A PVA-PET composite film preparation control system based on data analysis

Abstract

The present invention discloses a PVA-PET composite film preparation control system based on data analysis, which belongs to the technical field of data processing and analysis, and includes a data acquisition module, a data analysis module, a control strategy generation and early warning module, and a feedback optimization module that are interconnected and communicated with each other. The data acquisition module collects key parameters in the preparation process of the PVA-PET composite film; the data analysis module performs data preprocessing, statistical analysis, and machine learning training on the key parameters collected in the preparation process of the PVA-PET composite film. The present invention can acquire and monitor the key parameters in the preparation process of the PVA-PET composite film in real time by selecting suitable sensors and establishing an effective data acquisition system. The relationship between the key parameters is established by combining the preliminary identification with the secondary identification results. The data accuracy and control effectiveness of the PVA-PET composite film preparation control system are improved.

Description

Technical Field

[0001] The invention relates to the technical field of data processing and analysis, and in particular to a PVA-PET composite film preparation control system based on data analysis. Background Art

[0002] PVA-PET composite film is a film made of polyvinyl alcohol (PVA) and polyethylene terephthalate (PET). The composite film combines the excellent water solubility and biocompatibility of PVA with the excellent mechanical properties and chemical resistance of PET, so it has broad application prospects in many fields such as food packaging, medical dressings, protective films for electronic products, and insulating materials.

[0003] The preparation process of PVA-PET composite film usually involves multiple steps, including solution preparation, film forming, drying and post-processing, etc. Its preparation process directly affects the quality of PVA-PET composite film. Therefore, an efficient and intelligent control system is needed to ensure product quality and production efficiency. The PVA-PET composite film preparation control system is an intelligent system that integrates advanced sensor technology, automatic control, data analysis and machine learning, aiming to improve the production efficiency and quality of the film. With the continuous development of intelligent manufacturing, the application of this system will further promote the technological progress and market competitiveness of the membrane material industry.

[0004] However, the current PVA-PET composite film preparation control system still has the following problems in terms of intelligence and production efficiency:

[0005] First, the sensors that collect data may age due to long-term use or be installed in an improper position or be affected by the external environment (such as temperature, humidity, vibration, etc.), which may cause sensor failure or improper calibration, resulting in inaccurate data collection.

[0006] Secondly, due to the insufficient computing power of data processing equipment, it is impossible to quickly process large amounts of real-time data; the algorithms used are highly complex and require a long processing time; and there are delays in the data transmission process; resulting in data processing and feedback delays, affecting real-time control capabilities.

[0007] Secondly, the control model used was too simple and did not take into account all influencing factors, resulting in a slow response; the system failed to optimize itself based on historical data, resulting in an inability to adapt to new situations and a lack of self-learning ability; as a result, the control system had poor adaptability to changes and was unable to cope with complex production environments.

[0008] To solve the above problems, the present application proposes a PVA-PET composite film preparation control system based on data analysis to improve the intelligence level and production efficiency of the system. Summary of the invention

[0009] In order to solve the problems existing in the above background technology, the present invention proposes a PVA-PET composite film preparation control system based on data analysis to improve the intelligence level and production efficiency of the system. Specifically, the present invention adopts the following technical solutions:

[0010] The present application provides a PVA-PET composite film preparation control system based on data analysis, comprising: a data acquisition module, a data analysis module, a control strategy generation and early warning module, and a feedback optimization module that are interconnected; wherein,

[0011] A data acquisition module configured to acquire key parameters in the preparation process of the PVA-PET composite film, wherein the key parameters include the concentration and temperature of the PVA solution, the thickness of the PET film, the temperature and humidity during the drying process, and the production speed and flow rate of the PVA-PET composite film;

[0012] A data analysis module is configured to perform data preprocessing and statistical analysis as well as machine learning training on key parameters collected during the preparation process of the PVA-PET composite film to generate data analysis results;

[0013] A control strategy generation and early warning module, configured to generate a control strategy and an early warning mechanism according to the data analysis results obtained by the data analysis module;

[0014] A feedback optimization module is configured to regularly evaluate the performance of the PVA-PET composite film, collect production data and quality test results, and form a feedback loop; evaluating the performance of the film includes evaluating the physical and chemical properties of the film to obtain evaluation results; based on the evaluation results, the feedback optimization module adjusts and optimizes the production process and control strategy;

[0015] The data preprocessing, statistical analysis and machine learning training of the key parameters collected during the preparation of the PVA-PET composite film specifically include:

[0016] Preprocess the key parameters collected during the preparation of the PVA-PET composite film to generate preprocessing result data;

[0017] Performing statistical analysis on the preprocessing result data to generate statistical analysis results;

[0018] Combine statistical analysis results with historical data to train machine learning models.

[0019] As a preferred solution of the present application, the statistical analysis of the preprocessing result data to generate the statistical analysis results includes:

[0020] Perform data cleaning, identify missing values ​​and outliers, and perform missing and outlier processing;

[0021] Perform data organization, including data standardization or normalization, data type conversion, and generation of relationship features.

[0022] As a preferred solution of the present application, the data cleaning, identification of missing values ​​and outliers, and missing and outlier processing include:

[0023] Identify missing values;

[0024] Process the identified missing values, including deleting missing values ​​or filling in missing values;

[0025] Identify outliers;

[0026] The identified outliers are processed, including once identified as outliers, determining the relevance of the outliers to each data subset.

[0027] As a preferred solution of the present application, the identifying of abnormal values ​​includes:

[0028] The collected key parameters, namely, the concentration and temperature of the PVA solution, the thickness of the PET film, the temperature and humidity during the drying process, and the production speed and flow rate of the PVA-PET composite film, are classified to form a concentration and temperature data subset of the PVA solution, a thickness data subset of the PET film, a flow data subset, a temperature and humidity data subset during the drying process, and a production speed and flow rate data subset of the PVA-PET composite film;

[0029] Calculate the Z-score value of each data in each data subset;

[0030] Identify outliers based on the Z-score value of each data in each data subset.

[0031] As a preferred solution of the present application, the statistical analysis of the pretreatment result data is performed to generate statistical analysis results; including: statistical analysis of key parameters to identify the main factors affecting membrane performance; using correlation analysis or regression analysis methods to find out the relationship between key parameters.

[0032] As a preferred embodiment of the present application, the key parameters are statistically analyzed to identify the main factors affecting membrane performance, including: calculating the mean, standard deviation, maximum and minimum values ​​of each key parameter as descriptive statistical indicators; visualizing the data distribution according to the descriptive statistical indicators to obtain the distribution characteristics of each parameter; and preliminarily identifying the main factors affecting membrane performance among the key parameters according to the distribution characteristics of each parameter.

[0033] As a preferred embodiment of the present application, it also includes: comparing and analyzing the primary identified main factors with the factors highly correlated with membrane performance identified using correlation analysis or regression analysis methods to obtain the relationship between key parameters.

[0034] The present application also provides an electronic device, comprising a processor, a memory, an input device and an output device coupled to each other; wherein the memory is used to store computer program code, the computer program code includes computer instructions, and when the processor executes the computer instructions, the electronic device executes a PVA-PET composite film preparation control system based on data analysis as described above.

[0035] Compared with the prior art, the present invention has the following beneficial effects:

[0036] The present invention can obtain and monitor the concentration and temperature of the PVA solution, the thickness of the PET film, and the temperature, humidity, production speed and flow rate during the drying process in real time by selecting appropriate sensors and establishing an effective data acquisition system. This will help improve the production efficiency and product quality of the PVA-PET composite film and provide important support for subsequent data analysis and control strategies.

[0037] The present invention not only preliminarily identifies the main factors affecting the film performance through statistical analysis, but also secondary identifies the factors highly correlated with the film performance by using correlation analysis, regression analysis and other methods, and establishes the relationship between key parameters by combining the preliminary identification with the secondary identification results. The data accuracy of the PVA-PET composite film preparation control system can be greatly improved, thereby improving the effectiveness of the control, so that the prepared PVA-PET composite film has higher quality and the production efficiency is greatly improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0039] Figure 1 It is a structural schematic diagram of a PVA-PET composite film preparation control system based on data analysis according to one embodiment of the present invention;

[0040] Figure 2 A schematic diagram of the process of data preprocessing, statistical analysis and machine learning training according to an embodiment of the present invention;

[0041] Figure 3 A schematic diagram of a flow chart of the steps of generating statistical analysis results according to an embodiment of the present invention;

[0042] Figure 4 A schematic diagram of a flow chart of a data cleaning step according to an embodiment of the present invention;

[0043] Figure 5 A schematic structural diagram of an electronic device according to another embodiment of the present invention; DETAILED DESCRIPTION

[0044] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. It should be noted that relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0045] The PVA-PET composite film preparation control system is an intelligent system that integrates advanced sensor technology, automatic control, data analysis and machine learning. The main objectives of the PVA-PET composite film preparation control system are: Real-time monitoring: Real-time collection of key parameters in the production process (such as temperature, humidity, flow rate, film thickness, etc.). Intelligent control: Automatically adjust production parameters based on real-time data to optimize film performance. Quality assurance: Ensure that the final product meets the expected standards in terms of physical and chemical properties. Data analysis: Continuous optimization and improvement through data analysis and machine learning technology. The PVA-PET composite film preparation control system consists of hardware and software parts, including hardware including sensors: used to measure key indicators such as temperature, humidity, flow, and film thickness; PLC (programmable logic controller): used to control the production process in real time, process sensor data and execute control instructions; HMI (human-machine interface): provides an interactive interface between the user and the system, and displays real-time data and system status. The software includes data acquisition software responsible for real-time collection and storage of production data, data analysis tools used to analyze historical data, identify key factors affecting film performance, optimize production processes, and control algorithms to implement automated control strategies and adjust production parameters in real time based on data feedback.

[0046] The PVA-PET composite film preparation control system can monitor various parameters in the production process in real time through sensors and data acquisition systems; automatically adjust key production parameters such as temperature, humidity and flow rate according to real-time data and preset conditions; include an integrated online quality inspection system to ensure that the thickness, transparency and other performance indicators of the film meet the standards; and data storage and analysis: store historical data, conduct trend analysis and machine learning, and identify potential improvement opportunities. Provide decision support through data analysis to help companies develop more scientific production plans.

[0047] The specific implementation process of the present invention will be described in detail below.

[0048] Embodiment 1

[0049] The present invention provides a PVA-PET composite film preparation control system based on data analysis, such as Figure 1 As shown, it includes: a data acquisition module, a data analysis module, a control strategy generation and early warning module, and a feedback optimization module that are interconnected.

[0050] The data acquisition module is configured to collect key parameters in the preparation process of the PVA-PET composite film and store them in a database. The key parameters include the concentration and temperature of the PVA solution, the thickness of the PET film, the temperature and humidity during the drying process, and the production speed and flow rate of the PVA-PET composite film.

[0051] Among them, the concentration and temperature of the PVA solution have an important influence on the properties and quality of the PVA-PET composite film. The concentration of the PVA solution refers to the mass of PVA in a unit volume of solution, usually expressed as a percentage (such as w / v%). For example, a 10% PVA solution means that 10 grams of PVA is contained in every 100 ml of solution. Generally speaking, the higher the concentration of the PVA solution, the thicker the film formed after coating is usually, because the viscosity of the high-concentration solution is larger and the fluidity is poor. The concentration of the PVA solution will affect the mechanical strength, transparency, swelling and gas permeability of the film. For example, too high a concentration may increase the brittleness of the film. At the same time, changes in the concentration of the PVA solution will affect the uniformity of the coating process, and too high or too low a concentration may result in uneven film thickness. The temperature of the PVA solution refers to the actual temperature of the PVA solution during the preparation process, usually expressed in degrees Celsius (°C).

[0052] In an embodiment of the present invention, the concentration data of the PVA solution is collected by a solution concentration sensor, and the temperature data of the PVA solution is collected by a temperature sensor. In the embodiment of the present invention, there is no limitation on the specific solution concentration sensor and temperature sensor, and a solution concentration sensor commonly used in the art can be selected to collect the concentration data of the PVA solution, for example, a refractive index sensor: the concentration is estimated by measuring the refractive index of the solution; a conductivity sensor: the concentration is determined according to the change in the conductivity of the solution; and a density meter: the concentration is determined by measuring the density of the solution. A temperature sensor commonly used in the art can be selected to collect the temperature data of the PVA solution, for example, a thermocouple, a thermistor (RTD), and a digital temperature sensor (such as DS18B20).

[0053] In an embodiment of the present invention, the solution concentration sensor and the temperature sensor are also installed in the stirring tank or the conveying flow pipeline to ensure the accuracy and real-time performance of the measured solution concentration and temperature.

[0054] Among them, the thickness of PET film refers to the actual physical thickness of the polyethylene terephthalate (PET) base film, which is usually measured in micrometers (μm) or millimeters (mm). The thickness of PET film is a key parameter that directly affects the performance and application effect of PVA-PET composite film, including that the increase in the thickness of PET film usually improves the mechanical strength and tear resistance of the film, but too thick may increase the brittleness of the material; the increase in the thickness of PET film will also reduce the permeability of gas and water vapor; at the same time, too thick PET film may increase light scattering and affect transparency.

[0055] In an embodiment of the present invention, the thickness data of the PET film is collected by a thickness sensor, and the thickness sensor can be selected from commonly used thickness sensors in the art, including but not limited to: a laser ranging sensor: using a laser beam to measure the thickness of the film, which has the advantages of high precision and non-contact; an ultrasonic thickness meter: measuring the thickness by the propagation time of ultrasonic waves in the film, which is suitable for various materials; and a capacitive thickness sensor: measuring the thickness of the film by capacitance changes, which is suitable for thin film materials.

[0056] In an embodiment of the present invention, the thickness sensor is also installed in various links of the production line during the preparation of the PVA-PET composite film, including the discharge port of the film production line, the coater, the cooling zone and the conveyor belt before cutting, etc., to ensure real-time online monitoring and adjustment and control of the thickness of the PET film.

[0057] The temperature and humidity during the drying process refer to the temperature and relative humidity of the air or substrate set during the drying process. The temperature is usually expressed in degrees Celsius (°C), such as 30°C; the humidity is usually expressed in percentage, such as relative humidity below 60%.

[0058] In an embodiment of the present invention, an appropriate drying temperature helps to effectively volatilize the water or other solvents in the PVA coating, thereby accelerating the drying process. Too high a temperature may cause thermal deformation or degradation of the film material, while too low a temperature may cause incomplete drying, affecting the performance of the film. Therefore, it is usually necessary to control within a certain range (such as 60°C to 120°C) to ensure the drying effect and physical and chemical properties of the film. In an embodiment of the present invention, an environment with low relative humidity helps to improve the drying efficiency, because lower humidity can promote the volatilization of water; while too high humidity may cause water droplets, bubbles or other defects on the surface of the film, affecting the uniformity and adhesion of the film. Therefore, it is usually necessary to control the relative humidity at a lower level (such as below 30%) to ensure an effective drying process. It can be seen that in the preparation process of the PVA-PET composite film, the temperature and humidity during the drying process directly affect the drying efficiency and final performance of the film, and reasonable control of the temperature and humidity during the drying process helps to improve the quality and consistency of the film.

[0059] In an embodiment of the present invention, temperature and humidity data are collected during the drying process by using a temperature sensor (such as a thermocouple and a thermistor (RTD)) and a humidity sensor (such as a capacitive humidity sensor and a thermal conductivity humidity sensor).

[0060] In an embodiment of the present invention, the temperature and humidity sensors are also installed at the air inlet, air outlet and inside of drying equipment (such as hot air drying oven, vacuum dryer and infrared drying equipment, etc.) to ensure accurate monitoring of environmental conditions during the drying process.

[0061] Among the production speed and flow rate parameters of PVA-PET composite film, the production speed usually refers to the speed at which the film material passes through the equipment during the production process, usually expressed in meters per minute (m / min). Flow rate usually refers to the rate at which the coating liquid (such as PVA solution) flows in the coating equipment during the film preparation process, usually expressed in liters per minute (L / min) or milliliters per minute (mL / min). Among them, the coating thickness, drying conditions and equipment performance will affect the production speed of the PVA-PET composite film; while the coating method, the viscosity of the coating liquid and the film thickness requirements will affect the flow rate parameters. In the preparation process of PVA-PET composite film, the production speed and flow rate are closely related parameters. Appropriate adjustment and optimization of these two parameters can improve production efficiency, reduce costs, and ensure the performance and quality of the film. Therefore, in actual production, it is necessary to comprehensively consider and adjust according to the specific material properties and equipment conditions.

[0062] In an embodiment of the present invention, the production speed and flow data of the PVA-PET composite film are collected by a speed sensor (such as an encoder or a photoelectric sensor, etc.) and a flow sensor (such as a turbine flowmeter or an electromagnetic flowmeter, etc.). In an embodiment of the present invention, the flow sensor is also installed in the PVA solution delivery pipeline, and the speed sensor is installed on the moving parts related to the production line.

[0063] The present invention can obtain and monitor the concentration and temperature of the PVA solution, the thickness of the PET film, and the temperature, humidity, production speed and flow rate during the drying process in real time by selecting appropriate sensors and establishing an effective data acquisition system. This will help improve the production efficiency and product quality of the PVA-PET composite film and provide important support for subsequent data analysis and control strategies.

[0064] The data analysis module is configured to perform data preprocessing, statistical analysis and machine learning training on the key parameters collected during the preparation of the PVA-PET composite film to generate data analysis results. Preprocessing includes data cleaning and sorting to remove noise and outliers; the statistical analysis includes statistical analysis of key parameters to identify the main factors affecting the film performance, and use correlation analysis, regression analysis and other methods to find out the relationship between key parameters; machine learning training is to use machine learning models (such as linear regression, decision trees, random forests, etc.) based on historical data to predict the performance of the film, and to train machine learning models so as to provide real-time feedback and optimize control parameters during the production process. Figure 2 As shown, the specific process includes:

[0065] Step 1, preprocessing the key parameters collected during the preparation of the PVA-PET composite film to generate preprocessing result data; the key parameters include the concentration and temperature of the PVA solution, the thickness of the PET film, the temperature and humidity during the drying process, and the production speed and flow rate of the PVA-PET composite film. The preprocessing includes data cleaning and sorting, removing noise and outliers, and ensuring data quality, such as Figure 3 As shown, specifically including:

[0066] S10, perform data cleaning, identify missing values ​​and outliers, and perform missing and outlier processing. Figure 4 As shown in the figure, the data cleaning includes the following processes:

[0067] S101. Identify missing values. Missing values ​​are missing parts of the data, which may affect the results of data analysis. For example, use data analysis tools (such as the isnull() function in the Pandas library) to identify missing values.

[0068] S102. Process the missing values ​​after identification, including deleting missing values ​​or filling missing values. Specifically, if the missing values ​​account for a small proportion, the records containing missing values ​​can be directly deleted. For continuous variables (such as concentration, temperature, thickness, etc.), the mean, median or mode can be used for filling; for time series data, forward filling or backward filling methods can be used.

[0069] S103, identifying outliers, where an outlier refers to a value that is significantly different from other data points, which may be caused by equipment failure, sensor error, or data entry error. In an embodiment of the present invention, the outlier identification method includes:

[0070] S100. Classify the collected key parameters, i.e., the concentration and temperature of the PVA solution, the thickness of the PET film, the temperature and humidity during the drying process, and the production speed and flow rate of the PVA-PET composite film, to form a data subset of the concentration and temperature of the PVA solution, a data subset of the thickness of the PET film, a flow rate data subset, a data subset of the temperature and humidity during the drying process, and a data subset of the production speed and flow rate of the PVA-PET composite film.

[0071] S200, calculate the Z-score value of each data in each data subset. The Z-score value is calculated using the Z-score method. Specifically:

[0072] The Z-score calculation includes:

[0073] Calculate the value of each data x in each data subset i The mean and standard deviation std;

[0074] The Z-score value of each data is calculated based on the mean and standard deviation. The specific formula is:

[0075] z_score i = (x i - mean i ) / std i , i represents the amount of data in each data subset.

[0076] S300, identifying outliers according to the Z-score value of each data in each data subset, which specifically includes: identifying outliers according to the Z-score value of each data in each data subset, and generally, data with a Z-score value greater than 3 or less than -3 are regarded as outliers.

[0077] S104, processing the identified outliers, including once identified as outliers, determining the relevance of the outliers to each data subset. If it is obviously irrelevant, directly delete the outliers; if it is determined that the outliers are related to the data subset, replace the outliers with the mean or median, or directly mark the outliers in the data subset to establish an outlier data set for subsequent analysis.

[0078] S20, data organization, including data standardization or normalization, data type conversion, and generation of relationship features.

[0079] Among them, data standardization can use the Z-score standardization method to convert the data into a distribution with a mean of 0 and a standard deviation of 1; normalization can use the Min-Max scaling method to scale the data to the [0, 1] interval to eliminate the impact of the dimension.

[0080] The purpose of data type conversion is to ensure that all data types are correct. For example, converting temperature, concentration, flow rate, etc. into floating-point types can avoid calculation errors caused by strings or other types.

[0081] Among them, generating relationship features refers to generating new features (such as the interaction terms between temperature and humidity, the interaction terms between temperature and flow, and the interaction terms between thickness and production speed, etc.) in order to better capture the relationship between key parameter data.

[0082] Step 2, perform statistical analysis on the pretreatment result data to generate statistical analysis results; including performing statistical analysis on key parameters to identify the main factors affecting membrane performance; and using correlation analysis, regression analysis and other methods to find out the relationship between key parameters.

[0083] Among them, statistical analysis is performed on key parameters to identify the main factors affecting membrane performance, including: calculating descriptive statistical indicators such as the mean, standard deviation, maximum value, and minimum value of each key parameter; visualizing data distribution based on descriptive statistical indicators, such as using histograms, box plots, etc., to obtain the distribution characteristics of each parameter; based on the distribution characteristics of each parameter, preliminarily identifying the main factors affecting membrane performance among the key parameters.

[0084] Among them, correlation analysis, regression analysis and other methods are used to find out the relationship between key parameters.

[0085] For the correlation analysis method, it includes calculating the correlation coefficient (such as Pearson correlation coefficient, Spearman rank correlation coefficient, etc.) between the main factors in the key parameters and the membrane performance indicators to identify the strongly correlated factors. Alternatively, a heat map is used to visualize the correlation matrix to quickly identify factors that are highly correlated with membrane performance.

[0086] For regression analysis methods, a linear regression model can be constructed to evaluate the influence of each key parameter on membrane performance and determine the significant influencing factors. Alternatively, a multivariate regression model can be used to consider the combined influence of multiple parameters and identify the main influencing factors and their relative importance. In this way, factors that are highly correlated with membrane performance can be quickly identified.

[0087] In one embodiment of the present invention, the main factors initially identified are compared and analyzed with factors highly correlated with membrane performance identified using correlation analysis, regression analysis and other methods to obtain the relationship between key parameters.

[0088] The layout of the present invention preliminarily identifies the main factors affecting the film performance through statistical analysis, and also uses correlation analysis, regression analysis and other methods to secondary identify factors highly related to the film performance, and establishes the relationship between key parameters through preliminary identification combined with secondary identification results. The data accuracy of the PVA-PET composite film preparation control system can be greatly improved, thereby improving the effectiveness of the control, so that the prepared PVA-PET composite film has higher quality and greatly improved production efficiency.

[0089] Step 3, training the machine learning model in combination with the statistical analysis results and historical data. This includes predicting the performance of the membrane using a machine learning model (such as linear regression, decision tree, random forest, etc.) based on the historical data and the above statistical analysis results, obtaining the expected performance of the membrane based on the historical data, and obtaining the actual performance of the membrane based on the statistical analysis results; comparing the expected performance of the membrane with the actual performance, calculating the error and marking the data, updating the relevant performance data of the membrane based on the error calculation results and the data marking results, and generating an optimized training data set for the machine learning model based on the updated relevant performance data of the membrane, so as to provide real-time feedback and optimize the control parameters during the production process. Retrain the machine learning model based on the optimized training data set to further improve the prediction ability of the machine learning model, so as to improve the prediction accuracy and reliability of the actual machine learning model in the control system for the preparation of PVA-PET composite membranes.

[0090] Among them, obtaining the expected performance of the membrane based on historical data includes obtaining the typical performance and variability of the membrane through analysis and calculation of historical data; and then setting the expected performance of the membrane based on the results of calculation and analysis combined with industry standards.

[0091] The control strategy generation and early warning module is configured to generate control strategies and early warning mechanisms according to the data analysis results obtained by the data analysis module.

[0092] The generation of control strategies includes real-time monitoring of the production process and automatic adjustment of production parameters based on feedback data, including:

[0093] According to the data analysis results, set reasonable production parameter ranges (such as temperature, humidity, flow, etc.) and control operations. Including,

[0094] According to the data analysis results and the real-time collected PVA solution concentration and temperature data, the heating, cooling or PVA addition operations are automatically adjusted to maintain the set process conditions;

[0095] According to the data analysis results and the real-time collected PET film thickness data, the production parameters (such as extrusion speed, cooling speed, etc.) are automatically adjusted to keep the film thickness within the set range;

[0096] According to the data analysis results and the real-time collected temperature and humidity as well as production speed and flow data during the drying process, the operating parameters of the drying equipment are automatically adjusted to maintain the set process conditions.

[0097] Among them, generating an early warning mechanism includes establishing the upper and lower limit alarm ranges of the early warning mechanism. When the key parameters in the data analysis results, namely the concentration and temperature of the PVA solution, the thickness of the PET film, the temperature and humidity during the drying process, and the production speed and flow rate of the PVA-PET composite film, which are factors highly related to the film performance, exceed the set upper and lower limit alarm ranges, the system automatically issues an alarm to prompt the operator to handle the exception or perform system self-inspection and self-repair control.

[0098] The feedback optimization module is configured to regularly evaluate the performance of the membrane, collect production data and quality test results, and form a feedback loop. Among them, evaluating the performance of the membrane includes evaluating the physical and chemical properties of the membrane and obtaining evaluation results, such as the thickness, transparency, pressure resistance, chemical resistance, etc. of the membrane.

[0099] Furthermore, based on the evaluation results, the feedback optimization module will adjust and optimize the production process and control strategy to improve the performance and production efficiency of the membrane. For example, the feedback optimization module found in the evaluation that after a period of production, the transparency of the membrane gradually decreased, which may be due to changes in raw materials or wear and tear of equipment. The feedback optimization module will collect relevant data, analyze the reasons, and make improvement suggestions, such as replacing raw materials or maintaining equipment, to improve the quality of the produced membrane.

[0100] Among them, the control strategy generation and early warning module and the feedback optimization module form a closed-loop system in the production process. The control strategy generation and early warning module performs real-time response and control, while the feedback optimization module performs long-term optimization and improvement.

[0101] Furthermore, the control strategy generation and early warning module relies on the real-time data provided by the data analysis module, while the feedback optimization module relies on the long-term collected production data and quality inspection results. Both require accurate data support to ensure the effectiveness of the generated strategies and optimization suggestions.

[0102] Furthermore, the control strategy generated by the control strategy generation and early warning module can directly affect the evaluation results of the feedback optimization module. For example, if the control strategy successfully solves the problem of membrane thickness fluctuation, the feedback optimization module will show that the performance of the membrane has improved in subsequent evaluations, thus forming a positive feedback. Conversely, if the feedback optimization module finds new problems or performance degradation, the control strategy generation and early warning module needs to adjust its strategy based on these feedbacks to meet the emerging challenges.

[0103] The present invention can dynamically adjust and optimize the production process through the collaborative work of the control strategy generation and early warning module and the feedback optimization module. The control strategy generation and early warning module provides immediate response in real-time monitoring, while the feedback optimization module performs performance evaluation and strategy optimization from a long-term perspective to ensure the stability and efficiency of the production process. Through collaborative work, production efficiency and product quality can be effectively improved, and potential risks and losses can be reduced.

[0104] Embodiment 2

[0105] like Figure 5 As shown, the present invention also provides an electronic device 2, including a processor 21 and a memory 22, the memory 22 is used to store computer program codes, the computer program codes include computer instructions, when the processor 21 executes the computer instructions, the electronic device executes a control method corresponding to a PVA-PET composite film preparation control system based on data analysis in the above-mentioned embodiment.

[0106] The electronic device 2 also includes an input device 24 and an output device 23. The processor 21, the memory 22, the input device 24 and the output device 23 are coupled via a connector, and the connector includes various interfaces, transmission lines or buses, etc., which are not limited in the embodiments of the present invention. It should be understood that in various embodiments of the present invention, coupling refers to mutual connection in a specific manner, including direct connection or indirect connection through other devices, for example, through various interfaces, transmission lines, buses, etc.

[0107] The processor 21 may be one or more graphics processing units (GPUs). When the processor 21 is a GPU, the GPU may be a single-core GPU or a multi-core GPU. Optionally, the processor 21 may be a processor group consisting of multiple GPUs, and the multiple processors are coupled to each other via one or more buses. Optionally, the processor may also be other types of processors, etc., which are not limited in the embodiments of the present invention.

[0108] The memory 22 can be used to store computer program instructions and various computer program codes including program codes for executing the scheme of the present invention. Optionally, the memory includes but is not limited to random access memory (RAM), read-only memory (ROM), erasable programmable read only memory (EPROM), or portable read only memory (CD-ROM), which is used for related instructions and data.

[0109] The input device 24 is used to input data and / or signals, and the output device 23 is used to output data and / or signals. The output device 23 and the input device 24 can be independent devices or an integrated device.

[0110] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be 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 the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A PVA-PET composite film preparation control system based on data analysis, characterized in that: include: The data acquisition module, data analysis module, control strategy generation and early warning module and feedback optimization module are interconnected and communicated with each other; A data acquisition module is configured to collect key parameters in the preparation process of the PVA-PET composite film, wherein the key parameters include the concentration and temperature of the PVA solution, the thickness of the PET film, the temperature and humidity during the drying process, and the production speed and flow rate of the PVA-PET composite film; and is also configured to collect concentration data of the PVA solution through a solution concentration sensor, collect temperature data of the PVA solution through a temperature sensor, collect thickness data of the PET film through a thickness sensor, collect temperature and humidity data during the drying process through a temperature sensor and a humidity sensor, and collect production speed and flow rate data of the PVA-PET composite film through a speed sensor and a flow rate sensor; A data analysis module is configured to perform data preprocessing and statistical analysis as well as machine learning training on key parameters collected during the preparation process of the PVA-PET composite film to generate data analysis results; A control strategy generation and early warning module, configured to generate a control strategy and an early warning mechanism according to the data analysis results obtained by the data analysis module; A feedback optimization module is configured to regularly evaluate the performance of the PVA-PET composite film, collect production data and quality test results, and form a feedback loop; evaluating the performance of the film includes evaluating the physical and chemical properties of the film to obtain evaluation results; based on the evaluation results, the feedback optimization module adjusts and optimizes the production process and control strategy; The data preprocessing, statistical analysis and machine learning training of the key parameters collected during the preparation of the PVA-PET composite film specifically include: Preprocess the key parameters collected during the preparation of the PVA-PET composite film to generate preprocessing result data; Performing statistical analysis on the preprocessing result data to generate statistical analysis results; Combine statistical analysis results with historical data to train machine learning models.

2. A PVA-PET composite film preparation control system based on data analysis according to claim 1, characterized in that: Perform data cleaning, identify missing values ​​and outliers, and perform missing and outlier processing; Perform data organization, including data standardization or normalization, data type conversion, and generation of relationship features.

3. A PVA-PET composite film preparation control system based on data analysis according to claim 2, characterized in that: The data cleaning, identification of missing values ​​and outliers, and missing and outlier processing include: Identify missing values; Process the identified missing values, including deleting missing values ​​or filling in missing values; Identify outliers; The identified outliers are processed, including once identified as outliers, determining the relevance of the outliers to each data subset.

4. A PVA-PET composite film preparation control system based on data analysis according to claim 3, characterized in that: The identifying of outliers comprises: The collected key parameters, namely, the concentration and temperature of the PVA solution, the thickness of the PET film, the temperature and humidity during the drying process, and the production speed and flow rate of the PVA-PET composite film, are classified to form a data subset of the concentration and temperature of the PVA solution, a data subset of the thickness of the PET film, a data subset of the temperature and humidity during the drying process, and a data subset of the production speed and flow rate of the PVA-PET composite film; Calculate the Z-score value of each data in each data subset; Identify outliers based on the Z-score value of each data in each data subset.

5. A PVA-PET composite film preparation control system based on data analysis according to claim 1, characterized in that: The method of performing statistical analysis on the pretreatment result data to generate statistical analysis results includes: performing statistical analysis on key parameters to identify the main factors affecting membrane performance; and using correlation analysis or regression analysis methods to find out the relationship between key parameters.

6. A PVA-PET composite film preparation control system based on data analysis according to claim 5, characterized in that: The statistical analysis of key parameters is performed to identify the main factors affecting membrane performance, including: calculating the mean, standard deviation, maximum value and minimum value of each key parameter as descriptive statistical indicators; visualizing data distribution according to the descriptive statistical indicators to obtain the distribution characteristics of each parameter; and preliminarily identifying the main factors affecting membrane performance among the key parameters according to the distribution characteristics of each parameter.

7. A PVA-PET composite film preparation control system based on data analysis according to claim 6, characterized in that: Also includes: The primary factors initially identified were compared and analyzed with the factors highly correlated with membrane performance identified using correlation analysis or regression analysis to obtain the relationships between key parameters.

Images