Process for the preparation of plastic particles and formulations

Abstract

The application relates to the technical field of plastic particles, and provides a preparation method and a formula of plastic particles.The preparation method of the plastic particles comprises the following steps: mixing polyethylene resin, ultrahigh molecular weight polyethylene particles, compounded antioxidant, nano calcium carbonate, glycidyl methacrylate grafted polyethylene compatilizer, heat stabilizer, polycarbonate and ethylene propylene acrylate copolymer to obtain an initial mixture; sending a plasticizing request message to a plastic particle preparation device control system; receiving plasticizing state information corresponding to a target plasticizing unit from the plastic particle preparation device control system; determining the plasticizing quality of the raw material mixture corresponding to the plasticizing target based on the plasticizing state information; and based on the plasticizing quality, regulating and controlling the operation parameters of the target plasticizing unit, melting and plasticizing, granulating and cooling the initial mixture to obtain the plastic particles.The method can reduce the deviation accumulation to cause the plasticizing quality to deviate from the target requirement, and significantly improve the performance consistency of the plastic particle finished product.

Description

Technical Field

[0001] This application belongs to the field of plastic particle technology, and in particular relates to a method and formulation for preparing plastic particles. Background Technology

[0002] Plastic particles, as a basic polymer intermediate, are widely used in injection molding, extrusion molding, blow molding, and other fields. Their preparation quality directly determines the mechanical properties, processing performance, and appearance quality of downstream products. The preparation of plastic particles typically includes core steps such as raw material mixing, melt plasticizing, granulation, and cooling. In the raw material mixing stage, resin, fillers, and additives are mixed uniformly in proportion to obtain an initial mixture. In the melt plasticizing stage, the initial mixture is heated, melted, and kneaded using equipment such as a plastic particle preparation device. Finally, the finished plastic particles are obtained through granulation and cooling. To ensure the smooth operation of the preparation process, existing technologies have developed control systems to monitor the operating parameters of the plastic particle preparation device, which improves the automation level of the preparation process to a certain extent.

[0003] However, existing plastic particle preparation technologies still have many shortcomings in practical applications: On the one hand, when selecting plasticizing units for melt plasticizing, existing technologies often rely on the operator's experience or simple equipment parameter matching, without considering the combined influence of various plasticizing parameters on the plasticizing effect. This results in the selected plasticizing units not being able to accurately match the preset plasticizing target, and easily leading to problems such as uneven plasticizing and melt quality fluctuations. On the other hand, existing technologies mostly rely on static monitoring of a single or a few parameters to judge the plasticizing quality, making it difficult to accurately determine whether the plasticizing quality meets the target requirements. This leads to a lack of targeted control over subsequent operating parameters, ultimately resulting in poor performance consistency of the finished plastic particles, which cannot meet the stringent requirements for the quality stability of plastic particles in high-end application scenarios. Summary of the Invention

[0004] The purpose of this application is to provide a method and formulation for preparing plastic particles, which can improve the problem of poor performance consistency of finished plastic particle products.

[0005] To achieve the above-mentioned objectives, the technical solution adopted in this application is as follows: In a first aspect, this application provides a method for preparing plastic particles, the method comprising: A resin premix is ​​obtained by mixing and stirring polyethylene resin, ultra-high molecular weight polyethylene particles and compound antioxidants. A composite filler modification system is obtained by mixing nano-calcium carbonate and glycidyl methacrylate grafted polyethylene compatibilizer. The resin premix, the composite filler modification system, heat stabilizer, polycarbonate and ethylene acrylate copolymer are mixed to obtain an initial mixture. A plasticizing request message is sent to the control system of the plastic particle preparation device; wherein, the plasticizing request message is used to request the use of a target plasticizing unit to melt and plasticize the raw material mixture corresponding to the plasticizing target, and the plasticizing request message carries the identification information of the target plasticizing unit; the target plasticizing unit is the unit that minimizes the correlation between the two plasticizing parameter points with the least correlation in the plasticizing process corresponding to the plasticizing target among all available plasticizing units controlled by the preparation management function unit; The system receives plasticizing state information corresponding to the target plasticizing unit from the control system of the plastic particle preparation device; wherein the plasticizing state information is used to characterize the plasticizing state of the initial mixture in the target plasticizing unit, including the temperature of each section of the barrel, the screw speed, and the barrel pressure; Based on the plasticization state information, the plasticization quality of the raw material mixture corresponding to the plasticization target is determined; and based on the plasticization quality, the operating parameters of the target plasticization unit are adjusted to melt-plasticize, granulate, and cool the initial mixture to obtain plastic particles.

[0006] The method for preparing plastic particles provided in this application involves first mixing polyethylene resin, ultra-high molecular weight polyethylene particles, and a compounded antioxidant to obtain a resin premix. The molecular weight gradient of the polyethylene resin and ultra-high molecular weight polyethylene particles can improve the dispersion uniformity of the compounded antioxidant. A composite filler-modified system is obtained by mixing nano-calcium carbonate and glycidyl methacrylate-grafted polyethylene compatibilizer. This allows the glycidyl methacrylate-grafted polyethylene compatibilizer to pre-coat the surface of the nano-calcium carbonate, reducing the surface energy of the inorganic filler and decreasing its agglomeration. Consequently, when the resin premix, composite filler-modified system, heat stabilizer, and polycarbonate and ethylene acrylate copolymer are mixed, the two types of premixed systems can achieve precise interfacial bonding between the organic phase (resin) and the inorganic phase (filler) when they are compounded. During preparation, a plasticizing signal carrying a target plasticizing unit identifier is sent to the control system of the plastic particle preparation device. The request message selects a target plasticizing unit that minimizes the correlation between the two plasticizing parameter points with the lowest correlation during the plasticizing process. This balances the linkage between plasticizing parameters. By optimizing the correlation of parameter points, the target plasticizing unit ensures that the control of each parameter is directed towards the plasticizing target (such as the target melt flow rate and the target melt homogeneity), improving the adaptability between the plasticizing unit and the plasticizing target, thereby enhancing the stability of the plasticizing process. Then, it receives the plasticizing state information corresponding to the target plasticizing unit and captures core plasticizing data such as barrel temperature, screw speed, and barrel pressure in real time, providing comprehensive and continuous data support for accurate judgment of plasticizing quality. Based on the plasticizing state information, it determines the plasticizing quality and adjusts the operating parameters, constructing a closed-loop response mechanism of monitoring-judgment-control. This mechanism can promptly correct plasticizing deviations (such as temperature fluctuations and pressure anomalies) to reduce the accumulation of deviations that could cause the plasticizing quality to deviate from the target requirements. By implementing a closed-loop synergy of raw material mixing, plasticizing unit matching, real-time state monitoring, and dynamic quality control, the plasticizing process is automated and precisely controlled, effectively improving its stability and controllability. Ultimately, through precise control of the plasticizing process, the performance consistency of finished plastic particles (such as melt flow rate and uniformity of mechanical properties) can be significantly improved, ensuring that the products meet the quality requirements of high-end applications. At the same time, it reduces systematic errors caused by human experience judgment, thereby improving production efficiency and finished product qualification rate.

[0007] Secondly, this application provides a plastic particle prepared by the method described in any of the above embodiments. The formulation of the plastic particle includes the following components in parts by weight: Polyethylene resin, 40-50 parts; Ultra-high molecular weight polyethylene granules, 3-8 parts; Compound antioxidant, 0.3~0.6 parts; Nano calcium carbonate, 8-15 parts; Glycidyl methacrylate grafted polyethylene compatibilizer, 1-3 parts; Heat stabilizer, 0.8~1.5 parts; Polycarbonate, 5-10 parts; Ethylene acrylate copolymer, 2-5 parts.

[0008] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0010] Figure 1 This is a schematic flowchart of the method for preparing plastic particles provided in the embodiments of this application; Figure 2 This is a flowchart illustrating the implementation of the method for preparing plastic particles provided in the embodiments of this application; Figure 3 This is a schematic diagram of the control system of the plastic particle preparation apparatus provided in the embodiments of this application. Detailed Implementation

[0011] To make the technical problems, technical solutions, and beneficial effects of this application clearer, the following detailed description is provided in conjunction with embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. In the following description, specific details such as particular system structures and technologies are set forth for illustrative purposes rather than for limiting the scope of the application, in order to provide a thorough understanding of the embodiments. However, those skilled in the art should recognize that this application can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted to avoid unnecessary detail that could obscure the description of this application.

[0012] In this application, the term "and / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. When used in this application specification and appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or a collection thereof.

[0013] In this application, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or multiple items. For example, "at least one of a, b, or c", or "at least one of a, b, and c", can both mean: a, b, c, ab (i.e., a and b), ac, bc, or abc, where a, b, and c can be single or multiple.

[0014] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determination" or "if the described condition or event is detected" may be interpreted, depending on the context, as "once determination," "in response to determination," "once the described condition or event is detected," or "in response to the detection of the described condition or event."

[0015] References such as "in one possible implementation" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0016] It should be understood that in the various embodiments of this application, the order of the above processes does not imply the order of execution. Some or all steps may be executed in parallel or sequentially. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0017] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. The singular forms “a,” “the,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0018] The weights of the relevant components mentioned in the embodiments of this application can refer not only to the specific content of each component, but also to the proportional relationship between the weights of the components. Therefore, any scaling up or down of the content of the relevant components according to the embodiments of this application is within the scope disclosed in the embodiments of this application. Specifically, the mass described in the embodiments of this application can be a well-known unit of mass in the chemical industry, such as µg, mg, g, or kg.

[0019] The terms "first" and "second" are used for descriptive purposes only, to distinguish objects, such as substances, from one another, and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. For example, without departing from the scope of the embodiments of this application, "first XX" may also be referred to as "second XX," and similarly, "second XX" may also be referred to as "first XX." Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of that feature.

[0020] Existing plastic particle preparation technologies still have many shortcomings in practical applications: On the one hand, when selecting plasticizing units for melt plasticizing, existing technologies often rely on the operator's experience or simple equipment parameter matching, without considering the impact of the correlation between various plasticizing parameter points on the plasticizing effect. This results in the selected plasticizing units not being able to accurately adapt to the preset plasticizing target, easily leading to problems such as uneven plasticizing and melt quality fluctuations. On the other hand, existing technologies rely on static monitoring of a single or a few parameters to judge plasticizing quality, lacking comprehensive dynamic tracking of the plasticizing state. It is difficult to accurately determine whether the plasticizing quality meets the target requirements, which in turn leads to a lack of targeted control of subsequent operating parameters. Ultimately, this results in poor performance consistency of the finished plastic particles, failing to meet the stringent requirements for the quality stability of plastic particles in high-end application scenarios.

[0021] Based on this, to improve the problem of poor performance consistency of finished plastic particles in related technologies, this application provides a method and formulation for preparing plastic particles. In this method, a resin premix is ​​obtained by first mixing and stirring polyethylene resin, ultra-high molecular weight polyethylene particles, and a compound antioxidant. The molecular weight gradient of the polyethylene resin and ultra-high molecular weight polyethylene particles can improve the dispersion uniformity of the compound antioxidant. A composite filler-modified system is obtained by mixing nano-calcium carbonate and glycidyl methacrylate-grafted polyethylene compatibilizer. This allows the glycidyl methacrylate-grafted polyethylene compatibilizer to pre-coat the surface of the nano-calcium carbonate, reducing the surface energy of the inorganic filler and decreasing its agglomeration. This allows for precise interfacial bonding between the organic phase (resin) and the inorganic phase (filler) when the two types of premixes are combined, including the resin premix, the composite filler-modified system, the heat stabilizer, and the polycarbonate and ethylene acrylate copolymer. During preparation, a plasticizing request message carrying a target plasticizing unit identifier is sent to the control system of the plastic particle preparation device. By selecting a target plasticizing unit that minimizes the correlation between the two plasticizing parameter points with the lowest correlation during the plasticizing process, the linkage relationship of plasticizing parameters is balanced. The target plasticizing unit can optimize the correlation of parameter points so that the control of each parameter is directed towards the plasticizing target (such as the target melt flow rate and the target melt homogeneity), thereby improving the adaptability of the plasticizing unit and the plasticizing target and improving the stability of the plasticizing process. Then, the plasticizing state information corresponding to the target plasticizing unit is received, and core plasticizing data such as barrel temperature, screw speed, and barrel pressure are captured in real time, providing comprehensive and continuous data support for accurate judgment of plasticizing quality. Based on the plasticizing state information, the plasticizing quality is determined and the operating parameters are adjusted, constructing a closed-loop response mechanism of monitoring-judgment-control, which can promptly correct plasticizing deviations (such as temperature fluctuations and pressure anomalies) to reduce the accumulation of deviations that cause the plasticizing quality to deviate from the target requirements. By implementing a closed-loop synergy of raw material mixing, plasticizing unit matching, real-time state monitoring, and dynamic quality control, the plasticizing process is automated and precisely controlled, effectively improving its stability and controllability. Ultimately, through precise control of the plasticizing process, the performance consistency of finished plastic particles (such as melt flow rate and uniformity of mechanical properties) can be significantly improved, ensuring that the products meet the quality requirements of high-end applications. At the same time, it reduces systematic errors caused by human experience judgment, thereby improving production efficiency and finished product qualification rate.

[0022] At least some steps of the plastic particle preparation method provided in this application embodiment can be applied to a plastic particle preparation device. In this case, the plastic particle preparation device is the main body for executing the plastic particle preparation method provided in this application embodiment. This application embodiment does not limit the specific type of plastic particle preparation device.

[0023] For example, a plastic pellet preparation device may include a feeding system, a plasticizing extrusion system, a pelletizing and cooling system, and a control system. The feeding system may include a metering feeder for accurately conveying the initial resin mixture content. The plasticizing extrusion system is the core execution unit, enabling the melting, plasticizing, and mixing of the raw materials. The pelletizing and cooling system may include a die head, a pelletizer, and a cooling water tank for shaping, pelletizing, and cooling the plasticized melt. The control system monitors and controls the entire plasticizing process.

[0024] For example, the control system can be a microcontroller, PLC, mobile phone, tablet computer, laptop computer, ultra-mobile personal computer (UMPC), desktop computer, smart screen, computing device or other processing device connected to a wireless modem, Internet of Things terminal, computer, and / or other device for communication over a wireless system, as well as next-generation communication systems, such as mobile terminals in 5G networks or mobile terminals in future evolved Public Land Mobile Networks (PLMNs).

[0025] To better understand the method for preparing plastic particles provided in the embodiments of this application, the specific implementation process of the method for preparing plastic particles provided in the embodiments of this application will be described by way of example below.

[0026] Please see Figure 1 and Figure 2 The first aspect of this application provides a method for preparing plastic particles, comprising: S100, polyethylene resin, ultra-high molecular weight polyethylene particles and compound antioxidant are mixed and stirred to obtain resin premix, nano calcium carbonate and glycidyl methacrylate grafted polyethylene compatibilizer are mixed to obtain composite filler modified system; resin premix, composite filler modified system, heat stabilizer, polycarbonate and ethylene acrylate copolymer are mixed to obtain initial mixture.

[0027] S200, a plasticizing request message is sent to the control system of the plastic particle preparation device; wherein, the plasticizing request message is used to request the use of the target plasticizing unit to melt and plasticize the raw material mixture corresponding to the plasticizing target, and the plasticizing request message carries the identification information of the target plasticizing unit; the target plasticizing unit is the unit that minimizes the correlation between the two plasticizing parameter points with the least correlation in the plasticizing process corresponding to the plasticizing target among all available plasticizing units controlled by the preparation management function unit.

[0028] S300 receives plasticizing state information corresponding to the target plasticizing unit from the control system of the plastic particle preparation device; wherein, the plasticizing state information is used to characterize the plasticizing state of the initial mixture in the target plasticizing unit, including the temperature of each section of the barrel, the screw speed, and the barrel pressure.

[0029] S400 determines the plasticization quality of the raw material mixture corresponding to the plasticization target based on plasticization state information; and adjusts the operating parameters of the target plasticization unit based on the plasticization quality to melt, plasticize, granulate, and cool the initial mixture to obtain plastic particles.

[0030] Ultra-high molecular weight polyethylene (UHMWPE) granules refer to polyethylene polymer granules with a molecular weight between 1.5 million and 10 million, exhibiting excellent wear resistance, impact resistance, and self-lubricating properties. Compound antioxidants are anti-aging additives formed by compounding two or more different types of antioxidants in a specific ratio. Their core function is to synergistically inhibit the oxidative degradation of plastics during melting, plasticizing, and subsequent use. For example, they can be a mixture of hindered phenolic antioxidants (such as antioxidant 1010) and phosphite antioxidants (such as antioxidant 168) in a 1:2 mass ratio. Glycidyl methacrylate-grafted polyethylene compatibilizers are high-molecular-weight compatibilizers formed by grafting glycidyl methacrylate (GMA) monomers onto the polyethylene backbone through graft polymerization. Their molecular structure contains both polyethylene segments compatible with polyethylene and epoxy groups that react with inorganic fillers (such as nano-calcium carbonate). Heat stabilizers are additives that can inhibit or delay the degradation of plastics due to heat during processing. Examples include calcium-zinc composite heat stabilizers, organotin heat stabilizers (such as dibutyltin dilaurate), etc., but are not limited to these.

[0031] Plasticization status information can be acquired in real time by multiple high-precision sensors deployed on the target plasticizing unit. Specifically, the temperature of each section of the barrel can be acquired by PT100 platinum resistance temperature sensors embedded in the barrel wall, with an acquisition accuracy of ±0.1℃ and an acquisition frequency of once per second; the screw speed can be acquired by an incremental encoder installed on the end of the screw drive motor shaft, providing real-time feedback on screw speed fluctuations; the barrel pressure can be acquired by pressure sensors installed in the screw groove of the barrel, covering key areas such as the feeding section, compression section, and melting section, capturing pressure changes during the plasticization process.

[0032] As can be seen from the above, the method for preparing plastic particles provided in this application involves first mixing and stirring polyethylene resin, ultra-high molecular weight polyethylene particles, and a compound antioxidant to obtain a resin premix. The molecular weight gradient of the polyethylene resin and ultra-high molecular weight polyethylene particles can improve the dispersion uniformity of the compound antioxidant. A composite filler modification system is obtained by mixing nano-calcium carbonate and glycidyl methacrylate-grafted polyethylene compatibilizer. This allows the glycidyl methacrylate-grafted polyethylene compatibilizer to pre-coat the surface of the nano-calcium carbonate, reducing the surface energy of the inorganic filler and decreasing its agglomeration. Consequently, when the resin premix, composite filler modification system, heat stabilizer, and polycarbonate and ethylene acrylate copolymer are mixed, the two types of premix systems can achieve precise interfacial bonding between the organic phase (resin) and the inorganic phase (filler) when they are compounded. During preparation, a target plasticizing unit is sent to the control system of the plastic particle preparation device. The identified plasticizing request message selects a target plasticizing unit that minimizes the correlation between the two plasticizing parameter points with the lowest correlation during the plasticizing process. This balances the linkage between plasticizing parameters. By optimizing the correlation of parameter points, the target plasticizing unit ensures that the control of each parameter is directed towards the plasticizing target (such as the target melt flow rate and the target melt homogeneity), improving the adaptability between the plasticizing unit and the plasticizing target, thereby enhancing the stability of the plasticizing process. Then, it receives the plasticizing status information corresponding to the target plasticizing unit and captures core plasticizing data such as barrel temperature, screw speed, and barrel pressure in real time, providing comprehensive and continuous data support for accurate judgment of plasticizing quality. Based on the plasticizing status information, it determines the plasticizing quality and adjusts the operating parameters, constructing a closed-loop response mechanism of monitoring-judgment-control. This mechanism can promptly correct plasticizing deviations (such as temperature fluctuations and pressure anomalies) to reduce the accumulation of deviations that could cause the plasticizing quality to deviate from the target requirements. By implementing a closed-loop synergy of raw material mixing, plasticizing unit matching, real-time state monitoring, and dynamic quality control, the plasticizing process is automated and precisely controlled, effectively improving its stability and controllability. Ultimately, through precise control of the plasticizing process, the performance consistency of finished plastic particles (such as melt flow rate and uniformity of mechanical properties) can be significantly improved, ensuring that the products meet the quality requirements of high-end applications. At the same time, it reduces systematic errors caused by human experience judgment, thereby improving production efficiency and finished product qualification rate.

[0033] In one possible implementation, before sending the plasticizing request message to the plastic particle preparation apparatus control system in step S200, the method further includes: S10, obtain system control information and parameter details of the plasticizing target; the system control information includes unit information of all available plasticizing units, and the unit information includes the heating power of the plasticizing unit, the screw length-to-diameter ratio, and the historical plasticizing accuracy.

[0034] It is understandable that system control information is the fundamental data support for the precise selection of plasticizing units by the preparation management functional units. The acquisition process relies on the global data acquisition and management system of the plastic particle preparation device. Communication is established with the local controllers of each available plasticizing unit via industrial Ethernet to retrieve the inherent attribute parameters (heating power, screw length-to-diameter ratio) and historical operating data (historical plasticizing accuracy) of each unit in real time. Among these, heating power refers to the rated output power of the plasticizing unit's barrel heating module, typically ranging from 15kW to 60kW. This parameter directly determines the heating rate and maximum plasticizing temperature of the plasticizing unit, and is suitable for raw materials with different melting points (such as polyethylene resin with a melting point of 110–130℃). Key indicators include: 1) Polycarbonate melting point (220-230℃); 2) Screw length-to-diameter ratio (L / D ratio), which is the ratio of the effective screw length to the screw diameter, typically ranging from 20:1 to 40:1. This parameter determines the residence time and mixing intensity of the raw material in the barrel. A larger L / D ratio results in more thorough mixing but also higher energy consumption, requiring precise matching based on the mixing requirements of the plasticizing target; 3) Historical plasticizing accuracy, which refers to the degree of deviation between the actual plasticizing parameters and the target parameters when the plasticizing unit has previously completed similar plasticizing tasks. This is quantified by calculating the fluctuation coefficient (standard deviation / average) of key indicators such as melt flow rate (MFR) and melt density in historical batches. A fluctuation coefficient ≤3% indicates a high-precision plasticizing unit. The detailed parameters of the plasticizing target refer to the specific technical indicators that need to be achieved in this plasticizing task, including raw material compatibility parameters (such as the component ratio, moisture content, and bulk density of the raw material mixture), finished product performance targets (such as melt flow rate of 2-5 g / 10 min and tensile strength ≥ 20 MPa), and process control targets (such as target temperatures for each section of the barrel, target screw speed, and target barrel pressure range). These targets are obtained from product specifications in production orders, customer performance requirements, and process parameter ranges derived from raw material characteristics. For example, for composite raw materials containing nano-calcium carbonate, the upper limit of the barrel temperature in the plasticizing target needs to be reduced by 5-10°C to reduce nano-filler agglomeration. During the acquisition process, all data is standardized, converting parameters in different units into dimensionless data (such as normalizing heating power to the [0, 1] range), while removing abnormal data (such as extreme deviations in historical plasticizing accuracy caused by equipment failure).

[0035] S20, based on the unit information of any candidate plasticizing unit subset and the parameter details of the plasticizing target, calculate the correlation of all plasticizing parameter point pairs in the plasticizing process corresponding to the plasticizing target under all candidate plasticizing unit subsets; wherein, the candidate plasticizing unit subset includes the target number of units, and the plasticizing parameter point pair includes the parameters corresponding to two different plasticizing parameter monitoring points.

[0036] It is understandable that the selection of candidate plasticizing unit subsets needs to be based on the target number (such as 1 to 3 units, depending on the production capacity requirements). A combination algorithm is used to generate all possible subset combinations from all available plasticizing units. For example, if there are 5 available plasticizing units and the target number is 2, then C(5,2)=10 candidate plasticizing unit subsets are generated. Secondly, the determination of plasticizing parameter point pairs needs to be combined with the parameter details of the plasticizing target and the layout of monitoring points in the plasticizing unit. Plasticizing parameter monitoring points include barrel feed section temperature monitoring points, compression section temperature monitoring points, melting section temperature monitoring points, barrel feed section pressure monitoring points, melting section pressure monitoring points, screw speed monitoring points, etc. Each monitoring point corresponds to a real-time collected plasticizing parameter. A plasticizing parameter point pair is formed by selecting parameters corresponding to two different monitoring points from the above monitoring points, such as "feed section temperature - screw speed", "melting section pressure - melting section temperature", "screw speed - melting section pressure", etc. A total of C(n,2) parameter point pairs can be formed (n is the number of monitoring points, usually n≥6, so the number of parameter point pairs ≥15). Subsequently, the prerequisite for correlation calculation is to obtain the time series data of parameters of each candidate subset under the simulated plasticizing target conditions. Specifically, based on the unit information (heating power, screw length-to-diameter ratio) of the candidate subset and the process control target of the plasticizing target, the plasticizing process is simulated by finite element simulation software to obtain the time series data of each parameter monitoring point within a 10-minute plasticizing cycle (the acquisition frequency is once per second, with a total of 600 data points).

[0037] For example, the process timing distance between the first and second plasticizing parameter points can be calculated by multiplying the conjugate of the plasticizing response vector of the target number of units at the first plasticizing parameter point with the plasticizing response vector of the target number of units at the second plasticizing parameter point. The power is then used to calculate the distance between the first product value and the process timing. The second product value of the power of 1; the correlation between the first and second plasticizing parameter points is inversely proportional to the second product value; alternatively, time-series data of the unit at the first and second plasticizing parameter points can be extracted separately (such as the time-series data of the feed section temperature and screw speed of unit A), and the similarity between the two sets of time-series data can be calculated using the Dynamic Time Warping (DTW) algorithm, i.e., constructing a distance matrix between the two sets of time-series data, where the matrix elements are the Euclidean distances of the parameter values ​​at corresponding time points; the minimum cumulative distance from the starting point to the ending point in the distance matrix is ​​found through dynamic programming, and this minimum cumulative distance is the DTW distance between the two sets of time-series data. The smaller the DTW distance, the stronger the time-series correlation between the two parameter points within a single unit. The stronger the similarity, the more likely it is to be found. Then, the DTW distance of each unit is converted into similarity (similarity = 1 / (1+DTW distance), so that the similarity value range is (0, 1]). Then, the comprehensive similarity of the parameter point pairs under the candidate subset is calculated by weighted summation, that is, comprehensive similarity = Σ (unit weight × unit similarity). Then, the process correlation coefficient is introduced (set according to the correlation of the parameter's influence on plasticizing quality, such as the process correlation coefficient of "melting section temperature-melting section pressure" is set to 0.9, and the process correlation coefficient of "feeding section temperature-melting section pressure" is set to 0.5). The comprehensive similarity is multiplied by the process correlation coefficient to obtain the final correlation coefficient. Correlation is obtained in various ways, but not limited to these.

[0038] In one possible implementation, in step S20, the correlation of all plasticizing parameter point pairs during the plasticizing process corresponding to the plasticizing target under all candidate plasticizing unit subsets is calculated, including: S201, calculate the first product value of the conjugate of the first plasticizing composite vector and the second plasticizing composite vector; the first plasticizing composite vector is the plasticizing response vector of the target number of units at the first plasticizing parameter point, and the second plasticizing composite vector is the plasticizing response vector of the target number of units at the second plasticizing parameter point; the first plasticizing parameter point and the second plasticizing parameter point are arbitrary plasticizing parameter point pairs.

[0039] It can be understood that the conjugate of the first plasticized composite vector refers to the vector obtained by performing a conjugate operation on the first plasticized composite vector. Quantifying the correlation strength between two plasticized parameter points under multi-unit cooperative operating conditions through vector operations involves integrating the response data of a single parameter point across multiple units into a composite vector, and reflecting the degree of linear correlation between the two through the vector conjugate product.

[0040] First, determine the first and second plasticizing parameter points (e.g., "melting zone temperature" and "screw speed"). For a candidate plasticizing unit subset (e.g., containing two units, unit A and unit B), extract the plasticizing response data of this subset at the first parameter point during the simulated plasticizing process. This includes the time-series data of unit A at the first parameter point (e.g., 20 data points) and the time-series data of unit B at the first parameter point (e.g., 20 data points). Integrate these two sets of data into a 40-dimensional column vector in unit order, which is the first plasticizing composite vector. Similarly, extract the time-series data of this subset at the second parameter point and integrate it into a 40-dimensional column vector, which is the second plasticizing composite vector. Then, calculate the conjugate vector of the first plasticizing composite vector. For real-valued time-series data, the conjugate vector is its transpose (row vector). The first product value is calculated as the dot product of the conjugate vector and the second plasticizing composite vector, i.e., the sum of corresponding element-wise multiplication. Its mathematical expression is: First product value = conjugate (first composite vector) × second composite vector. The magnitude of this product value directly reflects the degree of alignment between the two composite vectors. The larger the product value, the more consistent the response trends of the two parameter points across multiple units, and the higher the initial correlation. It should be noted that the construction of composite vectors must ensure temporal alignment of the data, that is, the parameter data of the two units at the same time point must correspond one-to-one.

[0041] S202, Calculate the process timing distance between the first plasticizing parameter point and the second plasticizing parameter point. Power of 1 Greater than 0.

[0042] It can be understood that process timing distance refers to the degree of temporal correlation between the process steps corresponding to two plasticizing parameter points. First, the process logic chain of the plasticizing process is analyzed to clarify the process stages and temporal relationships corresponding to each plasticizing parameter point. For example, the process stage corresponding to "feed section temperature" is raw material preheating, which occurs in the early stage of plasticizing; the process stage corresponding to "melting section temperature" is raw material melting, which occurs in the middle stage of plasticizing; and "screw speed" runs through the entire plasticizing process, directly affecting the residence time of the raw material in each stage. The quantification method for process timing distance is as follows: using the plasticizing cycle (e.g., 10 minutes) as the time base, calculate the absolute value of the difference between the center moments of the process stages corresponding to the two parameter points, and then divide it by the plasticizing cycle to obtain the normalized timing distance, with a value range of [0, 0.5]. For example, if the center moment of the feed section temperature process is 1 minute and the center moment of the melting section temperature process is 5 minutes, then the timing distance = |5-1| / 10 = 0.4. Subsequently, the timing distance is calculated... Power of 1 This is an adjustment coefficient, the value of which is determined based on the characteristics of the plasticizing process, typically... ∈(0,2], the stronger the process correlation between the two parameter points (such as the temperature of the melting section and the pressure of the melting section). The smaller the value (e.g.) =0.5), weakening the effect of time distance on correlation; when the process correlation between two parameter points is weak (such as feed section temperature and melt section pressure). The larger the value (e.g.) =2), reinforcing the weakening effect of time series distance on correlation. For example, a time series distance of 0.4, When =1, the result of the power is 0.4; When the power is 2, the result is 0.16.

[0043] S203, calculate the distance between the first product value and the process timing. The second product value of the power of 1; the correlation between the first plasticizing parameter point and the second plasticizing parameter point is inversely proportional to the second product value.

[0044] It can be understood that the second product value = the first product value × time series distance. ɑ First, calculate the second product of all parameter pairs to obtain the maximum and minimum values. Then, using the formula: Correlation Coefficient = 1 - (Second Product Value - Minimum Value) / (Maximum Value - Minimum Value), map the second product values ​​to the interval [0, 1]. The closer the correlation coefficient is to 1, the stronger the correlation between the two parameter points; the closer it is to 0, the weaker the correlation. For example, if the first product value of a parameter pair is 800, and the time series distance... The power of 0.4 results in a second product value of 320. If the maximum value of the second product for all parameter pairs is 1000 and the minimum is 100, then the correlation coefficient of that parameter pair is 1 - (320 - 100) / (1000 - 100) = 1 - 220 / 900 ≈ 0.756, indicating a strong correlation between the two. A larger second product value means a more consistent response trend and a closer process timing between the two parameter points, resulting in stronger linkage between parameter controls. If there are parameter pairs with weak correlation, it can lead to control redundancy (adjusting one parameter cannot affect the other). Therefore, minimizing the correlation of the parameter pair with the lowest correlation ensures that the linkage between all parameter pairs is within a reasonable range.

[0045] This configuration, by integrating the parameter responses of multiple candidate units into a composite vector, achieves correlation quantification under multi-unit collaborative operating conditions, reduces the bias in correlation judgment caused by single-unit data, and ensures that the selected plasticizing unit subset can maintain reasonable parameter linkage during collaborative operation; the introduction of process timing distance... The power-law correction makes the correlation calculation more closely reflect the actual logic of the plasticizing process, avoiding the misjudgment of weakly correlated parameter pairs as highly correlated, thus improving the accuracy of the correlation calculation. Furthermore, by mapping the second product value to the inverse proportion of the correlation, the quantitative standard for the correlation of parameter pairs is clarified, providing a clear basis for subsequent minimum-maximum optimization selection. The implementation of this scheme means that the selection of plasticizing units no longer relies on empirical judgment but is based on precise quantitative data, laying the foundation for the stable operation of the subsequent plasticizing process. It effectively reduces problems such as uneven plasticizing and melt quality fluctuations caused by parameter linkage failures, improving the controllability of the plasticizing process.

[0046] S30, based on the correlation of all plasticizing parameter point pairs, adopts the min-max optimization method to select the target number of target plasticizing units from all available plasticizing units.

[0047] The core logic of the min-max optimization method is to select the subset with the maximum value among all subsets of minimum correlation indices. This means that through optimization, even the weakest link in the selected subset can reach an optimal level. For example, if the target number of units is any subset of candidate plasticizing units from all available plasticizing units, the correlation of each plasticizing parameter pair can be calculated. Then, the target plasticizing parameter pair with the lowest correlation among all plasticizing parameter pairs can be determined. Next, the target number of target plasticizing units that minimize the correlation of the target plasticizing parameter pair can be determined from the candidate plasticizing unit subsets. Alternatively, based on the core process constraints of the plasticizing target (e.g., unit heating power must match the raw material melting point requirement, operating energy consumption ≤ 35 kW·h / ton, historical monthly failure count ≤ 2 times), all generated candidate plasticizing unit subsets can be initially screened, eliminating subsets that do not meet the constraints. Then, min-max optimization can be performed on the screened subsets. For the remaining valid candidate subsets after the initial screening, the correlation coefficient of all plasticizing parameter pairs under each subset is calculated one by one, and the minimum correlation index (i.e., the correlation of the weakest linkage link) of each subset is extracted. Then, among the minimum correlation indices of all valid subsets, the subset corresponding to the maximum value is selected as the preliminary optimal subset. Finally, auxiliary indicators for production practicality (such as the average heating efficiency of the subset, unit product maintenance cost, and historical plasticizing pass rate) are introduced to verify the preliminary optimal subset. Auxiliary indicator thresholds are set (such as heating efficiency ≥85%, unit maintenance cost ≤50 yuan / ton, and historical plasticizing pass rate ≥98%). If the preliminary optimal subset meets all auxiliary indicator thresholds, the unit in the subset is directly determined as the target plasticizing unit; if not, the next subset is verified in descending order of minimum correlation index from the remaining valid subsets until a subset that simultaneously meets the minimum correlation index and the auxiliary indicators is met is found, and so on, but not limited to this.

[0048] This setup, by comprehensively acquiring unit information including key attributes such as heating power and screw length-to-diameter ratio, as well as detailed parameters of the plasticizing target, provides a precise and comprehensive data foundation for subsequent screening, reducing selection bias caused by missing data. By quantitatively calculating the correlation of plasticizing parameter pairs under each candidate subset, it achieves accurate evaluation of parameter linkage relationships under multi-unit collaborative operation, overcoming the limitations of single-unit parameter analysis. Furthermore, by using a min-max optimization method to focus on the weakest parameter linkage link in each subset, it selects the target unit with the optimal correlation for that weak link, ensuring that the selected units possess a balanced and reliable level of parameter linkage. This hardware adaptation ensures the stability of the plasticizing process, effectively reducing problems such as uneven plasticizing and melt quality fluctuations caused by parameter linkage failure. Simultaneously, it replaces the traditional experience-based selection method, reducing human intervention errors and improving the automation and intelligence level of plasticizing unit selection, laying a crucial foundation for subsequent precise control of plasticizing quality and improvement of finished product performance consistency.

[0049] In one possible implementation, in step S30, a min-max optimization method is used to select a target number of target plasticizing units from all available plasticizing units, including: S301, when the target number of units is any subset of candidate plasticizing units among all available plasticizing units, calculate the correlation of each plasticizing parameter point pair.

[0050] It can be understood that the coverage of any candidate plasticizing unit subset is all possible combinations selected from all available plasticizing units according to the target number. For example, if the number of available plasticizing units is 6 and the target number is 2, then the number of candidate subsets is C(6,2)=15. Each subset needs to be treated as an independent analysis object. Then, for each candidate subset, the correlation calculation process of steps S201 to S203 is executed to calculate the correlation coefficient of all plasticizing parameter point pairs under that subset.

[0051] S302, determine the target plasticizing parameter point pair with the lowest correlation among all plasticizing parameter point pairs.

[0052] It is understandable that for each candidate subset, the correlation coefficients of all corresponding parameter point pairs need to be organized into a correlation matrix. The rows and columns of the matrix represent the monitoring points of each plasticizing parameter, and the matrix elements are the correlation coefficients of the corresponding parameter point pairs. For the correlation matrix of each candidate subset, all off-diagonal elements of the matrix (i.e., the correlation coefficients of all parameter point pairs) are traversed. Since the correlation matrix is ​​a symmetric matrix (the correlation between A and B is equal to the correlation between B and A), only the upper or lower triangular elements can be traversed to improve traversal efficiency. Then, from all the correlation coefficients obtained, the coefficient with the smallest value is selected. The parameter point pair corresponding to this coefficient is the target plasticizing parameter point pair, representing the link with the weakest parameter linkage in the plasticizing process of this candidate subset. For example, in the correlation matrix of a certain candidate subset, the correlation coefficient of "feed section temperature - screw speed" is 0.25, which is the smallest among all parameter point pairs. Therefore, this parameter point pair is the target plasticizing parameter point pair. It should be noted that during the screening process, if multiple parameter pairs have the same correlation coefficient and are all at the minimum value, it is necessary to further rank these parameter pairs based on their process importance. The process importance is determined by the degree of influence of the corresponding parameter on the plasticizing quality. For example, the influence of "melting zone temperature - melting zone pressure" on the plasticizing quality is higher than that of "feed zone temperature - screw speed". If the correlation coefficients of the two are the same and are both at the minimum value, then "melting zone temperature - melting zone pressure" should be prioritized as the target plasticizing parameter pair.

[0053] S303, determine the number of target plasticizing units with the lowest correlation to the target plasticizing parameter point pairs from the subset of candidate plasticizing units.

[0054] It is understandable that by summarizing the "target plasticization parameter point-pair correlation coefficients" (i.e., the minimum correlation coefficients of each subset) of all candidate subsets, a coefficient set is formed; then, the maximum value is found in this coefficient set, and the candidate subset corresponding to the maximum value is the optimal subset, because the weak link (target plasticization parameter point pair) of this subset has the strongest correlation among all subsets, which means that its overall parameter linkage level is the most balanced and the risk of control redundancy is the lowest; finally, the number of plasticization units contained in the optimal subset is directly defined as the target plasticization unit.

[0055] This setup, through the step-by-step execution of S301 to S303, constructs a refined target plasticizing unit selection process encompassing full subset coverage, weak link location, and extreme value optimization screening. This further enhances the optimization effect and addresses the core pain points of inaccurate plasticizing unit selection and poor parameter linkage in existing technologies, bringing more significant technical advantages. First, the full subset correlation calculation in S301 ensures the comprehensiveness of the optimization selection, including all potential optimal unit combinations within the analysis scope. Second, the weak link location in S302 makes the optimization selection more targeted, focusing on the minimum correlation parameter pairs in each subset to ensure that the selected target plasticizing units do not have obvious parameter linkage shortcomings, thus improving the stability of the plasticizing process. Third, the extreme value optimization logic in S303 ensures the optimality of the selection results, enabling even the weak links of the target plasticizing units to reach a high level in the industry, significantly reducing the risk of parameter control failure. For example, it avoids the problem of insufficient melt uniformity caused by the weak correlation between "melting section pressure and screw speed".

[0056] In one possible implementation, in step S400, based on the plasticizing state information, the plasticizing quality of the raw material mixture corresponding to the plasticizing target is determined, including: S410 performs multi-feature tracking based on plasticizing process parameters in plasticizing state information, generating temperature feature chains, speed feature chains, and pressure feature chains.

[0057] It can be understood that the generation logic of the feature chain is to sequentially connect the feature values ​​of the same parameter along the time axis to form a continuous chain-like data structure.

[0058] S420 generates multiple time-series co-occurrence chain nodes based on the rotational speed feature chain.

[0059] It is understandable that the core of this step is to rely on the core driving attribute of the screw speed parameter to locate the key time nodes of the coordinated changes in temperature, pressure and screw speed during the plasticizing process, providing a precise time reference for subsequent feature chain segmentation and quality analysis. The reason for choosing the screw speed feature chain as the reference is that the screw speed is the core dynamic parameter of the plasticizing process. Its changes directly trigger changes in material conveying speed and frictional heat generation efficiency, thereby driving the coordinated response of temperature (changes in melting efficiency) and pressure (changes in material packing degree). The dynamic changes of the screw speed feature chain can accurately reflect the stage transitions of the plasticizing process (such as the transition from feed preheating to melt mixing). For example, multiple parameter monitoring points can be preset in the screw area of ​​the target plasticizing unit, located in the feed section, compression section and melting section, respectively. Then, based on the parameter monitoring points, time-series analysis of the screw speed feature chain can be performed to extract the changes in the screw speed stability of the initial mixture in the corresponding area over time, and generate multiple time-series co-occurring chain nodes based on the changes; alternatively, the screw speed feature chain can be input into a learning model, and the learning model can output the corresponding time-series co-occurring chain nodes, and so on, but not limited to these. The learning model is trained using multiple sets of training data. Each set of training data includes a rotational speed feature chain and a corresponding temporal co-occurrence chain node.

[0060] In one possible implementation, step S420 generates multiple time-series co-occurrence chain nodes based on the rotational speed feature chain, including: S421, multiple parameter monitoring points are preset in the screw area of ​​the target plasticizing unit, located in the feeding section, compression section and melting section respectively.

[0061] It is understandable that there are significant differences in the material state and parameter variation patterns in different process sections of the screw section. Pre-set monitoring points can accurately match the functional characteristics of each section. The core function of the feeding section is to transport raw materials, conveying solid raw materials from the hopper to the compression section. The parameter changes in this area are mainly reflected in the preheating and initial compaction of the raw materials. The core function of the compression section is to compact the raw materials, remove air, and begin the melting of the raw materials. The parameter changes in this area are drastic, with temperature and pressure rising rapidly. The core function of the melting section is to complete the complete melting and uniform mixing of the raw materials. The parameters in this area are relatively stable, but they directly determine the quality of the melt.

[0062] S422, based on parameter monitoring points, performs time-series analysis on the speed characteristic chain and extracts the feature vector time series of each parameter monitoring point; wherein, the feature vector time series is used to reflect the change of screw speed stability of the initial mixture in the corresponding region over time.

[0063] Understandably, the core of this step is to transform discrete rotational speed monitoring data into structured feature time series that can be used for collaborative node identification. First, a unified time series analysis window (e.g., 2 seconds / window) needs to be determined, and the rotational speed data collected synchronously from each monitoring point is segmented. For the rotational speed data within each window, the screw rotational speed stability is quantified by calculating indicators such as standard deviation and coefficient of variation (the smaller the standard deviation, the stronger the stability). Then, the quantified values ​​of rotational speed stability from each window are concatenated in chronological order to form a feature vector time series.

[0064] S423 generates multiple temporal co-occurrence chain nodes based on feature vector temporal sequence.

[0065] The core of this process is to identify key time points where temperature, pressure, and rotational speed change synergistically from the time-series data of rotational speed stability at various monitoring points, thus forming a time-series symbiotic chain. The core logic is to analyze the changing patterns of the characteristic vectors at each monitoring point to capture moments when rotational speed stability changes synchronously across multiple process stages. These moments often correspond to stage transitions in the plasticizing process (such as the transition from preheating the feed to compression and melting), at which point temperature and pressure parameters also exhibit synergistic responses along with changes in rotational speed stability.

[0066] For example, based on the feature vector time series of each parameter monitoring point, the abrupt change value of screw speed stability at each parameter monitoring point can be calculated. Then, the abrupt change values ​​of all parameter monitoring points are aligned on the time axis. When at least two parameter monitoring points have abrupt change values ​​at the same time, the time point corresponding to the abrupt change value is determined as an effective time series co-occurrence chain node. Finally, the effective time series co-occurrence chain nodes are arranged in chronological order to form multiple time series co-occurrence chain nodes. Alternatively, the speed stability feature vector time series of each monitoring point can be used as a benchmark, and the temperature and pressure time series data of the corresponding area can be retrieved synchronously. The Pearson correlation coefficient algorithm is used to calculate the pairwise relationship between speed stability and temperature change rate and pressure fluctuation value. The correlation coefficient is set; a correlation coefficient threshold is set (determined based on the accuracy requirements of the plasticizing process, usually ≥0.75). When the correlation coefficient between the rotational speed stability and the temperature and pressure parameters at the same monitoring point at a certain moment is ≥ the threshold, that moment is marked as a single-region candidate collaborative node; then, all single-region candidate nodes are integrated on the time axis, and candidate nodes that cover at least two different process segments at the same moment are selected as cross-region collaborative candidate nodes; finally, the cross-region collaborative candidate nodes are verified for continuous duration (e.g., the strong collaborative state is required to be maintained continuously for ≥20 seconds), and false nodes caused by instantaneous collaboration are eliminated. The nodes that pass the verification are arranged in ascending order of timestamp to form a temporal symbiotic chain node.

[0067] This setup ensures comprehensive acquisition of coordinated signals by aligning the monitoring point layout with the characteristics of each process segment; it focuses on the core indicator of rotational speed stability to accurately grasp the key driving factors of parameter coordination in the plasticizing process; and it structures discrete data through time-series analysis to provide a reliable data foundation for identifying coordinated nodes.

[0068] In one possible implementation, step S423 involves generating multiple temporal co-occurrence chain nodes based on the feature vector temporal sequence, including: S4231 calculates the abrupt change value of screw speed stability at each parameter monitoring point based on the feature vector time series of each parameter monitoring point.

[0069] It is understandable that, for the feature vector time series of each monitoring point, the difference (i.e., the change) of the rotational speed stability quantification value of adjacent time windows is calculated using the difference method; when the absolute value of the change in a certain window is greater than or equal to the preset threshold, the change is the sudden change value of the screw rotational speed stability, and the corresponding window timestamp is marked as the potential collaborative moment.

[0070] S4232 aligns the mutation values ​​of all parameter monitoring points with the time axis. When at least two parameter monitoring points have mutation values ​​at the same time, the time point corresponding to the mutation value is determined as a valid temporal co-occurrence chain node.

[0071] It is understandable that the timestamps corresponding to the mutation values ​​of all monitoring points are integrated into the same time axis (with a uniform precision of milliseconds); each moment on the time axis is traversed to determine whether there are mutation values ​​of at least two monitoring points in different process sections at that moment; if there are, it means that the change in rotational speed stability at that moment has triggered a coordinated response in multiple regions, and the corresponding time point is determined as an effective time-series symbiotic chain node; if there is only a mutation value of a single monitoring point, it is determined to be a local anomaly and is removed.

[0072] S4233, arrange the valid temporal symbiotic chain nodes in chronological order to form multiple temporal symbiotic chain nodes.

[0073] This can be understood as arranging nodes according to the time sequence in which the effective temporal symbiotic chain nodes appear, thus forming multiple temporal symbiotic chain nodes.

[0074] This setup, based on the time-series calculation of the rotational speed stability mutation value using the feature vectors of each parameter monitoring point, can quickly pinpoint the critical turning point of the coordinated change in temperature and pressure parameters driven by rotational speed during the plasticizing process. It accurately matches the transition requirements of process stages such as feed preheating, compression melting, and uniform mixing. By aligning the time axis and screening effective nodes with mutations at least two monitoring points at the same time, it can effectively eliminate false signals caused by local interference at a single monitoring point (such as sensor instantaneous error or uneven material distribution in a region), significantly improving the reliability and global representativeness of the symbiotic chain nodes. Finally, the time-series symbiotic chain formed by arranging the nodes in chronological order can provide a precise time reference for subsequent feature chain segmentation and plasticizing quality segmentation, helping to accurately locate abnormal quality stages and improve the controllability of the plasticizing process and the consistency of finished product quality.

[0075] S430 divides the temperature feature chain, speed feature chain, and pressure feature chain into multiple continuous multi-feature chain segments based on the time-series symbiotic chain nodes.

[0076] As can be understood, the core of this step is to decompose the three continuous feature chains into several independent stage segments (multi-feature chain segments) according to the "multi-parameter collaborative key moments," thereby realizing the transformation from overall analysis to segmented and precise analysis. The specific implementation logic is as follows: using the temporal co-occurrence chain nodes as the dividing points, the three feature chains of temperature, speed, and pressure are simultaneously divided—the feature chain segment between two adjacent effective temporal co-occurrence chain nodes is a multi-feature chain segment.

[0077] S440 determines the plasticization quality of the raw material mixture corresponding to the plasticization target based on multiple multi-feature chain segments.

[0078] It is understandable that the core of this step is to achieve dynamic and accurate judgment of plasticizing quality by analyzing the deviation between the parameter coordination state of each multi-feature chain segment and the target requirements, thus breaking through the limitations of traditional finished product endpoint detection. For example, temperature, pressure, and rotational speed parameters can be extracted from each multi-feature link. Then, the deviation values ​​of each feature parameter corresponding to each multi-feature link from the preset parameters of the plasticizing target can be calculated. Based on the weighting coefficients of each feature parameter, the deviation values ​​of the same multi-feature link are weighted and summed to obtain the comprehensive deviation value of each multi-feature link. Then, the decay trend of the comprehensive deviation value of multiple consecutive multi-feature links is calculated. If the decay trend converges and the comprehensive deviation value of the latest multi-feature link is less than or equal to the preset deviation threshold, then the plasticizing quality of the raw material mixture is determined to meet the plasticizing target. If the decay trend does not converge, or the comprehensive deviation value of the latest multi-feature link is greater than the preset deviation threshold, then the plasticizing quality of the raw material mixture is determined to not meet the plasticizing target, and the dominant deviation feature type is output. Alternatively, the plasticizing process stage characteristics (feed preheating, compression melting, homogenization) can be considered first. (Uniform mixing) Matches the corresponding stage quality thresholds for each multi-feature link (different stage thresholds are adapted to the allowable range of parameter fluctuations in the corresponding stage; for example, the temperature fluctuation threshold in the feeding stage can be relaxed to ±5℃, while that in the melting stage is strictly limited to ±2℃); then verifies whether the core parameters (average temperature, peak pressure, and speed stability coefficient) of each multi-feature link are all within the corresponding stage threshold, and counts the percentage of compliant links; at the same time, calculates the synergy consistency coefficient of temperature, pressure, and speed parameters within the same link (using Pearson correlation coefficient, a coefficient ≥0.7 indicates good synergy); if the percentage of compliant links is ≥80% and the synergy consistency coefficient of all links is ≥0.7, then the plasticizing quality is determined to meet the target; if the percentage of compliant links is <80% or there are links with a synergy consistency coefficient <0.7, then it is determined to not meet the target, and the process stage and parameter type (temperature / pressure / speed) corresponding to the non-compliant links are located, etc., but not limited to this.

[0079] This setup, through a progressive logic of chain segmentation, segmented analysis, and trend judgment, constructs a precise and dynamic plasticizing quality assessment system. Its core advantages are: first, strong real-time performance; by dynamically analyzing continuous multi-characteristic chain segments, it achieves in-process quality monitoring during plasticizing, avoiding raw material waste caused by discovering problems only at the finished product stage; second, high precision; by breaking down the entire process into independent stable stages, it can accurately locate the specific stage of quality anomalies, providing targeted direction for subsequent parameter adjustments; and third, comprehensiveness; by simultaneously analyzing data from three characteristic chains—temperature, pressure, and rotation speed—it avoids the one-sidedness of single-parameter analysis, ensuring comprehensive and reliable quality judgment and providing crucial support for improving the consistency of finished product quality.

[0080] In one possible implementation, in step S440, determining the plasticization quality of the raw material mixture corresponding to the plasticization target based on multiple multi-feature chain segments includes: S441, extract the temperature characteristic link parameters, pressure characteristic link parameters, and speed characteristic link parameters from each multi-feature link; wherein, the temperature characteristic link parameters include the temperature fluctuation amplitude and average temperature within the link, the pressure characteristic link parameters include the pressure peak value and pressure change gradient within the link, and the speed characteristic link parameters include the speed stability coefficient and speed fluctuation frequency within the link.

[0081] The core of this process is to extract key parameters that directly affect plasticizing quality from each collaborative stage (multi-feature link), providing targeted analysis targets for subsequent deviation quantification. Parameter selection is based on the plasticizing quality formation mechanism: temperature fluctuation amplitude and average temperature directly determine the material melting uniformity (average temperature deviation from the target leads to insufficient melting or excessive degradation, while large fluctuation amplitude results in uneven melting); pressure peak value and pressure gradient affect the material compaction degree and conveying stability (excessively high peak values ​​easily cause melt degradation, while excessive pressure gradients result in conveying fluctuations); rotational speed stability coefficient and fluctuation frequency determine the mixing intensity and material residence time (poor stability coefficient and frequent fluctuations lead to uneven mixing). The extraction method involves statistical analysis of time-series data within each multi-feature link: temperature fluctuation amplitude = maximum temperature value within the link - minimum temperature value; average temperature = arithmetic mean of temperature data within the link; pressure peak value = maximum pressure value within the link; pressure gradient = (maximum pressure value - minimum pressure value) / link duration; rotational speed stability coefficient = standard deviation of rotational speed data within the link; fluctuation frequency = number of times the rotational speed change rate exceeds the threshold within the link / link duration.

[0082] S442, calculate the deviation values ​​between each characteristic parameter corresponding to each multi-feature chain segment and the preset parameters of the plasticizing target; wherein, the preset parameters of the plasticizing target include the derived parameters corresponding to the target temperature range, target pressure range, and target speed stability range.

[0083] It is understandable that the preset parameters are derived based on plasticizing targets (such as melt flow rate and finished product density), covering the allowable range or fixed value of each characteristic parameter (such as the target average temperature of the melting section being 123-127℃, and temperature fluctuation range ≤5℃). These preset plasticizing target parameters can be manually input, obtained from a preparation database, etc., but are not limited to these methods. The preparation database refers to a database containing the preset plasticizing target parameters corresponding to plastic particles. This data can be obtained through laboratory experiments, on-site measurements and monitoring, and past experience. After acquisition, the collected data is organized, classified, and archived, useful information and patterns are extracted, and relevant data are saved to the database to form the preparation database. Deviation value calculation uses a differentiated logic: for range-type parameters (such as average temperature), deviation value = |actual value - target range midpoint value| / (target range upper limit - midpoint value), ensuring standardization of deviations within and outside the range; for fixed-value parameters (such as fluctuation range), deviation value = |actual value - target value| / target value, intuitively reflecting the deviation ratio. A deviation value ≥ 0 indicates a higher degree of conformity to the target.

[0084] S443, based on the weighting coefficients of each feature parameter, performs a weighted summation of the deviation values ​​of the same multi-feature chain segment to obtain the comprehensive deviation value of each multi-feature chain segment.

[0085] As can be understood, the weighting coefficients reflect the degree of influence of characteristic parameters on plasticization quality. Weighting coefficients can be manually entered or obtained from a preparation database. The overall deviation value = the sum of the deviation values ​​of each parameter × their corresponding weights; the smaller the value, the better the plasticization quality of that segment.

[0086] S444, calculate the decay trend of the comprehensive deviation value of multiple consecutive multi-feature links; if the decay trend is converging and the comprehensive deviation value of the latest multi-feature link is less than or equal to the preset deviation threshold, then determine that the plasticizing quality of the raw material mixture meets the plasticizing target; if the decay trend is not converging, or the comprehensive deviation value of the latest multi-feature link is greater than the preset deviation threshold, then determine that the plasticizing quality of the raw material mixture does not meet the plasticizing target, and output the deviation-dominant feature type; wherein, the deviation-dominant feature type includes at least one of temperature deviation-dominant, pressure deviation-dominant, and speed deviation-dominant.

[0087] It is understandable that the convergence of the decay trend means that the overall deviation value gradually decreases and the fluctuation amplitude shrinks as the chain links advance, indicating that the plasticizing process tends to stabilize; the preset deviation threshold (such as 0.3) is determined according to the plasticizing accuracy requirements, and the latest chain link deviation meeting the standard is the core condition for qualified quality. The deviation dominance type is determined by calculating the proportion of each parameter deviation value in the overall deviation value (e.g., if the proportion of temperature parameters is >40%, then it is temperature deviation dominance).

[0088] This setup, through a progressive logic of parameter extraction, deviation quantification, comprehensive evaluation, and trend judgment, constructs a dynamic and precise plasticizing quality assessment system. Its core advantages are: first, real-time performance, relying on multi-feature chain segmented analysis to achieve in-process quality monitoring, providing early warnings of risks, and avoiding raw material waste caused by delayed finished product testing; second, comprehensiveness, covering the key characteristics of the three core parameters of temperature, pressure, and rotation, reducing the one-sidedness of single-parameter judgment; third, accuracy, standardized deviation calculation and weighted evaluation improve quantitative accuracy, replacing experience-based judgment; and fourth, guidance, with deviation-dominant type output providing clear direction for control and improving process controllability.

[0089] In one possible implementation, step S400, the operating parameters of the target plasticizing unit based on plasticizing quality control include: S450, when the plasticizing quality of the raw material mixture does not meet the plasticizing target, based on the deviation-dominant feature type, the corresponding target control parameters are matched; wherein, the target control parameters correspond one-to-one with the deviation-dominant feature type, the target control parameters corresponding to temperature deviation-dominant are the heating power of each section of the barrel and the screw speed, the target control parameters corresponding to pressure deviation-dominant are the feeding rate and the screw speed, and the target control parameter corresponding to speed deviation-dominant is the screw speed.

[0090] It is understandable that the core cause of temperature deviation is insufficient / excessive heating power or improper screw speed (affecting frictional heat generation), so matching the heating power (direct temperature control) and screw speed (auxiliary temperature control) is necessary. Pressure deviation originates from the feeding rate (affecting material accumulation) or the screw speed (affecting conveying speed), so matching the feeding rate and screw speed is crucial. Speed ​​deviation is directly caused by the screw speed setting or fluctuations, so only the screw speed needs to be adjusted. For example, when temperature deviation is dominant, the heating power of the corresponding area can be increased; when pressure deviation is dominant, the feeding rate can be decreased.

[0091] S460 determines the control step size of the target control parameter based on the duration decay rate of multiple feature links; where the smaller the duration decay rate, the smaller the control step size, and the larger the duration decay rate, the larger the control step size.

[0092] It can be understood that the duration decay rate = (previous chain segment duration - current chain segment duration) / previous chain segment duration, reflecting the chain segment distribution density (a large decay rate corresponds to the later stage of plasticization, with dense chains and sensitive materials; a small decay rate corresponds to the earlier stage, with more room for material adjustment). Based on this, the step size should be matched: for decay rate > 0.3 (later stage), a small step size (e.g., heating power 0.5kW, rotation speed 2r / min) should be used to avoid parameter oscillation; for decay rate < 0.1 (early stage), a large step size (e.g., heating power 2kW, rotation speed 8r / min) should be used to improve control efficiency; a medium step size can be used in the middle stage to balance both.

[0093] S470 determines the degree of control of the target control parameter based on the deviation value.

[0094] It is understandable that the degree of deviation is first classified (mild: 0.3-0.5, moderate: 0.5-0.8, severe: >0.8), and then the corresponding adjustment level is set (mild: 1 times the base step size, moderate: 1.5-2 times, severe: 2-3 times). The base step size is the corresponding decay rate step size determined by S460. For example, for moderate pressure deviation with a decay rate of 0.25 (medium step size: feeding rate 10kg / h), the adjustment level is 1.5 times, that is, the feeding rate is reduced by 15kg / h.

[0095] This setup, through precise control logic of deviation type matching control parameters, duration decay rate determining step size, and deviation value determining degree, achieves dynamic optimization of the plasticizing unit's operating parameters, resulting in significant technical effects: First, based on the deviation-dominant characteristic type, it precisely matches the target control parameters, constructing a problem-solution one-to-one targeted control mechanism. For example, temperature deviation dominates the targeted control of heating power and screw speed, while pressure deviation dominates the control of feeding rate and screw speed, directly addressing the root cause of quality abnormalities and reducing ineffective energy consumption and parameter oscillations caused by blind control. Second, it combines the duration decay rate of multiple characteristic links to determine the control step size, adapting to the material characteristics at each stage of plasticizing (small decay rate and large material adjustment space in the early stage, using a large step size to improve control efficiency; large decay rate and sensitive material in the later stage, using a small step size to ensure stability), achieving a balance between control efficiency and process stability. Third, it quantifies the control degree based on the deviation value, ensuring precise matching between the control amplitude and the severity of quality abnormalities, avoiding problems of over-control or under-control. Overall, this solution, together with the aforementioned plasticizing quality assessment system, forms a complete closed loop of monitoring, assessment, and control. It can quickly bring plasticizing quality that deviates from the target back to the qualified range, significantly improving the controllability of the plasticizing process and the consistency of finished product quality.

[0096] The second aspect of this application provides a plastic particle, which is prepared by the plastic particle preparation method described in any of the above embodiments. The plastic particle formulation includes the following components in parts by weight: 40-50 parts of polyethylene resin; 3-8 parts of ultra-high molecular weight polyethylene particles; 0.3-0.6 parts of compound antioxidant; 8-15 parts of nano-calcium carbonate; 1-3 parts of glycidyl methacrylate grafted polyethylene compatibilizer; 0.8-1.5 parts of heat stabilizer; 5-10 parts of polycarbonate; and 2-5 parts of ethylene acrylate copolymer.

[0097] It can be understood that 40-50 parts of polyethylene resin means that when the total weight of the raw materials is 100, the weight of the unsaturated resin is 40-50. For example, it can be 40, 45, 50, etc., but it is not limited to this.

[0098] In this configuration, polyethylene resin serves as the matrix component (40-50 parts), providing basic moldability and mechanical support for the plastic particles. Its content dominates the formulation system to ensure a stable melt structure during plasticization. The addition of ultra-high molecular weight polyethylene particles (3-8 parts) significantly improves the wear resistance and impact resistance of the finished product. Compound antioxidants (0.3-0.6 parts) delay oxidative aging of the plastic particles during processing and use. Nano-calcium carbonate (8-15 parts), as an inorganic filler, enhances the rigidity and heat resistance of the finished product. Glycidyl methacrylate-grafted polyethylene... Compatibilizer (1-3 parts) is a key interface modifier that improves the compatibility between polyethylene resin and different components such as polycarbonate, solves the problem of easy stratification in multi-component systems, and ensures the effectiveness of multi-parameter synergistic control during plasticization. Heat stabilizer (0.8-1.5 parts) can resist the degradation and damage of components by high temperatures during plasticization. Polycarbonate (5-10 parts) can improve the heat resistance and mechanical strength of the finished product, making up for the shortcomings of polyethylene resin performance. Ethylene-acrylate copolymer (2-5 parts) can enhance the flexibility and impact resistance of the finished product, and synergistically optimize mechanical properties with ultra-high molecular weight polyethylene particles. The overall formulation has synergistic effects among its components, and the weight range has been verified by the process. Efficient plasticization can be achieved by controlling the parameters (such as temperature, pressure, and rotation speed) in the aforementioned preparation method, ultimately obtaining plastic particles with balanced comprehensive performance and stable quality, suitable for applications with high requirements for mechanical properties and aging resistance.

[0099] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0100] This application also provides a plastic particle preparation apparatus, including a feeding system, a plasticizing extrusion system, a granulation cooling system, and a control system, wherein the control system is electrically connected to the feeding system, the plasticizing extrusion system, and the granulation cooling system. Figure 3 This is a schematic diagram of the structure of a control system 4 provided in an embodiment of this application. Figure 3 As shown, the control system 4 of this embodiment includes: at least one processor 40 ( Figure 3 Only one is shown in the image), at least one memory 41 ( Figure 3 (Only one is shown in the image) and a computer program 42 stored in the at least one memory 41 and executable on the at least one processor 40, wherein when the processor 40 executes the computer program 42, it causes the control system 4 to implement the plasticizing process steps in the above-described plastic particle preparation method embodiment.

[0101] For example, the computer program 42 may be divided into one or more modules / units, which are stored in the memory 41 and executed by the processor 40 to complete this application. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program 42 in the control system 4.

[0102] The control system 4 can be a computing device such as a desktop computer, laptop, handheld computer, or cloud server. The kneading device may include, but is not limited to, a processor 40 and a memory 41. Those skilled in the art will understand that... Figure 3 This is merely an example of control system 4 and does not constitute a limitation on control system 4. It may include more or fewer components than shown in the figure, or combine certain components, or different components, such as input / output devices, network access devices, buses, etc.

[0103] The processor 40 can be a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0104] In some embodiments, the memory 41 may be an internal storage unit of the control system 4, such as a hard disk or memory of the control system 4. In other embodiments, the memory 41 may be an external storage device of the control system 4, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the control system 4. Furthermore, the memory 41 may include both internal storage units and external storage devices of the control system 4. The memory 41 is used to store operating systems, applications, bootloaders, data, and other programs, such as the program code of computer programs. The memory 41 can also be used to temporarily store data that has been output or will be output.

[0105] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0106] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0107] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for preparing plastic particles, characterized in that, The method includes: A resin premix is ​​obtained by mixing and stirring polyethylene resin, ultra-high molecular weight polyethylene particles and compound antioxidants. A composite filler modification system is obtained by mixing nano-calcium carbonate and glycidyl methacrylate grafted polyethylene compatibilizer. The resin premix, the composite filler modification system, heat stabilizer, polycarbonate and ethylene acrylate copolymer are mixed to obtain an initial mixture. A plasticizing request message is sent to the control system of the plastic particle preparation device; wherein, the plasticizing request message is used to request the use of the target plasticizing unit to melt and plasticize the raw material mixture corresponding to the plasticizing target, and the plasticizing request message carries the identification information of the target plasticizing unit; the target plasticizing unit is the unit that minimizes the correlation between the two plasticizing parameter points with the least correlation in the plasticizing process corresponding to the plasticizing target among all available plasticizing units controlled by the preparation management function unit; The system receives plasticizing state information corresponding to the target plasticizing unit from the control system of the plastic particle preparation device; wherein the plasticizing state information is used to characterize the plasticizing state of the initial mixture in the target plasticizing unit, including the temperature of each section of the barrel, the screw speed, and the barrel pressure; Based on the plasticization state information, the plasticization quality of the raw material mixture corresponding to the plasticization target is determined; and based on the plasticization quality, the operating parameters of the target plasticization unit are adjusted to melt-plasticize, granulate, and cool the initial mixture to obtain plastic particles.

2. The method for preparing plastic particles as described in claim 1, characterized in that, Before sending the plasticizing request message to the plastic particle preparation device control system, the method further includes: Obtain system control information and parameter details of the plasticizing target; the system control information includes unit information of all available plasticizing units, and the unit information includes the heating power, screw length-to-diameter ratio, and historical plasticizing accuracy of the plasticizing unit; Based on the unit information of any candidate plasticizing unit subset and the parameter details of the plasticizing target, calculate the correlation of all plasticizing parameter point pairs in the plasticizing process corresponding to the plasticizing target under all candidate plasticizing unit subsets; wherein, the candidate plasticizing unit subset includes the target number of units, and the plasticizing parameter point pair includes the parameters corresponding to two different plasticizing parameter monitoring points; Based on the correlation of all the plasticizing parameter point pairs, a minimum-maximum optimization method is used to select the target number of target plasticizing units from all the available plasticizing units.

3. The method for preparing plastic particles according to claim 2, characterized in that, The calculation of the correlation of all plasticizing parameter point pairs in the plasticizing process corresponding to the plasticizing target under all candidate plasticizing unit subsets includes: Calculate the first product value of the conjugate of the first plasticizing composite vector and the second plasticizing composite vector; the first plasticizing composite vector is the plasticizing response vector of the target number of units at the first plasticizing parameter point, and the second plasticizing composite vector is the plasticizing response vector of the target number of units at the second plasticizing parameter point; the first plasticizing parameter point and the second plasticizing parameter point are arbitrary plasticizing parameter point pairs; Calculate the process timing distance between the first plasticizing parameter point and the second plasticizing parameter point. The power, the Greater than 0; Calculate the distance between the first product value and the process timing. The second product value raised to the power of 1; the correlation between the first plasticizing parameter point and the second plasticizing parameter point is inversely proportional to the second product value.

4. The method for preparing plastic particles according to claim 2, characterized in that, The step of employing a min-max optimization method to select the target number of target plasticizing units from all available plasticizing units includes: When the target number of units is any subset of candidate plasticizing units among all available plasticizing units, the correlations corresponding to all plasticizing parameter point pairs are calculated respectively; Identify the target plasticizing parameter point pair with the lowest correlation among all plasticizing parameter point pairs; From the subset of candidate plasticizing units, determine the number of target plasticizing units with the lowest correlation corresponding to the target plasticizing parameter point pairs.

5. The method for preparing plastic particles according to claim 1, characterized in that, Determining the plasticization quality of the raw material mixture corresponding to the plasticization target based on the plasticization state information includes: Based on the plasticizing process parameters in the plasticizing state information, multi-feature tracking is performed to generate temperature feature chain, rotation speed feature chain and pressure feature chain; Multiple time-series co-occurrence chain nodes are generated based on the aforementioned rotational speed feature chain; Based on the time-series symbiotic chain nodes, the temperature feature chain, the rotation speed feature chain, and the pressure feature chain are chained to obtain multiple continuous multi-feature chain segments; The plasticization quality of the raw material mixture corresponding to the plasticization target is determined based on multiple of the aforementioned multi-feature chain segments.

6. The method for preparing plastic particles according to claim 5, characterized in that, The generation of multiple time-series co-occurrence chain nodes based on the rotational speed feature chain includes: Multiple parameter monitoring points are preset in the screw area of ​​the target plasticizing unit, located in the feeding section, compression section, and melting section respectively; Based on the parameter monitoring points, a time series analysis is performed on the rotational speed feature chain to extract the feature vector time series of each parameter monitoring point; wherein, the feature vector time series is used to reflect the change of screw rotational speed stability of the initial mixture in the corresponding region over time; Multiple temporal co-occurrence chain nodes are generated based on the aforementioned feature vectors.

7. The method for preparing plastic particles according to claim 6, characterized in that, The generation of multiple temporal co-occurrence chain nodes based on the feature vector temporally includes: Based on the feature vector time series of each parameter monitoring point, calculate the abrupt change value of the screw speed stability at each parameter monitoring point; The mutation values ​​of all the parameter monitoring points are aligned on the time axis. When at least two mutation values ​​of the parameter monitoring points occur at the same time, the time point corresponding to the mutation value is determined as a valid temporal co-occurrence chain node. The effective temporal symbiotic chain nodes are arranged in chronological order to form multiple temporal symbiotic chain nodes.

8. The method for preparing plastic particles as described in claim 5, characterized in that, The determination of the plasticizing quality of the raw material mixture corresponding to the plasticizing target based on multiple multi-feature chain segments includes: Extract the temperature characteristic link parameters, pressure characteristic link parameters, and rotational speed characteristic link parameters from each of the multi-feature link segments; wherein, the temperature characteristic link parameters include the temperature fluctuation amplitude and average temperature within the link segment, the pressure characteristic link parameters include the pressure peak value and pressure change gradient within the link segment, and the rotational speed characteristic link parameters include the rotational speed stability coefficient and rotational speed fluctuation frequency within the link segment; Calculate the deviation values ​​between each feature parameter corresponding to each of the multi-feature chain segments and the preset parameters of the plasticizing target; wherein, the preset parameters of the plasticizing target include derived parameters corresponding to the target temperature range, target pressure range, and target rotational speed stability range; Based on the weighting coefficients of each feature parameter, the deviation values ​​of each multi-feature chain are weighted and summed to obtain the comprehensive deviation value of each multi-feature chain. Calculate the decay trend of the comprehensive deviation value of multiple consecutive multi-feature links; if the decay trend is converging and the comprehensive deviation value of the latest multi-feature link is less than or equal to a preset deviation threshold, then determine that the plasticizing quality of the raw material mixture meets the plasticizing target; if the decay trend is not converging, or the comprehensive deviation value of the latest multi-feature link is greater than the preset deviation threshold, then determine that the plasticizing quality of the raw material mixture does not meet the plasticizing target, and output the deviation-dominant feature type; wherein, the deviation-dominant feature type includes at least one of temperature deviation-dominant, pressure deviation-dominant, and speed deviation-dominant.

9. The method for preparing plastic particles as described in claim 8, characterized in that, The operating parameters of the plasticizing unit based on the plasticizing quality control target include: When the plasticizing quality of the raw material mixture does not meet the plasticizing target, based on the deviation-dominant feature type, a corresponding target control parameter is matched; wherein, the target control parameter corresponds one-to-one with the deviation-dominant feature type, the target control parameter corresponding to the temperature deviation-dominant feature type is the heating power of each section of the barrel and the screw speed, the target control parameter corresponding to the pressure deviation-dominant feature type is the feeding rate and the screw speed, and the target control parameter corresponding to the speed deviation-dominant feature type is the screw speed; Based on the duration decay rate of the multi-feature chain segments, the control step size of the target control parameter is determined; wherein, the smaller the duration decay rate, the smaller the control step size, and the larger the duration decay rate, the larger the control step size. The degree of control of the target control parameter is determined based on the deviation value.

10. A type of plastic particle, characterized in that, The plastic particles are prepared by the method described in any one of claims 1 to 9, and the formulation of the plastic particles includes the following components in parts by weight: Polyethylene resin, 40-50 parts; Ultra-high molecular weight polyethylene granules, 3-8 parts; Compound antioxidant, 0.3~0.6 parts; Nano calcium carbonate, 8-15 parts; Glycidyl methacrylate grafted polyethylene compatibilizer, 1-3 parts; Heat stabilizer, 0.8~1.5 parts; Polycarbonate, 5-10 parts; Ethylene acrylate copolymer, 2-5 parts.

Images