Plastic particle deashing method and deashing device

Abstract

The invention discloses a plastic particle ash removal method and an ash removal device, and relates to the technical field related to dust cleaning.The method comprises the steps that plastic particle feature information is collected, plastic particle sampling detection is conducted, and dust feature information is obtained. And optimizing airflow separation parameters for airflow separation dust removal to obtain a plurality of optimized airflow separation parameters. And optimizing electrostatic dust collection parameters for electrostatic dust collection of the plastic particles to obtain a plurality of optimized electrostatic dust collection parameters, and predicting to obtain a plurality of final residual quantities after electrostatic dust collection. And combining the plurality of optimized airflow separation parameters, the plurality of electrostatic neutralization parameters and the plurality of optimized electrostatic dust collection parameters to obtain a plurality of ash removal parameter combinations, and selecting to obtain an optimal ash removal parameter combination according to the plurality of final residual quantities and the combined power consumption of the plurality of ash removal parameter combinations for ash removal. The technical problems that in the prior art, a plastic particle ash removal method is high in ash removal energy consumption, low in ash removal efficiency and poor in ash removal effect are solved.

Description

Technical Field

[0001] This application relates to the field of dust cleaning technology, specifically to a method and device for cleaning plastic particles. Background Technology

[0002] In modern industrial production, plastic granules are a common industrial raw material, and their cleanliness is crucial to product quality. Dust easily adheres to plastic granules during production and storage, affecting their quality and performance. However, existing dust removal technologies, including mechanical vibration, water washing, and chemical cleaning, suffer from low efficiency, high energy consumption, and poor dust removal effects.

[0003] Therefore, existing methods for cleaning plastic granules suffer from high energy consumption, low efficiency, and poor cleaning effect. Summary of the Invention

[0004] This application provides a method and apparatus for cleaning plastic particles, solving the technical problems of high energy consumption, low efficiency, and poor cleaning effect in existing plastic particle cleaning methods. By collecting characteristic information such as particle size and type of plastic particles, as well as characteristic information such as particle size, amount, and material of dust, targeted control parameters for airflow separation cleaning, electrostatic neutralization, and electrostatic dust removal are obtained. The optimal control parameters for energy consumption and cleaning effect are then selected, thereby achieving efficient cleaning of plastic particles, reducing energy consumption in the cleaning process, and improving the cleaning effect.

[0005] This application provides a method for cleaning plastic particles. The method includes: collecting characteristic information of the plastic particles to be cleaned, and sampling and detecting dust on the plastic particles to obtain dust characteristic information, wherein the dust characteristic information includes dust particle size information, dust quantity information, and dust material information. Based on the plastic particle characteristic information and dust characteristic information, the airflow separation parameters for airflow separation dust removal of the plastic particles are optimized to obtain multiple optimized airflow separation parameters, and multiple optimized dust residue amounts and multiple optimized electrostatic quantities are predicted and obtained after airflow separation, wherein the optimization aims to reduce the dust residue amount after airflow separation dust removal, reduce airflow separation energy consumption, and reduce the electrostatic quantity of dust. Based on the multiple optimized electrostatic quantities, multiple electrostatic neutralization parameters for electrostatic neutralization of the plastic particles are analyzed and obtained, and multiple neutralized electrostatic quantities are predicted and obtained after electrostatic neutralization. Based on multiple neutralization electrostatic quantities, multiple optimized dust residue amounts, and plastic particle characteristic information, the electrostatic dust removal parameters for plastic particles are optimized to obtain multiple optimized electrostatic dust removal parameters. Multiple final residue amounts after electrostatic dust removal are predicted, with the optimization aiming to reduce dust residue amounts and energy consumption. The multiple optimized airflow separation parameters, multiple electrostatic neutralization parameters, and multiple optimized electrostatic dust removal parameters are combined to obtain multiple cleaning parameter combinations. Based on the combined power consumption of the multiple final residue amounts and multiple cleaning parameter combinations, the optimal cleaning parameter combination is selected for cleaning.

[0006] In this implementation, the characteristic information of the plastic particles to be cleaned is collected, and the dust on the plastic particles is sampled and detected to obtain dust characteristic information, including: particle size detection of the plastic particles to be cleaned to obtain particle size information as plastic particle characteristic information; sampling detection of dust particle size, dust amount, and dust material of the plastic particles to obtain multiple sample dust particle size information, multiple sample dust amount information, and multiple sample dust material information; and statistical processing based on the multiple sample dust particle size information, multiple sample dust amount information, and multiple sample dust material information to obtain dust particle size information, dust amount information, and dust material information, thus obtaining dust characteristic information.

[0007] In the implementation method, based on the characteristic information of the plastic particles and the characteristic information of the dust, the airflow separation parameters for airflow separation and dust removal of the plastic particles are optimized to obtain multiple optimized airflow separation parameters, including: constructing an airflow separation parameter space based on the airflow separation and dust removal equipment. With the aim of reducing the amount of dust residue after airflow separation and dust removal, reducing airflow separation energy consumption, and reducing the static electricity of the dust, an airflow separation function is constructed as follows: Where ASF stands for airflow adaptability. , and The first dust weight, the first energy consumption weight, and the static electricity weight are respectively represented. This is to predict the amount of dust residue obtained by combining airflow separation parameters with the characteristics of plastic particles and dust. Information on dust quantity The actual power consumption when operating according to the airflow separation parameters. This represents the maximum power consumption of the airflow separation and dust removal equipment. The electrostatic quantity is obtained for predicting airflow separation and dust removal based on airflow separation parameters, combined with characteristics of plastic particles and dust. A preset electrostatic charge is used. Multiple first airflow separation parameters are randomly generated within the airflow separation parameter space. Combined with the plastic particle characteristic information and dust characteristic information, airflow separation dust removal prediction is performed to obtain multiple first dust residue amounts and multiple first electrostatic charges, as well as multiple first airflow separation power consumptions. Multiple first airflow fitness values ​​are calculated. The multiple first airflow separation parameters are updated and iteratively optimized until convergence conditions are met. The multiple airflow separation parameters with the highest final airflow fitness are output, obtaining multiple optimized airflow separation parameters. Multiple optimized dust residue amounts and multiple optimized electrostatic charges predicted based on these optimized airflow separation parameters are also obtained.

[0008] In the implementation, airflow separation and dust removal prediction is performed by combining the characteristic information of the plastic particles and the characteristic information of the dust. This includes: collecting a set of sample plastic particle characteristic information, a set of sample dust characteristic information, a set of sample airflow separation parameters, a set of sample dust residue, and a set of sample electrostatic charge based on the airflow separation and dust removal record data of the plastic particles, as training data for airflow separation prediction. The airflow separation prediction training data is then used to train an airflow separation predictor. The plastic particle characteristic information and dust characteristic information are combined with the multiple first airflow separation parameters and input into the airflow separation predictor for prediction, obtaining multiple first dust residue amounts and multiple first electrostatic charge amounts.

[0009] In the implementation, based on the multiple optimized electrostatic quantities, multiple electrostatic neutralization parameters for electrostatic neutralization of plastic particles are analyzed and obtained, and multiple neutralized electrostatic quantities are predicted and obtained. This includes: collecting a set of sample electrostatic quantities and a set of sample electrostatic neutralization parameters based on historical data of plastic particle electrostatic neutralization; constructing an index table for the set of sample electrostatic quantities and the set of sample electrostatic neutralization parameters, indexing based on the multiple optimized electrostatic quantities to obtain multiple electrostatic neutralization parameters; collecting a set of sample neutralized electrostatic quantities; and training an electrostatic neutralization predictor using the set of sample electrostatic quantities and the set of sample electrostatic neutralization parameters as input and as output to optimize the multiple optimized electrostatic quantities and the multiple electrostatic neutralization parameters to obtain multiple neutralized electrostatic quantities.

[0010] In the implementation method, based on multiple neutralized electrostatic quantities, multiple optimized dust residue quantities, and plastic particle characteristic information, the electrostatic dust removal parameters for electrostatic dust removal of plastic particles are optimized to obtain multiple optimized electrostatic dust removal parameters, including: constructing an electrostatic dust removal parameter space based on the operating parameter range of the electrostatic dust removal equipment. With the aim of reducing the dust residue quantity after electrostatic dust removal and reducing electrostatic dust removal energy consumption, an electrostatic dust removal function is constructed, as follows: Where EDR stands for electrostatic adaptability. and The second dust weight and the second energy consumption weight are respectively represented. To predict the final dust residue level in electrostatic precipitator analysis based on electrostatic precipitator parameters, neutralized static electricity, optimized dust residue level, plastic particle characteristics, and dust characteristics. To optimize dust residue levels, The actual power consumption is based on the electrostatic precipitator parameters. The maximum power consumption of the electrostatic precipitator is defined as follows: Multiple first electrostatic precipitator parameters are randomly generated within the electrostatic precipitator parameter space. These parameters are then combined with multiple neutralized static electricity values, multiple dust residue values, and information on plastic particle characteristics, dust particle size, and dust material to predict the final dust residue values. Multiple first electrostatic precipitator power consumption values ​​for these parameters are obtained, and combined with the final dust residue values, multiple first electrostatic fitness values ​​are calculated. The multiple first electrostatic precipitator parameters are continuously updated and iterated until convergence, resulting in multiple optimized electrostatic precipitator parameters with the highest electrostatic fitness values. Finally, multiple final residue values ​​predicted based on these optimized electrostatic precipitator parameters are obtained.

[0011] In the implementation method, multiple optimized airflow separation parameters, multiple electrostatic neutralization parameters, and multiple optimized electrostatic dust removal parameters are combined to obtain multiple dust removal parameter combinations. The optimal dust removal parameter combination is selected based on multiple final residue levels and the combined power consumption of the multiple dust removal parameter combinations. This includes: combining the multiple optimized airflow separation parameters, multiple electrostatic neutralization parameters, and multiple optimized electrostatic dust removal parameters accordingly to obtain multiple dust removal parameter combinations; obtaining multiple combined power consumption values ​​for the multiple dust removal parameter combinations and calculating multiple combined power consumption scores; calculating multiple combined dust removal scores based on the multiple final residue levels; calculating multiple combined dust removal scores based on the multiple combined power consumption scores and multiple combined dust removal scores; and selecting the dust removal parameter combination with the highest combined dust removal score to obtain the optimal dust removal parameter combination.

[0012] This application also provides a plastic particle dust removal device, comprising: a feature information acquisition module, used to collect plastic particle feature information of the plastic particles to be cleaned, and to sample and detect dust on the plastic particles to obtain dust feature information, wherein the dust feature information includes dust particle size information, dust quantity information, and dust material information; an airflow separation parameter acquisition module, used to optimize the airflow separation parameters for airflow separation dust removal of plastic particles based on the plastic particle feature information and dust feature information, to obtain multiple optimized airflow separation parameters, and to predict and obtain multiple optimized dust residue amounts and multiple optimized electrostatic quantities after airflow separation, wherein the optimization aims to reduce the dust residue amount after airflow separation dust removal, reduce airflow separation energy consumption, and reduce the electrostatic quantity of dust; and a neutralization parameter acquisition module, used to analyze and obtain multiple electrostatic neutralization parameters for electrostatic neutralization of plastic particles based on the multiple optimized electrostatic quantities, and to predict and obtain multiple neutralized electrostatic quantities after electrostatic neutralization. The electrostatic precipitator parameter acquisition module optimizes the electrostatic precipitator parameters for plastic particles based on multiple neutralization electrostatic quantities, multiple optimized dust residue amounts, and plastic particle characteristic information. It obtains multiple optimized electrostatic precipitator parameters and predicts multiple final residue amounts after electrostatic precipitator treatment, with the aim of reducing dust residue and energy consumption. The dust removal parameter acquisition module combines the multiple optimized airflow separation parameters, multiple electrostatic neutralization parameters, and multiple optimized electrostatic precipitator parameters to obtain multiple dust removal parameter combinations. Based on the multiple final residue amounts and the combined power consumption of the multiple dust removal parameter combinations, it selects the optimal dust removal parameter combination for dust removal.

[0013] This application proposes a method and apparatus for cleaning plastic particles. The method involves collecting and sampling characteristic information of the plastic particles to obtain dust characteristic information. Airflow separation parameters for dust removal are optimized to obtain multiple optimized airflow separation parameters. Electrostatic dust removal parameters for the plastic particles are also optimized to obtain multiple optimized electrostatic dust removal parameters, and multiple final residual amounts after electrostatic dust removal are predicted. These multiple optimized airflow separation parameters, multiple electrostatic neutralization parameters, and multiple optimized electrostatic dust removal parameters are combined to obtain multiple cleaning parameter combinations. Based on the combined power consumption of the multiple final residual amounts and multiple cleaning parameter combinations, the optimal cleaning parameter combination is selected for cleaning. This method solves the technical problems of high cleaning energy consumption, low cleaning efficiency, and poor cleaning effect in existing plastic particle cleaning methods. By collecting characteristic information such as particle size and type of plastic particles, as well as characteristic information such as particle size, amount and material of dust, the control parameters for airflow separation cleaning, electrostatic neutralization and electrostatic dust removal are obtained in a targeted manner. The control parameters with the best energy consumption and cleaning effect are then obtained, thereby achieving efficient cleaning of plastic particles, reducing energy consumption in the cleaning process and improving the technical effect of cleaning. Attached Figure Description

[0014] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings of the embodiments of this disclosure will be briefly described below. Flowcharts are used in this application to illustrate the operations performed by the apparatus according to the embodiments of this application. It should be understood that the preceding or following operations are not necessarily performed precisely in sequence. Instead, various steps can be processed in reverse order or simultaneously as needed. Furthermore, other operations can be added to these processes, or one or more steps can be removed from these processes.

[0015] Figure 1 A schematic flowchart illustrating a method for cleaning plastic particles provided in an embodiment of this application; Figure 2 This is a schematic diagram of a plastic particle cleaning device provided in an embodiment of this application.

[0016] Explanation of reference numerals in the attached figures: Feature information acquisition module 11, airflow separation parameter acquisition module 12, neutralization parameter acquisition module 13, electrostatic dust removal parameter acquisition module 14, and dust removal parameter acquisition module 15. Detailed Implementation

[0017] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, specific embodiments of this application are given below.

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description of this application will be provided in conjunction with the accompanying drawings. The described embodiments should not be considered as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0019] In the following description, references to "some embodiments" describe a subset of all possible embodiments. However, it is understood that "some embodiments" can be the same or different subsets of all possible embodiments and can be combined with each other without conflict. The terms "first" and "second" are used merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules not explicitly listed or inherent to these processes, methods, products, or apparatuses. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only.

[0020] This application provides a method and apparatus for cleaning plastic granules, such as... Figure 1 As shown, the method includes: Collect the characteristic information of the plastic particles to be cleaned, and sample and detect the dust on the plastic particles to obtain dust characteristic information, which includes dust particle size information, dust amount information and dust material information.

[0021] Based on the plastic particle characteristic information and dust characteristic information, the airflow separation parameters for airflow separation and dust removal of plastic particles are optimized to obtain multiple optimized airflow separation parameters. Multiple optimized dust residue amounts and multiple optimized electrostatic amounts are predicted and obtained after airflow separation. The optimization aims to reduce the dust residue amount after airflow separation and dust removal, reduce airflow separation energy consumption, and reduce the electrostatic amount of dust.

[0022] Based on the multiple optimized electrostatic quantities, multiple electrostatic neutralization parameters for electrostatic neutralization of plastic particles are analyzed and obtained, and multiple neutralized electrostatic quantities are predicted and obtained after electrostatic neutralization.

[0023] Plastic granules undergo grinding during production, generating dust. Environmental dust also exists in the production environment. This dust adheres to the surface of the plastic granules under static electricity, affecting their usability. The dust removal process includes airflow separation cleaning. Since airflow separation affects the static charge of the dust, static neutralization and electrostatic dust removal are performed after airflow separation cleaning. To achieve efficient dust removal of the plastic granules, the characteristic information of the plastic granules to be cleaned is collected, including particle size, particle type, and other characteristic parameters. Dust on the plastic granules is sampled and detected; dust adhering to the sample plastic granules is analyzed to obtain dust characteristic information, including dust particle size, dust quantity, and dust material information. Further, airflow separation dust removal is performed. Airflow separation dust removal is a technology that uses aerodynamic principles to remove dust from gas. During airflow separation dust removal, corresponding airflow separation parameters need to be set according to the specific characteristics of the dust. Based on the characteristic information of the plastic particles and dust, the airflow separation parameters for airflow separation and dust removal of the plastic particles are optimized to obtain multiple optimized airflow separation parameters. Multiple optimized dust residue amounts and multiple optimized electrostatic charges after airflow separation are predicted using an airflow separation predictor. The optimization aims to reduce the dust residue amount, reduce airflow separation energy consumption, and reduce the electrostatic charge of the dust after airflow separation and dust removal. Furthermore, based on the multiple optimized electrostatic charges, multiple electrostatic neutralization parameters for electrostatic neutralization of the plastic particles are analyzed and obtained. Finally, based on an electrostatic neutralization predictor, multiple neutralized electrostatic charges after electrostatic neutralization are predicted and obtained.

[0024] The method provided in this application embodiment also includes: The particle size of the plastic granules to be cleaned is measured to obtain particle size information, which is used as the characteristic information of the plastic granules.

[0025] The particle size, amount, and material of dust in plastic granules were sampled and tested to obtain information on the particle size, amount, and material of dust from multiple samples.

[0026] Based on the dust particle size information, dust quantity information, and dust material information of the multiple samples, statistical processing is performed to obtain dust particle size information, dust quantity information, and dust material information, thereby obtaining dust characteristic information.

[0027] The process involves collecting characteristic information of the plastic particles to be cleaned, and sampling and detecting dust on the plastic particles to obtain dust characteristic information. This includes particle size detection of the plastic particles to be cleaned, obtaining particle size information as characteristic information of the plastic particles. The particle size information reflects the size of the plastic particles, which is helpful for setting airflow separation parameters in subsequent airflow separation. Further, the sampled plastic particles are tested for dust particle size, dust quantity, and dust material, obtaining dust particle size information, dust quantity information, and dust material information for multiple plastic particle samples. Each sample information corresponds to one plastic particle sample. The obtained dust particle size information, dust quantity information, and dust material information are statistically analyzed to obtain the mode results among the multiple sample information, namely the mode of dust particle size information, the mode of dust quantity information, and the mode of dust material information. Since the mode is the value that appears most frequently in a set of data, it has good representativeness of the overall sample; therefore, the obtained mode results are used as dust characteristic information.

[0028] The method provided in this application embodiment also includes: Based on the airflow separation dust removal equipment, an airflow separation parameter space is constructed.

[0029] To reduce the amount of dust residue after airflow separation dust removal, reduce the energy consumption of airflow separation, and reduce the static electricity of dust, an airflow separation function is constructed as follows: .

[0030] Where ASF stands for airflow adaptability. , and The first dust weight, the first energy consumption weight, and the static electricity weight are respectively represented. This is to predict the amount of dust residue obtained by combining airflow separation parameters with the characteristics of plastic particles and dust. Information on dust quantity The actual power consumption when operating according to the airflow separation parameters. This represents the maximum power consumption of the airflow separation and dust removal equipment. The electrostatic quantity is obtained for predicting airflow separation and dust removal based on airflow separation parameters, combined with characteristics of plastic particles and dust. This is the preset static electricity level.

[0031] Multiple first airflow separation parameters are randomly generated within the airflow separation parameter space. Combined with the plastic particle characteristic information and dust characteristic information, airflow separation dust removal prediction is performed to obtain multiple first dust residue amounts and multiple first electrostatic quantities, as well as multiple first airflow separation power consumption, and multiple first airflow adaptability is calculated.

[0032] Multiple first airflow separation parameters are updated and iterated until the convergence condition is met. The multiple airflow separation parameters with the largest final airflow fitness are output to obtain multiple optimized airflow separation parameters. Multiple optimized dust residue and multiple optimized electrostatic quantities are obtained based on the prediction of the multiple optimized airflow separation parameters.

[0033] Multiple optimized airflow separation parameters are obtained, including: constructing an airflow separation parameter space based on the airflow separation dust removal equipment. This airflow separation parameter space is a parameter control range composed of the control parameters of the airflow separation dust removal equipment, where the control parameter range includes the adjustment ranges of control parameters such as airflow velocity, temperature, and humidity. With the aim of reducing the amount of dust residue after airflow separation dust removal, reducing airflow separation energy consumption, and reducing the static electricity of the dust, an airflow separation function is constructed as follows: Here, ASF stands for Airflow Fit; the higher the Airflow Fit, the better the control effect of the corresponding control parameters. , and These represent the first dust weight, the first energy consumption weight, and the electrostatic weight, respectively. The specific weight parameters can be set based on actual dust removal preferences. This is to predict the amount of dust residue obtained by combining airflow separation parameters with the characteristics of plastic particles and dust. Information on dust quantity The actual power consumption when operating according to the airflow separation parameters. This represents the maximum power consumption of the airflow separation and dust removal equipment. The electrostatic quantity is obtained for predicting airflow separation and dust removal based on airflow separation parameters, combined with characteristics of plastic particles and dust. The preset electrostatic charge is the average electrostatic charge of dust that has not been removed. This charge can be obtained by measuring the flight time of charged dust particles in a known electric field.

[0034] Multiple sets of airflow separation parameters are randomly extracted within the airflow separation parameter space. Each set of airflow separation parameters includes all control parameters, generating multiple first airflow separation parameters. Combining the plastic particle feature information and dust feature information, airflow separation dust removal prediction is performed based on the airflow separation predictor. The airflow separation predictor is constructed based on a neural network model to obtain multiple first dust residue amounts and multiple first electrostatic quantities, and to obtain the first airflow separation power consumption corresponding to the multiple first airflow separation parameters. Based on the obtained first dust residue amounts, first electrostatic quantities, and first airflow separation power consumption, the airflow separation function is input to calculate multiple first airflow fitness values. Finally, multiple first airflow separation parameters are updated and iterated for optimization. Each first airflow separation parameter is an independent iterative optimization object. The multiple first airflow separation parameters are independently optimized during the iterative optimization until convergence. The convergence adjustment is to reach a preset number of iterations. The iteration process is to continuously acquire new airflow separation parameters in the airflow separation parameter space and calculate their fitness. The fitness of the parameters is compared with that of the original parameters. The airflow separation parameters with larger fitness are retained until the convergence condition is met. The multiple airflow separation parameters with the largest final airflow fitness are output to obtain multiple optimized airflow separation parameters. Multiple optimized dust residue and multiple optimized electrostatic quantities are also obtained based on the prediction of the multiple optimized airflow separation parameters.

[0035] The method provided in this application embodiment also includes: Based on the airflow separation and dust removal record data of plastic particles, a set of sample plastic particle characteristic information, a set of sample dust characteristic information, a set of sample airflow separation parameters, a set of sample dust residue, and a set of sample electrostatic quantity are collected as training data for airflow separation prediction.

[0036] The airflow separation prediction training data is used to train the airflow separation predictor.

[0037] The plastic particle characteristic information and dust characteristic information are combined with the multiple first airflow separation parameters and input into the airflow separation predictor for prediction to obtain multiple first dust residue amounts and multiple first static electricity amounts.

[0038] Combining the characteristics of the plastic particles and dust, airflow separation dust removal prediction is performed, including: Based on airflow separation dust removal record data for plastic particles, which contains a large amount of dust removal data recorded during historical dust removal processes, including sample plastic particle characteristics, sample dust characteristics, sample airflow separation parameters, sample dust residue, and sample electrostatic charge. A set of sample plastic particle characteristic information, a set of sample dust characteristic information, a set of sample airflow separation parameters, a set of sample dust residue, and a set of sample electrostatic charge are collected and used as training data for airflow separation prediction. Based on this training data, a neural network model is supervisedly trained using the sample plastic particle characteristic information, sample dust characteristic information, and sample airflow separation parameter set as input data, and the sample dust residue and electrostatic charge set as output data. Training is completed when the model's final output meets the fool's accuracy, thus obtaining an airflow separation predictor. The airflow separation predictor can obtain corresponding dust residue and electrostatic charge output data based on the plastic particle characteristic information, dust characteristic information, and airflow separation parameters. Finally, the plastic particle characteristic information and dust characteristic information are combined with the multiple first airflow separation parameters and input into the airflow separation predictor for prediction to obtain multiple first dust residue amounts and multiple first electrostatic quantities.

[0039] The method provided in this application embodiment also includes: Based on historical data on the electrostatic neutralization of plastic particles, a set of sample electrostatic quantities and a set of sample electrostatic neutralization parameters were collected.

[0040] An index table is constructed for the set of sample electrostatic quantities and the set of sample electrostatic neutralization parameters. Based on the multiple optimized electrostatic quantities, multiple electrostatic neutralization parameters are obtained.

[0041] Collect the set of neutralized static electricity in the sample after static electricity neutralization.

[0042] Using the sample electrostatic quantity set and the sample electrostatic neutralization parameter set as inputs, and the sample neutralized electrostatic quantity set as outputs, an electrostatic neutralization predictor is trained to optimize the multiple optimized electrostatic quantities and multiple electrostatic neutralization parameters to obtain multiple neutralized electrostatic quantities.

[0043] Based on historical data on the electrostatic neutralization of plastic particles, a set of sample electrostatic quantities and a set of sample electrostatic neutralization parameters are collected. Since airflow separation and dust removal can introduce a certain charge into the plastic particles, electrostatic neutralization is necessary to restore or reduce their electrostatic quantity. The historical data on electrostatic neutralization of plastic particles consists of records of the electrostatic quantity and corresponding neutralization parameters from previous neutralization processes. An index table for the set of sample electrostatic quantities and the set of sample electrostatic neutralization parameters is constructed. Based on the multiple optimized electrostatic quantities, multiple corresponding electrostatic neutralization parameters are obtained. These parameters are used to control the electrostatic neutralization operation. A set of neutralized sample electrostatic quantities is collected, representing the sample electrostatic quantities after neutralization. Using the set of sample electrostatic quantities and the set of sample electrostatic neutralization parameters as input and as output, a supervised training of a neural network model is performed until the model output meets a preset accuracy, thus obtaining a trained electrostatic neutralization predictor. Based on the electrostatic neutralization predictor, the multiple optimized electrostatic quantities and multiple electrostatic neutralization parameters are optimized to obtain multiple neutralized electrostatic quantities, wherein the neutralized electrostatic quantity is the predicted remaining electrostatic quantity of the plastic particles after electrostatic neutralization is completed.

[0044] Based on multiple neutralized static electricity values, multiple optimized dust residue values, and plastic particle characteristic information, the electrostatic dust removal parameters for electrostatic dust removal of plastic particles are optimized to obtain multiple optimized electrostatic dust removal parameters, and multiple final residue values ​​after electrostatic dust removal are predicted. Among them, the optimization aims to reduce the dust residue value after electrostatic dust removal and reduce the energy consumption of electrostatic dust removal.

[0045] The multiple optimized airflow separation parameters, multiple electrostatic neutralization parameters, and multiple optimized electrostatic dust removal parameters are combined to obtain multiple dust removal parameter combinations. Based on the multiple final residual amounts and the combined power consumption of the multiple dust removal parameter combinations, the optimal dust removal parameter combination is selected for dust removal.

[0046] Based on multiple neutralization electrostatic quantities, multiple optimized dust residue quantities, and plastic particle characteristic information, the electrostatic dust removal parameters for plastic particles are optimized, resulting in multiple optimized electrostatic dust removal parameters. Multiple final residue quantities after electrostatic dust removal are predicted, with optimization aimed at reducing dust residue quantities and energy consumption. The multiple optimized airflow separation parameters, multiple electrostatic neutralization parameters, and multiple optimized electrostatic dust removal parameters are combined accordingly, with each combination including optimized airflow separation parameters, electrostatic neutralization parameters, and optimized electrostatic dust removal parameters, resulting in multiple dust removal parameter combinations. Based on these multiple dust removal parameter combinations, the corresponding final residue quantities and combined power consumption of the dust removal parameter combinations are obtained. A scoring system is used to select the dust removal parameter combination with the optimal score, and dust removal is then performed, thus achieving the acquisition of the optimal dust removal parameter combination. This solves the technical problems of high dust removal energy consumption, low dust removal efficiency, and poor dust removal effect in existing plastic particle dust removal methods. By collecting characteristic information such as particle size and type of plastic particles, as well as characteristic information such as particle size, amount and material of dust, the control parameters for airflow separation cleaning, electrostatic neutralization and electrostatic dust removal are obtained in a targeted manner. The control parameters with the best energy consumption and cleaning effect are then obtained, thereby achieving efficient cleaning of plastic particles, reducing energy consumption in the cleaning process and improving the technical effect of cleaning.

[0047] The method provided in this application embodiment also includes: Based on the operating parameter range of the electrostatic precipitator, an electrostatic precipitator parameter space is constructed.

[0048] To reduce the amount of dust residue after electrostatic precipitator cleaning and to reduce the energy consumption of electrostatic precipitator cleaning, an electrostatic precipitator function is constructed as follows: .

[0049] Wherein, EDR stands for electrostatic fitness. and The second dust weight and the second energy consumption weight are respectively represented. To predict the final dust residue level in electrostatic precipitator analysis based on electrostatic precipitator parameters, neutralized static electricity, optimized dust residue level, plastic particle characteristics, and dust characteristics. To optimize dust residue levels, The actual power consumption is based on the electrostatic precipitator parameters. This represents the maximum power consumption of the electrostatic precipitator.

[0050] Multiple first electrostatic dust removal parameters are randomly generated within the electrostatic dust removal parameter space. These parameters are then combined with the multiple neutralized static electricity values, multiple dust residue values, and the plastic particle characteristic information, dust particle size information, and dust material information to perform electrostatic dust removal prediction and obtain multiple final dust residue values.

[0051] Multiple first electrostatic dust removal power consumptions of multiple first electrostatic dust removal parameters are obtained, and multiple first electrostatic fitness values ​​are calculated by combining the multiple final dust residue amounts.

[0052] The multiple first electrostatic dust removal parameters are continuously updated and iterated until convergence is achieved, resulting in multiple optimized electrostatic dust removal parameters with the highest electrostatic fitness, and multiple final residual amounts predicted based on the multiple optimized electrostatic dust removal parameters.

[0053] Based on the operating parameter range of the electrostatic precipitator, an electrostatic precipitator parameter space is constructed. This parameter space is built upon the control range of the operating parameters of the electrostatic precipitator. With the aim of reducing the amount of dust residue after electrostatic precipitator removal and reducing energy consumption, an electrostatic precipitator function is constructed as follows: .

[0054] Wherein, EDR stands for electrostatic fitness. and These represent the second dust weight and the second energy consumption weight, respectively. The specific weight parameters can be set based on actual conditions. To predict the final dust residue level in electrostatic precipitator analysis based on electrostatic precipitator parameters, neutralized static electricity, optimized dust residue level, plastic particle characteristics, and dust characteristics. To optimize dust residue levels, The actual power consumption is based on the electrostatic precipitator parameters. This represents the maximum power consumption of the electrostatic precipitator. Multiple first electrostatic precipitator parameters are randomly generated within the electrostatic precipitator parameter space, each being a set of parameters randomly obtained from that space. Combining the multiple neutralized static electricity values, multiple dust residue values, and the plastic particle characteristic information, dust particle size information, and dust material information, electrostatic precipitator prediction is performed to predict the amount of dust residue remaining on the plastic particles after electrostatic precipitator removal, thus obtaining multiple final dust residue values. Before performing electrostatic precipitator prediction, an electrostatic precipitator prediction model needs to be constructed. This model is built based on a neural network model, and the construction data consists of historical data of neutralized static electricity values, historical data of dust residue values, electrostatic precipitator parameters, and corresponding plastic particle characteristic information, dust particle size information, and dust material information. Supervised training is performed based on this historical data to construct the electrostatic precipitator prediction model. The electrostatic precipitator prediction model can obtain the final dust residue value based on the current neutralized static electricity value and electrostatic precipitator parameters, considering the same type of plastic particle characteristic information, dust particle size information, and dust material information. Multiple first electrostatic dust removal parameters are obtained, representing the energy consumption of electrostatic dust removal. Combined with the multiple final dust residue amounts, multiple first electrostatic fitness values ​​are calculated, where a higher fitness value corresponds to a better electrostatic dust removal effect. The multiple first electrostatic dust removal parameters are then continuously updated and iterated for optimization. Each first electrostatic dust removal parameter is an iterative optimization object, and the iterations are independent until convergence. The convergence is adjusted to reach a preset number of iterations. The iteration process involves continuously acquiring new electrostatic dust removal parameters within the electrostatic dust removal parameter space and calculating their fitness. These fitness values ​​are compared with the original parameters, and the parameters with higher fitness values ​​are retained until convergence. This process yields multiple optimized electrostatic dust removal parameters with the highest electrostatic fitness, and multiple final residue amounts predicted based on these optimized electrostatic dust removal parameters are obtained.

[0055] The method provided in this application embodiment also includes: Multiple combinations of optimized airflow separation parameters, multiple electrostatic neutralization parameters, and multiple optimized electrostatic dust removal parameters are obtained by combining them accordingly.

[0056] The combined power consumption of the multiple dust removal parameter combinations is obtained, and multiple combined power consumption scores are calculated.

[0057] Based on the multiple final residual amounts, multiple combined dust removal scores are calculated.

[0058] Based on the multiple combined power consumption scores and multiple combined dust removal scores, multiple dust removal combination scores are calculated, and the dust removal parameter combination with the highest dust removal combination score is selected to obtain the optimal dust removal parameter combination.

[0059] Multiple optimized airflow separation parameters, multiple electrostatic neutralization parameters, and multiple optimized electrostatic dust removal parameters are combined to obtain multiple dust removal parameter combinations. Each dust removal parameter combination includes optimized airflow separation parameters, electrostatic neutralization parameters, and optimized electrostatic dust removal parameters. A pre-set scoring comparison parameter database is used, containing corresponding scoring data for the energy consumption of different airflow dust removal, electrostatic neutralization, and electrostatic dust removal processes, as well as the final residual amount parameters and their corresponding scoring data. Multiple combined power consumption values ​​of the multiple dust removal parameter combinations are obtained, and scores are obtained based on the scoring comparison parameter database. The scores are summed to obtain multiple combined power consumption scores. Based on the multiple final residual amounts, multiple combined dust removal scores are obtained based on the scoring comparison parameter database. The multiple combined power consumption scores and combined dust removal scores are summed to calculate multiple combined dust removal scores. The dust removal parameter combination with the highest combined dust removal score is selected as the optimal dust removal parameter combination.

[0060] In the above text, refer to Figure 1 A method for cleaning plastic particles according to an embodiment of the present invention has been described in detail. Next, reference will be made to... Figure 2 A plastic particle cleaning device according to an embodiment of the present invention is described.

[0061] A plastic particle cleaning device according to an embodiment of the present invention solves the technical problems of high energy consumption, low efficiency, and poor cleaning effect in existing plastic particle cleaning methods. By collecting characteristic information such as particle size and type of plastic particles, and characteristic information such as particle size, amount, and material of dust, control parameters for airflow separation cleaning, electrostatic neutralization, and electrostatic dust removal are specifically obtained. The device then identifies the control parameters that provide the best energy consumption and cleaning effect, thereby achieving efficient cleaning of plastic particles, reducing energy consumption in the cleaning process, and improving the cleaning effect. The plastic particle cleaning device includes: a characteristic information acquisition module 11, an airflow separation parameter acquisition module 12, a neutralization parameter acquisition module 13, an electrostatic dust removal parameter acquisition module 14, and a cleaning parameter acquisition module 15.

[0062] The feature information acquisition module 11 is used to collect the feature information of the plastic particles to be cleaned, and to sample and detect the dust on the plastic particles to obtain dust feature information, wherein the dust feature information includes dust particle size information, dust amount information and dust material information.

[0063] The airflow separation parameter acquisition module 12 is used to optimize the airflow separation parameters for airflow separation and dust removal of plastic particles based on the plastic particle characteristic information and dust characteristic information, obtain multiple optimized airflow separation parameters, and predict and obtain multiple optimized dust residue amounts and multiple optimized electrostatic amounts after airflow separation. The optimization aims to reduce the dust residue amount after airflow separation and dust removal, reduce airflow separation energy consumption, and reduce the electrostatic amount of dust.

[0064] The neutralization parameter acquisition module 13 is used to analyze and acquire multiple electrostatic neutralization parameters for electrostatic neutralization of plastic particles based on the multiple optimized electrostatic quantities, and to predict and acquire multiple neutralized electrostatic quantities after electrostatic neutralization.

[0065] The electrostatic dust removal parameter acquisition module 14 is used to optimize the electrostatic dust removal parameters of plastic particles based on multiple neutralized static electricity amounts, multiple optimized dust residue amounts, and plastic particle characteristic information, to obtain multiple optimized electrostatic dust removal parameters, and to predict multiple final residue amounts after electrostatic dust removal. Among these, the optimization aims to reduce the dust residue amount after electrostatic dust removal and reduce the energy consumption of electrostatic dust removal.

[0066] The dust removal parameter acquisition module 15 is used to combine the multiple optimized airflow separation parameters, multiple electrostatic neutralization parameters and multiple optimized electrostatic dust removal parameters to obtain multiple dust removal parameter combinations, and select the optimal dust removal parameter combination based on the multiple final residual amounts and the combined power consumption of the multiple dust removal parameter combinations for dust removal.

[0067] The specific configuration of the feature information acquisition module 11 will be described in detail below. The feature information acquisition module 11 may further include: collecting the feature information of the plastic particles to be cleaned, and sampling and detecting the dust on the plastic particles to obtain dust feature information, including: detecting the particle size of the plastic particles to be cleaned to obtain particle size information as plastic particle feature information; sampling and detecting the dust particle size, dust quantity, and dust material of the plastic particles to obtain multiple sample dust particle size information, multiple sample dust quantity information, and multiple sample dust material information; and statistically processing the multiple sample dust particle size information, multiple sample dust quantity information, and multiple sample dust material information to obtain dust particle size information, dust quantity information, and dust material information, thereby obtaining dust feature information.

[0068] The specific configuration of the airflow separation parameter acquisition module 12 will be described in detail below. The airflow separation parameter acquisition module 12 further includes: optimizing the airflow separation parameters for airflow separation and dust removal of plastic particles based on the plastic particle characteristic information and dust characteristic information, obtaining multiple optimized airflow separation parameters, including: constructing an airflow separation parameter space based on the airflow separation and dust removal equipment. With the aim of reducing the amount of dust residue after airflow separation and dust removal, reducing airflow separation energy consumption, and reducing the static electricity of the dust, an airflow separation function is constructed as follows: Where ASF stands for airflow adaptability. , and The first dust weight, the first energy consumption weight, and the static electricity weight are respectively represented. This is to predict the amount of dust residue obtained by combining airflow separation parameters with the characteristics of plastic particles and dust. Information on dust quantity The actual power consumption when operating according to the airflow separation parameters. This represents the maximum power consumption of the airflow separation and dust removal equipment. The electrostatic quantity is obtained for predicting airflow separation and dust removal based on airflow separation parameters, combined with characteristics of plastic particles and dust. A preset electrostatic charge is used. Multiple first airflow separation parameters are randomly generated within the airflow separation parameter space. Combined with the plastic particle characteristic information and dust characteristic information, airflow separation dust removal prediction is performed to obtain multiple first dust residue amounts and multiple first electrostatic charges, as well as multiple first airflow separation power consumptions. Multiple first airflow fitness values ​​are calculated. The multiple first airflow separation parameters are updated and iteratively optimized until convergence conditions are met. The multiple airflow separation parameters with the highest final airflow fitness are output, obtaining multiple optimized airflow separation parameters. Multiple optimized dust residue amounts and multiple optimized electrostatic charges predicted based on these optimized airflow separation parameters are also obtained.

[0069] The specific configuration of the airflow separation parameter acquisition module 12 will be described in detail below. The airflow separation parameter acquisition module 12 further includes: combining the plastic particle feature information and dust feature information to perform airflow separation dust removal prediction, including: collecting a set of sample plastic particle feature information, a set of sample dust feature information, a set of sample airflow separation parameters, a set of sample dust residue, and a set of sample electrostatic charge based on the airflow separation dust removal record data of the plastic particles, as airflow separation prediction training data. The airflow separation predictor is trained using the airflow separation prediction training data. The plastic particle feature information and dust feature information are combined with the multiple first airflow separation parameters and input into the airflow separation predictor for prediction to obtain multiple first dust residue amounts and multiple first electrostatic charge amounts.

[0070] The specific configuration of the neutralization parameter acquisition module 13 will be described in detail below. The neutralization parameter acquisition module 13 may further include: analyzing and acquiring multiple electrostatic neutralization parameters for electrostatic neutralization of plastic particles based on the multiple optimized electrostatic quantities, and predicting and acquiring multiple neutralized electrostatic quantities after electrostatic neutralization, including: collecting a sample electrostatic quantity set and a sample electrostatic neutralization parameter set based on historical data of plastic particle electrostatic neutralization; constructing an index table for the sample electrostatic quantity set and the sample electrostatic neutralization parameter set, indexing based on the multiple optimized electrostatic quantities to obtain multiple electrostatic neutralization parameters; collecting a sample neutralized electrostatic quantity set after electrostatic neutralization; using the sample electrostatic quantity set and the sample electrostatic neutralization parameter set as input and the sample neutralized electrostatic quantity set as output, training an electrostatic neutralization predictor to optimize the multiple optimized electrostatic quantities and the multiple electrostatic neutralization parameters to obtain multiple neutralized electrostatic quantities.

[0071] The specific configuration of the dust removal parameter acquisition module 15 will be described in detail below. The dust removal parameter acquisition module 15 further includes: optimizing the electrostatic dust removal parameters for electrostatic dust removal of plastic particles based on multiple neutralized static electricity values, multiple optimized dust residue values, and plastic particle characteristic information, to obtain multiple optimized electrostatic dust removal parameters, including: constructing an electrostatic dust removal parameter space based on the operating parameter range of the electrostatic dust removal equipment. With the aim of reducing the dust residue after electrostatic dust removal and reducing electrostatic dust removal energy consumption, an electrostatic dust removal function is constructed as follows: Where EDR stands for electrostatic adaptability. and The second dust weight and the second energy consumption weight are respectively represented. To predict the final dust residue level in electrostatic precipitator analysis based on electrostatic precipitator parameters, neutralized static electricity, optimized dust residue level, plastic particle characteristics, and dust characteristics. To optimize dust residue levels, The actual power consumption is based on the electrostatic precipitator parameters. The maximum power consumption of the electrostatic precipitator is defined as follows: Multiple first electrostatic precipitator parameters are randomly generated within the electrostatic precipitator parameter space. These parameters are then combined with multiple neutralized static electricity values, multiple dust residue values, and information on plastic particle characteristics, dust particle size, and dust material to predict the final dust residue values. Multiple first electrostatic precipitator power consumption values ​​for these parameters are obtained, and combined with the final dust residue values, multiple first electrostatic fitness values ​​are calculated. The multiple first electrostatic precipitator parameters are continuously updated and iterated until convergence, resulting in multiple optimized electrostatic precipitator parameters with the highest electrostatic fitness values. Finally, multiple final residue values ​​predicted based on these optimized electrostatic precipitator parameters are obtained.

[0072] The specific configuration of the dust removal parameter acquisition module 15 will be described in detail below. The dust removal parameter acquisition module 15 further includes: combining the multiple optimized airflow separation parameters, multiple electrostatic neutralization parameters, and multiple optimized electrostatic dust removal parameters to obtain multiple dust removal parameter combinations; and selecting the optimal dust removal parameter combination based on multiple final residual amounts and the combined power consumption of the multiple dust removal parameter combinations. This includes: correspondingly combining the multiple optimized airflow separation parameters, multiple electrostatic neutralization parameters, and multiple optimized electrostatic dust removal parameters to obtain multiple dust removal parameter combinations; acquiring multiple combined power consumption of the multiple dust removal parameter combinations and calculating multiple combined power consumption scores; calculating multiple combined dust removal scores based on the multiple final residual amounts; calculating multiple combined dust removal combination scores based on the multiple combined power consumption scores and multiple combined dust removal scores; and selecting the dust removal parameter combination with the highest combined dust removal combination score to obtain the optimal dust removal parameter combination.

[0073] The plastic particle cleaning device provided in this embodiment of the invention can perform a plastic particle cleaning method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0074] While this application makes various references to certain modules in the apparatus according to embodiments of this application, any number of different modules can be used and run on user terminals and / or servers. The various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved. In addition, the specific names of each functional unit are only for easy distinction and are not intended to limit the scope of protection of this invention.

[0075] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method of dedusting plastic particles, characterized by, The method comprises: Collecting plastic particle characteristic information of plastic particles to be dedusted, and sampling and detecting dust on the plastic particles to obtain dust characteristic information, wherein the dust characteristic information comprises dust particle size information, dust amount information and dust material information; According to the plastic particle characteristic information and the dust characteristic information, optimizing airflow separation parameters of the plastic particles in airflow separation and dedusting to obtain a plurality of optimized airflow separation parameters, and predicting a plurality of optimized dust residual amounts and a plurality of optimized electrostatic amounts after the airflow separation, wherein the optimization is performed for the purpose of reducing the dust residual amount after the airflow separation and dedusting, reducing the energy consumption of the airflow separation and reducing the electrostatic amount of the dust; According to the plurality of optimized electrostatic amounts, analyzing and obtaining a plurality of electrostatic neutralization parameters of the plastic particles in electrostatic neutralization, and predicting a plurality of neutralized electrostatic amounts after the electrostatic neutralization; According to the plurality of neutralized electrostatic amounts, the plurality of optimized dust residual amounts and the plastic particle characteristic information, optimizing electrostatic dedusting parameters of the plastic particles in electrostatic dedusting to obtain a plurality of optimized electrostatic dedusting parameters, and predicting a plurality of final residual amounts after the electrostatic dedusting, wherein the optimization is performed for the purpose of reducing the dust residual amount after the electrostatic dedusting and reducing the energy consumption of the electrostatic dedusting; Combining the plurality of optimized airflow separation parameters, the plurality of electrostatic neutralization parameters and the plurality of optimized electrostatic dedusting parameters to obtain a plurality of dedusting parameter combinations, and selecting an optimal dedusting parameter combination according to the plurality of final residual amounts and the combined energy consumption of the plurality of dedusting parameter combinations to perform dedusting.

2. The method of claim 1, wherein, Collecting plastic particle characteristic information of plastic particles to be dedusted, and sampling and detecting dust on the plastic particles to obtain dust characteristic information, comprising: Performing particle size detection on the plastic particles to be dedusted to obtain particle size information as the plastic particle characteristic information; Sampling and detecting dust particle size, dust amount and dust material of the plastic particles to obtain a plurality of sample dust particle size information, a plurality of sample dust amount information and a plurality of sample dust material information; According to the plurality of sample dust particle size information, the plurality of sample dust amount information and the plurality of sample dust material information, statistically processing to obtain dust particle size information, dust amount information and dust material information to obtain the dust characteristic information.

3. The method of claim 1, wherein, According to the plastic particle characteristic information and the dust characteristic information, optimizing airflow separation parameters of the plastic particles in airflow separation and dedusting to obtain a plurality of optimized airflow separation parameters, comprising: According to the airflow separation and dedusting equipment, constructing an airflow separation parameter space; For the purpose of reducing the dust residual amount after the airflow separation and dedusting, reducing the energy consumption of the airflow separation and reducing the electrostatic amount of the dust, constructing an airflow separation function as follows: ； wherein, ASF is airflow suitability, , and respectively represent the first dust weight, the first energy consumption weight and the static electricity weight, is the dust residual amount obtained by performing airflow separation dedusting prediction according to the airflow separation parameter in combination with the plastic particle characteristic information and the dust characteristic information, is the dust amount information, is the actual power consumption when the airflow separation parameter is run, is the maximum power consumption of the airflow separation dedusting equipment, is the static electricity amount obtained by performing airflow separation dedusting prediction according to the airflow separation parameter in combination with the plastic particle characteristic information and the dust characteristic information, is the preset static electricity amount; Randomly generating a plurality of first airflow separation parameters in the airflow separation parameter space, combining the plastic particle characteristic information and the dust characteristic information, performing airflow separation and dedusting prediction to obtain a plurality of first dust residual amounts and a plurality of first electrostatic amounts, and obtaining a plurality of first airflow separation energy consumptions to calculate a plurality of first airflow fitnesses; The first plurality of airflow separation parameters are iteratively updated until a convergence condition is met, and a final plurality of airflow separation parameters with the largest fitness is outputted, obtaining a plurality of optimized airflow separation parameters, and a plurality of optimized dust residue amounts and a plurality of optimized electrostatic amounts are obtained based on the plurality of optimized airflow separation parameters.

4. The method of claim 3, wherein, The plastic particle characteristic information and the dust characteristic information are combined to perform airflow separation and dust removal prediction, including: According to the airflow separation and dust removal record data of the plastic particles, a sample plastic particle characteristic information set, a sample dust characteristic information set, a sample airflow separation parameter set, a sample dust residue amount set, and a sample electrostatic amount set are collected as airflow separation prediction training data; The airflow separation predictor is trained using the airflow separation prediction training data; The plastic particle characteristic information and the dust characteristic information are combined with the plurality of first airflow separation parameters, and input into the airflow separation predictor for prediction to obtain a plurality of first dust residue amounts and a plurality of first electrostatic amounts.

5. The method of claim 1, wherein, According to the plurality of optimized electrostatic amounts, a plurality of electrostatic neutralization parameters for electrostatic neutralization of the plastic particles are analyzed and obtained, and a plurality of neutralized electrostatic amounts after electrostatic neutralization are predicted, including: According to the historical data of electrostatic neutralization of the plastic particles, a sample electrostatic amount set and a sample electrostatic neutralization parameter set are collected; An index table of the sample electrostatic amount set and the sample electrostatic neutralization parameter set is constructed, and the plurality of optimized electrostatic amounts are indexed to obtain a plurality of electrostatic neutralization parameters; A sample neutralized electrostatic amount set after electrostatic neutralization is collected; The sample electrostatic amount set and the sample electrostatic neutralization parameter set are used as input, and the sample neutralized electrostatic amount set is used as output to train the electrostatic neutralization predictor, and the plurality of optimized electrostatic amounts and the plurality of electrostatic neutralization parameters are optimized to obtain a plurality of neutralized electrostatic amounts.

6. The method of claim 1, wherein, According to the plurality of neutralized electrostatic amounts, the plurality of optimized dust residue amounts, and the plastic particle characteristic information, the electrostatic dust removal parameters for electrostatic dust removal of the plastic particles are optimized to obtain a plurality of optimized electrostatic dust removal parameters, including: According to the operating parameter range of the electrostatic dust removal equipment, an electrostatic dust removal parameter space is constructed; An electrostatic dust removal function is constructed for the purpose of reducing the dust residue amount after electrostatic dust removal and reducing the electrostatic dust removal energy consumption, as follows: ； wherein EDR is electrostatic adaptability, and respectively represent the second dust weight and the second energy consumption weight, is the final dust residue amount for electrostatic dust removal prediction according to the electrostatic dust removal parameters combined with the neutralized electrostatic amount, the optimized dust residue amount, the plastic particle characteristic information, and the dust characteristic information, is the optimized dust residue amount, is the actual power consumption according to the operation of the electrostatic dust removal parameters, is the maximum power consumption of the electrostatic dust removal equipment; A plurality of first electrostatic dust removal parameters are randomly generated in the electrostatic dust removal parameter space, combined with the plurality of neutralized electrostatic amounts, the plurality of dust residue amounts, and combined with the plastic particle characteristic information, dust particle size information, and dust material information, to perform electrostatic dust removal prediction and obtain a plurality of final dust residue amounts; A plurality of first electrostatic dust removal power consumptions of the plurality of first electrostatic dust removal parameters are obtained, combined with the plurality of final dust residue amounts, to calculate a plurality of first electrostatic fitnesses; The plurality of first electrostatic dust removal parameters are iteratively updated until convergence is achieved, obtaining a plurality of optimized electrostatic dust removal parameters with the largest electrostatic fitness, and a plurality of final residue amounts are obtained based on the plurality of optimized electrostatic dust removal parameters.

7. The method of claim 1, wherein, The multiple optimized airflow separation parameters, the multiple electrostatic neutralization parameters and the multiple optimized electrostatic precipitation parameters are combined to obtain multiple dust removal parameter combinations, and an optimal dust removal parameter combination is selected according to the multiple final residual amounts and the combined power consumption of the multiple dust removal parameter combinations, including: The multiple optimized airflow separation parameters, the multiple electrostatic neutralization parameters and the multiple optimized electrostatic precipitation parameters are combined to obtain multiple dust removal parameter combinations; The multiple combined power consumptions of the multiple dust removal parameter combinations are obtained, and multiple combined dust removal scores are calculated; The multiple final residual amounts are used to calculate multiple combined dust removal scores; The multiple combined power consumption scores and the multiple combined dust removal scores are used to calculate multiple dust removal combination scores, and a dust removal parameter combination with the maximum dust removal combination score is selected to obtain an optimal dust removal parameter combination.

8. A soot cleaning device for plastic particles, characterized by The device comprises: A feature information acquisition module is configured to collect plastic particle feature information of plastic particles to be cleaned and sample and detect dust on the plastic particles to obtain dust feature information, wherein the dust feature information includes dust particle size information, dust amount information and dust material information; An airflow separation parameter acquisition module is configured to optimize airflow separation parameters for airflow separation and dust removal of the plastic particles according to the plastic particle feature information and the dust feature information, obtain multiple optimized airflow separation parameters, and predict multiple optimized dust residual amounts and multiple optimized electrostatic amounts after airflow separation, wherein the optimization is performed for the purpose of reducing the dust residual amount after airflow separation and dust removal, reducing airflow separation energy consumption and reducing the electrostatic amount of the dust; A neutralization parameter acquisition module is configured to analyze and obtain multiple electrostatic neutralization parameters for electrostatic neutralization of the plastic particles according to the multiple optimized electrostatic amounts, and predict multiple neutralized electrostatic amounts after electrostatic neutralization; An electrostatic precipitation parameter acquisition module is configured to optimize electrostatic precipitation parameters for electrostatic precipitation of the plastic particles according to the multiple neutralized electrostatic amounts, the multiple optimized dust residual amounts and the plastic particle feature information, obtain multiple optimized electrostatic precipitation parameters, and predict multiple final residual amounts after electrostatic precipitation, wherein the optimization is performed for the purpose of reducing the dust residual amount after electrostatic precipitation and reducing electrostatic precipitation energy consumption; A dust removal parameter acquisition module is configured to combine the multiple optimized airflow separation parameters, the multiple electrostatic neutralization parameters and the multiple optimized electrostatic precipitation parameters to obtain multiple dust removal parameter combinations, and select an optimal dust removal parameter combination according to the multiple final residual amounts and the combined power consumption of the multiple dust removal parameter combinations, and perform dust removal.

Images