A method and system for controlling the filtration and cooling of polymers.

Abstract

This application provides a method and system for polymer filtration cooling control, relating to the field of polymer filtration technology. The method includes: collecting polymer filtration data and polymer characteristic information; randomly selecting control parameters for polymer viscosity analysis; predicting impurity filtration and filtration efficiency based on viscosity and impurity distribution information, compensating and adjusting impurity filtration information, and performing overheating degradation analysis to classify and obtain degradation filtration fitness; configuring primary and secondary weights to obtain filtration fitness; optimizing control parameters for filtration cooling control, and updating impurity distribution information and impurity distribution uniformity. This application solves the technical problem in existing technologies where the lack of real-time response to changes in polymer characteristics in current filtration control leads to unstable filtration efficiency and effect. By optimizing control parameters through real-time data analysis and fitness calculation, overheating degradation is avoided, thus improving filtration effect and efficiency.

Description

Technical Field

[0001] This application relates to the field of polymer filtration technology, and in particular to a method and system for controlling the filtration and cooling of polymers. Background Technology

[0002] During polymer processing, various impurities are often generated due to impurities in the raw materials, byproducts produced during the reaction, particles generated from mechanical wear, and pollutants in the environment. The presence of these impurities directly affects the performance and application range of the product. Therefore, filtration is crucial to ensuring the quality and performance of the final product. Heating and cooling control is a key step in ensuring appropriate polymer viscosity and avoiding overheating degradation. The viscosity of the polymer has a significant impact on its processing performance and filtration efficiency. Precise temperature control is essential for maintaining the appropriate polymer viscosity because high temperatures result in low viscosity, which, while beneficial for filtration, can easily lead to overheating degradation; conversely, low temperatures result in high viscosity, increasing the difficulty of filtration and reducing filtration efficiency. However, existing control methods are not precise enough in terms of temperature control and cannot respond in real time to changes in polymer properties, leading to unstable filtration efficiency and effectiveness.

[0003] In summary, existing technologies suffer from the problem of unstable filtration efficiency and effectiveness due to the lack of real-time response to changes in polymer properties in current filtration control methods. Summary of the Invention

[0004] The purpose of this application is to provide a method and system for filtering and cooling polymers, in order to solve the technical problem in the prior art where the existing filtration control lacks real-time response to changes in polymer properties, resulting in unstable filtration efficiency and effect.

[0005] In view of the above problems, this application provides a method and system for controlling the filtration and cooling of polymers.

[0006] In a first aspect, this application provides a method for controlling the filtration and cooling of polymers. This method is implemented through a filtration and cooling control system for polymers. The method includes: collecting polymer filtration data within a recent preset time span to obtain impurity distribution information and impurity distribution uniformity; collecting polymer characteristic information of the polymer to be filtered; and obtaining a filtration and cooling control space; randomly selecting filtration and cooling control parameters within the filtration and cooling control space; performing polymer viscosity analysis based on the polymer characteristic information to obtain polymer viscosity information; and performing impurity filtration prediction and filtration efficiency prediction based on the polymer viscosity information and impurity distribution information to obtain impurity filtration information and filtration efficiency information, and determining the impurity distribution uniformity based on the filtration and cooling control space. The impurity filtration information is compensated and adjusted to obtain adjusted impurity filtration information. Polymer overheating degradation analysis is performed based on polymer characteristic information and filtration cooling control parameters to obtain overheating degradation information, and degradation filtration fitness is classified. Based on the impurity distribution information and impurity distribution uniformity, a first-level weight is configured to calculate the impurity filtration fitness based on the adjusted impurity filtration information and filtration efficiency information. A second-level weight is configured based on the impurity distribution information to weightedly calculate the impurity filtration fitness and degradation filtration fitness to obtain the filtration fitness. Based on the filtration fitness, the filtration cooling control parameters are further optimized to obtain the optimal filtration cooling control parameters. Polymer filtration cooling control is performed, and real-time impurity distribution information is detected after filtration is completed, updating the impurity distribution information and impurity distribution uniformity.

[0007] Secondly, this application also provides a filtration cooling control system for polymers, used to execute a filtration cooling control method for polymers as described in the first aspect, wherein the filtration cooling control system for polymers includes: a data acquisition module, which is used to acquire polymer filtration data within a recent preset time span, obtain impurity distribution information and impurity distribution uniformity, and acquire polymer characteristic information of the polymer to be filtered, and obtain a filtration cooling control space; a viscosity analysis module, which is used to randomly select filtration cooling control parameters within the filtration cooling control space, and perform polymer viscosity analysis in combination with the polymer characteristic information to obtain polymer viscosity information; and a filtration prediction module, which is used to perform impurity filtration prediction and filtration efficiency prediction based on the polymer viscosity information and impurity distribution information, to obtain impurity filtration information and filtration efficiency information, and based on the impurity distribution data... The system includes a polymer distribution uniformity module, which compensates for and adjusts the impurity filtration information to obtain adjusted impurity filtration information, and performs polymer overheating degradation analysis based on the polymer characteristic information and filtration cooling control parameters to obtain overheating degradation information and classify the degradation filtration fitness. A weight configuration module configures primary weights based on the impurity distribution information and impurity distribution uniformity, calculates the impurity filtration fitness based on the adjusted impurity filtration information and filtration efficiency information, and configures secondary weights based on the impurity distribution information to perform a weighted calculation of the impurity filtration fitness and degradation filtration fitness to obtain the filtration fitness. A parameter optimization module further optimizes the filtration cooling control parameters based on the filtration fitness to obtain optimal filtration cooling control parameters, performs polymer filtration cooling control, and detects and obtains real-time impurity distribution information after filtration, updating the impurity distribution information and impurity distribution uniformity.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] By collecting polymer filtration data within a recent preset time span, impurity distribution information and impurity distribution uniformity are obtained, along with polymer characteristic information of the polymer to be filtered, and a filtration cooling control space is acquired. Within the filtration cooling control space, filtration cooling control parameters are randomly selected, and polymer viscosity analysis is performed in conjunction with the polymer characteristic information to obtain polymer viscosity information. Based on the polymer viscosity information and impurity distribution information, impurity filtration prediction and filtration efficiency prediction are performed to obtain impurity filtration information and filtration efficiency information. Based on the impurity distribution uniformity, the impurity filtration information is compensated and adjusted to obtain adjusted impurity filtration information. Finally, based on the polymer characteristic information and the... The filter cooling control parameters are analyzed for polymer overheating degradation to obtain overheating degradation information, and degradation filtration fitness is obtained by classification. Based on the impurity distribution information and impurity distribution uniformity, a first-level weight is configured to calculate the impurity filtration fitness by adjusting the impurity filtration information and filtration efficiency information. A second-level weight is then configured based on the impurity distribution information to calculate the filtration fitness by weighting the impurity filtration fitness and degradation filtration fitness. Based on the filtration fitness, the filter cooling control parameters are further optimized to obtain the optimal filter cooling control parameters for polymer filtration cooling control. Real-time impurity distribution information is detected after filtration and updated accordingly. In other words, by optimizing control parameters through real-time data analysis and fitness calculation, overheating degradation is avoided, and filtration effect and efficiency are improved.

[0010] The above description is merely an overview of the technical solution of this application. To better understand the technical means of this application and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of this application more apparent, specific embodiments of this application are described below. It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent through the following description. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0012] Figure 1 This is a schematic flowchart of a filtration and cooling control method for polymers according to this application;

[0013] Figure 2This is a schematic diagram of a filter cooling control system for polymers according to this application.

[0014] Figure labeling: Data acquisition module 11, viscosity analysis module 12, filtering and prediction module 13, weight configuration module 14, parameter optimization module 15. Detailed Implementation

[0015] This application provides a filtration cooling control method and system for polymers, solving the technical problem in existing filtration controls where the lack of real-time response to changes in polymer properties leads to unstable filtration efficiency and effectiveness. Through real-time data analysis and fitness calculations, control parameters are optimized to prevent overheating and degradation, thereby improving filtration effect and efficiency.

[0016] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application. It should also be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all of them.

[0017] Example 1, please refer to the appendix. Figure 1 This application provides a method for controlling the filtration and cooling of polymers, wherein the method is applied to a filtration and cooling control system for polymers, and the method specifically includes the following steps:

[0018] Step 1: Collect polymer filtration data within the most recent preset time span to obtain impurity distribution information and impurity distribution uniformity, as well as polymer characteristic information of the polymer to be filtered, and obtain the filtration cooling control space.

[0019] Specifically, polymer filtration data is collected within a recent preset time span, typically one week or one month. Based on this data, the average impurity content of the polymer is calculated, yielding impurity distribution information that reflects the average impurity content within the polymer over the preset time span. Next, the variance of multiple impurity content data is calculated and compared to a preset variance. This preset variance can be based on a large batch of filtered sample data. The ratio of the current variance to the preset variance serves as the impurity distribution uniformity, reflecting the degree of fluctuation in impurity content. A large current variance indicates uneven impurity distribution. Simultaneously, characteristic information of the polymer to be filtered, such as its physical and chemical properties (e.g., molecular weight and its distribution), is collected. Based on the collected data and polymer characteristics, a space for filtration cooling control is determined. This space primarily considers the control temperature parameters during the filtration process. Real-time data acquisition and analysis improve the accuracy and adaptability of the filtration process.

[0020] Step 2: Within the filter cooling control space, randomly select filter cooling control parameters and perform polymer viscosity analysis in conjunction with the polymer characteristic information to obtain polymer viscosity information.

[0021] Specifically, a set of filtration and cooling control parameters is randomly selected within the filtration and cooling control space. Based on historical data of polymer temperature control, polymer characteristic information and filtration and cooling control parameters are collected. The viscosity is calculated under different filtration and cooling control parameters based on different polymer characteristic information, and the acquired viscosity information is classified and labeled. Using the collected and standardized sample data—namely, the polymer characteristic information set, the filtration and cooling control parameter set, and the polymer viscosity information set—a polymer viscosity predictor is trained based on a machine learning algorithm to predict the polymer viscosity under different conditions. For the randomly selected filtration and cooling control parameters, viscosity prediction is performed in conjunction with polymer characteristic information to obtain the polymer viscosity information. High temperatures result in low viscosity but may lead to overheating and degradation; low temperatures result in high viscosity, making filtration more difficult and inefficient. Therefore, selecting an appropriate temperature is crucial for optimizing the filtration process. By randomly selecting filtration and cooling control parameters and combining them with polymer characteristic information for viscosity analysis, different filtration conditions can be explored, helping to discover the optimal parameter combination and improve filtration efficiency and polymer quality.

[0022] Step 3: Based on the polymer viscosity information and impurity distribution information, perform impurity filtration prediction and filtration efficiency prediction to obtain impurity filtration information and filtration efficiency information. Based on the impurity distribution uniformity, compensate and adjust the impurity filtration information to obtain adjusted impurity filtration information. Also, based on the polymer characteristic information and filtration cooling control parameters, perform polymer overheating degradation analysis to obtain overheating degradation information and classify the degradation filtration suitability.

[0023] Specifically, polymer viscosity and impurity distribution information sets are obtained by collecting filtration data over a period of time. The filtration rate and efficiency of impurities during the filtration process are then labeled, resulting in impurity filtration information sets and filtration efficiency information sets. A polymer filtration predictor is trained using these sets. The polymer viscosity and impurity distribution information are input into the predictor to predict the filtration effect and efficiency of impurities during the filtration process. The impurity filtration information is adjusted based on the uniformity of impurity distribution. The uniformity of impurity distribution reflects the evenness of impurity content; a higher value indicates a more uneven distribution. The adjustment aims to more accurately reflect the actual filtration situation. If the impurity distribution is uneven, the simple impurity filtration rate cannot fully reflect the filtration effect. Through compensation calculations, adjusted impurity filtration information is obtained, more accurately reflecting the filtration effect and taking into account the unevenness of impurity distribution.

[0024] By collecting test data on the overheating degradation of polymers at different temperatures, a set of polymer viscosity information and a set of filtration and cooling control parameters were obtained. Overheating degradation tests were conducted on the polymers under different temperature conditions, and the extent of overheating degradation was labeled based on the test results. An overheating degradation predictor was trained using the collected sample data (polymer characteristic information, filtration and cooling control parameters, and overheating degradation information). The polymer characteristic information and filtration and cooling control parameters were input into the predictor to obtain information about the degree of polymer overheating degradation. The overheating degradation information was compared with a pre-established degradation fitness table, and polymers were classified according to the degree of overheating degradation to obtain degradation filtration fitness. The degradation fitness table stores the overheating degradation information of different samples and their corresponding degradation filtration fitness, which helps to quickly classify and evaluate the degree of overheating degradation of new samples. There is a negative correlation between sample overheating degradation information and sample degradation filtration fitness; that is, the higher the degree of overheating degradation, the lower the degradation filtration fitness. By combining polymer viscosity with recent impurity content, the impurity filtration effect and filtration efficiency are analyzed. Based on polymer characteristics and temperature, the extent of overheating degradation is analyzed, and the degradation filtration adaptability is finally obtained. Parameters in the filtration process are optimized to improve filtration efficiency and reduce impurity content.

[0025] Step 4: Based on the impurity distribution information and impurity distribution uniformity, configure a first-level weight, calculate the impurity filtration fitness based on the adjusted impurity filtration information and filtration efficiency information, and configure a second-level weight based on the impurity distribution information to calculate the filtration fitness by weighting the impurity filtration fitness and degradation filtration fitness.

[0026] Specifically, a primary weight is configured based on the ratio of the impurity distribution information obtained from the calculated mean to the preset impurity distribution information, combined with the impurity distribution uniformity. This primary weight reflects the degree of influence of the impurity distribution on the filtration process and is used to weight the adjusted impurity filtration information and filtration efficiency information. For example, if the impurity distribution information indicates uneven impurity distribution, a higher primary weight is assigned to emphasize this factor's impact on filtration fitness. Using the configured primary weight, the ratio of the adjusted impurity filtration information to the preset impurity filtration information, as well as the ratio of the predicted filtration efficiency information to the preset filtration information, are weighted and calculated. The calculation result yields a comprehensive evaluation index, namely, impurity filtration fitness.

[0027] A secondary weight is configured based on the ratio of the impurity distribution information to the preset impurity distribution information. The secondary weight reflects the combined influence of impurity distribution and degradation filtration fitness on filtration fitness, and is used to perform a weighted calculation of impurity filtration fitness and degradation filtration fitness. Using the configured secondary weight, a weighted calculation is performed on impurity filtration fitness and degradation filtration fitness. The calculation result yields a comprehensive evaluation index, namely filtration fitness. By configuring and applying primary and secondary weights, the effectiveness and efficiency of the filtration process can be accurately evaluated.

[0028] Step 5: Based on the filtration adaptability, continue to optimize the filtration cooling control parameters to obtain the optimal filtration cooling control parameters, perform polymer filtration cooling control, and detect and obtain real-time impurity distribution information after filtration is completed, and update the impurity distribution information and impurity distribution uniformity.

[0029] Specifically, filtration fitness is used as an evaluation metric. Parameter optimization is performed within the filtration cooling control space using algorithms such as genetic algorithms, particle swarm optimization, and simulated annealing to find the filtration cooling control parameters that maximize filtration fitness. The optimization process continues until a parameter combination that meets the convergence criteria is found. When the optimization process converges, the filtration cooling control parameters with the highest filtration fitness are output; that is, the optimal parameter combination that achieves the highest filtration fitness under the current conditions. The found optimal filtration cooling control parameters are then used for actual polymer filtration cooling control. After filtration, real-time impurity distribution information is detected and collected, including the content and distribution of impurities in the filtered polymer. Using the collected real-time impurity distribution information, the impurity distribution information and impurity distribution uniformity are calculated and updated for the filtration control of the next batch of polymer, helping to optimize the filtration parameter settings for the next batch, improving filtration efficiency and polymer quality. By continuously optimizing the filtration cooling control parameters, the effectiveness and efficiency of the filtration process are continuously improved, which helps to optimize filtration parameter settings, select appropriate filtration conditions, improve filtration efficiency and polymer quality, and reduce scrap rate and production costs.

[0030] Furthermore, step one of this application includes:

[0031] Collect polymer filtration data within the most recent preset time span to obtain multiple historical impurity filtration information, each of which includes impurity content information; calculate the mean value based on the multiple historical impurity filtration information to obtain impurity distribution information, and calculate the ratio of the variance to the preset variance as the impurity distribution uniformity; collect polymer characteristic information of the polymer to be filtered; obtain the filtration cooling control space, wherein the filtration cooling control space includes the temperature parameter range for filtration cooling control.

[0032] Specifically, filtering data from a recent period is collected to obtain multiple historical impurity filtering information entries, each containing detailed information about impurity content. The preset time span refers to the time range set during data collection, such as the past week, month, or quarter. Historical impurity filtering information refers to the impurity content data recorded for each filtering operation within the preset time span. Impurity content information is the mass or volume percentage of impurities detected in the polymer. The average value of the historical impurity filtering information is calculated by adding the impurity content of all historical data points and then dividing by the total number of data points to obtain a representative value, i.e., impurity distribution information, reflecting the average impurity content in the polymer within the preset time span.

[0033] Next, the variance of historical impurity filtration information is calculated. This is done by summing the squares of the differences between the impurity content and the mean for each data point, and then dividing by the total number of data points. The calculated variance is compared with a preset variance value, and the ratio between the two is calculated. This ratio is called the impurity distribution uniformity, reflecting the degree of uniformity in the distribution of impurity content. The preset variance is the variance under a large batch of filtered sample data; the larger the current variance, the more uneven the distribution. In a specific example, suppose there is polymer filtration data from the most recent month: the impurity content of sample 1 is 0.8%, the impurity content of sample 2 is 0.7%, the impurity content of sample 3 is 0.9%, and the impurity content of sample 4 is 0.85%. The calculated mean is 0.8125%, and the calculated variance is 0.00547%. Assuming the preset variance is 0.01%, the impurity distribution uniformity is 0.54.

[0034] Collect characteristic information about the polymer to be filtered, such as polymer type, molecular weight, viscosity, temperature, humidity, color, and particle size. Determine the adjustable range of the filtration cooling control parameters, i.e., the filtration cooling control space, which mainly includes the adjustable temperature parameter range during the filtration process. By collecting and analyzing historical impurity filtration data, monitor and adjust the impurity content during the polymer filtration process to ensure product quality. Calculating impurity distribution information and impurity distribution uniformity helps identify potential problems during the filtration process, such as abnormal fluctuations in impurity content. By collecting polymer characteristic information and setting the filtration cooling control space, the filtration process can be precisely controlled, reducing product defects and improving production efficiency and product quality.

[0035] Furthermore, step two of this application includes:

[0036] Within the filtration and cooling control space, filtration and cooling control parameters are randomly selected. Based on historical polymer temperature control data, a set of sample polymer feature information and a set of sample filtration and cooling control parameters are collected. Based on the viscosity of polymers with different sample polymer feature information under different sample filtration and cooling control parameters, a set of sample polymer viscosity information is obtained. Using the set of sample polymer feature information, the set of sample filtration and cooling control parameters, and the set of sample polymer viscosity information, a polymer viscosity predictor is trained. Using the polymer viscosity predictor, polymer viscosity prediction analysis is performed on the filtration and cooling control parameters and polymer feature information to obtain polymer viscosity information.

[0037] Specifically, a set of control parameters is randomly selected within the filtration cooling control space; these parameters represent the control temperature during the filtration process. Random selection is used to explore different parameter combinations to find the optimal filtration conditions. Based on historical data of polymer temperature control, sample data is collected, including a set of sample polymer characteristic information and a set of sample filtration cooling control parameters. The sample polymer characteristic information set contains the features of different sample polymers, such as molecular weight, viscosity, and temperature sensitivity; the sample filtration cooling control parameters set represents the control temperature during the filtration cooling process. Based on the viscosity values ​​of different sample polymers under specific filtration cooling control parameters, the acquired viscosity information is classified and labeled. For example, viscosity data can be classified according to different temperature and pressure conditions.

[0038] Using previously collected and labeled sample data, including polymer characteristics, filtration and cooling control parameters, and polymer viscosity data under these parameter settings, a predictor is trained using machine learning or statistical models to predict the polymer viscosity based on the input polymer characteristics and filtration and cooling control parameters. The training process typically includes data preprocessing, model selection, model training, model evaluation, and model optimization. The trained polymer viscosity predictor is then applied to randomly selected filtration and cooling control parameters, combined with polymer characteristics, to predict the viscosity of the polymer under the current conditions. By using historical data and machine learning methods to predict polymer viscosity under different conditions, the number of experiments and costs are reduced. Predicting viscosity helps adjust filtration and cooling control parameters to optimize the polymer filtration and cooling process, improving product quality and consistency. By predicting viscosity, parameters that may lead to polymer overheating and degradation during filtration and cooling can be avoided, thereby reducing scrap rates.

[0039] Furthermore, step three of this application includes:

[0040] Based on historical polymer filtration data, a set of sample polymer viscosity information and a set of sample impurity distribution information are collected. The filtration rate and efficiency of impurities during the filtration process are labeled to obtain a set of sample impurity filtration information and a set of sample filtration efficiency information. Using these sets of sample polymer viscosity information, sample impurity distribution information, sample impurity filtration information, and sample filtration efficiency information, a polymer filtration predictor is trained to predict impurity filtration and filtration efficiency based on the polymer viscosity information and impurity distribution information, thus obtaining impurity filtration information and filtration efficiency information. Based on the uniformity of the impurity distribution, the impurity filtration information is compensated and adjusted to obtain adjusted impurity filtration information.

[0041] Specifically, viscosity and impurity distribution information of polymers under different filtration conditions are collected from polymer filtration data over a period of time, resulting in a set of sample polymer viscosity information and a set of sample impurity distribution information. The filtration rate and efficiency of impurities during the filtration process are labeled, forming a set of impurity filtration information and a set of sample filtration efficiency information. Filtration rate refers to the proportion of impurities removed during filtration; for example, if there are 100 impurities before filtration and 10 remain after filtration, the filtration rate is 90%. Filtration efficiency refers to the efficiency with which impurities are removed during filtration. Using the collected sample polymer viscosity and impurity distribution information sets, along with the labeled sample impurity filtration and filtration efficiency information sets, a polymer filtration predictor is trained based on a machine learning algorithm. This predictor can predict the impurity filtration rate and filtration efficiency during the filtration process based on different input polymer viscosity and impurity distribution information.

[0042] The calculated impurity distribution information and the predicted polymer viscosity information are input into the predictor for prediction, analyzing the effect and efficiency of impurity filtration. Based on the impurity distribution uniformity obtained from the ratio of the calculated variance to the preset variance, compensation calculations are performed to adjust the impurity filtration information. The predicted value of filtration efficiency is corrected based on the uniformity of impurity distribution to more accurately reflect the actual situation of the filtration process. The purpose of this adjustment is to more accurately reflect the actual filtration of impurities during the filtration process. If the impurity distribution is uneven, the impurity filtration rate alone cannot fully reflect the filtration effect. By combining viscosity and impurity distribution information, the filtration rate and filtration efficiency are predicted. The prediction results help adjust filtration parameters to optimize the filtration process and improve impurity removal efficiency.

[0043] Furthermore, this application also includes the following steps:

[0044] Based on the overheating degradation test data of polymers at different temperatures, a set of sample polymer feature information and a set of sample filtration and cooling control parameters are collected. Based on the magnitude of polymer overheating degradation, a set of sample overheating degradation information is obtained. Using the sample polymer feature information set, sample filtration and cooling control parameter set, and sample overheating degradation information set, an overheating degradation predictor is trained to perform polymer overheating degradation analysis on the polymer feature information and filtration and cooling control parameters to obtain overheating degradation information. Based on the overheating degradation information, degradation filtration fitness is obtained by classification. This classification is performed by inputting the overheating degradation information into a degradation fitness table, which includes an index relationship between sample overheating degradation information and sample degradation filtration fitness, with a negative correlation between the two.

[0045] Specifically, based on test data of polymer overheating degradation at different temperatures, a set of polymer characteristic information and a set of filtering and cooling control parameters are collected. Overheating degradation tests are conducted on the polymer under different temperature conditions. The magnitude of polymer overheating degradation is obtained from the test results, and a set of sample overheating degradation information, containing detailed data on the polymer's overheating degradation behavior, is generated. Using the collected sample data, including polymer characteristic information (such as type, molecular weight, etc.), filtering and cooling control parameters, and the polymer's overheating degradation information under these parameter settings, an overheating degradation predictor is trained based on a machine learning algorithm. This predictor can predict the degree of polymer overheating degradation based on the input polymer characteristic information and filtering and cooling control parameters. The collected polymer characteristic information and randomly selected filtering and cooling control parameters are input into the predictor for overheating degradation analysis to predict the possible degree of polymer overheating degradation under specific conditions.

[0046] Polymers are classified based on their degree of overheating degradation under different conditions to assess their stability and adaptability under various filtration conditions. Overheating degradation information is compared with a pre-established degradation fitness table. This table is a data structure built based on historical data or previous experimental results, containing an index relationship between sample overheating degradation information and corresponding sample degradation filtration fitness. In this table, there is a negative correlation between sample overheating degradation information and sample degradation filtration fitness. That is, when the degree of overheating degradation is high, the corresponding degradation filtration fitness is low; conversely, when the degree of overheating degradation is low, the degradation filtration fitness is high. New overheating degradation information is compared with the data in the degradation fitness table to classify polymers and obtain their degradation filtration fitness. By collecting and analyzing sample data, a predictor is trained to accurately predict and evaluate the degree of overheating degradation of polymers under different conditions. The degradation filtration fitness obtained from the classification helps optimize filtration parameter settings, select appropriate temperature ranges to reduce the risk of overheating degradation, and improve polymer quality and production efficiency.

[0047] Furthermore, step four of this application includes:

[0048] Based on the ratio of the impurity distribution information to the preset impurity distribution information, and combined with the impurity distribution uniformity, the preset impurity weight is adjusted and configured to obtain the primary impurity filtration weight and the primary filtration efficiency weight. Based on the primary impurity filtration weight and the primary filtration efficiency weight, the ratio of the adjusted impurity filtration information to the preset impurity filtration information, and the ratio of the filtration efficiency information to the preset filtration efficiency information are weighted and calculated to obtain the impurity filtration adaptability.

[0049] Specifically, based on the ratio of the impurity distribution information obtained from the calculated mean to the preset impurity distribution information, and combined with the impurity distribution uniformity obtained from the ratio of the calculated variance to the preset variance, the preset impurity weight is corrected. This correction calculation yields the corrected first-level impurity filtration weight. The preset impurity weight is a pre-defined weight indicating the importance of impurity filtration. For example, if the preset impurity weight is 0.6, the first-level impurity filtration weight is obtained by multiplying the ratio of the impurity distribution information to the preset impurity distribution information, combined with the impurity distribution uniformity, and then multiplying by the preset impurity weight. The first-level filtration efficiency weight is then obtained using Formula 1 - First-level Impurity Filtration Weight = First-level Filtration Efficiency Weight. The first-level impurity filtration weight represents the priority of impurity removal during the filtration process, while the first-level filtration efficiency weight represents the importance of filtration efficiency.

[0050] Based on the primary impurity filtration weight and the primary filtration efficiency weight, a weighted calculation is performed on the ratio of the adjusted impurity filtration information obtained through compensation adjustment to the preset impurity filtration information, and the ratio of the predicted filtration efficiency information to the preset filtration efficiency information. This weighted calculation involves evaluating both the ratio of the adjusted impurity filtration information to the preset impurity filtration information and the ratio of the filtration efficiency information to the preset filtration efficiency information. Through this weighted calculation, a comprehensive evaluation index, namely the impurity filtration fitness, is obtained. Impurity filtration fitness is an important evaluation index that considers the influence of multiple factors on the filtration process, helping to understand and predict the effectiveness of the filtration process. By correcting the calculation weights and performing the weighted calculation, parameters in the filtration process are evaluated and optimized, improving filtration efficiency and reducing impurity content.

[0051] Furthermore, this application also includes the following steps:

[0052] Based on the ratio of the impurity distribution information to the preset impurity distribution information, the preset impurity filtration weight is modified and configured to obtain the secondary differential filtration weight and the secondary degradation filtration weight; based on the secondary differential filtration weight and the secondary degradation filtration weight, the impurity filtration fitness and degradation filtration fitness are weighted and calculated to obtain the filtration fitness.

[0053] Specifically, the ratio of the impurity distribution information obtained by calculating the mean to the preset impurity distribution information is used to correct the preset impurity filtration weight, resulting in the secondary differential filtration weight and the secondary degradation filtration weight. The preset impurity filtration weight is a pre-defined weight indicating the importance of impurity filtration. The secondary differential filtration weight is obtained by correcting the preset impurity filtration weight based on the ratio of the impurity distribution information to the preset impurity distribution information, and is used to measure the effectiveness of impurity filtration. The secondary degradation filtration weight corresponds to the secondary differential filtration weight and is used to measure the importance of degradation filtration.

[0054] By utilizing secondary differential filtration weights and secondary degradation filtration weights, a weighted calculation is performed on the impurity filtration fitness and the degradation filtration fitness obtained by classifying the overheat degradation information in the degradation fitness table. This weighted calculation evaluates both impurity filtration fitness and degradation filtration fitness, taking into account the influence of the secondary differential filtration weights and secondary degradation filtration weights. A comprehensive evaluation index, namely filtration fitness, is calculated, reflecting the stability and adaptability of the filtration process under different conditions. For example, assuming a primary impurity filtration weight of 0.7 and a primary filtration efficiency weight of 0.3, the impurity filtration fitness and degradation filtration fitness are weighted according to these weights. If the secondary differential filtration weight is high, the weighted calculation will increase its contribution to the final filtration fitness. Through weighted calculation, a more accurate filtration fitness is obtained, thereby optimizing the filtration process and improving production efficiency and product quality.

[0055] Furthermore, step five of this application includes:

[0056] Continue optimizing the filtration cooling control parameters within the filtration cooling control space until convergence, outputting the filtration cooling control parameters with the highest filtration adaptability to obtain the optimal filtration cooling control parameters; perform polymer filtration cooling control accordingly, and detect and obtain real-time impurity distribution information after filtration is completed, calculate and update the impurity distribution information and impurity distribution uniformity for use in the filtration control of the next batch of polymer.

[0057] Specifically, within the filter cooling control space, filter fitness is used as an evaluation metric to continue parameter optimization. Optimization algorithms such as genetic algorithms, particle swarm optimization, and simulated annealing are employed to find filter cooling control parameters that maximize filter fitness. The optimization process continues until a parameter combination that meets convergence conditions is found. Convergence conditions include no further significant increase in filter fitness and reaching a preset number of iterations. Convergence means that filter fitness no longer increases significantly, indicating that the filtration process has reached its optimal state. Once convergence conditions are met, the filter cooling control parameters with the highest filter fitness are output. These parameters represent the combination that achieves the highest filtration efficiency and best product quality under the current conditions.

[0058] The polymer filtration and cooling process is controlled using optimal filtration and cooling control parameters. After filtration, real-time impurity distribution information is detected and collected, including the content and distribution of impurities in the filtered polymer. This collected real-time impurity distribution information is used to calculate and update the impurity distribution information and uniformity. The updated information reflects the filtration effect of the current batch of polymer and is used to optimize and control the filtration parameters for the next batch. By detecting and updating impurity distribution information in real time, parameters are automatically adjusted to achieve a more advanced closed-loop control. Continuous parameter optimization and actual filtration operations optimize the filtration process, ensuring production efficiency and product quality.

[0059] In summary, the filtration cooling control method for polymers provided in this application has the following technical advantages:

[0060] By collecting polymer filtration data within a recent preset time span, impurity distribution information and impurity distribution uniformity are obtained, along with polymer characteristic information of the polymer to be filtered, and a filtration cooling control space is acquired. Within the filtration cooling control space, filtration cooling control parameters are randomly selected, and polymer viscosity analysis is performed in conjunction with the polymer characteristic information to obtain polymer viscosity information. Based on the polymer viscosity information and impurity distribution information, impurity filtration prediction and filtration efficiency prediction are performed to obtain impurity filtration information and filtration efficiency information. Based on the impurity distribution uniformity, the impurity filtration information is compensated and adjusted to obtain adjusted impurity filtration information. Finally, based on the polymer characteristic information and the... The filter cooling control parameters are analyzed for polymer overheating degradation to obtain overheating degradation information, and degradation filtration fitness is obtained by classification. Based on the impurity distribution information and impurity distribution uniformity, a first-level weight is configured to calculate the impurity filtration fitness by adjusting the impurity filtration information and filtration efficiency information. A second-level weight is then configured based on the impurity distribution information to calculate the filtration fitness by weighting the impurity filtration fitness and degradation filtration fitness. Based on the filtration fitness, the filter cooling control parameters are further optimized to obtain the optimal filter cooling control parameters for polymer filtration cooling control. Real-time impurity distribution information is detected after filtration and updated accordingly. In other words, by optimizing control parameters through real-time data analysis and fitness calculation, overheating degradation is avoided, and filtration effect and efficiency are improved.

[0061] Example 2: Based on the same inventive concept as the polymer filtration and cooling control method in Example 1, this application also provides a polymer filtration and cooling control system. Please refer to the appendix. Figure 2 The aforementioned filter cooling control system for polymers includes:

[0062] The data acquisition module 11 is used to acquire polymer filtration data within the most recent preset time span, obtain impurity distribution information and impurity distribution uniformity, acquire polymer characteristic information of the polymer to be filtered, and obtain the filtration cooling control space.

[0063] Viscosity analysis module 12 is used to randomly select filter cooling control parameters within the filter cooling control space, and perform polymer viscosity analysis in combination with the polymer characteristic information to obtain polymer viscosity information.

[0064] The filtration prediction module 13 is used to predict impurity filtration and filtration efficiency based on the polymer viscosity information and impurity distribution information, obtain impurity filtration information and filtration efficiency information, compensate and adjust the impurity filtration information according to the impurity distribution uniformity, obtain adjusted impurity filtration information, and perform polymer overheating degradation analysis based on the polymer characteristic information and filtration cooling control parameters to obtain overheating degradation information and classify and obtain degradation filtration adaptability.

[0065] The weight configuration module 14 is used to configure a first-level weight based on the impurity distribution information and the impurity distribution uniformity, calculate the impurity filtration fitness based on the adjusted impurity filtration information and filtration efficiency information, and configure a second-level weight based on the impurity distribution information to calculate the filtration fitness based on the weighted calculation of the impurity filtration fitness and the degradation filtration fitness.

[0066] The parameter optimization module 15 is used to further optimize the filter cooling control parameters according to the filter adaptability, obtain the optimal filter cooling control parameters, perform polymer filter cooling control, and detect and obtain real-time impurity distribution information after filtration is completed, and update the impurity distribution information and impurity distribution uniformity.

[0067] Furthermore, the data acquisition module 11 in the polymer filtration and cooling control system is also used for:

[0068] Collect polymer filtration data within the most recent preset time span to obtain multiple historical impurity filtration information, each of which includes impurity content information; calculate the mean value based on the multiple historical impurity filtration information to obtain impurity distribution information, and calculate the ratio of the variance to the preset variance as the impurity distribution uniformity; collect polymer characteristic information of the polymer to be filtered; obtain the filtration cooling control space, wherein the filtration cooling control space includes the temperature parameter range for filtration cooling control.

[0069] Furthermore, the viscosity analysis module 12 in the polymer filtration and cooling control system is also used for:

[0070] Within the filtration and cooling control space, filtration and cooling control parameters are randomly selected. Based on historical polymer temperature control data, a set of sample polymer feature information and a set of sample filtration and cooling control parameters are collected. Based on the viscosity of polymers with different sample polymer feature information under different sample filtration and cooling control parameters, a set of sample polymer viscosity information is obtained. Using the set of sample polymer feature information, the set of sample filtration and cooling control parameters, and the set of sample polymer viscosity information, a polymer viscosity predictor is trained. Using the polymer viscosity predictor, polymer viscosity prediction analysis is performed on the filtration and cooling control parameters and polymer feature information to obtain polymer viscosity information.

[0071] Furthermore, the filtration prediction module 13 in the aforementioned filtration cooling control system for polymers is also used for:

[0072] Based on historical polymer filtration data, a set of sample polymer viscosity information and a set of sample impurity distribution information are collected. The filtration rate and efficiency of impurities during the filtration process are labeled to obtain a set of sample impurity filtration information and a set of sample filtration efficiency information. Using these sets of sample polymer viscosity information, sample impurity distribution information, sample impurity filtration information, and sample filtration efficiency information, a polymer filtration predictor is trained to predict impurity filtration and filtration efficiency based on the polymer viscosity information and impurity distribution information, thus obtaining impurity filtration information and filtration efficiency information. Based on the uniformity of the impurity distribution, the impurity filtration information is compensated and adjusted to obtain adjusted impurity filtration information.

[0073] Furthermore, the aforementioned filtration and cooling control system for polymers also includes a fitness analysis module for:

[0074] Based on the overheating degradation test data of polymers at different temperatures, a set of sample polymer feature information and a set of sample filtration and cooling control parameters are collected. Based on the magnitude of polymer overheating degradation, a set of sample overheating degradation information is obtained. Using the sample polymer feature information set, sample filtration and cooling control parameter set, and sample overheating degradation information set, an overheating degradation predictor is trained to perform polymer overheating degradation analysis on the polymer feature information and filtration and cooling control parameters to obtain overheating degradation information. Based on the overheating degradation information, degradation filtration fitness is obtained by classification. This classification is performed by inputting the overheating degradation information into a degradation fitness table, which includes an index relationship between sample overheating degradation information and sample degradation filtration fitness, with a negative correlation between the two.

[0075] Furthermore, the weight configuration module 14 in the aforementioned polymer filtration and cooling control system is also used for:

[0076] Based on the ratio of the impurity distribution information to the preset impurity distribution information, and combined with the impurity distribution uniformity, the preset impurity weight is adjusted and configured to obtain the primary impurity filtration weight and the primary filtration efficiency weight. Based on the primary impurity filtration weight and the primary filtration efficiency weight, the ratio of the adjusted impurity filtration information to the preset impurity filtration information, and the ratio of the filtration efficiency information to the preset filtration efficiency information are weighted and calculated to obtain the impurity filtration adaptability.

[0077] Furthermore, the aforementioned filter cooling control system for polymers also includes a fitness calculation module for:

[0078] Based on the ratio of the impurity distribution information to the preset impurity distribution information, the preset impurity filtration weight is modified and configured to obtain the secondary differential filtration weight and the secondary degradation filtration weight; based on the secondary differential filtration weight and the secondary degradation filtration weight, the impurity filtration fitness and degradation filtration fitness are weighted and calculated to obtain the filtration fitness.

[0079] Furthermore, the parameter optimization module 15 in the polymer filtration and cooling control system is also used for:

[0080] Continue optimizing the filtration cooling control parameters within the filtration cooling control space until convergence, outputting the filtration cooling control parameters with the highest filtration adaptability to obtain the optimal filtration cooling control parameters; perform polymer filtration cooling control accordingly, and detect and obtain real-time impurity distribution information after filtration is completed, calculate and update the impurity distribution information and impurity distribution uniformity for use in the filtration control of the next batch of polymer.

[0081] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Figure 1 The method and specific example for controlling the filtration and cooling of polymers in Example 1 are also applicable to the control system for controlling the filtration and cooling of polymers in this embodiment. Through the foregoing detailed description of the method for controlling the filtration and cooling of polymers, those skilled in the art can clearly understand the control system for controlling the filtration and cooling of polymers in this embodiment; therefore, for the sake of brevity, it will not be described in detail here. As the system disclosed in the embodiments corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant details can be found in the method section.

[0082] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0083] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for controlling the cooling of polymer filters, characterized in that, include: Collect polymer filtration data within the most recent preset time span to obtain impurity distribution information and impurity distribution uniformity, as well as collect polymer characteristic information of the polymer to be filtered and obtain the filtration cooling control space. Within the filtration and cooling control space, filtration and cooling control parameters are randomly selected, and polymer viscosity analysis is performed in conjunction with the polymer characteristic information to obtain polymer viscosity information. Based on the polymer viscosity and impurity distribution information, impurity filtration prediction and filtration efficiency prediction are performed to obtain impurity filtration information and filtration efficiency information. The impurity filtration information is then compensated and adjusted based on the impurity distribution uniformity to obtain adjusted impurity filtration information. Furthermore, polymer overheating degradation analysis is performed based on the polymer characteristic information and filtration cooling control parameters to obtain overheating degradation information. Degradation filtration fitness is then classified, including: Based on historical filtration data of polymers, a set of sample polymer viscosity information and a set of sample impurity distribution information are collected. The filtration rate and filtration efficiency of impurities during the filtration process are labeled to obtain a set of sample impurity filtration information and a set of sample filtration efficiency information. Using the sample polymer viscosity information set, sample impurity distribution information set, sample impurity filtering information set, and sample filtering efficiency information set, a polymer filtering predictor is trained to perform impurity filtering prediction and filtering efficiency prediction on the polymer viscosity information and impurity distribution information, thereby obtaining impurity filtering information and filtering efficiency information. Based on the uniformity of impurity distribution, the impurity filtration information is compensated and adjusted to obtain adjusted impurity filtration information; Based on the overheating degradation test data of polymers at different temperatures, a set of polymer characteristic information and a set of sample filtration and cooling control parameters were collected. Based on the extent of polymer overheating degradation, a set of sample overheating degradation information was obtained by labeling. Using the sample polymer feature information set, sample filtration and cooling control parameter set, and sample overheating degradation information set, an overheating degradation predictor is trained to perform polymer overheating degradation analysis based on the polymer feature information and filtration and cooling control parameters, thereby obtaining overheating degradation information; Based on the overheating degradation information, degradation filtration fitness is obtained by classification. The classification is performed by inputting the overheating degradation information into a degradation fitness table. The degradation fitness table includes an index relationship between sample overheating degradation information and sample degradation filtration fitness. Sample overheating degradation information and sample degradation filtration fitness are negatively correlated. Based on the impurity distribution information and impurity distribution uniformity, a first-level weight is configured to calculate the impurity filtration fitness based on the adjusted impurity filtration information and filtration efficiency information. Then, based on the impurity distribution information, a second-level weight is configured to calculate the filtration fitness by weighting the impurity filtration fitness and degradation filtration fitness, including: Based on the ratio of the impurity distribution information to the preset impurity distribution information, and combined with the impurity distribution uniformity, the preset impurity weight is corrected and configured to obtain the primary impurity filtration weight and the primary filtration efficiency weight. Based on the first-level impurity filtration weight and the first-level filtration efficiency weight, the ratio of the adjusted impurity filtration information to the preset impurity filtration information, and the ratio of the filtration efficiency information to the preset filtration efficiency information are weighted and calculated to obtain the impurity filtration adaptability. Based on the filtration adaptability, the filtration cooling control parameters are further optimized to obtain the optimal filtration cooling control parameters. Polymer filtration cooling control is then performed, and real-time impurity distribution information is detected after filtration is completed. The impurity distribution information and impurity distribution uniformity are then updated.

2. The method for controlling the filtration and cooling of polymers according to claim 1, characterized in that, Collect polymer filtration data within the most recent preset time span to obtain impurity distribution information and impurity distribution uniformity, as well as polymer characteristic information of the polymer to be filtered, and obtain the filtration cooling control space, including: Collect polymer filtration data within the most recent preset time span to obtain multiple historical impurity filtration information, each of which includes impurity content information; Based on the multiple historical impurity filtering information, the mean is calculated to obtain impurity distribution information, and the ratio of the variance to the preset variance is calculated as the impurity distribution uniformity. Collect polymer characteristic information of the polymer to be filtered; Obtain the filter cooling control space, wherein the filter cooling control space includes the temperature parameter range for filter cooling control.

3. The method for controlling the filtration and cooling of polymers according to claim 1, characterized in that, Within the filtration and cooling control space, filtration and cooling control parameters are randomly selected, and polymer viscosity analysis is performed in conjunction with the polymer characteristic information, including: Within the filter cooling control space, filter cooling control parameters are randomly selected; Based on historical data of polymer temperature control, a set of sample polymer characteristic information and a set of sample filtration and cooling control parameters are collected. Based on the viscosity of polymers with different sample polymer characteristic information under different sample filtration and cooling control parameters, a set of sample polymer viscosity information is obtained by labeling. A polymer viscosity predictor is trained using the sample polymer feature information set, the sample filtering and cooling control parameter set, and the sample polymer viscosity information set. The polymer viscosity predictor is used to perform polymer viscosity prediction analysis on the filter cooling control parameters and polymer characteristic information to obtain polymer viscosity information.

4. The method for controlling the filtration and cooling of polymers according to claim 1, characterized in that, Based on the impurity distribution information, a secondary weight is configured, and the filtration fitness is obtained by weighting the impurity filtration fitness and degradation filtration fitness, including: Based on the ratio of the impurity distribution information to the preset impurity distribution information, the preset impurity filtration weight is modified and configured to obtain the secondary differential filtration weight and the secondary degradation filtration weight. The filtration fitness is obtained by weighting the impurity filtration fitness and the degradation filtration fitness based on the secondary differential filtration weight and the secondary degradation filtration weight.

5. The method for controlling the filtration and cooling of polymers according to claim 1, characterized in that, Based on the filtration adaptability, the filtration cooling control parameters are further optimized to obtain the optimal filtration cooling control parameters. Polymer filtration cooling control is then implemented, and real-time impurity distribution information is detected after filtration, including: Continue to optimize the filter cooling control parameters within the filter cooling control space until convergence, and output the filter cooling control parameters with the highest filter fitness to obtain the optimal filter cooling control parameters. The polymer filtration cooling control is performed as described above, and real-time impurity distribution information is detected after filtration is completed. The impurity distribution information and impurity distribution uniformity are calculated and updated for use in the filtration control of the next batch of polymer.

6. A filtration and cooling control system for polymers, characterized in that, The step of implementing the filter cooling control method for polymers according to any one of claims 1 to 5, wherein the filter cooling control system for polymers comprises: The data acquisition module is used to acquire polymer filtration data within the most recent preset time span, obtain impurity distribution information and impurity distribution uniformity, acquire polymer characteristic information of the polymer to be filtered, and obtain the filtration cooling control space. A viscosity analysis module is used to randomly select filter cooling control parameters within the filter cooling control space and perform polymer viscosity analysis in combination with the polymer characteristic information to obtain polymer viscosity information. The filter prediction module is used to predict impurity filtration and filtration efficiency based on the polymer viscosity information and impurity distribution information, obtain impurity filtration information and filtration efficiency information, compensate and adjust the impurity filtration information according to the impurity distribution uniformity, obtain adjusted impurity filtration information, and perform polymer overheating degradation analysis based on the polymer characteristic information and filtration cooling control parameters to obtain overheating degradation information and classify the degradation filtration adaptability. The weight configuration module is used to configure a first-level weight based on the impurity distribution information and the impurity distribution uniformity, calculate the impurity filtration fitness based on the adjusted impurity filtration information and filtration efficiency information, and configure a second-level weight based on the impurity distribution information to calculate the filtration fitness based on the weighted calculation of the impurity filtration fitness and the degradation filtration fitness. The parameter optimization module is used to further optimize the filter cooling control parameters based on the filter adaptability, obtain the optimal filter cooling control parameters, perform polymer filter cooling control, and detect and obtain real-time impurity distribution information after filtration is completed, and update the impurity distribution information and impurity distribution uniformity.

Images