor can also directly measure the intermediate dielectric constant 321 of the composite material at a preset time point using a dielectric constant measuring device. The dielectric constant measuring device can be a dielectric temperature spectrometer, etc.

[0161] In some embodiments, the dielectric constant measuring device is configured to perform the measurement at a specific temperature of 322°C.

[0162] The specific temperature 322 refers to a preset temperature value. For example, the specific temperature 322 may include the holding temperature during the magnetization process.

[0163] In some embodiments, the specific temperature 322 may also be a system default value, a manually preset value, or a value determined based on actual production conditions or scenarios.

[0164] Different preset time points 310 may correspond to the same or different specific temperatures 322.

[0165] In some embodiments, the processor can generate control commands at a preset time point 310 and send them to the temperature sensor and the dielectric constant measuring device to control the temperature sensor and the dielectric constant measuring device to perform measurements respectively, thereby obtaining a specific temperature 322 and an intermediate dielectric constant value 321 at the preset time point 310.

[0166] The preset requirements are the criteria for evaluating the intermediate dielectric constant value 321. For example, the preset requirements may include the intermediate dielectric constant value 321 at a certain preset time point being equal to the preset value of the stage in which the preset time point is located, or the preset range of the intermediate dielectric constant value 321 in the stage in which the preset time point is located.

[0167] Preset values ​​and preset ranges can be preset parameter values ​​or ranges related to dielectric constants. Preset values ​​and preset ranges can be manually preset or obtained by system defaults. Different preset values ​​or ranges can correspond to different magnetization stages.

[0168] In some embodiments, the processor can determine that the composite material is qualified 360 based on the intermediate dielectric constant value 321 measured at all preset time points and at a specific temperature, which meets preset requirements.

[0169] In some embodiments, the processor can predict the intermediate dielectric constant 340 of the composite material at the current time point and target temperature based on the specific temperature 322 and the corresponding intermediate dielectric constant 321 of the composite material at at least one preset time point 310 using a second prediction model 330, where the second prediction model 330 is a machine learning model; in response to the predicted intermediate dielectric constant satisfying the preset requirement 350, the magnetization process of the current stage ends, and the final composite material is obtained.

[0170] The current point in time refers to the current moment. In some embodiments, the current moment can be the moment when the magnetic field is turned off, heating stops, cooling begins, or other moments, such as the moment during cooling.

[0171] The target temperature is a preset temperature value. For example, the target temperature could be room temperature, etc. In some embodiments, the target temperature can be obtained through manual input.

[0172] The second prediction model 330 is used to predict the intermediate dielectric constant value 340 of the composite material at the current time and target temperature. In some embodiments, the second prediction model 330 may be a machine learning model such as a recurrent neural network model.

[0173] In some embodiments, the second prediction model can be trained based on multiple second training samples with second labels. For example, multiple second training samples with second labels are input into an initial second prediction model, a loss function is constructed using the labels and the output of the initial second prediction model, and the parameters of the initial second prediction model are iteratively updated based on the loss function using gradient descent or other methods until training is completed when a preset condition is met, resulting in a trained second prediction model. The preset condition may be that the loss function converges, the number of iterations reaches a threshold, etc.

[0174] In some embodiments, the second training samples include at least one sample temperature at a first time point and the corresponding intermediate dielectric constant value of the sample. The second label for training can be the actual dielectric constant value of the final sample composite material at a second time point and a target temperature. The second training samples can be determined based on historical data. The second label can be based on processor or manual annotation. Both the first and second time points are historical time points, and the first time point precedes the second time point.

[0175] In some embodiments, the processor may determine that the composite material is qualified 360 in response to the predicted intermediate dielectric constant value meeting a preset requirement 350, end the magnetization process of the current stage, and obtain the final composite material.

[0176] In some embodiments, the processor can determine that the composite material is unqualified in response to the predicted intermediate dielectric constant value not meeting a preset requirement, terminate the current stage of magnetization processing, redetermine the magnetization parameters, and re-magnetize the composite material. For example, at the moment the magnetization process stops, the processor can select qualified and identical composite materials from historical magnetization data and use their corresponding magnetization parameters as the redefined magnetization parameters. Alternatively, the processor can determine the adjustment amount of the magnetization parameters based on the difference between the predicted intermediate dielectric constant value and the dielectric constant value in the target performance parameters, and redetermine the magnetization parameters based on the adjustment amount and the current magnetization parameters. Different differences correspond to different adjustment amounts.

[0177] During the magnetization process, if the measured intermediate dielectric constant of the composite material meets the preset requirements, the magnetization is terminated. Because the dielectric constant of the composite material is temperature-dependent, and the magnetization process must be carried out at a set temperature, the actual measured dielectric constant during magnetization corresponds to the set temperature. When the magnetic field is turned off, heating is stopped, and the composite material is cooled to room temperature, its dielectric constant will change. Therefore, it is necessary to measure the temperature and corresponding dielectric constant at multiple time points during the magnetization process to predict the dielectric constant of the composite material at the current time point and room temperature. If the predicted dielectric constant meets the production requirements, magnetization is stopped, and the final composite material is obtained.

[0178] In some embodiments of this specification, the second prediction model can efficiently and accurately predict the dielectric constant of the composite material at the current time and target temperature, comprehensively and intuitively characterizing the effect of magnetization treatment. This allows for the early treatment of unqualified composite materials, improving the quality and efficiency of magnetization.

[0179] In some embodiments of this specification, since the composite material needs to be cooled to room temperature after being heated and magnetized, and the dielectric constant value is related to temperature, the dielectric constant value obtained by measuring at multiple preset time points can accurately reflect the law of change of the dielectric constant value of the composite material with temperature, thereby improving the accuracy of the predicted dielectric constant value at the current time and room temperature, which is beneficial for predicting the magnetization effect of the composite material and improving the efficiency and quality of magnetization.

[0180] One or more embodiments of this specification also provide a control device for the properties of composite materials, the device including at least one processor and at least one memory; the at least one memory is used to store computer instructions; the at least one processor is used to execute at least a portion of the computer instructions to implement the method as described in any of the above embodiments.

[0181] One or more embodiments of this specification also provide a computer-readable storage medium that stores computer instructions, which, when read by a computer, execute the method described in any of the above embodiments.

[0182] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this specification. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are suggested in this specification and therefore remain within the spirit and scope of the exemplary embodiments described herein.

[0183] Furthermore, this specification uses specific terms to describe embodiments thereof. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "an embodiment," "one embodiment," or "an alternative embodiment" in different locations throughout this specification do not necessarily refer to the same embodiment. Moreover, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0184] Furthermore, unless expressly stated in the claims, the order of processing elements and sequences, the use of numbers and letters, or other names described in this specification are not intended to limit the order of the processes and methods described herein. Although various examples have been discussed in the foregoing disclosure of some embodiments that are currently considered useful, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments; rather, the claims are intended to cover all modifications and equivalent combinations that conform to the substance and scope of the embodiments described herein. For example, while the system components described above can be implemented using hardware devices, they can also be implemented solely using software solutions, such as installing the described system on existing servers or mobile devices.

[0185] Similarly, it should be noted that, in order to simplify the description disclosed herein and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of embodiments in this specification may sometimes combine multiple features into a single embodiment, drawing, or description thereof. However, this method of disclosure does not imply that the subject matter of this specification requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of a single embodiment disclosed above.

[0186] In some embodiments, numbers describing the quantity of components and attributes are used. It should be understood that such numbers used in the description of embodiments are modified in some examples with the terms "approximately," "approximately," or "generally." Unless otherwise stated, "approximately," "approximately," or "generally" indicates that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may be changed depending on the characteristics required by individual embodiments. In some embodiments, numerical parameters should take into account specified significant digits and employ a general method of digit reservation. Although the numerical ranges and parameters used to confirm their breadth of range in some embodiments of this specification are approximate values, in specific embodiments, such values ​​are set as precisely as feasible.

[0187] For each patent, patent application, patent application publication, and other material, such as articles, books, specifications, publications, and documents, referenced in this specification, the entire contents of which are incorporated herein by reference. This excludes historical application documents that are inconsistent with or conflict with the content of this specification, as well as documents that limit the broadest scope of the claims in this specification (currently or subsequently appended to this specification). It should be noted that in the event of any inconsistency or conflict between the descriptions, definitions, and / or terminology used in the supplementary materials to this specification and the content of this specification, the descriptions, definitions, and / or terminology used in this specification shall prevail.

[0188] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be consistent with the teachings of this specification, rather than as examples or limitations. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. A method for controlling the performance of composite materials, the method being processor-based, the method comprising: Raw materials are selected and mixed according to a preset ratio. The raw materials include polyetherimide, soluble polytetrafluoroethylene, and optional metal powder and / or metal oxide powder. The preset ratio includes: 55%-65% by mass of polyetherimide, 35%-45% by mass of soluble polytetrafluoroethylene, and 0-5% by mass of metal powder and / or metal oxide powder. Based on a preset temperature and a preset current, the molding device is controlled to heat, pressurize, and extrude the mixed mixture into granules to obtain a composite material, including: placing the composite material in a heated and magnetic environment, and subjecting the composite material to at least one stage of magnetization treatment with corresponding magnetization parameters; the magnetization parameters include at least one of heat preservation temperature, magnetic field strength, and magnetization treatment time; The determination of the magnetization parameters for the at least one stage of magnetization treatment includes: For the magnetization treatment in the first stage, the target magnetization parameters for the first stage are determined based on the composition ratio and target performance parameters of the raw materials. For magnetization processes other than the first stage, a second retrieval vector is constructed based on the target magnetization parameters and the composition ratio of the raw materials from at least one completed stage. Reference vectors that satisfy the same or similar conditions as the second retrieval vector are retrieved from the historical database. Based on the magnetization parameter sequences used in subsequent stages from one or more reference vectors that satisfy the same or similar conditions, at least one set of candidate magnetization parameter combinations is generated. The same or similar conditions include a similarity between the second retrieval vector and the reference vector exceeding a first preset threshold. The first preset threshold is negatively correlated with the total magnetization processing time, which is the weighted sum of the magnetization processing times for each completed stage. The weight of the magnetization processing time for each stage is negatively correlated with the heat preservation temperature of the corresponding stage's magnetization processing. Based on the target magnetization parameters of at least one completed stage, the sensing data of at least one completed stage, and the at least one set of candidate magnetization parameter combinations, a first prediction model is used to predict the estimated dielectric constant value corresponding to the at least one set of candidate magnetization parameter combinations; the first prediction model is a deep neural network model. Based on at least one of the estimated dielectric constant values, a target magnetization parameter combination is determined; based on the target magnetization parameter combination, the target magnetization parameters for the non-first stage magnetization process are determined.

2. The method according to claim 1, characterized in that, The method further includes: At at least one preset time point in the preparation of the composite material, the intermediate dielectric constant value of the composite material is measured by a dielectric constant measuring device, wherein the at least one preset time point includes the time point at which the composite material is obtained; In response to the intermediate dielectric constant value of the composite material meeting a preset requirement, the composite material is determined to be qualified.

3. A composite material performance control system, characterized in that, The system includes: A mixing module is used to select and mix raw materials in a preset ratio. The raw materials include polyetherimide, soluble polytetrafluoroethylene, and optional metal powder and / or metal oxide powder. The preset ratio includes at least: 55%-65% by mass of polyetherimide, 35%-45% by mass of soluble polytetrafluoroethylene, and 0-5% by mass of metal powder and / or metal oxide powder. A control module is used to control a molding device to heat, pressurize, and extrude the mixed mixture into granules based on a preset temperature and a preset current to obtain a composite material. The control module also includes a magnetization module, which is configured to place the composite material in a heated and magnetized environment and perform at least one stage of magnetization treatment on the composite material with corresponding magnetization parameters. The magnetization parameters include at least one of heat preservation temperature, magnetic field strength, and magnetization treatment time. The magnetization module is configured as follows: For the magnetization treatment in the first stage, the target magnetization parameters for the first stage are determined based on the composition ratio and target performance parameters of the raw materials. For magnetization processes other than the first stage, a second retrieval vector is constructed based on the target magnetization parameters and the composition ratio of the raw materials from at least one completed stage. Reference vectors that satisfy the same or similar conditions as the second retrieval vector are retrieved from the historical database. Based on the magnetization parameter sequences used in subsequent stages from one or more reference vectors that satisfy the same or similar conditions, at least one set of candidate magnetization parameter combinations is generated. The same or similar conditions include a similarity between the second retrieval vector and the reference vector exceeding a first preset threshold. The first preset threshold is negatively correlated with the total magnetization processing time, which is the weighted sum of the magnetization processing times for each completed stage. The weight of the magnetization processing time for each stage is negatively correlated with the heat preservation temperature of the corresponding stage's magnetization processing. Based on the target magnetization parameters of at least one completed stage, the sensing data of at least one completed stage, and the at least one set of candidate magnetization parameter combinations, a first prediction model is used to predict the estimated dielectric constant value corresponding to the at least one set of candidate magnetization parameter combinations; the first prediction model is a deep neural network model. Based on at least one of the estimated dielectric constant values, a target magnetization parameter combination is determined; based on the target magnetization parameter combination, the target magnetization parameters for the non-first stage magnetization process are determined.

4. The control system as described in claim 3, characterized in that, The magnetization module is configured as follows: At at least one preset time point in the preparation of the composite material, the intermediate dielectric constant value of the composite material is measured by a dielectric constant measuring device, wherein the at least one preset time point includes the time point at which the composite material is obtained; In response to the intermediate dielectric constant value of the composite material meeting a preset requirement, the composite material is determined to be qualified.

5. A device for controlling the properties of composite materials, characterized in that, The device includes at least one processor and at least one memory; The at least one memory is used to store computer instructions; The at least one processor is configured to execute at least a portion of the computer instructions to implement the control method as described in any one of claims 1 to 2.

6. A computer-readable storage medium, characterized in that, The storage medium stores computer instructions. When the computer reads the computer instructions from the storage medium, the computer executes the control method as described in any one of claims 1 to 2.

Images