Drying and recycling equipment control system and method for plastic particle processing

Abstract

The invention discloses a drying recovery equipment control system and method for plastic particle processing, and relates to the technical field of plastic particles, and the method comprises the following steps: setting the maximum hot air flow rate of a fan according to the drying requirement of the plastic particles, and drying the plastic particles at the maximum hot air flow rate; a plurality of high-sensitivity airflow sensors are arranged at key positions of a drying cavity, the flowing condition of airflow in the drying cavity is collected in real time through all the arranged airflow sensors, and collected data are transmitted to a monitoring system in real time through a high-speed data transmission interface. Through the high-sensitivity airflow sensor and the support vector machine model, the tiny eddy current in the drying cavity is monitored in real time, prediction and early warning are conducted in advance, airflow uniformity is ensured, and the drying effect and the product quality are improved. The airflow rate of the fan is regulated and controlled according to the severity of the vortex, slight vortex is slightly adjusted, serious vortex is greatly reduced, vortex formation is prevented, energy consumption is reduced, the service life of equipment is prolonged, and operation efficiency is improved.

Description

Technical Field

[0001] The invention relates to the technical field of plastic particles, and in particular to a control system and method for drying and recycling equipment used for processing plastic particles. Background Art

[0002] The control system for drying and recycling equipment for plastic particle processing refers to a system that manages and controls drying and recycling equipment during the plastic particle processing process. Its main functions include monitoring and adjusting key parameters such as temperature, humidity, and air flow velocity of the equipment to ensure that the plastic particles reach a suitable dryness level before processing to avoid residual moisture affecting the quality. The system also controls the recycling device to recycle the waste gas, dust or remaining plastic particles generated during the processing process, filter or treat them, reduce resource waste and reduce the impact on the environment. Through automated and intelligent control, the operating efficiency and accuracy of the equipment can be improved.

[0003] In the process of drying plastic particles, in order to speed up the drying rate, the existing technology usually controls the fan to increase the hot air flow rate without blowing away the plastic particles to achieve drying, thereby improving the drying efficiency. When the hot air flow rate is large, the airflow is easy to generate tiny vortices in the drying chamber, and it is not easy to be detected. When this happens, the tiny vortices will cause uneven airflow distribution, stagnant or weak airflow in some areas, and too strong airflow in other areas. This will cause the plastic particles to be heated unevenly during the drying process, some particles will not be dried enough, and other particles will be over-dried. Insufficiently dried particles still contain too much moisture, which may lead to a decrease in polymer performance during subsequent processing, such as reduced mechanical strength and poor heat resistance, and even cracking or breaking during the use of the final product, resulting in product failure, especially under stress or high temperature conditions.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0005] The purpose of the present invention is to provide a control system and method for drying and recycling equipment for plastic particle processing. Through a high-sensitivity airflow sensor and a pre-trained support vector machine model, it is possible to monitor and identify potential micro-eddies in the drying chamber in real time, make predictions and early warnings in advance, prevent poor drying of plastic particles caused by uneven airflow, ensure drying uniformity, and improve product quality. At the same time, the hot air flow rate of the fan is regulated differently according to the severity of the eddy current, and the airflow is slightly adjusted for slight eddies, and the airflow rate is greatly reduced for severe eddies to avoid eddy current formation, thereby ensuring efficient and stable drying process, saving energy consumption, extending equipment life, and improving overall operating efficiency, so as to solve the problems in the above-mentioned background technology.

[0006] In order to achieve the above object, the present invention provides the following technical solution: a control method for a drying and recycling device for processing plastic particles, comprising the following steps:

[0007] According to the drying requirements of the plastic particles, the maximum hot air flow rate of the fan is set, and the plastic particles are dried at the maximum hot air flow rate;

[0008] Multiple high-sensitivity airflow sensors are arranged at key positions of the drying chamber. The airflow conditions in the drying chamber are collected in real time through all the arranged airflow sensors, and the collected data are transmitted to the monitoring system in real time through a high-speed data transmission interface;

[0009] The monitoring system extracts features from the data collected by the airflow sensor. After analyzing the extracted features, the pre-trained support vector machine model is used to predict the airflow in the drying chamber and identify the potential tiny vortices in the drying chamber.

[0010] After the support vector machine model preliminarily identifies the existence of potential micro-eddies, it classifies the potential micro-eddies into different levels according to their severity;

[0011] According to the identified potential micro-vortices of different severity levels, different types of regulation are performed on the actual thermal air flow rate of the fan to avoid the actual occurrence of micro-vortices.

[0012] Preferably, the maximum hot air flow rate of the fan refers to the highest hot air flow speed that the fan can generate without blowing away the plastic particles, which is used to accelerate the drying process of the plastic particles.

[0013] Preferably, the key position of the drying chamber refers to the area where the airflow is prone to change or eddy currents are prone to form, and the key positions include: air inlets and outlets; turning points of the air duct; edges and corners of the drying chamber; and above and below the plastic particle accumulation area.

[0014] Preferably, feature extraction is performed on the data collected by the airflow sensor, and the extracted features include the rotational motion intensity of the airflow in a certain area of ​​the drying chamber and the air pressure difference between different positions of the drying chamber. After analyzing the rotational motion intensity of the airflow in a certain area of ​​the drying chamber and the air pressure difference between different positions of the drying chamber, an airflow rotation quantification value and a local pressure difference quantification value are generated respectively, and the rotational motion intensity of the airflow in a certain area of ​​the drying chamber is quantified by the airflow rotation quantification value, and the air pressure difference between different positions in the drying chamber is quantified by the local pressure difference quantification value;

[0015] The obtained airflow rotation quantization value and local pressure difference quantization value are input into the pre-trained support vector machine model to generate the potential vortex occurrence coefficient. The airflow flow in the drying chamber is predicted by the potential vortex occurrence coefficient, and the potential tiny vortex in the drying chamber is identified.

[0016] Preferably, the specific steps of generating the airflow rotation quantization value after analyzing the rotational motion intensity of the airflow in the drying chamber are as follows:

[0017] The rotation velocity gradient of the airflow in a certain area is calculated to indicate the degree of change in airflow velocity. The specific calculation formula is: In the formula, It represents the rotational velocity gradient of the airflow, describing the velocity change of the airflow in the radial direction, V θ is the tangential velocity of the airflow, indicating the movement of the airflow in the circumferential direction, r is the radius of the airflow rotation or the distance from the center, indicating the distance from the position of the airflow to the center of rotation;

[0018] After obtaining the rotation velocity gradient, the rotation momentum index is further calculated to quantify the intensity of the airflow rotation. The calculation expression of the rotation momentum index is: θ =∫ Ω ρr 2 V θ dA, where L θ represents the rotational momentum index of the airflow, ρ is the density of the airflow, which represents the mass distribution of the airflow in the rotating area, Ω represents the integration area, that is, the area where the rotational momentum is calculated, and dA is the differential area element, which is used to represent a small area unit in the area:

[0019] The airflow rotation reference value is generated according to the rotation speed gradient and the rotation momentum index of the airflow. The expression for generating the airflow rotation reference value is:

[0020] ,

[0021] In the formula, Rθ is the final generated airflow rotation reference value, which quantifies the rotational motion intensity of the airflow in a certain area of ​​the drying chamber, and ω is the adjustment coefficient, which is used to adjust the relative influence weight of the rotation speed gradient and the rotation momentum index;

[0022] The airflow rotation reference values ​​of several areas are obtained to establish an analysis set, the airflow rotation reference values ​​in the analysis set are sorted in order, the maximum airflow rotation reference value is screened out, the maximum airflow rotation reference value is recorded as the airflow rotation quantization value, and the maximum rotational motion intensity of the airflow in the drying chamber is quantified by the airflow rotation quantization value.

[0023] Preferably, the specific steps of generating a local pressure difference quantization value after analyzing the air pressure difference between different positions of the drying chamber are as follows:

[0024] The air pressure data at different positions are collected in real time through the air flow sensors arranged in the drying chamber. Suppose N sensors are arranged in the drying chamber, and the measurement point of each air flow sensor is represented by P. i , where P i Represents the air pressure at the i-th position. The local air pressure gradient vector is calculated by the air pressure difference between adjacent airflow sensors. The calculation expression is:

[0025] ,

[0026] In the formula, G i is the pressure gradient vector at the ith position, reflecting the pressure difference between adjacent positions, P i and P i+1 is the air pressure value at the i-th position and the i+1-th position, d i，i+1 is the physical distance between the i-th position and the i+1-th position;

[0027] The pressure gradient vector is used to construct a rotation field map to reflect the overall rotation characteristics of the pressure gradient. The potential vortex area is detected by the rotation field. The construction expression of the rotation field map is:

[0028] ,

[0029] In the formula, R i is the rotation field value of the i-th position, G i ×G i+1 is the cross product of the pressure gradient vectors between the i-th and i+1-th positions, indicating the rotation trend of the region. is the square of the distance between two adjacent positions, which is used to normalize the rotation field strength;

[0030] According to the calculated pressure gradient vector and rotation field, the local pressure difference quantification value is further generated. The local pressure difference quantification value quantifies the overall pressure difference between different positions in the drying chamber and reflects the correlation between the pressure gradient and the vortex. The generated expression is: In the formula, represents the local pressure difference reference value at the i-th position, quantifying the pressure difference and rotation trend at that position, G ij is the pressure gradient vector between the ith position and the ith position, indicating the pressure difference between the two points, R ij is the rotation field value between the i-th position and the j-th position, indicating the rotation trend or vortex possibility of the airflow in this area. α and β are |G ij | and R ij The weight coefficients control the influence of the pressure gradient vector and the rotation field on the local pressure difference reference value, LPI θRepresents the maximum value of the local pressure difference reference value among all positions, that is, the local pressure difference quantization value.

[0031] Preferably, the potential vortex occurrence coefficient generated when the pre-trained support vector machine model is used to predict the airflow condition in the drying chamber is compared and analyzed with a pre-set reference threshold value of the potential vortex occurrence coefficient to identify the potential micro-vortex condition in the drying chamber. The specific steps are:

[0032] If the potential eddy current occurrence coefficient is greater than or equal to the potential eddy current occurrence coefficient reference threshold, a potential eddy current signal is generated, indicating that there is a hidden danger of potential tiny eddy currents in the drying chamber at this time; if the potential eddy current occurrence coefficient is less than the potential eddy current occurrence coefficient reference threshold, a high-efficiency drying signal is generated, indicating that there is no hidden danger of potential tiny eddy currents in the drying chamber at this time.

[0033] Preferably, after the support vector machine model preliminarily identifies the existence of potential micro-eddies, the potential micro-eddies are divided into different levels according to their severity, and different types of regulation are performed on the actual thermal air flow rate of the fan for the identified potential micro-eddies of different severity levels. The specific steps are as follows:

[0034] The generated potential eddy current occurrence coefficient is compared with the potential eddy current occurrence coefficient reference threshold, and the relative coefficient ΔV of the eddy current severity level is calculated. The calculation expression is: In the formula, Poten Vort represents the potential vortex generation coefficient generated when the airflow in the drying chamber is predicted by the pre-trained support vector machine model, V th Indicates the reference threshold value of potential eddy current occurrence coefficient;

[0035] According to the value of the relative vortex level, the potential micro-vortex situation is divided into different levels, specifically:

[0036] Set the classification criteria of mild, moderate and severe, and the specific classification expression is:

[0037] Preferably, according to different vortex severity levels, the actual thermal flow rate is regulated according to the maximum thermal flow rate to control the formation of the vortex. The adjustment of the maximum thermal flow rate depends on the severity level of the potential micro-vortex. The specific adjustment expression is: V f is the actual thermal flow rate after adjustment, is the maximum thermal airflow rate initially set, K1, K2, and K3 are the adjustment constants of potential micro-eddies at the mild, moderate, and severe levels, respectively, K1>K2>K3, which are used to control the adjustment range of the airflow rate;

[0038] After the actual hot air flow rate of the fan is initially adjusted, the air flow state is monitored in real time, and the potential vortex generation coefficient generated by the pre-trained support vector machine model is used to adjust the actual hot air flow rate so that the actual hot air flow rate dynamically adapts to the air flow state in the drying chamber. The expression for adjusting the actual hot air flow rate is:

[0039] ,

[0040] Where V f (t+1) is the actual thermal flow rate at the next moment, V f (t) is the actual thermal flow rate at the current moment, is the rate of change of the potential eddy current generation coefficient, λ is the feedback adjustment coefficient, which is used to control the feedback adjustment amplitude, Poten Vort (t) represents the potential eddy current occurrence coefficient at the current moment;

[0041] After multiple feedback adjustments, the actual thermal flow rate is finally determined. The expression for determining the final actual thermal flow rate is: In the formula, is the actual thermal flow rate after final adjustment, The upper limit of safe thermal velocity.

[0042] A control system for drying and recycling equipment for plastic particle processing, including a fan maximum airflow rate setting module, an airflow data acquisition module, an airflow data analysis and vortex prediction module, an vortex severity classification module, and a fan hot airflow rate control module;

[0043] The fan maximum airflow rate setting module sets the maximum hot airflow rate of the fan according to the drying requirements of the plastic particles, and dries the plastic particles at the maximum hot airflow rate;

[0044] The airflow data acquisition module arranges multiple high-sensitivity airflow sensors at key positions of the drying chamber. The airflow conditions in the drying chamber are collected in real time through all arranged airflow sensors, and the collected data is transmitted to the monitoring system in real time through a high-speed data transmission interface;

[0045] The airflow data analysis and vortex prediction module extracts features from the data collected by the airflow sensor through the monitoring system. After analyzing the extracted features, it uses the pre-trained support vector machine model to predict the airflow conditions in the drying chamber and identify potential tiny vortices in the drying chamber:

[0046] The eddy current severity classification module, when the support vector machine model preliminarily identifies the existence of potential micro-eddy currents, divides the potential micro-eddy currents into different levels according to their severity;

[0047] The fan thermal air flow rate control module performs different types of control on the fan's actual thermal air flow rate according to the identified potential micro-eddies of different severity levels, so as to avoid the actual occurrence of micro-eddies.

[0048] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0049] The present invention uses a highly sensitive airflow sensor to collect airflow data in the drying chamber in real time. Combined with a pre-trained support vector machine model, it can accurately identify potential micro-eddies in the drying chamber. This process ensures real-time monitoring of airflow distribution and can identify signs of micro-eddies before they occur in the airflow, thus avoiding uneven airflow caused by eddies. Through early prediction and early warning, the problem of uneven drying of plastic particles caused by local airflow stagnation or excessive strength during the drying process is reduced, which helps to improve the uniformity of drying, ensure that all plastic particles can reach an ideal drying state during the drying process, avoid moisture residue caused by insufficient drying or particle degradation caused by excessive drying, and ultimately improve the overall quality and performance of the product.

[0050] After identifying the potential tiny vortex in the drying chamber, the present invention divides the vortex into different levels according to its severity, and performs different types of regulation on the actual hot air flow rate of the fan, which can effectively avoid the actual formation of the vortex. For different levels of potential vortex conditions, a slight vortex only needs to slightly adjust the air flow rate to ensure the drying efficiency, while for moderate and severe vortices, the air flow rate is greatly reduced to reduce the tendency of air flow rotation and avoid air flow out of control, ensuring that the fan is running efficiently while avoiding the problem of local air flow unevenness caused by vortices, making the drying process more stable and reliable, thereby improving the overall equipment operation efficiency, saving energy consumption, and extending the equipment life, while avoiding product quality problems caused by vortices. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0052] Figure 1 The present invention is a method flow chart of a method for controlling a drying recovery device for processing plastic particles.

[0053] Figure 2 The module schematic diagram of the control system of the drying and recycling equipment for plastic particle processing of the present invention. DETAILED DESCRIPTION

[0054] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0055] The present invention provides Figure 1 The control method of the drying and recycling equipment for plastic particle processing shown includes the following steps:

[0056] According to the drying requirements of the plastic particles, the maximum hot air flow rate of the fan is set, and the plastic particles are dried at the maximum hot air flow rate;

[0057] The drying requirements of plastic particles refer to the specific drying conditions that plastic particles need to meet during the drying process to ensure that their moisture content drops to an ideal range suitable for subsequent processing. Specific requirements include parameters such as target moisture content, drying time, suitable temperature range and airflow velocity. Drying requirements usually depend on the type of plastic particles, particle size, initial moisture content and subsequent processing requirements, such as the material dryness required for injection molding or extrusion. Meeting these drying requirements can ensure that the plastic particles have stable physical properties and mechanical strength during processing and avoid quality problems caused by excessive moisture. When drying plastic particles, it is necessary to ensure that the airflow is large enough to accelerate drying while avoiding excessive airflow that causes the plastic particles to be blown away. Through the precise control of the fan speed, the airflow rate is maximized while maintaining the stability of the plastic particles.

[0058] The maximum hot air flow rate of the fan refers to the highest hot air flow speed that the fan can generate without blowing away the plastic particles, which is used to accelerate the drying process of the plastic particles.

[0059] Multiple high-sensitivity airflow sensors are arranged at key positions of the drying chamber. The airflow conditions in the drying chamber are collected in real time through all the arranged airflow sensors, and the collected data are transmitted to the monitoring system in real time through a high-speed data transmission interface;

[0060] The key positions of the drying chamber usually refer to those areas where the airflow is prone to change or eddy currents are prone to form, which have a significant impact on the airflow distribution and drying effect. Key positions include: the air inlet and outlet, because these are where the airflow enters and leaves the drying chamber, and the airflow rate and direction may change dramatically; the bends in the air duct, where the airflow is prone to eddy currents or stagnation; the edges and corners of the drying chamber, where the airflow is weak or easily trapped, resulting in uneven drying; the upper and lower parts of the plastic particle accumulation area, where the hot airflow directly contacts the particles, and the uniformity of the airflow is particularly critical here. By arranging high-sensitivity airflow sensors at these locations, the airflow flow in the drying chamber can be effectively monitored to ensure uniform drying.

[0061] Highly sensitive airflow sensors can monitor airflow speed, direction, and temperature changes. The distribution of sensors should be scientific and reasonable to ensure that the airflow conditions in all areas of the drying chamber can be accurately monitored. Through the arrangement of sensors, a comprehensive airflow monitoring network can be established to provide high-precision airflow information for subsequent data analysis.

[0062] The monitoring system extracts features from the data collected by the airflow sensor. After analyzing the extracted features, the pre-trained support vector machine model is used to predict the airflow in the drying chamber and identify the potential tiny vortices in the drying chamber.

[0063] The data collected by the airflow sensor are subjected to feature extraction, and the extracted features include the rotational movement intensity of the airflow in a certain area of ​​the drying chamber and the air pressure difference between different positions of the drying chamber. After analyzing the rotational movement intensity of the airflow in a certain area of ​​the drying chamber and the air pressure difference between different positions of the drying chamber, an airflow rotation quantification value and a local pressure difference quantification value are generated respectively. The rotational movement intensity of the airflow in a certain area of ​​the drying chamber is quantified by the airflow rotation quantification value, reflecting whether the airflow forms a vortex or eddy in the area and its rotation degree. The air pressure difference between different positions of the drying chamber is quantified by the local pressure difference quantification value, reflecting the pressure unevenness caused by obstacles or airflow turning during the airflow flow. The obtained airflow rotation quantification value and local pressure difference quantification value are input into a pre-trained support vector machine model to generate a potential vortex occurrence coefficient. The airflow flow in the drying chamber is predicted by the potential vortex occurrence coefficient, and the potential micro-vortex in the drying chamber is identified.

[0064] A pre-trained support vector machine model refers to a support vector machine (SVM) that is trained with a known data set so that it has the ability to perform classification or regression prediction based on new input data. Support vector machine is a supervised learning algorithm that classifies or regresses data by finding the optimal hyperplane. The model learns the relationship between different data features during training. For example, in the application scenario here, it can learn the relationship between the quantized value of airflow rotation and the quantized value of local pressure difference and vortex. During training, SVM establishes a prediction model through a set of labeled data (such as labeled data of whether vortex exists or not) to ensure that the possibility of vortex can be accurately predicted when new airflow data is input. By selecting a suitable kernel function (such as linear kernel, radial basis kernel, etc.), SVM can handle linear or nonlinear classification problems, thereby effectively identifying potential small vortex conditions in the drying chamber.

[0065] In this application, the pre-trained SVM model is learned through a large number of airflow data sets, which include the quantized values ​​of airflow rotation, the quantized values ​​of local pressure difference and their corresponding vortex states under different conditions. Through the training process, the SVM model learns how to distinguish between normal airflow and airflow patterns with vortices. The training goal of the model is to optimize the position of the hyperplane so that the model can distinguish the vortex state from the normal state to the greatest extent when predicting. After the training is completed, the model can accept the newly input feature data such as the quantized values ​​of airflow rotation and the quantized values ​​of local pressure difference, generate the potential vortex occurrence coefficient, and predict whether there are tiny vortices in the airflow in the drying chamber. The pre-trained SVM model has the ability to predict unknown vortices through the experience accumulation of historical data, ensuring that the abnormal state of airflow flow can be identified in real time.

[0066] When the intensity of the rotational motion of the airflow in a certain area of ​​the drying chamber is high, it usually indicates that there may be potential tiny eddies in the drying chamber. The intensity of the rotational motion of the airflow reflects the rotation and vortex tendency of the airflow in a specific area, and the formation of eddies is often accompanied by the intensification of the rotation of the local airflow. In the drying chamber, eddies can cause uneven distribution of the airflow, affecting the drying effect of the plastic particles, causing stagnation of the airflow or weakening of the flow rate in some areas, resulting in uneven drying. Although tiny eddies are difficult to detect, they can have a significant impact on the stability and efficiency of the drying process, especially when the intensity of the rotational motion increases, which means that the airflow has produced obvious rotational flow in the area, and the risk of eddy formation increases.

[0067] The specific steps for generating the quantitative value of airflow rotation after analyzing the rotational motion intensity of the airflow in the drying chamber are as follows:

[0068] The rotation velocity gradient of the airflow in a certain area is calculated to indicate the degree of change in airflow velocity. The specific calculation formula is: In the formula, It represents the rotational velocity gradient of the airflow, describing the velocity change of the airflow in the radial direction, V θ is the tangential velocity of the airflow (i.e., rotational velocity), indicating the movement of the airflow in the circumferential direction, r is the radius of the airflow rotation or the distance from the center, indicating the distance from the airflow location to the rotation center;

[0069] This formula can be used to measure how the rotation speed of the airflow changes with distance. The larger the rotation speed gradient, the more intense the rotation motion.

[0070] After obtaining the rotation velocity gradient, the rotation momentum index is further calculated to quantify the intensity of the airflow rotation. The calculation expression of the rotation momentum index is: θ =∫ Ω ρr 2 V θ dA, where L θ represents the rotational momentum index of the airflow, ρ is the density of the airflow, which represents the mass distribution of the airflow in the rotating area, Ω represents the integration area, that is, the area where the rotational momentum is calculated, and dA is the differential area element, which is used to represent a small area unit in the area;

[0071] The rotational momentum index can reflect the energy of the airflow's rotational motion. The larger the rotational momentum index is, the stronger the airflow's rotation is.

[0072] The airflow rotation reference value is generated according to the rotation speed gradient and the rotation momentum index of the airflow. The expression for generating the airflow rotation reference value is:

[0073] ,

[0074] In the formula, Rθ is the final generated airflow rotation reference value, which quantifies the rotational motion intensity of the airflow in a certain area of ​​the drying chamber. ω is the adjustment coefficient, which is used to adjust the relative influence weight of the rotation speed gradient and the rotation momentum index, and is set according to the specific application scenario.

[0075] This step provides a comprehensive measure of the airflow rotation intensity by combining the rotation velocity gradient and the rotation momentum index. The higher the airflow rotation reference value, the more significant the airflow vortex phenomenon and the greater the possibility of vortex occurrence.

[0076] The airflow rotation reference values ​​of several areas are obtained to establish an analysis set, the airflow rotation reference values ​​in the analysis set are sorted in order, the maximum airflow rotation reference value is screened out, the maximum airflow rotation reference value is recorded as the airflow rotation quantization value, and the maximum rotational motion intensity of the airflow in the drying chamber is quantified by the airflow rotation quantization value.

[0077] It can be seen from the airflow rotation quantification value that the larger the performance value of the airflow rotation quantification value generated after analyzing the rotational motion intensity of the airflow in the drying chamber, the greater the hidden danger of potential tiny vortices in the drying chamber. The airflow rotation quantification value reflects whether the airflow forms a vortex and its degree of rotation by quantifying the rotational motion intensity of the airflow in a specific area. When the airflow rotation quantification value is high, it means that the rotational motion of the airflow in this area is strong, which may produce vortices, leading to problems such as uneven airflow distribution and uneven drying, thereby affecting the drying effect of plastic particles. On the contrary, when the airflow rotation quantification value is small, the airflow flows more smoothly, the probability of vortices is lower, and the hidden danger of tiny vortices in the drying chamber is smaller. By selecting the maximum airflow rotation reference value as the airflow rotation quantification value, the potential hidden danger of tiny vortices in the airflow in the drying chamber can be effectively reflected.

[0078] When the air pressure difference between different positions in the drying chamber is large, it indicates that there are potential tiny eddies in the drying chamber. The generation of eddies is usually accompanied by the rotational motion or turbulence of local airflow, and the instability of these airflows can cause significant changes in air pressure in different areas. When the airflow encounters an obstacle or makes a sharp turn, the change in airflow speed and direction will cause an uneven pressure distribution, resulting in higher air pressure in local areas and lower air pressure in other areas, forming a significant pressure difference. This situation may lead to the formation of eddies in the drying chamber, because eddies are usually accompanied by large local air pressure fluctuations. Therefore, real-time monitoring of air pressure differences, especially the air pressure distribution at different positions in the drying chamber, can serve as an important basis for identifying potential tiny eddies. When the air pressure difference increases significantly, it means that the airflow distribution has become abnormal, and it is very likely to be accompanied by the generation of eddies, which will affect the uniformity of airflow during the drying process, and thus affect the drying effect of plastic particles.

[0079] The specific steps for analyzing the air pressure difference between different positions in the drying chamber and generating a quantitative value of the local pressure difference are as follows:

[0080] The air pressure data at different positions are collected in real time through the air flow sensors arranged in the drying chamber. Suppose N sensors are arranged in the drying chamber, and the measurement point of each air flow sensor is represented by P. i , where P i Represents the air pressure at the i-th position. The local air pressure gradient vector is calculated by the air pressure difference between adjacent airflow sensors. The calculation expression is:

[0081] ,

[0082] In the formula, G i is the pressure gradient vector at the ith position, reflecting the pressure difference between adjacent positions, P i and P i+1 is the air pressure value at the i-th position and the i+1-th position, di，i+1 is the physical distance between the i-th position and the i+1-th position;

[0083] By calculating the pressure gradient between adjacent airflow sensor locations, the pressure changes in the local area can be quantified. The larger the pressure gradient, the more significant the pressure difference, and the greater the possibility of significant fluctuations or vortex formation in the airflow in the area.

[0084] In order to capture how the pressure differences between different positions are distributed throughout the drying chamber, a rotation field map is constructed using the pressure gradient vector to reflect the overall rotation characteristics of the pressure gradient. Potential vortex areas can be detected through the rotation field. The construction expression of the rotation field map is:

[0085] ,

[0086] In the formula, R i is the rotation field value at the ith position, reflecting how the pressure difference at that position induces rotational motion or vortex, G i ×G i+1 is the cross product of the pressure gradient vectors between the i-th and i+1-th positions, indicating the rotation trend of the region. is the square of the distance between two adjacent positions, which is used to normalize the rotation field strength;

[0087] The rotation field map reflects the rotation characteristics of the pressure difference in the drying chamber. If the rotation field value is large, it means that the pressure difference in this area forms an obvious rotation motion, indicating the existence of potential vortices.

[0088] According to the calculated pressure gradient vector and rotation field, the local pressure difference quantification value is further generated. The local pressure difference quantification value quantifies the overall pressure difference between different positions in the drying chamber and reflects the correlation between the pressure gradient and the vortex. The generated expression is: In the formula, represents the local pressure difference reference value at the i-th position, quantifying the pressure difference and rotation trend at that position, G ij is the pressure gradient vector between the i-th position and the j-th position, indicating the pressure difference between the two points, R ij is the rotation field value between the i-th position and the j-th position, indicating the rotation trend or vortex possibility of the airflow in this area. α and β are |G ij | and R ij The weight coefficients control the influence of the pressure gradient vector and the rotation field on the local pressure difference reference value, LPI θ It represents the maximum value of the local pressure difference reference value among all positions, that is, the local pressure difference quantization value (N is the total number of airflow sensors in the drying chamber).

[0089] The local pressure difference quantification value combines the pressure gradient vector and the rotation field to quantify the comprehensive effect of the pressure difference. When the local pressure difference quantification value is high, it means that the pressure difference in the area is significant and the airflow has a strong rotation tendency, indicating that there may be tiny vortices.

[0090] It can be seen from the local pressure difference quantification value that the larger the performance value of the local pressure difference quantification value generated after analyzing the air pressure difference between different positions in the drying chamber, the more significant the air pressure difference between different positions in the drying chamber, which means that the airflow distribution is more uneven, the airflow rotation trend is stronger, and the potential hidden danger of small vortices is greater. This is because vortices are usually accompanied by an increase in air pressure differences and airflow rotation, so the local pressure difference quantification value can quantify these phenomena. On the contrary, if the local pressure difference quantification value is small, it means that the air pressure difference is small, the airflow is more uniform, and the possibility of vortices is lower.

[0091] The support vector machine model is not specifically limited here, and can realize the quantization of airflow rotation value Rθ and local pressure difference quantization value LPI θ Comprehensive analysis is performed to generate the potential eddy current occurrence coefficient Poten Vort The support vector machine model can be used. In order to realize the technical solution of the present invention, the present invention provides a specific implementation method; the potential eddy current generation coefficient Poten Vort The resulting calculation formula is: Poten Vort =δ1*R θ +δ2*LPI θ , where δ1 and δ2 are the airflow rotation quantization values ​​R θ and local pressure difference quantification value LPI θ The preset proportional coefficient, and δ1 and δ2 are both greater than 0.

[0092] It can be seen from the potential vortex occurrence coefficient that the greater the expression value of the airflow rotation quantization value generated after analyzing the rotational motion intensity of the airflow in the drying chamber, the greater the expression value of the local pressure difference quantization value generated after analyzing the air pressure difference between different positions in the drying chamber. In other words, the greater the expression value of the potential vortex occurrence coefficient generated when the airflow flow in the drying chamber is predicted by using the pre-trained support vector machine model, the greater the hidden danger of potential tiny vortices in the drying chamber, and vice versa.

[0093] The potential vortex occurrence coefficient generated when the pre-trained support vector machine model is used to predict the airflow in the drying chamber is compared with the pre-set reference threshold of the potential vortex occurrence coefficient to identify the potential micro-vortex in the drying chamber. The specific steps are as follows:

[0094] If the potential eddy current occurrence coefficient is greater than or equal to the potential eddy current occurrence coefficient reference threshold, a potential eddy current signal is generated, indicating that there is a hidden danger of potential tiny eddy currents in the drying chamber at this time; if the potential eddy current occurrence coefficient is less than the potential eddy current occurrence coefficient reference threshold, a high-efficiency drying signal is generated, indicating that there is no hidden danger of potential tiny eddy currents in the drying chamber at this time.

[0095] After the support vector machine model preliminarily identifies the existence of potential micro-eddies, it classifies the potential micro-eddies into different levels according to their severity;

[0096] According to the potential micro-vortices of different severity levels identified, different types of regulation are performed on the actual hot air flow rate of the fan to avoid the actual occurrence of micro-vortices;

[0097] After the support vector machine model preliminarily identifies the existence of potential micro-vortices, the potential micro-vortices are divided into different levels according to their severity. For the potential micro-vortices of different severity levels identified, different types of regulation are performed on the actual thermal air flow rate of the fan. The specific steps are as follows:

[0098] The generated potential eddy current occurrence coefficient is compared with the potential eddy current occurrence coefficient reference threshold, and the relative coefficient ΔV of the eddy current severity level is calculated. The calculation expression is: In the formula, Poten Vort represents the potential vortex generation coefficient generated when the airflow in the drying chamber is predicted by the pre-trained support vector machine model, V th Indicates the reference threshold value of potential eddy current occurrence coefficient;

[0099] If the relative coefficient of the eddy current severity level is greater than 1, it means that the potential eddy current occurrence coefficient is greater than the reference threshold of the potential eddy current occurrence coefficient, and there is a hidden danger of potential micro-eddy currents; if the relative coefficient of the eddy current severity level is less than 1, it means that the potential eddy current occurrence coefficient is less than the reference threshold of the potential eddy current occurrence coefficient, and there is no hidden danger of potential micro-eddy currents.

[0100] According to the value of relative vortex level, the potential micro-vortex situation is divided into different levels;

[0101] For example, you can set the classification criteria of mild, moderate, and severe. The specific classification expression is:

[0102] According to the classification of vortex levels, specific control strategies can be provided for subsequent fan control.

[0103] According to different vortex severity levels, the actual thermal flow rate is adjusted according to the maximum thermal flow rate to control the formation of vortices. The adjustment of the maximum thermal flow rate depends on the severity level of potential micro-vortices. The specific adjustment expression is: V f is the actual thermal flow rate after adjustment, is the maximum thermal airflow rate initially set, K1, K2, and K3 are the adjustment constants of potential micro-eddies at the mild, moderate, and severe levels, respectively, K1>K2>K3, which are used to control the adjustment range of the airflow rate;

[0104] When setting K1, K2, and K3, the airflow rate should be adjusted according to the different vortex severity levels. K1, K2, and K3 are used to adjust the airflow rate for mild, medium, and severe vortex levels, respectively, to ensure that the airflow rate adjustment range gradually increases as the vortex severity increases.

[0105] K1 (mild vortex level): sets a larger adjustment constant to ensure that at the mild vortex level, the air flow rate is adjusted less, maintaining drying efficiency while slightly reducing the risk of vortex.

[0106] K2 (Medium swirl level): Sets a medium adjustment constant so that when the swirl level is medium, the air flow rate adjustment is more significant to reduce the impact of swirl.

[0107] K3 (severe vortex level): Set a smaller adjustment constant to ensure that the airflow rate is adjusted to the maximum extent under the severe vortex level, greatly reducing the risk of vortex formation and giving priority to ensuring the stability and safety of the system.

[0108] By properly setting K1, K2, and K3, refined airflow control for different vortex levels can be achieved, which can reduce the formation of vortex and maintain drying efficiency;

[0109] When the swirl level is high, the actual thermal flow rate is significantly reduced to reduce the formation of swirls; when the swirl level is low, the actual thermal flow rate is adjusted less.

[0110] After the actual hot air flow rate of the fan is initially adjusted, the air flow state is monitored in real time, and the potential vortex generation coefficient generated by the pre-trained support vector machine model is used to adjust the actual hot air flow rate so that the actual hot air flow rate dynamically adapts to the air flow state in the drying chamber. The expression for adjusting the actual hot air flow rate is:

[0111] ,

[0112] Where V f (t+1) is the actual thermal flow rate at the next moment, V f (t) is the actual thermal flow rate at the current moment, is the rate of change of the potential eddy current generation coefficient, λ is the feedback adjustment coefficient, which is used to control the feedback adjustment amplitude, PotenVort (t) represents the potential eddy current occurrence coefficient at the current time (time t);

[0113] If the potential vortex occurrence factor continues to increase over time, the actual thermal flow rate will further decrease; if the vortex risk decreases, the actual thermal flow rate will gradually recover.

[0114] After multiple feedback adjustments, the appropriate actual thermal air flow rate is finally determined to ensure both efficient drying and avoid vortex formation. The final actual thermal air flow rate is determined by: In the formula, is the actual thermal flow rate after final adjustment, is the upper limit of safe thermal flow rate;

[0115] The final actual hot air flow rate should be controlled within a safe range, while meeting the requirements of drying efficiency and avoiding the risk of eddy currents.

[0116] The present invention provides Figure 2 The control system of the drying and recycling equipment for plastic particle processing shown includes a fan maximum airflow rate setting module, an airflow data acquisition module, an airflow data analysis and vortex prediction module, an vortex severity level classification module, and a fan hot airflow rate control module;

[0117] The fan maximum airflow rate setting module sets the maximum hot airflow rate of the fan according to the drying requirements of the plastic particles, and dries the plastic particles at the maximum hot airflow rate;

[0118] The airflow data acquisition module arranges multiple high-sensitivity airflow sensors at key positions of the drying chamber. The airflow conditions in the drying chamber are collected in real time through all arranged airflow sensors, and the collected data is transmitted to the monitoring system in real time through a high-speed data transmission interface;

[0119] The airflow data analysis and vortex prediction module extracts features from the data collected by the airflow sensor through the monitoring system. After analyzing the extracted features, it uses a pre-trained support vector machine model to predict the airflow conditions in the drying chamber and identify potential tiny vortices in the drying chamber.

[0120] The eddy current severity classification module, when the support vector machine model preliminarily identifies the existence of potential micro-eddy currents, divides the potential micro-eddy currents into different levels according to their severity;

[0121] The fan thermal air flow rate control module performs different types of control on the fan's actual thermal air flow rate according to the potential micro-eddies of different severity levels identified, to avoid the actual occurrence of micro-eddies;

[0122] The control method of the dry recovery equipment for plastic particle processing provided in the embodiment of the present invention is realized by the above-mentioned control system of the dry recovery equipment for plastic particle processing. The specific method and process of the control system of the dry recovery equipment for plastic particle processing are detailed in the embodiment of the control method of the dry recovery equipment for plastic particle processing, which will not be repeated here.

[0123] The present invention uses a highly sensitive airflow sensor to collect airflow data in the drying chamber in real time. Combined with a pre-trained support vector machine model, it can accurately identify potential micro-eddies in the drying chamber. This process ensures real-time monitoring of airflow distribution and can identify signs of micro-eddies before they occur in the airflow, thus avoiding uneven airflow caused by eddies. Through early prediction and early warning, the problem of uneven drying of plastic particles caused by local airflow stagnation or excessive strength during the drying process is reduced, which helps to improve the uniformity of drying, ensure that all plastic particles can reach an ideal drying state during the drying process, avoid moisture residue caused by insufficient drying or particle degradation caused by excessive drying, and ultimately improve the overall quality and performance of the product.

[0124] After identifying the potential tiny vortex in the drying chamber, the present invention divides the vortex into different levels according to its severity, and performs different types of regulation on the actual hot air flow rate of the fan, which can effectively avoid the actual formation of the vortex. For different levels of potential vortex conditions, a slight vortex only needs to slightly adjust the air flow rate to ensure the drying efficiency, while for moderate and severe vortices, the air flow rate is greatly reduced to reduce the tendency of air flow rotation and avoid air flow out of control, ensuring that the fan is running efficiently while avoiding the problem of local air flow unevenness caused by vortices, making the drying process more stable and reliable, thereby improving the overall equipment operation efficiency, saving energy consumption, and extending the equipment life, while avoiding product quality problems caused by vortices.

[0125] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0126] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0127] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A control method for a drying and recycling device for plastic particle processing, characterized in that: The following steps are involved: According to the drying requirements of the plastic particles, the maximum hot air flow rate of the fan is set, and the plastic particles are dried at the maximum hot air flow rate; Multiple high-sensitivity airflow sensors are arranged at key positions of the drying chamber. The airflow conditions in the drying chamber are collected in real time through all the arranged airflow sensors, and the collected data are transmitted to the monitoring system in real time through a high-speed data transmission interface; The monitoring system extracts features from the data collected by the airflow sensor. After analyzing the extracted features, the pre-trained support vector machine model is used to predict the airflow in the drying chamber and identify the potential tiny vortices in the drying chamber. After the support vector machine model preliminarily identifies the existence of potential micro-eddies, it classifies the potential micro-eddies into different levels according to their severity; According to the identified potential micro-vortices of different severity levels, different types of regulation are performed on the actual thermal air flow rate of the fan to avoid the actual occurrence of micro-vortices.

2. The control method for drying and recycling equipment for plastic particle processing according to claim 1, characterized in that: The maximum hot air flow rate of the fan refers to the highest hot air flow speed that the fan can generate without blowing away the plastic particles, which is used to accelerate the drying process of the plastic particles.

3. The control method for drying and recycling equipment for plastic particle processing according to claim 1, characterized in that: The key positions of the drying chamber refer to the areas where the airflow is prone to change or eddy currents are prone to form. The key positions include: air inlets and outlets; turning points in the air duct; edges and corners of the drying chamber; and the upper and lower parts of the plastic particle accumulation area.

4. The control method for drying and recycling equipment for plastic particle processing according to claim 1, characterized in that: Feature extraction is performed on the data collected by the airflow sensor, and the extracted features include the rotational movement intensity of the airflow in a certain area of ​​the drying chamber and the air pressure difference between different positions of the drying chamber. After analyzing the rotational movement intensity of the airflow in a certain area of ​​the drying chamber and the air pressure difference between different positions of the drying chamber, an airflow rotation quantification value and a local pressure difference quantification value are generated respectively. The rotational movement intensity of the airflow in a certain area of ​​the drying chamber is quantified by the airflow rotation quantification value, and the air pressure difference between different positions in the drying chamber is quantified by the local pressure difference quantification value; The obtained airflow rotation quantization value and local pressure difference quantization value are input into the pre-trained support vector machine model to generate the potential vortex occurrence coefficient. The airflow flow in the drying chamber is predicted by the potential vortex occurrence coefficient, and the potential tiny vortex in the drying chamber is identified.

5. The control method for drying and recycling equipment for plastic particle processing according to claim 4, characterized in that: The specific steps for generating the quantitative value of airflow rotation after analyzing the rotational motion intensity of the airflow in the drying chamber are as follows: The rotation velocity gradient of the airflow in a certain area is calculated to indicate the degree of change in airflow velocity. The specific calculation formula is: In the formula, It represents the rotational velocity gradient of the airflow, describing the velocity change of the airflow in the radial direction, V θ is the tangential velocity of the airflow, indicating the movement of the airflow in the circular direction, r is the radius of the airflow rotation or the distance from the center, indicating the distance from the position of the airflow to the center of rotation; After obtaining the rotation velocity gradient, the rotation momentum index is further calculated to quantify the intensity of the airflow rotation. The calculation expression of the rotation momentum index is: θ =∫ Ω ρr 2 V θ dA, where L θ represents the rotational momentum index of the airflow, ρ is the density of the airflow, which represents the mass distribution of the airflow in the rotating area, Ω represents the integration area, that is, the area where the rotational momentum is calculated, and dA is the differential area element, which is used to represent a small area unit in the area; The airflow rotation reference value is generated according to the rotation speed gradient and the rotation momentum index of the airflow. The expression for generating the airflow rotation reference value is: ， In the formula, R θ is the final generated airflow rotation reference value, which quantifies the rotational motion intensity of the airflow in a certain area of ​​the drying chamber, and ω is the adjustment coefficient, which is used to adjust the relative influence weight of the rotation speed gradient and the rotation momentum index; The airflow rotation reference values ​​of several areas are obtained to establish an analysis set, the airflow rotation reference values ​​in the analysis set are sorted in order, the maximum airflow rotation reference value is screened out, the maximum airflow rotation reference value is recorded as the airflow rotation quantization value, and the maximum rotational motion intensity of the airflow in the drying chamber is quantified by the airflow rotation quantization value.

6. The control method for drying and recycling equipment for plastic particle processing according to claim 4, characterized in that: The specific steps for analyzing the air pressure difference between different positions in the drying chamber and generating a quantitative value of the local pressure difference are as follows: The air pressure data at different positions are collected in real time through the air flow sensors arranged in the drying chamber. Suppose N sensors are arranged in the drying chamber, and the measurement point of each air flow sensor is represented by P. i , where P i Represents the air pressure at the i-th position. The local air pressure gradient vector is calculated by the air pressure difference between adjacent airflow sensors. The calculation expression is: ， In the formula, G i is the pressure gradient vector at the ith position, reflecting the pressure difference between adjacent positions, P i and P i+1 is the air pressure value at the i-th position and the i+1-th position, d i，i+1 is the physical distance between the i-th position and the i+1-th position; The pressure gradient vector is used to construct a rotation field map to reflect the overall rotation characteristics of the pressure gradient. The potential vortex area is detected by the rotation field. The construction expression of the rotation field map is: ， In the formula, R i is the rotation field value of the i-th position, G i ×G i+1 is the cross product of the pressure gradient vectors between the i-th and i+1-th positions, indicating the rotation trend of the region. is the square of the distance between two adjacent positions, which is used to normalize the rotation field strength; According to the calculated pressure gradient vector and rotation field, the local pressure difference quantification value is further generated. The local pressure difference quantification value quantifies the overall pressure difference between different positions in the drying chamber and reflects the correlation between the pressure gradient and the vortex. The generated expression is: In the formula, represents the local pressure difference reference value at the i-th position, quantifying the pressure difference and rotation trend at that position, G ij is the pressure gradient vector between the i-th position and the j-th position, indicating the pressure difference between the two points, R ij is the rotation field value between the i-th position and the j-th position, α and β are |G ij | and R ij The weight coefficients control the influence of the pressure gradient vector and the rotation field on the local pressure difference reference value, LPI θ Represents the maximum value of the local pressure difference reference value among all positions, that is, the local pressure difference quantization value.

7. The control method for drying and recycling equipment for plastic particle processing according to claim 4, characterized in that: The potential vortex occurrence coefficient generated when the pre-trained support vector machine model is used to predict the airflow in the drying chamber is compared with the pre-set reference threshold of the potential vortex occurrence coefficient to identify the potential micro-vortex in the drying chamber. The specific steps are as follows: If the potential eddy current occurrence coefficient is greater than or equal to the potential eddy current occurrence coefficient reference threshold, a potential eddy current signal is generated, indicating that there is a hidden danger of potential tiny eddy currents in the drying chamber at this time; if the potential eddy current occurrence coefficient is less than the potential eddy current occurrence coefficient reference threshold, a high-efficiency drying signal is generated, indicating that there is no hidden danger of potential tiny eddy currents in the drying chamber at this time.

8. The control method for drying and recycling equipment for plastic particle processing according to claim 7, characterized in that: After the support vector machine model preliminarily identifies the existence of potential micro-vortices, the potential micro-vortices are divided into different levels according to their severity. For the potential micro-vortices of different severity levels identified, different types of regulation are performed on the actual thermal air flow rate of the fan. The specific steps are as follows: The generated potential eddy current occurrence coefficient is compared with the potential eddy current occurrence coefficient reference threshold, and the relative coefficient ΔV of the eddy current severity level is calculated. The calculation expression is: In the formula, Poten Vort represents the potential vortex generation coefficient generated when the airflow in the drying chamber is predicted by the pre-trained support vector machine model, V th Indicates the reference threshold value of potential eddy current occurrence coefficient; According to the value of the relative vortex level, the potential micro-vortex situation is divided into different levels, specifically: Set the classification criteria of mild, moderate and severe, and the specific classification expression is:

9. The control method for drying and recycling equipment for plastic particle processing according to claim 8, characterized in that: According to different vortex severity levels, the actual thermal flow rate is adjusted according to the maximum thermal flow rate to control the formation of vortices. The adjustment of the maximum thermal flow rate depends on the severity level of potential micro-vortices. The specific adjustment expression is: V f is the actual thermal flow rate after adjustment, is the maximum thermal airflow rate initially set, K1, K2, and K3 are the adjustment constants of potential micro-eddies at the mild, moderate, and severe levels, respectively, K1>K2>K3, which are used to control the adjustment range of the airflow rate; After the actual hot air flow rate of the fan is initially adjusted, the air flow state is monitored in real time, and the potential vortex generation coefficient generated by the pre-trained support vector machine model is used to adjust the actual hot air flow rate so that the actual hot air flow rate dynamically adapts to the air flow state in the drying chamber. The expression for adjusting the actual hot air flow rate is: ， Where V f (t+1) is the actual thermal flow rate at the next moment, V f (t) is the actual thermal flow rate at the current moment, is the rate of change of the potential eddy current generation coefficient, λ is the feedback adjustment coefficient, which is used to control the feedback adjustment amplitude, Poten Vort (t) represents the potential eddy current occurrence coefficient at the current moment; After multiple feedback adjustments, the actual thermal flow rate is finally determined. The expression for determining the final actual thermal flow rate is: In the formula, is the actual thermal flow rate after final adjustment, The upper limit of safe thermal velocity.

10. A control system for a drying and recycling device for processing plastic particles, used to implement the control method for a drying and recycling device for processing plastic particles as claimed in any one of claims 1 to 9, characterized in that: It includes a fan maximum airflow rate setting module, an airflow data acquisition module, an airflow data analysis and vortex prediction module, a vortex severity level classification module, and a fan hot airflow rate control module; The fan maximum airflow rate setting module sets the maximum hot airflow rate of the fan according to the drying requirements of the plastic particles, and dries the plastic particles at the maximum hot airflow rate; The airflow data acquisition module arranges multiple high-sensitivity airflow sensors at key positions of the drying chamber. The airflow conditions in the drying chamber are collected in real time through all arranged airflow sensors, and the collected data is transmitted to the monitoring system in real time through a high-speed data transmission interface; The airflow data analysis and vortex prediction module extracts features from the data collected by the airflow sensor through the monitoring system. After analyzing the extracted features, it uses a pre-trained support vector machine model to predict the airflow conditions in the drying chamber and identify potential tiny vortices in the drying chamber. The eddy current severity classification module, when the support vector machine model preliminarily identifies the existence of potential micro-eddy currents, divides the potential micro-eddy currents into different levels according to their severity; The fan thermal air flow rate control module performs different types of control on the fan's actual thermal air flow rate according to the identified potential micro-eddies of different severity levels, so as to avoid the actual occurrence of micro-eddies.

Images