Water-based resin quality on-line detection method

Abstract

The invention provides a water-based resin quality online detection method, and relates to the technical field of material detection. The method comprises the following steps: constructing a high-dimensional chimeric tensor model based on collected original data, and generating a high-dimensional chimeric tensor; further, through a time-frequency characteristic enhancement technology, obtaining a tensor after time-frequency characteristic enhancement; based on the tensor after time-frequency characteristic enhancement, correcting a key quality parameter prediction value of the water-based resin by adopting a prediction method based on a high-dimensional information embedded tensor and combining an adaptive disturbance factor; on the basis of the key quality parameter predicted value of the water-based resin, calculating a water-based resin quality online detection result; and judging whether the quality of the water-based resin meets the standard or not by comparing a water-based resin quality online detection result with a set quality tolerance threshold value. The problem that an existing water-based resin quality detection method is insufficient in environment fluctuation, non-linear relation capture and complex working condition adaptation, and consequently prediction accuracy is lowered is solved.

Description

Technical Field

[0001] The invention relates to the technical field of material detection, and in particular to an online detection method for water-based resin quality. Background Art

[0002] As an environmentally friendly polymer material, water-based resin has been widely used in industries such as coatings, adhesives, textile auxiliaries, inks and electronic materials. Compared with traditional solvent-based resins, water-based resins have the advantages of low volatile organic compound emissions, non-flammability, and easy processing. Therefore, under the background of increasingly stringent global environmental regulations, its market demand shows a continuous growth trend. With the continuous expansion of water-based resins in high-performance application fields, the requirements for their quality stability and production consistency are also getting higher and higher. The final properties of water-based resins, such as viscosity, solid content, molecular weight distribution, pH, etc., not only depend on the ratio of raw materials, but also are affected by production processes, environmental factors and equipment parameters. Therefore, how to detect and optimize the quality of water-based resins in real time during the production process has become a key issue affecting product performance and production efficiency.

[0003] The production process of water-based resins usually involves chemical reactions such as emulsion polymerization, condensation polymerization, and addition polymerization. Different types of resins require different production processes, such as stirring in a reactor, high-temperature heating, and catalyst addition. In these production processes, changes in process parameters such as raw material mixing uniformity, reaction temperature, reaction pressure, and shear rate will directly affect the microstructure of the resin, thereby affecting its rheological properties, film-forming properties, mechanical strength, and weather resistance. Therefore, in the production process, real-time monitoring of the key quality parameters of water-based resins and timely adjustment of process parameters when quality deviations are found to ensure that the performance of the final product meets the requirements are the core goals of improving product competitiveness and production efficiency.

[0004] The existing water-based resin quality detection methods have shortcomings in environmental fluctuations, capturing nonlinear relationships and adapting to complex working conditions, resulting in large errors in the detection results and low prediction accuracy. Therefore, there is an urgent need to provide an online water-based resin quality detection method to solve the above problems. Summary of the invention

[0005] The invention provides an online detection method for water-based resin quality, so as to solve the problems that most existing water-based resin quality detection methods lack the ability to dynamically monitor environmental variables, so that when the environment fluctuates greatly, the detection results are prone to large errors, thereby affecting the stability of the production process; linear regression or a simple neural network model is usually used for prediction, which cannot effectively capture nonlinear relationships, resulting in insufficient prediction accuracy of the detection system; and most mathematical models that rely on fixed parameters are difficult to adapt to complex working condition changes occurring in the production process, such as dynamic changes in quality parameters caused by factors such as raw material formula adjustment, equipment aging, and differences between production batches, thereby resulting in reduced prediction accuracy.

[0006] A method for online detection of waterborne resin quality of the present invention comprises the following steps: S1. Collecting raw data including physical properties of water-based resin and external parameters of production environment, constructing a high-dimensional chimeric tensor model based on the raw data, and generating a high-dimensional chimeric tensor; based on the high-dimensional chimeric tensor, obtaining a tensor with enhanced time-frequency features through time-frequency feature enhancement technology; S2. Based on the tensor after time-frequency feature enhancement, a prediction method based on high-dimensional information mosaic tensor is adopted, and the predicted values ​​of key quality parameters of water-based resin are corrected in combination with adaptive disturbance factors; based on the predicted values ​​of key quality parameters of water-based resin, the online quality detection results of water-based resin are calculated; the quality tolerance threshold is set, and by comparing the online quality detection results of water-based resin with the quality tolerance threshold, it is determined whether the quality of water-based resin meets the standards.

[0007] Preferably, the S1 specifically includes: The physical properties of water-based resins and external parameters of the production environment are monitored by sensors. The collected raw data are expressed as multi-dimensional time-varying series, which contain information in time and feature space. A high-dimensional chimeric tensor model is constructed to characterize the multi-dimensional characteristics of the quality of water-based resins by fusing time series data, physical feature vectors and environmental parameters.

[0008] Preferably, the S1 specifically includes: The mathematical representation of the high-dimensional chimeric tensor model is as follows: , in, is a high-dimensional chimeric tensor; Indicates Time series data acquired by sensors; is the time step, which indicates the number of time points at which the time series data is collected; It is A physical feature vector that describes the physical properties of the waterborne resin; It is the physical characteristic number of water-based resin; It is Environmental parameters; is the number of environmental parameters; is the chimeric weight; is the tensor product.

[0009] Preferably, the S1 specifically includes: In the process of implementing the time-frequency feature enhancement technology, the frequency features in the high-dimensional chimeric tensor are extracted by performing complex Fourier transform on the high-dimensional chimeric tensor, and the fluctuation of the high-dimensional chimeric tensor is smoothed by a sine function.

[0010] Preferably, the S2 specifically includes: The deviation between the tensor enhanced by time-frequency features and the target value is integrated in real time, and the adaptive perturbation factor is calculated in combination with the nonlinear compensation term. The calculation formula of the adaptive perturbation factor is: , in, is the adaptive perturbation factor; is the upper limit of the time integral; It is The sensor at the time Time series data after time-frequency feature enhancement; It is The expected value of each sensor in the historical data, the historical data is obtained from the database; It is at the moment After time-frequency feature enhancement physical eigenvectors; It is The target value of the physical feature vector; It is at the moment After time-frequency feature enhancement Environmental parameters; It is Reference values ​​of environmental parameters; , and are weight factors that control the contributions of time series deviation, physical property deviation, and environmental parameter deviation to the adaptive perturbation factor, respectively; , , are nonlinear indices, which are used to adjust the contribution intensity of time series deviation, physical property deviation and environmental parameter deviation respectively; is the nonlinear compensation term, and is a regularization factor used to adjust the impact strength of the nonlinear compensation term; It is the tensor after time-frequency feature enhancement.

[0011] Preferably, the S2 specifically includes: The calculation formula for the predicted value of the key quality parameters of water-based resins is: , in, It's in time Predicted values ​​of key quality parameters of waterborne resins, including viscosity of waterborne resins , solid content , pH value and molecular weight distribution ; is the regression weight; is the angular frequency; is a constant that prevents the denominator from being zero; It's in time Predicted values ​​of critical quality parameters of waterborne resins.

[0012] Preferably, the S2 specifically includes: Based on the predicted values ​​of the key quality parameters of water-based resins, evaluate whether the quality of the current water-based resins meets the standards and decide whether the production parameters need to be adjusted.

[0013] Preferably, the S2 specifically includes: The online test results of water-based resin quality are calculated by the following formula: , in, is the quality error evaluation value of online detection; is the total number of critical quality parameters; It's in time No. The predicted values ​​of key quality parameters; It is The ideal target value of each key quality parameter; It's in time Adaptive weighting factor.

[0014] Preferably, the S2 specifically includes: Set the quality tolerance threshold. When the quality error evaluation value of the online detection is less than or equal to the quality tolerance threshold, the quality of the water-based resin meets the standards and there is no need to adjust the production parameters. Otherwise, the quality of the water-based resin does not meet the standards and the production parameters need to be adjusted.

[0015] The beneficial effects of the technical solution of the present invention are: 1. Construct a high-dimensional chimeric tensor model to form a comprehensive characterization of the quality of water-based resin by integrating time series data, physical property parameters and environmental parameters; by introducing time-frequency feature enhancement technology, effectively separate short-term fluctuations and long-term trends in the water-based resin production process, accurately capture the dynamic changes in the water-based resin production process, thereby improving the accuracy and stability of water-based resin quality detection.

[0016] 2. Based on the tensor with enhanced time-frequency characteristics, the output of the water-based resin quality online detection system is corrected in combination with the adaptive disturbance factor, which effectively reduces the error of the water-based resin quality online detection system and enhances the adaptability of the water-based resin quality online detection system to changes in the external environment.

[0017] 3. Adjust production parameters based on the quality error assessment value of online detection to ensure that the quality of water-based resin is always within the standard range; realize automated real-time monitoring during the production process and provide accurate quality prediction results to improve production efficiency while reducing production costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 The present invention is a flow chart of an online detection method for water-based resin quality. DETAILED DESCRIPTION

[0019] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0021] The specific scheme of the on-line detection method for water-based resin quality provided by the present invention is described in detail below with reference to the accompanying drawings.

[0022] Refer to the attached Figure 1 , which shows a flow chart of an online water-based resin quality detection method provided by an embodiment of the present invention, the method comprising the following steps: S1. Collect original data including the physical properties of water-based resin and external parameters of the production environment, build a high-dimensional chimeric tensor model based on the original data, and generate a high-dimensional chimeric tensor; based on the high-dimensional chimeric tensor, use time-frequency feature enhancement technology to obtain a tensor with enhanced time-frequency features.

[0023] In the production process of water-based resins, the stability of quality is closely related to multiple factors, including the ratio of raw materials, temperature, pressure, humidity changes during the reaction, and even the operating status of the equipment. Therefore, the collected raw data should not only cover the physical properties of water-based resins, but also include the external parameters of the production environment to ensure that the factors affecting quality changes are fully captured.

[0024] First of all, the physical properties of water-based resins, such as viscosity, solid content, molecular weight distribution, pH value, etc., need to be accurately measured by real-time online sensors. Viscosity is a key parameter that affects the stability and fluidity of water-based resins and is measured by a rotational viscometer or a vibration viscometer. Solid content indicates the proportion of solid components in water-based resins and is obtained using a drying method or infrared analysis method. Molecular weight distribution is a molecular structure characteristic of water-based resins and is measured by gel permeation chromatography (GPC) technology. The molecular weight distribution obtained can further help understand the rheological properties of water-based resins. The pH value measured by the pH meter reflects the acidity and alkalinity of the water-based resin. The physical properties of water-based resins, such as viscosity, solid content, molecular weight distribution, pH value, etc., are key parameters to ensure product quality, i.e., key quality parameters.

[0025] Secondly, external factors such as temperature, humidity in the production environment, and pressure inside the reactor also need to be monitored by sensors. Temperature has a direct impact on the reaction rate and the chemical reaction balance between the reactants, so it is necessary to obtain temperature data in real time through a temperature sensor. Humidity changes may also affect the solid content of water-based resins, especially in high humidity environments. The moisture in water-based resins may affect their viscosity and solid content, thereby affecting the quality of the final product. Therefore, it is necessary to obtain humidity data in real time through humidity sensors. Monitoring pressure changes inside the reactor through pressure sensors is also a factor that cannot be ignored for understanding the stability of the reaction system.

[0026] The collected raw data are expressed as multidimensional time-varying sequences, which contain information in time and feature space. In order to make full use of the raw data, a high-dimensional chimeric tensor model is constructed to characterize the multidimensional characteristics of the quality of water-based resin by fusing time series data, physical feature vectors and environmental parameters.

[0027] , in, It is a high-dimensional mosaic tensor, which represents the fusion representation of multiple feature data in the production process of water-based resin; Indicates The time series data obtained by the sensors include the time variation characteristics of the water-based resin production process; is the time step, i.e. the number of time points at which the time series data is collected; It is A physical feature vector that describes the physical properties of the waterborne resin, such as viscosity, solid content, pH value, and molecular weight distribution; It is the physical characteristic number of water-based resin; It is Environmental parameters, such as temperature, humidity and other influencing factors in the production environment; is the number of environmental parameters; is the chimeric weight; It is a tensor product, which is used to combine data from different dimensions so that they can jointly represent a high-dimensional feature space. The raw data are combined through the tensor product operation to form a high-dimensional chimeric tensor for comprehensive prediction of water-based resin quality.

[0028] Embedding weights in high-dimensional embedding tensors It is calculated based on the similarity between the original data and is used to represent , , The calculation formula of chimeric weight is as follows: , in, and They are , as well as , The Euclidean distance between them is used to measure the similarity between data; is the distance attenuation factor, which controls the effect of Euclidean distance on the chimera weight, and its value range is , the specific value is calibrated through experiments; is a regularization factor used to avoid over-weighting when the data distance difference is too large.

[0029] On the basis of high-dimensional mosaic tensors, the time-frequency feature enhancement technology is introduced to capture the dynamic change characteristics of the quality of water-based resins during the production process. The frequency characteristics in the high-dimensional mosaic tensors are extracted by complex Fourier transforming the high-dimensional mosaic tensors, and the high-dimensional mosaic tensor fluctuations are smoothed by sine functions to enhance the periodic change characteristics of the high-dimensional mosaic tensors. Time-frequency feature enhancement is very critical for processing production data with periodic changes, because in the production process of water-based resins, factors such as temperature and reaction time usually show periodic fluctuations.

[0030] , in, It is the tensor after time-frequency feature enhancement; is the Hadamard product, which stands for element-wise multiplication; The term is the complex Fourier transform term, which is used to extract the periodic changes of the high-dimensional chimeric tensor; represents an imaginary number; is the angular frequency, calculated by Fourier transform; It’s time; The term is used to smooth the high-dimensional embedded tensor and reduce the interference of high-frequency noise; is the oscillation frequency control parameter, which depends on the periodicity of the high-dimensional fitting tensor; is a smoothing factor used to avoid zero denominator.

[0031] S2. Based on the tensor after time-frequency feature enhancement, a prediction method based on high-dimensional information mosaic tensor is adopted, and the predicted values ​​of key quality parameters of water-based resin are corrected in combination with adaptive disturbance factors; based on the predicted values ​​of key quality parameters of water-based resin, the online quality detection results of water-based resin are calculated; the quality tolerance threshold is set, and by comparing the online quality detection results of water-based resin with the quality tolerance threshold, it is determined whether the quality of water-based resin meets the standards.

[0032] In order to ensure that the online water-based resin quality detection system maintains efficient adaptability to complex and changeable working conditions in the actual production process, an adaptive disturbance factor is introduced to dynamically adjust the stability of data processing and improve the ability to accurately predict the quality change trend of water-based resins. In the actual production process, the key quality parameters of water-based resins, such as viscosity, solid content, molecular weight distribution and pH value, are easily affected by factors such as environmental temperature and humidity fluctuations, raw material batch differences, and equipment operation status, which may lead to sudden changes or drifts in the measurement data, and may also cause short-term misjudgment or prediction distortion in the online water-based resin quality detection system, thereby affecting the accuracy of the overall quality control. Therefore, a dynamically adjustable adaptive disturbance factor must be used to adaptively correct the output of the online water-based resin quality detection system, so that it can still provide highly reliable data prediction and decision support under complex working conditions. The adaptive disturbance factor performs real-time integral calculation of the deviation between the tensor after the time-frequency feature enhancement and the target value, and combines the nonlinear compensation term to ensure that the subsequent prediction of the key quality parameters of the water-based resin can effectively adapt to data changes and avoid the error amplification problem caused by excessive response to short-term fluctuations. The calculation formula of the adaptive disturbance factor is: , in, is the adaptive perturbation factor; is the upper limit of the time integral; It is The sensor at the time Time series data after time-frequency feature enhancement, ); It is The expected value of a sensor in historical data (such as historical average or smoothed estimate), where the historical data is obtained from a database; It is at the moment After time-frequency feature enhancement physical eigenvectors, ); It is a target value of a physical characteristic vector (such as a target viscosity or a target solid content); It is at the moment After time-frequency feature enhancement environmental parameters, ); It is reference values ​​of environmental parameters (such as target temperature or target humidity); , and are weight factors that control the contributions of time series deviation, physical property deviation, and environmental parameter deviation to the adaptive perturbation factor, respectively; , , are nonlinear indices, which are used to adjust the contribution intensity of time series deviation, physical property deviation and environmental parameter deviation respectively; is the nonlinear compensation term, and is a regularization factor used to adjust the impact strength of the nonlinear compensation term.

[0033] Obtain the prediction results of key quality parameters in the production process of water-based resins, such as viscosity, solid content, molecular weight distribution and pH value. Since the quality of water-based resins is affected by many factors, including raw material ratio, production environment, temperature changes, etc., it is necessary to integrate multidimensional data and dynamically adjust short-term fluctuations and long-term trends in time series. To this end, a prediction method based on high-dimensional information mosaic tensor is adopted to fuse data from multiple data sources (time series, physical properties, environmental parameters), and weight correction is performed in combination with adaptive perturbation factors to enhance the adaptability of the prediction process of key quality parameters of water-based resins to the real-time production environment. First, time-frequency analysis is performed in the high-dimensional tensor space to extract its periodic and non-periodic components, and then high-frequency components are extracted by Fourier transform to identify short-term fluctuations that may affect the quality of water-based resins. At the same time, smoothing terms are introduced to suppress high-frequency noise. Finally, in order to make the prediction results more stable, dynamic weighting is performed through adaptive perturbation factors so that high-precision predictions can be maintained under different production conditions, thereby obtaining the predicted values ​​of key quality parameters of water-based resins: , in, It's in time Predicted values ​​of key quality parameters of waterborne resins, including viscosity of waterborne resins , solid content , pH value and molecular weight distribution ; is the regression weight, which is used to measure the importance of the tensor after time-frequency feature enhancement in the prediction process; is the angular frequency, which represents the periodic variation of the correction term; is a constant that prevents the denominator from being zero; It's in time Predicted values ​​of critical quality parameters of waterborne resins.

[0034] After obtaining the predicted values ​​of the key quality parameters of the water-based resin, it is necessary to calculate the online quality test results of the water-based resin, that is, to evaluate whether the quality of the current water-based resin meets the standards and decide whether the production parameters need to be adjusted. The final result of the online quality test of the water-based resin is calculated by the following formula: , in, is the quality error evaluation value of online detection; is the total number of critical quality parameters; It's in time No. The predicted values ​​of key quality parameters; It is The ideal target value of each key quality parameter; It's in time The adaptive weighting factor represents the The importance of a critical quality parameter in the current production batch is calculated as follows: , in, is the error attenuation factor, which is used to control the impact of different critical quality parameters on the overall quality assessment; is the error compensation term, It is The error compensation factor of each key quality parameter is used to prevent the key quality parameter error from being too large and affecting the overall quality assessment; is a regularization factor used to adjust the smoothness of the adaptive weighting factors.

[0035] Set a quality tolerance threshold through expert experience , by comparing the quality tolerance threshold Quality error evaluation value with online detection , to judge whether the quality of water-based resin meets the standards. , it means that the quality parameters of the current water-based resin are within an acceptable range and there is no need to adjust the production parameters; otherwise, it means that the quality of the water-based resin deviates from the target value and the production parameters need to be adjusted to optimize the quality.

[0036] In summary, an online detection method for water-based resin quality was completed.

[0037] The order of the embodiments of the invention is for description only and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0038] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0039] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A method for online detection of waterborne resin quality, characterized in that: The following steps are involved: S1. Collecting raw data including physical properties of water-based resin and external parameters of production environment, constructing a high-dimensional chimeric tensor model based on the raw data, and generating a high-dimensional chimeric tensor; based on the high-dimensional chimeric tensor, obtaining a tensor with enhanced time-frequency features through time-frequency feature enhancement technology; S2. Based on the tensor enhanced with time-frequency features, a prediction method based on high-dimensional information mosaic tensor is adopted, and the prediction value of the key quality parameter of the water-based resin is corrected in combination with an adaptive perturbation factor; based on the prediction value of the key quality parameter of the water-based resin, the online detection result of the water-based resin quality is calculated; A quality tolerance threshold is set, and whether the quality of the water-based resin meets the standard is determined by comparing the online detection result of the water-based resin quality with the quality tolerance threshold.

2. The method for online detection of waterborne resin quality according to claim 1, characterized in that: The S1 specifically includes: The physical properties of water-based resins and external parameters of the production environment are monitored by sensors. The collected raw data are expressed as multi-dimensional time-varying series, which contain information in time and feature space. A high-dimensional chimeric tensor model is constructed to characterize the multi-dimensional characteristics of the quality of water-based resins by fusing time series data, physical feature vectors and environmental parameters.

3. The method for online detection of waterborne resin quality according to claim 2, characterized in that: The S1 specifically includes: The mathematical representation of the high-dimensional chimeric tensor model is as follows: ， middle, is a high-dimensional chimeric tensor; Indicates Time series data acquired by sensors; is the time step, which indicates the number of time points at which the time series data is collected; It is A physical feature vector that describes the physical properties of the waterborne resin; It is the physical characteristic number of water-based resin; It is Environmental parameters; is the number of environmental parameters; is the chimeric weight; is the tensor product.

4. The method for online detection of waterborne resin quality according to claim 3, characterized in that: The S1 specifically includes: In the process of implementing the time-frequency feature enhancement technology, the frequency features in the high-dimensional chimeric tensor are extracted by performing complex Fourier transform on the high-dimensional chimeric tensor, and the fluctuation of the high-dimensional chimeric tensor is smoothed by a sine function.

5. The method for online detection of waterborne resin quality according to claim 1, characterized in that: The S2 specifically includes: The deviation between the tensor enhanced by time-frequency features and the target value is integrated in real time, and the adaptive perturbation factor is calculated in combination with the nonlinear compensation term. The calculation formula of the adaptive perturbation factor is: ， in, is the adaptive perturbation factor; is the upper limit of the time integral; It is The sensor at the time Time series data after time-frequency feature enhancement; It is The expected value of each sensor in the historical data, the historical data is obtained from the database; It is at the moment After time-frequency feature enhancement physical eigenvectors; It is The target value of the physical feature vector; It is at the moment After time-frequency feature enhancement Environmental parameters; It is Reference values ​​of environmental parameters; , and are weight factors that control the contributions of time series deviation, physical property deviation, and environmental parameter deviation to the adaptive perturbation factor, respectively; , , are nonlinear indices, which are used to adjust the contribution intensity of time series deviation, physical property deviation and environmental parameter deviation respectively; is the nonlinear compensation term, and is a regularization factor used to adjust the impact strength of the nonlinear compensation term; It is the tensor after time-frequency feature enhancement.

6. The method for online detection of waterborne resin quality according to claim 5, characterized in that: The S2 specifically includes: The calculation formula for the predicted value of the key quality parameters of water-based resins is: ， in, It's in time Predicted values ​​of key quality parameters of waterborne resins, including viscosity of waterborne resins , solid content , pH value and molecular weight distribution ; is the regression weight; is the angular frequency; is a constant that prevents the denominator from being zero; It's in time Predicted values ​​of critical quality parameters of waterborne resins.

7. The method for online detection of waterborne resin quality according to claim 6, characterized in that: The S2 specifically includes: Based on the predicted values ​​of the key quality parameters of water-based resins, evaluate whether the quality of the current water-based resins meets the standards and decide whether the production parameters need to be adjusted.

8. The method for online detection of waterborne resin quality according to claim 1, characterized in that: The S2 specifically includes: The online test results of water-based resin quality are calculated by the following formula: ， in, is the quality error evaluation value of online detection; is the total number of critical quality parameters; It's in time No. The predicted values ​​of key quality parameters; It is The ideal target value of each key quality parameter; It's in time Adaptive weighting factor.

9. The method for online detection of waterborne resin quality according to claim 8, characterized in that: The S2 specifically includes: Set the quality tolerance threshold. When the quality error evaluation value of the online detection is less than or equal to the quality tolerance threshold, the quality of the water-based resin meets the standards and there is no need to adjust the production parameters. Otherwise, the quality of the water-based resin does not meet the standards and the production parameters need to be adjusted.

Images