Temperature control system and method in plastic particle production process

Abstract

The invention discloses a temperature control system and method in a plastic particle production process, and belongs to the technical field of temperature control, and the method specifically comprises the steps: carrying out the characteristic analysis of a plastic raw material, obtaining a key temperature node in the plastic particle production process, and obtaining a temperature control result based on the characteristics of the plastic raw material and the structural parameters of plastic particle production equipment; the method comprises the following steps: establishing a temperature prediction model, setting a time interval to correct the temperature prediction model, calculating the dynamic adjustment amount of the temperature of the plastic particles according to different production stages, monitoring the temperature of the plastic material in real time in the production process, feeding back and controlling in real time, and entering a cooling stage after the plastic particles are formed. Controlling the temperature and flow of the cooling medium; different temperature control targets are respectively set in different stages of the production process, and the temperature control in each stage is dynamically adjusted according to real-time data, so that the accurate control of the temperature is realized, and the energy consumption is effectively reduced.

Description

Technical Field

[0001] The invention belongs to the technical field of temperature control, and in particular to a temperature control system and method in a plastic particle production process. Background Art

[0002] In the production process of plastic particles, temperature control is a key factor affecting product quality and production efficiency. Plastic particles are usually produced through melt extrusion, cooling, granulation and other process flows, all of which have strict requirements on temperature. Temperature fluctuations not only affect the appearance and physical properties of the product, but may also lead to a series of problems such as equipment failure and increased energy consumption. Therefore, it is particularly important to implement precise temperature control during the production process.

[0003] At present, most of the temperature control technologies in plastic particle production lines use simple temperature control equipment, such as constant temperature heaters, cooling water circulation systems, and temperature sensors. These devices are used to maintain the temperature stability of each link in the production process. However, the existing technology has certain limitations in many aspects: 1) The temperature fluctuates greatly and it is difficult to achieve precise control: most of the temperature control systems in the existing technology can only be adjusted within a predetermined temperature range, and cannot be adjusted in real time according to the actual changes in the production process; 2) The response speed is slow and cannot adapt to complex changes: In the production process, the temperature is affected by many factors, such as raw material characteristics, production speed, external environment temperature, etc.; 3) Low energy efficiency and serious waste: Traditional temperature control systems usually use fixed power heating and cooling equipment at each stage, and cannot be dynamically adjusted according to actual needs, resulting in energy waste.

[0004] Based on these problems, a temperature control method that can control the temperature more accurately and flexibly and optimize the entire production process is particularly important. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention proposes a temperature control system and method for the production process of plastic particles. By real-time monitoring and adjustment of the temperature at each stage of the production process, combined with a dynamic feedback mechanism, the influence of temperature fluctuations on the quality of plastic particles can be effectively avoided, thereby improving the stability and efficiency of the production process.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A temperature control method in a plastic particle production process, comprising:

[0008] Analyze the characteristics of plastic raw materials and obtain the key temperature nodes in the production process of plastic particles;

[0009] Based on the characteristics of plastic raw materials and the structural parameters of plastic particle production equipment, a temperature prediction model is established;

[0010] Set time intervals to revise the temperature prediction model and calculate the dynamic adjustment of the plastic particle temperature according to different production stages;

[0011] During the production process, the temperature of plastic materials is monitored in real time and feedback is provided in real time;

[0012] After the plastic particles are formed, they enter the cooling stage to control the temperature and flow of the cooling medium.

[0013] Specifically, the temperature prediction model has the following formula:

[0014]

[0015] Where ρ represents the density of the plastic material, C p represents the specific heat capacity of plastic materials, represents the partial derivative function, T represents the temperature, represents the velocity vector of the plastic material, λ represents the thermal conductivity of the plastic material, ΔT represents the change in temperature, represents the temperature gradient, Q qxt represents the external heat source term, Q flow It represents the viscous heat dissipation generated by the flow of plastic materials, Q chem Represents the heat generated by the chemical reaction, Q rad Represents the thermal radiation term.

[0016] Specifically, the setting time interval to correct the temperature prediction model includes:

[0017] Set the time interval Δt to collect temperature data at key locations in the plastic particle production process, including but not limited to different sections of the extruder screw, multiple points on the inner wall of the barrel, inside the mold cavity, etc., including M monitoring points, and filter the collected temperature data;

[0018] Based on the collected temperature data of key locations and the predicted temperature value calculated by the temperature prediction model, a temperature error function E is constructed. The specific formula is:

[0019]

[0020] Where E represents the temperature error function, T filt (m,t) represents the filtered temperature value of the mth monitoring point at the actual time t. represents the predicted temperature value calculated by the temperature prediction model at the mth monitoring point at the actual time t;

[0021] Based on the temperature error function E, the key parameters in the temperature prediction model are adjusted and optimized.

[0022] Specifically, the calculation of the dynamic adjustment amount of the temperature of the plastic particles according to different production stages includes:

[0023] During the production process of plastic particles, characteristic parameters related to each production stage are extracted;

[0024] Using the extracted characteristic parameters, a production stage status assessment model is constructed, with the characteristic parameters as input variables and the production stage status assessment indicators as output variables;

[0025] According to the output results of the production stage status evaluation model, an adaptive adjustment strategy is used to dynamically determine the temperature adjustment amount.

[0026] Specifically, during the production process, the temperature of the plastic material is monitored in real time and feedback controlled in real time, including:

[0027] The sliding window method is used to calculate the change rate of the temperature adjustment amount, and the temperature adjustment amount data in the past period of time is linearly fitted to obtain the slope of the fitting line as the change rate of the temperature adjustment amount;

[0028] A neural network hybrid control strategy is used to determine the control output of heating. The specific formula is:

[0029]

[0030] Where u(t) represents the output signal of feedback control, x j represents the input variable, ω ij represents the connection weight from the input layer to the hidden layer, b i represents the bias of the hidden layer neurons, f() represents the activation function of the hidden layer neurons, represents the connection weight from the hidden layer to the output layer, g() represents the activation function of the output layer, n represents the number of neurons in the hidden layer, and J represents the number of input variables.

[0031] Specifically, after the plastic particles are formed, the cooling stage is entered to control the temperature and flow rate of the cooling medium, including:

[0032] Set the initial temperature of the cooling medium according to the size of the plastic particles and the required cooling rate;

[0033] The thermal characteristics of the produced plastic particles are analyzed. Based on the thermophysical properties of the cooling medium and plastic particles, as well as the geometric structure of the cooling system, a plastic particle cooling model is established to calculate the temperature of the plastic particles after cooling at time t. The specific formula is:

[0034]

[0035] Among them, ψ(t) represents the temperature of the plastic particles at the cooling time t, ψ0 represents the initial temperature, that is, the temperature of the plastic particles after molding, and ψ ι represents the temperature corresponding to the ιth boundary condition, ι represents the ιth boundary condition, τ represents the time parameter, t c Indicates the characteristic cooling time, represents the equivalent thermal diffusion coefficient, cos() represents the cosine function, e represents the exponential function, and t represents time;

[0036] When the monitored temperature of the plastic particles reaches the preset cooling end temperature, the cooling process is determined to be finished.

[0037] Specifically, the characteristic analysis of the plastic raw material includes: determination of the melting point range, thermal decomposition temperature, specific heat capacity, and thermal conductivity parameters of the raw material.

[0038] A temperature control system in a plastic particle production process, used to implement a temperature control method in a plastic particle production process, comprising: a characteristic analysis module, a temperature prediction module, a dynamic adjustment module, a feedback control module and a cooling control module;

[0039] The characteristic analysis module is used to perform characteristic analysis on the plastic raw materials and obtain key temperature nodes in the production process of plastic particles;

[0040] The temperature prediction module is used to establish a temperature prediction model based on the characteristics of the plastic raw material and the structural parameters of the plastic particle production equipment;

[0041] The dynamic adjustment module is used to set a time interval to correct the temperature prediction model and calculate the dynamic adjustment amount of the plastic particle temperature according to different production stages;

[0042] The feedback control module is used to monitor the temperature of the plastic material in real time during the production process and to provide real-time feedback control;

[0043] The cooling control module is used to control the temperature and flow rate of the cooling medium during the cooling stage after the plastic particles are formed.

[0044] Specifically, the dynamic adjustment module includes: an error function unit, a state evaluation unit and an adjustment amount determination unit;

[0045] The error function unit is used to construct a temperature error function to adjust and optimize key parameters in the temperature prediction model;

[0046] The state evaluation unit is used to extract characteristic parameters related to each production stage and construct a production stage state evaluation model;

[0047] The adjustment amount determination unit is used to dynamically determine the temperature adjustment amount by adopting an adaptive adjustment strategy according to the output result of the production stage state evaluation model.

[0048] Specifically, the feedback control module includes: a variation calculation unit and a feedback control unit;

[0049] The change amount calculation unit is used to perform linear fitting on the temperature adjustment amount data in the past period of time to obtain the slope of the fitting line as the change rate of the temperature adjustment amount;

[0050] The feedback control unit is used to determine the control output of heating by adopting a neural network hybrid control strategy.

[0051] Compared with the prior art, the present invention has the following beneficial effects:

[0052] 1. The present invention proposes a temperature control method in the production process of plastic particles. Different temperature control targets are set at different stages of the production process, such as plasticization, extrusion, cooling, etc., and the temperature control at each stage is dynamically adjusted according to real-time data, thereby achieving precise temperature control.

[0053] 2. The present invention proposes a temperature control method in the production process of plastic particles, which adjusts the power of heating and cooling equipment according to real-time needs in the production process, avoiding the problems of overheating and overcooling in traditional methods, thereby effectively reducing energy consumption.

[0054] 3. The present invention proposes a temperature control method in the production process of plastic particles, introduces a dynamic feedback control mechanism, can respond quickly according to the temperature changes in the production process of plastic particles, adjust the working state of related equipment, ensure that the temperature in the production process of plastic particles is always maintained within the optimal control range, adapt to complex factors such as raw material fluctuations, production speed changes, and external environmental temperature changes, thereby improving production stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 A flow chart of a temperature control method in a plastic particle production process provided by the present invention;

[0056] Figure 2 This is a diagram of the temperature control system architecture in a plastic particle production process provided by the present invention. DETAILED DESCRIPTION

[0057] The present application is described in detail below in conjunction with specific embodiments. The following embodiments will help those skilled in the art to further understand the present application, but do not limit the present application in any form. It should be noted that, for those of ordinary skill in the art, several variations and improvements can also be made without departing from the concept of the present application. These all belong to the protection scope of the present application.

[0058] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0059] It should be noted that, if there is no conflict, the various features in the embodiments of the present application can be combined with each other, all within the scope of protection of the present application. In addition, although the functional module division is performed in the device schematic diagram and the logical order is shown in the flow chart, in some cases, the steps shown or described can be performed in a sequence different from the module division in the device or the flow chart. In addition, the words "first", "second", "third" and the like used in the present application do not limit the data and the execution order, but only distinguish the same items or similar items with substantially the same functions and effects.

[0060] Unless otherwise defined, all technical and scientific terms used in this specification have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used in this specification and in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. The term "and / or" used in this specification includes any and all combinations of one or more of the related listed items.

[0061] Example 1

[0062] See also Figure 1 The present invention provides an embodiment: a temperature control method in a plastic particle production process, comprising the following specific steps:

[0063] Step S1: Analyze the characteristics of the plastic raw materials to obtain the key temperature nodes in the production process of plastic particles;

[0064] Characteristic analysis of plastic raw materials, including: accurate determination of parameters such as melting point range, thermal decomposition temperature, specific heat capacity, thermal conductivity, etc. Through these parameters, combined with the final performance indicators required by plastic particles, key temperature nodes in the entire production process, such as melting temperature, extrusion temperature, molding temperature, etc., are determined;

[0065] Step S2: establishing a temperature prediction model based on the characteristics of the plastic raw materials and the structural parameters of the plastic particle production equipment;

[0066] The structural parameters of plastic production equipment include: pitch, diameter, length change of extruder screw, wall thickness of barrel, thermal properties of material, cavity structure of mold, layout of cooling channel, etc. Through high-precision 3D modeling of plastic particle production equipment, laser scanning or computer-aided design technology is used to accurately obtain the geometric shape, size and internal structure information of the equipment;

[0067] The temperature prediction model in step S2 has the following specific formula:

[0068]

[0069] Where ρ represents the density of the plastic material, which is calculated by fitting experimental data or state equation considering its change relationship with temperature and pressure. p Express the specific heat capacity of plastic materials, taking into account its temperature and pressure dependence, obtain data under different conditions through experimental methods such as DSC, and use polynomial fitting or piecewise function to express it. represents the partial derivative function, T represents the temperature, It represents the velocity vector of the plastic material. It is obtained by simulating the flow field of the material in the equipment through computational fluid dynamics (CFD), taking into account the influence of factors such as screw rotation, plunger push and material viscosity resistance on the material flow. λ represents the thermal conductivity of the plastic material, which is corrected according to the microstructure and temperature conditions of the material. For composite materials or filled plastics, the effective medium theory model is used to calculate the thermal conductivity. ΔT represents the change in temperature. represents the temperature gradient, Q qxt represents the external heat source term, Q flow It represents the viscous heat dissipation generated by the flow of plastic materials, Q chem Indicates the heat generated by the chemical reaction, Q rad represents the thermal radiation term;

[0070] The principle of the above formula: The first term on the left side of the formula It indicates the rate of change of the internal energy of the plastic material per unit volume over time, reflecting the change of the heat stored inside the plastic material due to the change of temperature over time, that is, the rate of heat accumulation or heat consumption. The influence of plastic material flow on temperature distribution is considered, that is, the convection heat transfer term. The flow of plastic material carries heat and transfers it in space. The velocity vector With temperature gradient The dot product of represents the direction and rate of heat transfer caused by material flow. This term plays an important role in describing the dynamic heat transfer process of materials in the equipment, especially in the conveying section and metering section of the extruder screw. The material flows faster and the convection heat transfer has a significant effect on the temperature distribution. The first term on the right It is the heat conduction term, which describes the heat conduction process caused by the temperature gradient inside the material, that is, the transfer of heat from the high temperature area to the low temperature area. The thermal conductivity λ determines the rate of heat conduction, and the external heat source term Q qxt Taking into account the direct impact of equipment heating on material temperature, by accurately calculating the power input and heat distribution of the heating element, it is possible to accurately simulate the contribution of external heating to the temperature rise of the material during the production process, and the viscous dissipation heat Q flow It reflects the heat generated by the viscous resistance of the material during the flow process. This part of heat will cause the material temperature to rise, especially in the high shear area. The chemical reaction heat term Q chem The influence of chemical reactions on temperature during the production of plastic particles is taken into account. Different chemical reactions will release or absorb heat. The generation or consumption of this heat will change the temperature of the material. By accurately calculating the heat of chemical reactions and incorporating it into the temperature prediction model, the thermal changes in the production process can be simulated more realistically. The thermal radiation term Q rad The heat radiation exchange between the material and the surrounding environment is taken into account. In the high-temperature production process, heat radiation is a heat transfer method that cannot be ignored, especially when there is a large temperature difference between the material and the inner wall of the equipment and between different parts of the material, heat radiation will affect the temperature distribution. This method of establishing a temperature prediction model can more accurately predict the temperature changes in the production process by considering the various physical phenomena and complex factors in the production process of plastic particles in detail, providing strong support for achieving precise temperature control, thereby improving the production quality and production efficiency of plastic particles and reducing scrap rate and energy consumption.

[0071] Step S3: set a time interval to revise the temperature prediction model, and calculate the dynamic adjustment amount of the plastic particle temperature according to different production stages;

[0072] The specific steps of step S3 are:

[0073] Step S301: Set a time interval Δt to collect temperature data at key locations during the production process of plastic particles, including but not limited to different sections of the extruder screw, multiple points on the inner wall of the barrel, inside the mold cavity, etc., including M monitoring points, and perform filtering on the collected temperature data;

[0074] Filtering is used to remove noise interference;

[0075] Step S302: Based on the collected key position temperature data and the predicted temperature value calculated by the temperature prediction model, a temperature error function E is constructed. The specific formula is:

[0076]

[0077] Where E represents the temperature error function, T filt(m,t) represents the filtered temperature value of the mth monitoring point at the actual time t. represents the predicted temperature value calculated by the temperature prediction model at the mth monitoring point at the actual time t;

[0078] This error function comprehensively considers the temperature prediction errors of multiple monitoring points over a period of time, and can more comprehensively reflect the deviation between the temperature prediction model and the actual situation;

[0079] Step S303: Based on the temperature error function E, key parameters in the temperature prediction model are adjusted and optimized;

[0080] For example, thermal conductivity, specific heat capacity, etc. Taking thermal conductivity λ as an example, its update formula is as follows: Among them, λ new represents the updated thermal conductivity, μ represents the learning rate, It represents the partial derivative of the temperature error function E with respect to the thermal conductivity λ. Through iterative calculation, the parameters are continuously adjusted so that the temperature error function E gradually decreases until the preset convergence condition (such as the error change is less than a certain threshold) is reached, thereby optimizing the parameters of the temperature prediction model and enabling the model to more accurately reflect the heat transfer characteristics and temperature change laws in the current production process.

[0081] Step S304: extracting characteristic parameters related to each production stage during the production process of plastic particles;

[0082] For example, during the raw material melting stage, the screw torque, motor current and feed rate of the raw material are monitored; during the extrusion molding stage, the screw speed and die pressure of the extruder are monitored, and these parameters are collected and analyzed in real time to extract their characteristic values, such as calculating the average value of the screw torque, the root mean square value of the motor current, the standard deviation of the feed rate fluctuation, the screw speed fluctuation frequency, the change slope of the die pressure, etc., as the basis for judging the production stage status and adjusting the target temperature;

[0083] Step S305: construct a production stage status assessment model using the extracted characteristic parameters, taking the characteristic parameters as input variables and the production stage status assessment indicators as output variables;

[0084] In this embodiment, the state evaluation indicators include: degree of melting, mixing uniformity, extrusion stability, etc.;

[0085] For example, for the evaluation of the melting degree in the raw material melting stage, the fuzzy rules are defined as follows: 1) If the average value of the screw torque is large, the RMS value of the motor current is large, and the standard deviation of the fluctuation of the feed rate is small, the melting degree is high; 2) If the average value of the screw torque is medium, the RMS value of the motor current is medium, and the standard deviation of the fluctuation of the feed rate is medium, the melting degree is medium; 3) If the average value of the screw torque is small, the RMS value of the motor current is small, and the standard deviation of the fluctuation of the feed rate is large, the melting degree is low;

[0086] According to the production stage status evaluation model, the status evaluation value of the current production stage is obtained. The value is between 0 and 1. The closer it is to 1, the closer the ideal state of this stage is to being achieved.

[0087] Step S306: Adopting an adaptive adjustment strategy to dynamically determine the temperature adjustment amount according to the output result of the production stage status evaluation model.

[0088] In this embodiment, taking the extrusion molding stage as an example, the current extrusion temperature target value is T target (t), based on the slope of the nose pressure change being k p , the fluctuation frequency of the screw speed is f n , then the temperature adjustment amount is calculated as: ΔTT = α1 × k p +α2×f n +α3×(1-S), where ΔTT represents the temperature adjustment amount, α1, α2 and α3 represent weight coefficients determined based on experience, and S represents the extrusion stage state evaluation value. When the head pressure change slope is large, the screw speed fluctuation frequency is high, or the extrusion stage state evaluation value is low, the target temperature is increased or decreased accordingly to optimize the temperature conditions during the extrusion molding process and ensure the fluidity and molding performance of the plastic melt.

[0089] Step S4: During the production process, the temperature of the plastic material is monitored in real time and feedback controlled in real time;

[0090] The specific steps of step S4 are:

[0091] Step S401: Calculate the change rate of the temperature adjustment amount by using the sliding window method, perform linear fitting on the temperature adjustment amount data in the past period of time, and obtain the slope of the fitting line as the change rate of the temperature adjustment amount;

[0092] Step S402: Using a neural network hybrid control strategy to determine the control output of heating, the specific formula is:

[0093]

[0094] Where u(t) represents the output signal of feedback control, such as heating power, heating time, etc., and x jrepresents the input variables, including the temperature adjustment amount, the temperature adjustment amount change rate and other possible parameters, such as the operating parameters of the production equipment, the real-time characteristic parameters of the raw materials, etc., ω ij represents the connection weight from the input layer to the hidden layer, b i It represents the bias of the hidden layer neurons, providing an additional learnable parameter for the hidden layer neurons, which helps the neural network to better fit complex nonlinear relationships, improve its expressiveness and generalization capabilities, and enable the control strategy to adapt to a wider range of production conditions. f() represents the activation function of the hidden layer neurons. represents the connection weight from the hidden layer to the output layer, g() represents the activation function of the output layer, n represents the number of neurons in the hidden layer, and J represents the number of input variables.

[0095] The neural network here is a feed-forward neural network FNN;

[0096] The principle of the above formula: the activation function introduces nonlinear characteristics, so that the neural network can handle complex nonlinear system control problems. The activation function f() of the hidden layer transforms the input signal nonlinearly to increase the expression ability of the network; the activation function g() of the output layer adjusts the final result according to the specific requirements of the control output. For example, the linear activation function is suitable for continuous control quantity output (such as heating power adjustment).

[0097] Step S5: After the plastic particles are formed, the cooling stage is entered to control the temperature and flow rate of the cooling medium.

[0098] The specific steps of step S5 are:

[0099] Step S501: setting the initial temperature of the cooling medium according to the size of the plastic particles and the required cooling rate;

[0100] For example, for a heat-sensitive plastic particle, a lower temperature cooling medium and a higher flow rate may be required to achieve rapid and uniform cooling while avoiding excessive temperature gradients that may cause internal stress.

[0101] Step S502: Analyze the thermal characteristics of the produced plastic particles. Based on the thermophysical properties of the cooling medium and the plastic particles, and the geometric structure of the cooling system, establish a plastic particle cooling model to calculate the temperature of the plastic particles after cooling at time t. The specific formula is:

[0102]

[0103] Among them, ψ(t) represents the temperature of the plastic particles at the cooling time t, ψ0 represents the initial temperature, that is, the temperature of the plastic particles after molding, and ψ ιrepresents the temperature corresponding to the ιth boundary condition, which is related to the cooling medium temperature and heat exchange conditions, ι represents the ιth boundary condition, τ represents the time parameter, which is related to the cooling medium flow characteristics and heat transfer process, t c Indicates the characteristic cooling time, It represents the equivalent thermal diffusion coefficient, which comprehensively considers the thermal diffusivity, thermal conductivity and interaction between plastic particles and cooling medium. cos() represents the cosine function, e represents the exponential function, and t represents time.

[0104] Explanation and principle of the above formula: ψ ι It reflects the temperature value corresponding to the complex heat exchange relationship between plastic particles and cooling medium under different boundary conditions. For example, when the cooling medium flow rate changes or the cooling medium temperature distribution is uneven, there will be different ψ ι The value needs to consider the specific structure of the cooling system, the physical properties of the cooling medium, and the position of the particles in the cooling process.

[0105] τ is closely related to the flow characteristics of the cooling medium, including factors such as the flow rate of the cooling medium, the frequency of change of flow direction, and the residence time in the cooling channel. It reflects the dynamic characteristics of heat transfer between the cooling medium and the plastic particles. A smaller τ value may indicate that the cooling medium is updated faster and the heat exchange efficiency is higher, but it may also lead to uneven temperature distribution. A larger τ value may mean that the heat exchange is relatively slow and stable.

[0106] Characteristic cooling time t c It is a parameter that describes the overall time scale of the cooling process, taking into account the geometric shape and size of the plastic particles, the thermophysical properties of the material, and the overall performance of the cooling system. c For example, for larger plastic particles or those with lower thermal conductivity, t c The value will be relatively large, indicating that the cooling process is relatively slow;

[0107] The boundary conditions mainly include the following aspects: cooling medium temperature, cooling medium flow rate, cooling medium flow direction, ambient temperature, etc.;

[0108] The thermal diffusivity and thermal conductivity of the plastic particles themselves are taken into account, as well as the thermal resistance between the particles and the cooling medium, contact heat conduction, and heat transfer changes caused by the surface state of the particles (such as roughness, whether there is a coating, etc.), reflecting the comprehensive efficiency of heat diffusion inside the particles and exchange with the external cooling medium under a complex cooling environment;

[0109] The formula is based on the Fourier heat conduction analysis of the cooling process of plastic particles, and takes into account the complex heat exchange boundary conditions between the cooling medium and the particles and the dynamic changes of these conditions over time. The infinite series part in the formula represents the contribution of heat conduction modes of different frequencies to temperature changes. The superposition of these modes accurately describes the temperature changes over time during the cooling process. Compared with the traditional cooling stage control formula, this formula more comprehensively considers the dynamic characteristics of the cooling medium in actual production, the complex and changeable heat exchange relationship between the particles and the cooling medium, and the comprehensive influence of the thermophysical properties of the particles themselves, rather than simply based on assumptions such as steady-state heat conduction or average heat transfer coefficients. This enables it to more accurately predict the temperature changes of plastic particles during the cooling stage, thereby providing theoretical support for more accurate temperature control, helping to improve the product quality of plastic particles, reduce defects such as internal stress and deformation caused by uneven cooling, and optimize the energy consumption and production efficiency of the cooling process.

[0110] Step S503: When the monitored temperature of the plastic particles reaches a preset cooling end temperature, it is determined that the cooling process is ended.

[0111] Example 2

[0112] See also Figure 2 , another embodiment provided by the present invention: a temperature control system in a plastic particle production process, comprising: a characteristic analysis module, a temperature prediction module, a dynamic adjustment module, a feedback control module and a cooling control module;

[0113] The characteristic analysis module is used to perform characteristic analysis on the plastic raw materials and obtain key temperature nodes in the production process of plastic particles;

[0114] The temperature prediction module is used to establish a temperature prediction model based on the characteristics of the plastic raw material and the structural parameters of the plastic particle production equipment;

[0115] The dynamic adjustment module is used to set a time interval to correct the temperature prediction model and calculate the dynamic adjustment amount of the plastic particle temperature according to different production stages;

[0116] The feedback control module is used to monitor the temperature of the plastic material in real time during the production process and to provide real-time feedback control;

[0117] The cooling control module is used to control the temperature and flow rate of the cooling medium during the cooling stage after the plastic particles are formed.

[0118] The dynamic adjustment module includes: an error function unit, a state evaluation unit and an adjustment amount determination unit;

[0119] The error function unit is used to construct a temperature error function to adjust and optimize key parameters in the temperature prediction model;

[0120] The state evaluation unit is used to extract characteristic parameters related to each production stage and construct a production stage state evaluation model;

[0121] The adjustment amount determination unit is used to dynamically determine the temperature adjustment amount by adopting an adaptive adjustment strategy according to the output result of the production stage state evaluation model.

[0122] The feedback control module comprises: a variation calculation unit and a feedback control unit;

[0123] The change amount calculation unit is used to perform linear fitting on the temperature adjustment amount data in the past period of time to obtain the slope of the fitting line as the change rate of the temperature adjustment amount;

[0124] The feedback control unit is used to determine the control output of heating by adopting a neural network hybrid control strategy.

[0125] In addition, the parts of the above-mentioned technical solutions provided in the embodiments of the present application that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail to avoid excessive redundancy.

[0126] The specific implementation modes as described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation mode of the present invention and is not intended to limit the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for controlling temperature in a plastic particle production process, characterized in that: include: Analyze the characteristics of plastic raw materials and obtain the key temperature nodes in the production process of plastic particles; Based on the characteristics of plastic raw materials and the structural parameters of plastic particle production equipment, a temperature prediction model is established; Set time intervals to revise the temperature prediction model and calculate the dynamic adjustment of the plastic particle temperature according to different production stages; During the production process, the temperature of plastic materials is monitored in real time and feedback is provided in real time; After the plastic particles are formed, they enter the cooling stage to control the temperature and flow of the cooling medium.

2. A temperature control method in a plastic particle production process as claimed in claim 1, characterized in that: The temperature prediction model has the following specific formula: Where ρ represents the density of the plastic material, C p Represents the specific heat capacity of plastic materials, represents the partial derivative function, T represents the temperature, represents the velocity vector of the plastic material, λ represents the thermal conductivity of the plastic material, ΔT represents the change in temperature, ▽T represents the temperature gradient, Q qxt represents the external heat source term, Q flow It represents the viscous heat dissipation generated by the flow of plastic materials, Q chem Indicates the heat generated by the chemical reaction, Q rad represents the thermal radiation term, and t represents the time.

3. A temperature control method in a plastic particle production process as claimed in claim 2, characterized in that: The setting time interval to correct the temperature prediction model includes: Set the time interval Δt to collect temperature data at key locations in the plastic particle production process, including but not limited to different sections of the extruder screw, multiple points on the inner wall of the barrel, inside the mold cavity, etc., including M monitoring points, and filter the collected temperature data; Based on the collected temperature data of key locations and the predicted temperature value calculated by the temperature prediction model, a temperature error function E is constructed. The specific formula is: Where E represents the temperature error function, T filt (m,t) represents the filtered temperature value of the mth monitoring point at the actual time t. represents the predicted temperature value calculated by the temperature prediction model at the mth monitoring point at the actual time t; Based on the temperature error function E, the key parameters in the temperature prediction model are adjusted and optimized.

4. A method for controlling temperature in a plastic particle production process as claimed in claim 3, characterized in that: The calculation of the dynamic adjustment amount of the temperature of the plastic particles according to different production stages includes: During the production process of plastic particles, characteristic parameters related to each production stage are extracted; Using the extracted characteristic parameters, a production stage status assessment model is constructed, with the characteristic parameters as input variables and the production stage status assessment indicators as output variables; According to the output results of the production stage status evaluation model, an adaptive adjustment strategy is used to dynamically determine the temperature adjustment amount.

5. A method for controlling temperature in a plastic particle production process as claimed in claim 4, characterized in that: During the production process, the temperature of the plastic material is monitored in real time and feedback controlled in real time, including: The sliding window method is used to calculate the change rate of the temperature adjustment amount, and the temperature adjustment amount data in the past period of time is linearly fitted to obtain the slope of the fitting line as the change rate of the temperature adjustment amount; A neural network hybrid control strategy is used to determine the control output of heating. The specific formula is: Where u(t) represents the output signal of feedback control, x j represents the input variable, ω ij represents the connection weight from the input layer to the hidden layer, b i represents the bias of the hidden layer neurons, f() represents the activation function of the hidden layer neurons, represents the connection weight from the hidden layer to the output layer, g() represents the activation function of the output layer, n represents the number of neurons in the hidden layer, and J represents the number of input variables.

6. A method for controlling temperature in a plastic particle production process as claimed in claim 5, characterized in that: After the plastic particles are formed, the cooling stage is entered to control the temperature and flow rate of the cooling medium, including: Set the initial temperature of the cooling medium according to the size of the plastic particles and the required cooling rate; The thermal characteristics of the produced plastic particles are analyzed. Based on the thermophysical properties of the cooling medium and plastic particles, as well as the geometric structure of the cooling system, a plastic particle cooling model is established to calculate the temperature of the plastic particles after cooling at time t. The specific formula is: Among them, ψ(t) represents the temperature of the plastic particles at the cooling time t, ψ0 represents the initial temperature, that is, the temperature of the plastic particles after molding, and ψ ι represents the temperature corresponding to the ιth boundary condition, ι represents the ιth boundary condition, τ represents the time parameter, t c Indicates the characteristic cooling time, represents the equivalent thermal diffusion coefficient, cos() represents the cosine function, e represents the exponential function, and t represents time; When the monitored temperature of the plastic particles reaches the preset cooling end temperature, the cooling process is determined to be finished.

7. A method for controlling temperature in a plastic particle production process as claimed in claim 6, characterized in that: The characteristic analysis of the plastic raw material includes: determination of the melting point range, thermal decomposition temperature, specific heat capacity, and thermal conductivity parameters of the raw material.

8. A temperature control system in a plastic particle production process, used to implement a temperature control method in a plastic particle production process according to any one of claims 1 to 7, characterized in that: include: Characteristic analysis module, temperature prediction module, dynamic adjustment module, feedback control module and cooling control module; The characteristic analysis module is used to perform characteristic analysis on the plastic raw materials and obtain key temperature nodes in the production process of plastic particles; The temperature prediction module is used to establish a temperature prediction model based on the characteristics of the plastic raw material and the structural parameters of the plastic particle production equipment; The dynamic adjustment module is used to set a time interval to correct the temperature prediction model and calculate the dynamic adjustment amount of the plastic particle temperature according to different production stages; The feedback control module is used to monitor the temperature of the plastic material in real time during the production process and to provide real-time feedback control; The cooling control module is used to control the temperature and flow rate of the cooling medium during the cooling stage after the plastic particles are formed.

9. A temperature control system for a plastic particle production process as claimed in claim 8, characterized in that: The dynamic adjustment module includes: an error function unit, a state evaluation unit and an adjustment amount determination unit; The error function unit is used to construct a temperature error function to adjust and optimize key parameters in the temperature prediction model; The state evaluation unit is used to extract characteristic parameters related to each production stage and construct a production stage state evaluation model; The adjustment amount determination unit is used to dynamically determine the temperature adjustment amount by adopting an adaptive adjustment strategy according to the output result of the production stage state evaluation model.

10. A temperature control system for a plastic particle production process as claimed in claim 9, characterized in that: The feedback control module comprises: a variation calculation unit and a feedback control unit; The change amount calculation unit is used to perform linear fitting on the temperature adjustment amount data in the past period of time to obtain the slope of the fitting line as the change rate of the temperature adjustment amount; The feedback control unit is used to determine the control output of heating by adopting a neural network hybrid control strategy.

Images