A control method for the solvent removal process of an aqueous resin

Abstract

The present invention relates to the field of automatic control technology, and particularly to a control method for the solvent removal process of waterborne resin. The content includes: monitoring parameter data and performing preprocessing to obtain the preprocessed parameter data; dynamically adjusting equipment parameters based on the preprocessed parameter data; dynamically optimizing the dynamically adjusted equipment parameters based on environmental factors and the real-time monitored parameter data to obtain the optimized equipment parameters; and controlling the solvent removal process of waterborne resin based on the optimized equipment parameters. It solves the technical problems of relatively low control accuracy and poor stability existing in the traditional control method for the solvent removal of waterborne resin.

Description

Technical Field

[0001] The present invention relates to the technical field of automatic control, and particularly relates to a control method for the desolvation process of waterborne resins. Background Art

[0002] Waterborne resins are widely used in industrial fields such as coatings and adhesives. As environmentally friendly materials, the desolvation process of waterborne resins plays a crucial role in their performance and the quality of the final products. However, during the desolvation process of waterborne resins, affected by various factors such as temperature, humidity, and solvent concentration, process fluctuations often occur, resulting in unstable quality of the final products and even defects. In addition, traditional control methods for waterborne resin desolvation mostly rely on manual experience, fail to fully utilize modern intelligent control means, and have poor adaptability to environmental changes and equipment aging, easily leading to problems such as low production efficiency, high energy consumption, and frequent equipment failures.

[0003] In summary, traditional control methods for waterborne resin desolvation have technical problems of low control accuracy and poor stability. Summary of the Invention

[0004] The present invention provides a control method for the desolvation process of waterborne resins to solve the technical problems of low control accuracy and poor stability during the desolvation process of waterborne resins.

[0005] A control method for the desolvation process of waterborne resins according to the present invention specifically includes the following technical solutions:

[0006] A control method for the desolvation process of waterborne resins includes the following steps:

[0007] S1. Monitor parameter data and perform preprocessing to obtain preprocessed parameter data; based on the preprocessed parameter data, dynamically adjust equipment parameters;

[0008] S2. Based on environmental factors and the parameter data monitored in real time, dynamically optimize the dynamically adjusted equipment parameters to obtain optimized equipment parameters; based on the optimized equipment parameters, control the desolvation process of waterborne resins.

[0009] Preferably, the S1 specifically includes:

[0010] Based on the preprocessed parameter data, introduce an adaptive optimization control algorithm to dynamically adjust equipment parameters to obtain dynamically adjusted equipment parameters.

[0011] Preferably, the S1 specifically includes:

[0012] During the implementation of the adaptive optimization control algorithm, based on the preprocessed parameter data, calculate the change rate of the preprocessed parameter data over time and construct a dynamic change model.

[0013] Preferably, the S1 specifically includes:

[0014] In the implementation process of the adaptive optimization control algorithm, based on the preprocessed parameter data at the current moment, calculate the error; combine the non-linear function to dynamically correct the error, obtain the dynamically corrected error, and use the dynamically corrected error as the current error.

[0015] Preferably, the S1 specifically includes:

[0016] Based on the current error, combine the error at the historical moment to calculate the adaptive control increment; the adaptive control increment formula is as follows:

[0017] ,

[0018] where, is the adaptive control increment at time ; is the adjustment coefficient of the current error; is the dynamically corrected error at time ; is the adjustment coefficient of the cumulative error; is the dynamically corrected error at time ; is the time integral variable; is the non-linear feedback coefficient of the current error; is the non-linear feedback coefficient of the error change rate; is the error at time .

[0019] Preferably, the S1 specifically includes:

[0020] Based on the dynamic change model, analyze and calculate the device parameters through the state feedback control method; gradually adjust the device parameters based on the adaptive control increment to obtain the dynamically adjusted device parameters.

[0021] Preferably, the S2 specifically includes:

[0022] Quantify the environmental factors and the parameter data of the real-time monitoring to obtain the influence quantification index of the environmental factors and the quantization feedback of the parameter data of the real-time monitoring, and introduce the multi-dimensional adaptive feedback optimization algorithm to dynamically optimize the dynamically adjusted device parameters to obtain the optimized device parameters.

[0023] Preferably, the S2 specifically includes:

[0024] In the implementation process of the multi-dimensional adaptive feedback optimization algorithm, based on the quantization feedback of the parameter data monitored in real time and the quantization index of the influence of environmental factors, the current error is adjusted to obtain the comprehensive error.

[0025] Preferably, the S2 specifically includes:

[0026] Based on the comprehensive error, combining the quantization index of the influence of environmental factors and the quantization feedback of the parameter data monitored in real time, a feedback optimization iteration mechanism is introduced to perform feedback optimization processing on the dynamically adjusted device parameters to obtain the optimized device parameters. The specific formula is:

[0027] ,

[0028] where, is the optimized device parameter; is the device parameter at time , representing the dynamically adjusted device parameter; is the feedback adjustment factor; is the comprehensive error at time ; is the error adjustment coefficient; is the feedback influence coefficient; is the quantization index of the influence of environmental factors at time ; is the quantization feedback of the parameter data monitored in real time at time ;

[0029] The optimized device parameters are converted into control signals through the PID control algorithm; based on the control signals, the desolvation process of the waterborne resin is controlled.

[0030] The beneficial effects of the technical solution of the present invention are:

[0031] 1. By introducing adaptive control algorithms such as dynamic modeling, lag compensation, and non-linear feedback correction, precise adjustment of device parameters is achieved; the introduction of the influence coefficient of the lag effect and the dynamic attenuation coefficient effectively describes the time-delay characteristics of the waterborne resin during the desolvation process to provide a more delicate control ability; by dynamically correcting the error and calculating the adaptive control increment, the device parameters are adjusted in real time to achieve continuous optimization of the process, thereby improving production efficiency and reducing human intervention and errors.

[0032] 2. Through the multi-dimensional adaptive feedback optimization algorithm, the device parameters can be optimized under the changes of different environmental factors (such as temperature, humidity, etc.). The multi-dimensional adaptive feedback optimization algorithm can not only eliminate the interference of the external environment, but also adaptively process the state fluctuations during long-term operation, improving the stability of the desolvation process of the waterborne resin and reducing the quality fluctuations caused by environmental changes. Description of the Drawings

[0033] Figure 1 It is a flow chart of a control method for the desolventization process of an aqueous resin according to the present invention. Detailed Embodiments

[0034] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0035] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this invention belongs.

[0036] The following specifically describes the specific solution of a control method for the desolventization process of an aqueous resin provided by the present invention in conjunction with the drawings.

[0037] Refer to the attached Figure 1 , which shows a flow chart of a control method for the desolventization process of an aqueous resin provided by an embodiment of the present invention. The method includes the following steps:

[0038] S1. Monitor parameter data and perform preprocessing to obtain preprocessed parameter data; based on the preprocessed parameter data, dynamically adjust equipment parameters;

[0039] Use high-precision sensors (such as temperature and humidity sensors, flow meters, pressure sensors, solvent concentration sensors, etc.) to monitor various parameter data during the desolventization process of the aqueous resin, including temperature, humidity, solvent concentration, air flow rate, pressure, etc.; perform preprocessing on the parameter data such as denoising, normalization, and filling of missing data to obtain preprocessed parameter data. The technical means adopted for the preprocessing are all well-known prior arts to those skilled in the art and will not be elaborated here.

[0040] Furthermore, introduce an adaptive optimization control algorithm to dynamically adjust equipment parameters. The adaptive optimization control algorithm is based on the preprocessed parameter data and gradually adjusts the working state of the equipment through multiple methods such as dynamic modeling, lag compensation, non-linear feedback correction, and adaptive control, so that the desolventization process of the aqueous resin can be continuously optimized. The specific implementation process is as follows:

[0041] First, based on the preprocessed parameter data, a dynamic change model is constructed. For the hysteresis effect during the desolvation process, the dynamic behavior of the desolvation process is described by a differential equation. Assume that the key parameters (preprocessed parameter data) during the desolvation process are , and the preprocessed parameter data is affected by various factors, not only depending on the current input but also being closely related to the past state. To represent this time-delay effect, the influence coefficient of the hysteresis effect and the dynamic decay coefficient are introduced, and the dynamic change model is as follows:

[0042] ,

[0043] where, is the preprocessed parameter data (such as temperature, humidity, solvent concentration, air flow rate, pressure, etc.) at time , which changes with time ; is the rate of change of the preprocessed parameter data with time, estimated by the difference in values at adjacent time points; is the preprocessed parameter data at time ; is the equipment parameter (such as heating power); is the influence coefficient of the hysteresis effect, indicating the degree of influence of the past state on the current state, obtained by the experimental method, and the reference value range is ; is the time lag (also known as time delay), reflecting the time delay of the equipment parameter on the response, determined by the expert experience method, and the reference value range is ; is the equipment parameter influence coefficient, indicating the direct influence degree of the equipment parameter on the dynamic behavior of the desolvation process, obtained by the experimental method, and the reference value range is ; is the dynamic decay coefficient, used to describe the natural decay or dissipation effect, reflecting the decay process without external control input, obtained by the experimental method, and the reference value range is ; is the time variable;

[0044] Furthermore, error dynamic correction is carried out. The goal of the desolvation process is to make the actual desolvation state as close as possible to the desired state. Therefore, it is necessary to continuously calculate the error and make corrections. The error is the gap between the target value and the current actual value , and can be expressed as:

[0045] ,

[0046] To avoid large errors, a weighted non - linear correction function is introduced. This function combines non - linear functions such as sigmoid and tanh to achieve dynamic correction of errors and obtain the dynamically corrected errors. The specific form is as follows:

[0047] ,

[0048] where, is the dynamically corrected error and serves as the error at the current moment; is the first adjustment coefficient, which is used to adjust the weight or influence degree of the sigmoid function in error correction. It is determined by the experimental method, and the reference value range is ; is an activation function commonly used in neural networks. Its shape is a smooth S - shaped curve, and its role is to adjust the control response according to the magnitude of the current error. Using the sigmoid function can control the error correction within a certain range and avoid over - adjustment; is the first amplification coefficient, which is used to control the amplification effect when the error is input into the sigmoid function, and determines the sensitivity of the error to correction. It is determined by the existing control strategy, and the reference value range is ; is the second adjustment coefficient, which is used to adjust the weight or influence degree of the tanh function in error correction. It is determined by the experimental method, and the reference value range is ; is a non - linear activation function, similar to the sigmoid function, but its output range is , and it has stronger symmetry. It is another way of error correction provided by adjusting the relationship between the second adjustment coefficient and the error . Combining it with the sigmoid function can increase the non - linearity of control and enhance adaptability; is the second amplification coefficient, which determines the amplification effect when the error is passed to the tanh function. It is determined by the experimental method, and the reference value range is ;

[0049] After the error correction is completed, based on the dynamically corrected error and combined with the error at the historical moment, the adaptive control increment is calculated to optimize the control input. The formula for the adaptive control increment is as follows:

[0050] ,

[0051] where, is the adaptive control increment; is the adjustment coefficient of the current error, which is a weight factor used for calculating the control increment and determines the error at the current moment The influence degree on the adaptive control increment is determined according to the expert experience method, and the reference value range is ; is the adjustment coefficient of the cumulative error and another weight factor used for controlling the increment calculation. It controls the influence of the historical accumulation of errors on the adaptive control increment and is determined according to the expert experience method. The reference value range is ; is the accumulation of all dynamically corrected errors from the start to the current time . It reflects the overall trend of errors over a period of time, has the function of removing short-term fluctuations and smooth adjustment; is the time integral variable; is the non-linear feedback coefficient of the current error, which determines the influence degree of the square term of the error on the adaptive control increment and is determined according to the expert experience method. The reference value range is ; is the non-linear feedback coefficient of the error change rate, which determines the influence degree of the square term of the error change rate (i.e., ) on the adaptive control increment and is determined according to the expert experience method. The reference value range is . The above formula determines the adaptive control increment by weighting the current error and the cumulative error over a past period of time, so as to ensure that the adjustment of the equipment parameters is not only sensitive to the current error, but also can smooth the influence of historical errors and avoid oscillation or overreaction;

[0052] Further, entering the adaptive adjustment stage, the equipment parameters are gradually adjusted through the adaptive control increment, causing the working state of the equipment to change. The dynamically adjusted equipment parameters are:

[0053] ,

[0054] where is the equipment parameter at the next time , that is, the dynamically adjusted equipment parameter; is the equipment parameter at the current moment, which is obtained by analyzing and calculating through the existing state feedback control method based on the dynamic change model.

[0055] S2. Based on the environmental factors and the parameter data of real-time monitoring, the dynamically adjusted equipment parameters are dynamically optimized to obtain the optimized equipment parameters; based on the optimized equipment parameters, the waterborne resin desolventization process is controlled.

[0056] Based on the environmental factors and the parameter data of real-time monitoring, the dynamically adjusted equipment parameters are dynamically optimized by using the multi-dimensional adaptive feedback optimization algorithm to obtain the optimized equipment parameters; the specific implementation process is as follows:

[0057] First, quantify the environmental factors and the parameter data of real-time monitoring to obtain the quantification index of the influence of environmental factors and the quantification feedback of the parameter data of real-time monitoring; based on the quantification feedback of the parameter data of real-time monitoring and the quantification index of the influence of environmental factors, adjust the current error to obtain the comprehensive error:

[0058] ,

[0059] wherein, is the error after being adjusted by environmental factors and real-time feedback at time , that is, the comprehensive error; is the environmental factor weighting coefficient, which is used to control the influence degree of the quantification index of environmental factors , indicating the influence intensity of environmental changes on error adjustment, such as the effects of factors like temperature and humidity on the desolvation process of waterborne resin, obtained through the experimental method, and the reference value range is ; is the quantification index of the influence of environmental factors, indicating the influence of environmental changes on the desolvation process of waterborne resin at time , obtained by using the existing regression analysis method; is the feedback factor weighting coefficient, which is used to adjust the influence degree of the quantification feedback of the parameter data of real-time monitoring on the error, determined by the experimental method, and the reference value range is ; is the quantification feedback of the parameter data of real-time monitoring at time , indicating the influence of parameter data such as temperature, humidity, and solvent concentration during the desolvation process on the desolvation process of waterborne resin, obtained by using the existing model predictive control technology;

[0060] Based on the comprehensive error , combined with the quantification index of the influence of environmental factors and the quantification feedback of the parameter data of real-time monitoring, introduce a feedback optimization iteration mechanism to perform feedback optimization processing on the dynamically adjusted equipment parameters to obtain the optimized equipment parameters:

[0061] ,

[0062] wherein, is the optimized equipment parameter; is the equipment parameter at the next time , that is, the dynamically adjusted equipment parameter; is the feedback adjustment factor, which is used to determine the importance degree of feedback information in the optimization of equipment parameters, determined by the experimental method, and the reference value range is ; is the error adjustment coefficient, representing the influence degree of the error change rate (comprehensive error derivative) on the optimized device parameters, which can affect the sensitivity of the device response to the error change rate and is determined according to the expert experience method. The reference value range is ; is the feedback influence coefficient, which is used to control the influence of environmental factors and real-time monitoring feedback on the optimization of device parameters, determines the sensitivity of environmental factors and real-time monitoring feedback to the optimization of device parameters, and is set through methods such as sensitivity analysis and deviation inversion modeling. The reference value range is , and the larger the value, the more conservative it is to environmental disturbances;

[0063] Finally, the optimized device parameters are converted into control signals through the existing PID control algorithm, and the control of the desolventization process of the waterborne resin is realized based on the control signals.

[0064] To further verify the above embodiments, the real-time data of temperature and solvent concentration are collected, and the experimental steps of the above adaptive optimization control algorithm are carried out. For the two control strategies of PID control and adaptive optimization control, the verification results are as follows:

[0065] In terms of temperature response, the adaptive optimization control method can stabilize the temperature at the preset target temperature (such as 85°C) faster and with a smaller fluctuation range (within ±1°C); in contrast, the traditional PID control has a larger initial overshoot and continuous oscillation, and the fluctuation amplitude is larger (about ±3.2°C);

[0066] In terms of solvent concentration response, the adaptive optimization control method can achieve a rapid decrease and stabilization of the solvent concentration faster (such as dropping below 200 ppm within 15 minutes), while the traditional PID control has not fully converged within the same time duration and has a high tail residue;

[0067] In terms of error attenuation, the error of the adaptive optimization control drops rapidly and stabilizes close to zero; the error attenuation process of the traditional PID control is slower and there are obvious errors;

[0068] Therefore, the adaptive optimization control algorithm is significantly superior to the traditional PID control strategy in terms of accuracy, stability and response speed, verifying the effectiveness and engineering practical value of the present invention; using the adaptive optimization control method, the convergence speed of temperature and solvent concentration is significantly improved; the error attenuation speed is much faster than that of the traditional PID control strategy; the control response is smooth and there are no overshoot or oscillation phenomena.

[0069] In summary, a control method for the desolventization process of a waterborne resin is completed.

[0070] The order of the invention embodiments is only for description and does not represent the superiority or inferiority 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.

[0071] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments.

[0072] The above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments or perform equivalent replacements for some of the technical features. These modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of each embodiment of the present invention and should all be included in the protection scope of the present invention.

Claims

1. A control method for the solvent removal process of an aqueous resin, characterized in that, It includes the following steps: S1. Monitor parameter data and perform preprocessing to obtain preprocessed parameter data; Introduce an adaptive optimization control algorithm. Based on the preprocessed parameter data, calculate the error, and dynamically correct the error by combining with a nonlinear function to obtain the dynamically corrected error. Take the dynamically corrected error as the current error; Based on the current error, combine with the error at the historical moment, calculate the adaptive control increment, and dynamically adjust the device parameters to obtain the dynamically adjusted device parameters. The formula for the adaptive control increment is as follows: ， Among them, is the adaptive control increment at time ; is the adjustment coefficient of the current error; is the error after dynamic correction at time ; is the adjustment coefficient of the cumulative error; is the error after dynamic correction at time ; is the time integral variable; is the non - linear feedback coefficient of the current error; is the non - linear feedback coefficient of the error change rate; is the error at time ; S2. Based on environmental factors and the parameter data monitored in real time, dynamically optimize the dynamically adjusted device parameters to obtain optimized device parameters; Based on the optimized device parameters, control the waterborne resin desolventization process.

2. The control method for the solvent removal process of the aqueous resin according to claim 1, wherein, The specific content of S1 includes: During the implementation of the adaptive optimization control algorithm, based on the preprocessed parameter data, calculate the change rate of the preprocessed parameter data over time, and construct a dynamic change model.

3. The control method for the solvent removal process of the aqueous resin according to claim 2, characterized in that, The specific content of S1 includes: Based on the dynamic change model, analyze and calculate the device parameters by the state feedback control method; Gradually adjust the device parameters based on the adaptive control increment to obtain the dynamically adjusted device parameters.

4. The control method for the solvent removal process of the aqueous resin according to claim 1, wherein The specific content of S2 includes: Quantify the environmental factors and the parameter data monitored in real time to obtain the influence quantification index of environmental factors and the quantification feedback of the parameter data monitored in real time. Introduce a multi-dimensional adaptive feedback optimization algorithm to dynamically optimize the dynamically adjusted device parameters to obtain optimized device parameters.

5. The control method for the desolventization process of an aqueous resin according to claim 4, characterized in that, The specific content of S2 includes: During the implementation of the multi-dimensional adaptive feedback optimization algorithm, adjust the current error based on the quantification feedback of the parameter data monitored in real time and the influence quantification index of environmental factors to obtain a comprehensive error.

6. The control method for the solvent removal process of the aqueous resin according to claim 5, wherein, The specific content of S2 includes: Based on the comprehensive error, combine with the influence quantification index of environmental factors and the quantification feedback of the parameter data monitored in real time, introduce a feedback optimization iteration mechanism, and perform feedback optimization processing on the dynamically adjusted device parameters to obtain optimized device parameters. The specific formula is: ， Among them, are the optimized device parameters; is at time of the device parameters, representing the device parameters after dynamic adjustment; is the feedback adjustment factor; is at time of the comprehensive error; is the error adjustment coefficient; is the feedback influence coefficient; is at time when the influence quantification index of environmental factors; is at time when the quantization feedback of the parameter data monitored in real time; Convert the optimized device parameters into a control signal through the PID control algorithm; Based on the control signal, control the waterborne resin desolventization process.

Images