Prediction method, device and system for curing degree of coating, medium and program product

The iterative optimization method for nonlinear fitting addresses the inaccuracies in coating curing degree predictions by using the Levenberg-Marquardt algorithm, enhancing prediction accuracy and reliability.

CN119067486APending Publication Date: 2024-12-03JIANGSU XCMG CONSTRUCTION MACHINERY RESEARCH INSTITUTE LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411055592.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-02
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

Existing methods for predicting the curing degree of coatings suffer from inaccuracies due to the complex nonlinear characteristics of the coating curing process, leading to large errors in prediction results.

Method used

An iterative optimization method is employed for nonlinear fitting on coating curing degree sample data to optimize the curing degree objective function, using the Levenberg-Marquardt algorithm and steepest descent method, to establish a coating curing degree prediction model.

Benefits of technology

The method significantly improves the accuracy and reliability of curing trend predictions, achieving high determination coefficients close to 1 and enabling precise quantification of coating curing degrees at different times.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119067486A_ABST
    Figure CN119067486A_ABST
Patent Text Reader

Abstract

The invention relates to a method, a device and a system for predicting the curing degree of a coating, a medium and a program product. The method for predicting the curing degree of the coating comprises the following steps: acquiring spectral data of a to-be-measured coating at different moments; processing the spectral data to obtain coating curing degree sample data at different moments; determining a curing degree objective function; performing nonlinear fitting on the coating curing degree sample data by adopting an iterative optimization mode so as to optimize the curing degree objective function and obtain a coating curing degree prediction model; and according to the target coating curing time and the coating curing degree prediction model, determining a coating curing degree prediction value of the target coating curing time. According to the method and the device, nonlinear fitting is performed on the coating curing degree sample data by adopting an iterative optimization mode, so that the accuracy and the reliability of curing trend data prediction are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of coating application, and in particular to a method, device, system, medium and program product for predicting the curing degree of a coating. Background Art

[0002] The coating curing degree is a core indicator that affects the product appearance quality. There is no standard detection method in the industry. In the coating process, the accurate prediction of the coating curing degree is of great significance for controlling product quality and optimizing the production process. Summary of the invention

[0003] The inventors have found through research that the dynamic process of coating curing in the related art is affected by multiple factors and exhibits complex nonlinear characteristics. The curing degree prediction method in the related art is often difficult to accurately handle the nonlinear relationship, resulting in large errors in the prediction results.

[0004] In view of at least one of the above technical problems, the present disclosure provides a method, device and system, medium and program product for predicting the curing degree of a coating. By adopting an iterative optimization method, nonlinear fitting is performed on the sample data of the curing degree of the coating, thereby improving the accuracy and reliability of the prediction of the curing trend data.

[0005] According to one aspect of the present disclosure, a method for predicting the curing degree of a coating is provided, comprising:

[0006] Obtaining spectral data of the coating to be tested at different times;

[0007] Processing the spectral data to obtain coating curing degree sample data at different times;

[0008] Determine the curing degree objective function;

[0009] Using an iterative optimization method, nonlinear fitting is performed on the coating curing degree sample data to optimize the curing degree objective function and obtain a coating curing degree prediction model;

[0010] According to the target coating curing time and the coating curing degree prediction model, a coating curing degree prediction value of the target coating curing time is determined.

[0011] In some embodiments of the present disclosure, the curing degree objective function includes model parameters.

[0012] In some embodiments of the present disclosure, the iterative optimization method is used to perform nonlinear fitting on the coating curing degree sample data to optimize the curing degree objective function, and the coating curing degree prediction model is obtained, which includes:

[0013] The model parameters are optimized according to the coating curing degree sample data by adopting an iterative optimization method to obtain a coating curing degree prediction model.

[0014] In some embodiments of the present disclosure, the iterative optimization method is used to optimize the model parameters according to the coating curing degree sample data to obtain the coating curing degree prediction model, which includes:

[0015] Determining the initial value of the model parameter according to the coating curing degree sample data;

[0016] Adopting an iterative optimization method, optimizing the model parameters according to the coating curing degree sample data;

[0017] Determine whether the iteration exit condition is met;

[0018] When the iteration exit condition is met, the current curing degree objective function is used as the coating curing degree prediction model.

[0019] In some embodiments of the present disclosure, the iterative optimization method is used to optimize the model parameters according to the coating curing degree sample data to obtain the coating curing degree prediction model, which further includes:

[0020] In the case where the iteration exit condition is not met, the steps of optimizing the model parameters according to the coating curing degree sample data by adopting an iterative optimization method are repeatedly performed to determine whether the iteration exit condition is met.

[0021] In some embodiments of the present disclosure, the iteration exit condition includes at least one of the following conditions:

[0022] The current number of iterations is greater than or equal to the predetermined number of iterations;

[0023] The current determination coefficient is greater than or equal to a predetermined value.

[0024] In some embodiments of the present disclosure, the method for predicting the coating curing degree further includes:

[0025] Determine the residual sum of squares of the coating curing degree according to the measured value of the coating curing degree and the predicted value of the coating curing degree;

[0026] Determining the total sum of squares of the coating curing degree according to the measured values ​​and the average value of the measured values;

[0027] The current determination coefficient is determined according to the residual sum of squares and the total sum of squares.

[0028] In some embodiments of the present disclosure, determining the current determination coefficient according to the residual sum of squares and the total sum of squares includes:

[0029] Taking the ratio of the residual sum of squares to the total sum of squares as a first ratio;

[0030] The difference between 1 and the first ratio is used as the current determination coefficient.

[0031] In some embodiments of the present disclosure, the predetermined value is 0.99.

[0032] In some embodiments of the present disclosure, the independent variable of the curing degree objective function is the curing time, and the dependent variable of the curing degree objective function is the curing degree.

[0033] In some embodiments of the present disclosure, the model parameters include a curing degree parameter, an amplitude parameter, and a curing time parameter.

[0034] In some embodiments of the present disclosure, determining the curing degree objective function includes:

[0035] The inverse of the ratio of the degree of cure to the degree of cure parameter is used as a first expression;

[0036] Using the exponential function of the Euler number as the second expression, wherein the exponential of the Euler number is the first expression;

[0037] The difference between 1 and the second expression is taken as the third expression;

[0038] The product of the third expression and the amplitude parameter is taken as a fourth expression;

[0039] The degree of cure is equal to the sum of the degree of cure parameter and the fourth expression to determine the degree of cure objective function.

[0040] In some embodiments of the present disclosure, the adopting an iterative optimization method to perform nonlinear fitting on the coating curing degree sample data includes:

[0041] The steepest descent method combined with the Gauss-Newton method is used to perform nonlinear fitting on the coating curing degree sample data.

[0042] In some embodiments of the present disclosure, obtaining spectral data of the coating to be tested at different times includes:

[0043] The spectral data of the coating to be tested at different times are obtained through a data acquisition device, wherein the data acquisition device includes a temperature acquisition module, an in-situ measurement module and a data acquisition module, the temperature acquisition module is used to collect temperature data, the in-situ measurement module includes an electric heating module and a heatable crystal attenuated total reflection module, and the data acquisition module is used to collect the spectral data of the coating to be tested.

[0044] According to another aspect of the present disclosure, there is provided a coating curing degree prediction device, comprising:

[0045] A spectral data acquisition module is configured to acquire spectral data of the coating to be tested at different times;

[0046] A sample data acquisition module is configured to process the spectral data to obtain sample data of coating curing degree at different times;

[0047] A curing model determination module is configured to determine a curing degree objective function, and adopt an iterative optimization method to perform nonlinear fitting on the coating curing degree sample data to obtain a coating curing degree prediction model;

[0048] The curing degree prediction module is configured to determine a coating curing degree prediction value of the target coating curing time according to the target coating curing time and the coating curing degree prediction model.

[0049] According to another aspect of the present disclosure, there is provided a coating curing degree prediction device, comprising:

[0050] a memory configured to store instructions;

[0051] The processor is configured to execute the instructions so that the coating curing degree prediction device performs the coating curing degree prediction method as described in any of the above embodiments.

[0052] According to another aspect of the present disclosure, a coating curing degree prediction system is provided, comprising a data acquisition device and a coating curing degree prediction apparatus as described in any of the above embodiments.

[0053] According to another aspect of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and when the instructions are executed by a processor, the method for predicting the coating curing degree as described in any of the above embodiments is implemented.

[0054] According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the method for predicting the coating curing degree as described in any of the above embodiments is implemented.

[0055] The present disclosure adopts an iterative optimization method to perform nonlinear fitting on the coating curing degree sample data, thereby improving the accuracy and reliability of the curing trend data prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the embodiments of the present disclosure 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 disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0057] Figure 1 Schematic diagram of some embodiments of the method for predicting the curing degree of coating disclosed in the present invention.

[0058] Figure 2 Schematic diagram of attenuated total reflection measurement in some embodiments of the present disclosure.

[0059] Figure 3 Schematic diagram of infrared curve of curing of polyurea coating in some embodiments of the present disclosure.

[0060] Figure 4 Schematic diagram of the curing trend model of polyurea coating in some embodiments of the present disclosure.

[0061] Figure 5 Schematic diagram of infrared curve of curing of waterborne polyurethane coating in some embodiments of the present disclosure.

[0062] Figure 6 Schematic diagram of the curing trend model of waterborne polyurethane coating in some embodiments of the present disclosure.

[0063] Figure 7 Schematic diagram of some embodiments of the coating curing degree prediction device disclosed in the present invention.

[0064] Figure 8 Schematic diagrams of the structures of other embodiments of the coating curing degree prediction device disclosed in the present invention. DETAILED DESCRIPTION

[0065] The technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and is by no means intended to limit the present disclosure and its application or use. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0066] Unless specifically stated otherwise, the relative arrangement of components and steps, the numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present disclosure.

[0067] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0068] Technologies, methods, and apparatus known to ordinary technicians in the relevant field may not be discussed in detail, but where appropriate, such technologies, methods, and apparatus should be considered part of the authorization specification.

[0069] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0070] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0071] The inventors also found through research that the relevant technology predicts the curing characteristics of the coating by solving the coating curing kinetics equation, and the unknown parameters in the curing kinetics equation: apparent activation energy Ea, pre-exponential factor A and curing kinetics reaction order n, are usually estimated using data such as the heating rate β, peak temperature Tp, and degree of cure measured by differential scanning calorimetry (DSC), combined with the Kissinger or Ozawa empirical equation. By establishing the curing kinetics equation, the change of the degree of cure of the coating over time can be understood, thereby realizing the prediction of the degree of cure.

[0072] The inventors also found through research that the technical problems of the related art include at least one of the following problems: (1) The establishment of the curing kinetics equation of the related art first requires the determination of the curing kinetics model through the analysis of the curing mechanism, which is quite difficult; (2) The related art uses a differential scanning calorimeter (DSC) to test the degree of curing and combines empirical formulas to solve unknown parameters. The process is relatively cumbersome, and the kinetic parameters obtained by calculation have large errors and certain inaccuracies; (3) There is a certain error between the predicted value of the degree of curing obtained by fitting the curing kinetics equation of the related art and the actual result, which makes it difficult to reflect the true curing trend of the coating.

[0073] In view of at least one of the above technical problems, the present disclosure provides a method, device and system, medium and program product for predicting the curing degree of a coating. The present disclosure is described below through specific embodiments.

[0074] Figure 1 Schematic diagram of some embodiments of the method for predicting the degree of curing of a coating disclosed in the present invention. Preferably, this embodiment can be performed by the device for predicting the degree of curing of a coating disclosed in the present invention or the device for predicting the degree of curing of a coating disclosed in the present invention or the prediction system. The method may include at least one of steps 10 to 14.

[0075] Step 10, obtaining spectral data of the coating to be tested at different times.

[0076] In some embodiments of the present disclosure, step 10 may include: acquiring spectral data of the coating to be tested at different times through a data acquisition device, wherein the data acquisition device includes a temperature acquisition module, an in-situ measurement module and a data acquisition module, the temperature acquisition module is used to collect temperature data, the in-situ measurement module includes an electric heating module and a heatable crystal attenuated total reflection module, and the data acquisition module is used to collect spectral data of the coating to be tested.

[0077] In some embodiments of the present disclosure, the data acquisition device may be a curing degree data acquisition device.

[0078] In some embodiments of the present disclosure, step 10 may include: building a curing degree data acquisition system.

[0079] In some embodiments of the present disclosure, the temperature acquisition module is connected to a computer terminal by a temperature sensor, and displays temperature data in real time through a Temperature Controller.

[0080] In some embodiments of the present disclosure, the in-situ measurement module is composed of a heatable zinc selenide crystal ATR (attenuated total reflection) and an electric heating module.

[0081] Figure 2 Schematic diagram of attenuated total reflection measurement in some embodiments of the present disclosure. Figure 2 As shown, the in-situ measurement module includes an ATR crystal and a press, and the press is used to fit the coating to be tested and the crystal tightly. The attenuated total reflection measurement process may include: focusing infrared light onto the surface of the ATR crystal, and then incident on the coating to be tested. Since the refractive index of the ATR crystal is greater than the refractive index of the coating to be tested, and the incident angle is greater than the critical angle, the infrared light penetrates the surface of the coating to be tested and can return to the crystal while total reflection occurs at the coating to be tested-crystal interface. If the coating to be tested has infrared absorption, the infrared light returning to the crystal will have corresponding attenuation, so it is called attenuated total reflection. The infrared light enters the surface of the coating to be tested and returns, so ATR measures the infrared characteristic spectrum of the surface of the coating to be tested. At the same time, if the coating to be tested and the crystal are not tightly fitted, the infrared characteristic spectrum of the coating to be tested cannot be measured.

[0082] The high-temperature ATR module of the above-mentioned embodiment of the present disclosure has a heating function, and can accurately control different curing temperatures. With the help of infrared spectrometers such as Timebase, the spectrum of coatings with different curing degrees can be automatically collected, reducing human errors.

[0083] In some embodiments of the present disclosure, the data acquisition module collects infrared spectrum data and inputs it into a computer terminal, and the built-in spectrum analysis software processes the infrared spectrum graph.

[0084] Step 11, processing the spectral data to obtain coating curing degree sample data at different times.

[0085] In some embodiments of the present disclosure, step 11 may include at least one step from step 111 to step 112 .

[0086] Step 111, perform peak area integration processing to obtain characteristic peak area.

[0087] In some embodiments of the present disclosure, step 111 may include: performing peak area integration processing on the spectral data by using software such as Origin.

[0088] Step 112, determining the coating curing degree sample data at different times according to the characteristic peak area.

[0089] In some embodiments of the present disclosure, step 112 may include: calculating the degree of curing (curing extent) of the coating by quantitative analysis of characteristic peaks.

[0090] In some embodiments of the present disclosure, step 112 may include: determining the degree of curing of the coating at time t based on the characteristic peak area of ​​the target peak at time t and the initial characteristic peak area of ​​the internal standard peak at time t and the initial characteristic peak area.

[0091] In some embodiments of the present disclosure, the curing degree of the coating at time t is the conversion rate of the coating at time t.

[0092] In some embodiments of the present disclosure, step 112 may include: determining the degree of solidification according to formula (1):

[0093]

[0094] In formula (1), α (t) is the conversion rate of the coating at time t; SMB(t) and SMB(0) represent the characteristic peak areas of the target peak at time t and the initial time, respectively; SNB(t) and SNB(0) represent the characteristic peak areas of the internal standard peak at time t and the initial time, respectively.

[0095] Step 12, determining the curing degree objective function.

[0096] In some embodiments of the present disclosure, step 12 may include: setting or defining a solidification degree objective function, wherein the solidification degree objective function includes model parameters.

[0097] In some embodiments of the present disclosure, the independent variable of the curing degree objective function is the curing time x, and the dependent variable of the curing degree objective function is the curing degree y.

[0098] In some embodiments of the present disclosure, the model parameters may include a curing degree parameter y0, an amplitude parameter A1, and a curing time parameter t1.

[0099] In some embodiments of the present disclosure, step 12 may include at least one of steps 121 to 125 .

[0100] Step 121 , taking the inverse of the ratio of the curing degree to the curing degree parameter t1 as the first expression -x / t1.

[0101] Step 122, using the exponential function of the Euler number e as the second expression The exponent of the Euler number is a first expression -x / t1.

[0102] Step 123, replace 1 with the second expression The difference is the third expression

[0103] Step 124: transform the third expression The product of the amplitude parameter A1 is given by the fourth expression

[0104] Step 125, the curing degree y is equal to the curing degree parameter y0 and the fourth expression The sum of and determines the curing degree objective function.

[0105] In some embodiments of the present disclosure, step 125 may include: according to formula (2)

[0106]

[0107] In formula (2), y0 is the curing degree parameter, A1 is the amplitude parameter, t1 is the curing time parameter, and x and y represent the independent variable curing time and the dependent variable curing degree, respectively.

[0108] In some embodiments of the present disclosure, the curing degree objective function of the present disclosure is an objective function obtained by simplifying the fitting function defined by the ExpAssoc formula.

[0109] The function model of the above-mentioned embodiment of the present disclosure is simplified based on the ExpAssoc formula, which reduces the number of unknown parameters while ensuring the reliability of the model and reduces the difficulty of fitting.

[0110] Step 13: adopt an iterative optimization method to perform nonlinear fitting on the coating curing degree sample data to optimize the curing degree objective function and obtain a coating curing degree prediction model.

[0111] In some embodiments of the present disclosure, step 13 may include: using an iterative optimization method to perform nonlinear fitting on the coating curing degree sample data to obtain a coating curing degree prediction model.

[0112] In some embodiments of the present disclosure, the iterative optimization method may be an L-MLevenberg-Marquardt optimization algorithm.

[0113] The coating curing degree prediction method of the above embodiment of the present disclosure is based on the iterative optimization of the Levenberg-Marquardt algorithm, which can achieve a faster convergence effect.

[0114] In some embodiments of the present disclosure, step 13 may include: using an iterative optimization method to optimize and solve the model parameters according to the coating curing degree sample data to obtain a coating curing degree prediction model.

[0115] In some embodiments of the present disclosure, step 13 may include: performing nonlinear fitting on the coating curing degree sample data by adopting an iterative optimization method combining the steepest descent method with the Gauss-Newton method.

[0116] In some embodiments of the present disclosure, step 13 may include: performing nonlinear fitting on the coating curing degree sample data using a LM (Levenberg-Marquardt) nonlinear optimization algorithm.

[0117] In some embodiments of the present disclosure, step 13 may include at least one of steps 130 to 134 .

[0118] Step 130: determining the initial values ​​of the model parameters according to the coating curing degree sample data.

[0119] In some embodiments of the present disclosure, step 130 may include: initializing and assigning values ​​to the model parameters.

[0120] Step 131 , optimizing the model parameters according to the coating curing degree sample data by adopting an iterative optimization method.

[0121] Step 132, determine whether the iteration exit condition is met.

[0122] Step 133, when the iteration exit condition is met, the current curing degree objective function is used as a coating curing degree prediction model.

[0123] Step 134, when the iteration exit condition is not met, repeatedly execute the step of optimizing the model parameters according to the coating curing degree sample data by adopting the iteration optimization method to determine whether the iteration exit condition is met, and repeat the steps of step 131 and step 132.

[0124] In some embodiments of the present disclosure, step 13 may include: the LM nonlinear optimization algorithm may be specifically described by formula (3).

[0125]

[0126] In formula (3), X K represents the initial solution of the parameter estimate at the kth iteration, for example: X K represents the solidification time at the kth iteration, Indicates that at the kth iteration, K The Jacobian matrix at , express The inverse matrix of f(X K ) indicates an estimated value.

[0127] In some embodiments of the present disclosure, step 13 may include: performing nonlinear fitting on the curing degree objective function of formula (2) based on the LM iterative optimization algorithm, and calculating the objective function f(X K ) and the first-order derivative According to formula (3), the new iteration point X is obtained K+1 , until the convergence condition is met or the iteration limit is reached.

[0128] In some embodiments of the present disclosure, the iteration exit condition includes at least one of a convergence condition and an iteration number limit, wherein the iteration number limit is that the current iteration number is greater than or equal to a predetermined iteration number; the convergence condition is that the current determination coefficient R 2 Greater than or equal to the predetermined value.

[0129] In some embodiments of the present disclosure, the predetermined value may be 0.99.

[0130] In some embodiments of the present disclosure, step 13 may include: using the Levenberg-Marquardt iterative optimization algorithm to solve and optimize the model parameters of the nonlinear model of formula (2), and iteratively updating the model parameters to minimize the residual sum of squares (RSS) between the predicted degree of cure output by the model and the measured degree of cure.

[0131] In some embodiments of the present disclosure, step 13 may include: calculating the residual sum of squares (RSS) and the coefficient of determination (R 2) Verify the accuracy of the function model. The smaller the RRS, the better the R 2 The closer it is to 1, the higher the prediction accuracy of the function model.

[0132] The above embodiment of the present disclosure predicts the coating curing degree based on the LM iterative optimization algorithm, using the residual sum of squares (RSS) and the coefficient of determination (R 2 ) was used to evaluate the function model and improve the accuracy and reliability of the solidification trend data prediction.

[0133] In some embodiments of the present disclosure, step 13 may further include at least one of steps 135 to 137 .

[0134] Step 135, based on the measured value t of the coating curing degree data , coating curing degree fit The predicted value of the coating curing degree is determined by the residual sum of squares (RSS).

[0135] In some embodiments of the present disclosure, step 131 may include: determining the residual sum of squares RSS of the coating curing degree according to formula (4).

[0136] RSS=∑(y data -y fit ) 2 (4)

[0137] Step 136, based on the measured value y data , the average value of the measured values Determine the total square sum SST of the coating's degree of cure.

[0138] In some embodiments of the present disclosure, step 132 may include: determining the total square sum SST of the coating curing degree according to formula (5).

[0139]

[0140] Step 137: Determine the current determination coefficient R according to the residual sum of squares RSS and the total sum of squares SST. 2 .

[0141] In some embodiments of the present disclosure, step 137 may include: taking the ratio of the residual sum of squares to the total sum of squares as a first ratio; taking the difference between 1 and the first ratio as the current determination coefficient R 2 .

[0142] In some embodiments of the present disclosure, step 137 may include: determining the current determination coefficient R according to formula (6): 2 .

[0143] R 2=1-(RSS / SST) (6)

[0144] Step 14: Determine a coating curing degree prediction value for the target coating curing time according to the target coating curing time and the coating curing degree prediction model.

[0145] In some embodiments of the present disclosure, step 14 may include: substituting the target coating curing time into the coating curing degree prediction model after fitting optimization, and determining the coating curing degree prediction value of the target coating curing time.

[0146] The purpose of the above-mentioned embodiments of the present disclosure is to provide a coating curing degree prediction system and method based on the Levenberg-Marquardt nonlinear fitting algorithm. The infrared curing curve of the sample is tested in situ by a heatable ATR accessory, and the curing degree data is nonlinearly fitted based on the LM iterative optimization algorithm to achieve the purpose of rapid convergence of the objective function, and a curing degree trend prediction model is obtained. The known coating curing time is substituted to achieve quantitative analysis of the coating curing degree under different reaction times, thereby providing a feasible method for quantifying the coating curing degree.

[0147] The prediction of the coating curing degree based on the LM iterative optimization algorithm in the above embodiment of the present disclosure can predict the coating curing degree at different temperatures and different reaction times, and the prediction result is highly accurate, with a determination coefficient R 2 Close to 1.

[0148] The above-mentioned embodiment of the present disclosure predicts the curing degree of the coating based on the LM iterative optimization algorithm, establishes a curing trend model, and can quantitatively analyze and predict the curing degree of the film-forming coating, thereby solving the technical problem that the curing degree of the film-forming coating cannot be quantitatively analyzed.

[0149] The above-mentioned embodiments of the present disclosure can use software such as Python to perform a full-process analysis of the output results of the coating curing degree prediction model, which is convenient and quick.

[0150] The method for predicting the curing degree of the coating disclosed in the present invention is described below through specific examples.

[0151] First type of embodiment

[0152] In some embodiments of the present disclosure, aspartame polyurea coating is used as a test object to predict the curing degree of the coating at different curing times, and the steps may include at least one of steps S1 to S7.

[0153] S1, based on the in-situ infrared spectrometer, build data acquisition equipment, including the measurement device high temperature ATR installation, the sample is coated on the crystal and heated, the temperature controller is used to control the test temperature and real-time monitoring, the infrared spectrum processing module is used for automatic spectrum collection and analysis and processing, the polyurea coating sample test temperature is room temperature, the infrared spectrum is shown in Figure 3 . Figure 3 Schematic diagram of infrared curve of curing of polyurea coating in some embodiments of the present disclosure.

[0154] S2, the curing degree of the coating at different times is calculated by integrating the characteristic peaks using software such as Origin, and the results are shown in Table 1. Table 1 shows the curing degree results of the coating at different curing times.

[0155] Table 1

[0156]

[0157] S3, define the objective function as shown in formula (2).

[0158] S4, use the LM iterative optimization algorithm to solve the unknown model parameters of the function model. Before solving, the unknown model parameters are first assigned values, y0=0.5, A1=0.75, t1=100.

[0159] S5, through the iterative optimization algorithm, the unknown model parameters of the function model are solved, y0 = -0.0497, A1 = 0.995, t1 = 134.788.

[0160] S6, calculate the accuracy of the function model, based on the RSS solution formula, RSS = 0.00929, based on the determination coefficient R 2 Solving formula (6) yields R 2 =0.992, indicating that the function model has high prediction accuracy for the degree of curing.

[0161] S7: Plot the original data points and the fitted curve. Figure 4 , Figure 4 This is a schematic diagram of the curing trend model of the polyurea coating in some embodiments of the present disclosure. The function formula is used to solve the curing degree of the coating with a known curing time. The function model obtained by solving the solution is shown in formula (7).

[0162] y=-0.0497+0.995×(1-e -x / 134.788 ) (7)

[0163] Second Type of Embodiment

[0164] This embodiment uses water-based paint as a test object to predict the degree of curing under different curing times. The steps may include at least one of steps S1 to S7.

[0165] S1 is the same as step S1 of the first type of embodiment, except that the sample heating temperature is set to 80°C. The infrared spectrum is shown in FIG. Figure 5 . Figure 5 Schematic diagram of infrared curve of curing of waterborne polyurethane coating in some embodiments of the present disclosure.

[0166] S2, the calculation of the curing degree of the coating at different times is performed by integrating the characteristic peaks using software such as Origin, and the results are shown in Table 2. Table 2 shows the curing degree results of the coating at different curing times.

[0167] Table 2

[0168]

[0169] S3, define the objective function as shown in formula (2).

[0170] S4, use the LM iterative optimization algorithm to solve the unknown parameters of the model function. Before solving, the unknown parameters are first assigned values, y0=0.5, A1=1, t1=1.

[0171] S5, through the iterative optimization algorithm, the unknown parameters of the function model are solved, y0 = -0.0313, A1 = 1.0245, t1 = 7.5803.

[0172] S6, calculate the accuracy of the function model, based on the RSS solution formula, RSS = 0.005, based on the determination coefficient R 2 Solving formula (6) yields R 2 =0.995, indicating that the function model has high prediction accuracy for the degree of curing.

[0173] S7, draw the original data points and the fitting curve, the results are shown in the attached Figure 6 , Figure 6 This is a schematic diagram of the curing trend model of the waterborne polyurethane coating in some embodiments of the present disclosure. The function formula is used to solve the curing degree of the coating with a known curing time. The function model obtained by solving the solution is shown in formula (8).

[0174] y=-0.0313+1.0245×(1-e -x / 7.5803 ) (8)

[0175] The method for predicting the coating curing degree based on the LM iterative optimization algorithm in the above embodiment of the present disclosure is applicable to a wide range of coatings. The above embodiment of the present disclosure can be applied to the prediction of the curing degree of coatings such as water-based polyurethane coatings and aspartame polyurea coatings.

[0176] Figure 7 Schematic diagram of some embodiments of the coating curing degree prediction device disclosed in the present invention. Figure 7 As shown, the coating curing degree prediction device disclosed in the present invention may include a spectral data acquisition module 71 , a sample data acquisition module 72 , a curing model determination module 73 and a curing degree prediction module 74 .

[0177] The spectrum data acquisition module 71 is configured to acquire spectrum data of the coating to be tested at different times.

[0178] In some embodiments of the present disclosure, the spectral data acquisition module 71 can be configured to acquire spectral data of the coating to be tested at different times through a data acquisition device, wherein the data acquisition device includes a temperature acquisition module, an in-situ measurement module and a data acquisition module, the temperature acquisition module is used to collect temperature data, the in-situ measurement module includes an electric heating module and a heatable crystal attenuated total reflection module, and the data acquisition module is used to collect spectral data of the coating to be tested.

[0179] The sample data acquisition module 72 is configured to process the spectral data to obtain sample data of coating curing degree at different moments.

[0180] The curing model determination module 73 is configured to determine a curing degree objective function; and adopt an iterative optimization method to perform nonlinear fitting on the coating curing degree sample data to optimize the curing degree objective function and obtain a coating curing degree prediction model.

[0181] In some embodiments of the present disclosure, the curing degree objective function includes model parameters.

[0182] In some embodiments of the present disclosure, the independent variable of the curing degree objective function may be the curing time, and the dependent variable of the curing degree objective function may be the curing degree.

[0183] In some embodiments of the present disclosure, the model parameters may include a curing degree parameter, an amplitude parameter, and a curing time parameter.

[0184] In some embodiments of the present disclosure, the curing model determination module 73 can be configured to use the opposite of the ratio of the degree of curing to the degree of curing parameter as the first expression when determining the degree of curing target function; use the exponential function of the Euler number as the second expression, wherein the exponent of the Euler number is the first expression; use the difference between 1 and the second expression as the third expression; use the product of the third expression and the amplitude parameter as the fourth expression; and determine the degree of curing target function by setting the degree of curing to be equal to the sum of the degree of curing parameter and the fourth expression.

[0185] In some embodiments of the present disclosure, the curing model determination module 73 can be configured to use an iterative optimization method combining the steepest descent method with the Gauss-Newton method to perform nonlinear fitting on the coating curing degree sample data when using an iterative optimization method to perform nonlinear fitting on the coating curing degree sample data.

[0186] In some embodiments of the present disclosure, the curing model determination module 73, when adopting an iterative optimization method to perform nonlinear fitting on the coating curing degree sample data to optimize the curing degree objective function and obtain a coating curing degree prediction model, can be configured to adopt an iterative optimization method to optimize the model parameters according to the coating curing degree sample data to obtain a coating curing degree prediction model.

[0187] In some embodiments of the present disclosure, the curing model determination module 73, when adopting an iterative optimization method to optimize the model parameters according to the coating curing degree sample data to obtain a coating curing degree prediction model, can be configured to determine the initial values ​​of the model parameters according to the coating curing degree sample data; adopt an iterative optimization method to optimize the model parameters according to the coating curing degree sample data; determine whether the iteration exit condition is met; and if the iteration exit condition is met, use the current curing degree objective function as the coating curing degree prediction model.

[0188] In some embodiments of the present disclosure, the curing model determination module 73, when optimizing the model parameters according to the coating curing degree sample data by an iterative optimization method to obtain a coating curing degree prediction model, can also be configured to repeatedly execute the operation of optimizing the model parameters according to the coating curing degree sample data by an iterative optimization method to determine whether the iterative exit condition is met when the iterative exit condition is not met.

[0189] In some embodiments of the present disclosure, the iteration exit condition includes at least one of the following conditions: the current number of iterations is greater than or equal to a predetermined number of iterations; the current determination coefficient is greater than or equal to a predetermined value.

[0190] In some embodiments of the present disclosure, the predetermined value may be 0.99.

[0191] In some embodiments of the present disclosure, the curing model determination module 73 can also be configured to determine the residual sum of squares of the coating curing degree based on the measured value of the coating curing degree and the predicted value of the coating curing degree; determine the total sum of squares of the coating curing degree based on the measured value and the average value of the measured value; determine the current determination coefficient based on the residual sum of squares and the total sum of squares.

[0192] In some embodiments of the present disclosure, the solidified model determination module 73 can be configured to use the ratio of the residual sum of squares and the total sum of squares as the first ratio; and use the difference between 1 and the first ratio as the current determination coefficient when determining the current determination coefficient based on the residual sum of squares and the total sum of squares.

[0193] The curing degree prediction module 74 is configured to determine a coating curing degree prediction value at the target coating curing time according to the target coating curing time and the coating curing degree prediction model.

[0194] In some embodiments of the present disclosure, the coating curing degree prediction device can be used to implement any of the above embodiments (for example Figure 1 Operation of the method for predicting the degree of coating cure as described in Example 1.

[0195] The above-mentioned embodiment of the present disclosure adopts an iterative optimization method to perform nonlinear fitting on the coating curing degree sample data, thereby improving the accuracy and reliability of the curing trend data prediction.

[0196] Figure 8 Schematic diagram of the structure of some other embodiments of the coating curing degree prediction device disclosed in the present invention. Figure 8 As shown, the coating curing degree prediction device includes a memory 81 and a processor 82.

[0197] The memory 81 is used to store instructions. The processor 82 is coupled to the memory 81. The processor 82 is configured to execute the instructions stored in the memory to implement any of the above embodiments (for example, Figure 1 The method for predicting the degree of curing of the coating described in Example 1 is as follows.

[0198] like Figure 8 As shown, the coating curing degree prediction device also includes a communication interface 83 for information exchange with other devices. At the same time, the coating curing degree prediction device also includes a bus 84, through which the processor 82, the communication interface 83, and the memory 81 communicate with each other.

[0199] The memory 81 may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory. The memory 81 may also be a memory array. The memory 81 may also be divided into blocks, and the blocks may be combined into virtual volumes according to certain rules.

[0200] In addition, the processor 82 may be a central processing unit (CPU), or may be an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present disclosure.

[0201] According to another aspect of the present disclosure, a coating curing degree prediction system is provided, comprising a data acquisition device and any one of the above embodiments (e.g. Figure 7 or Figure 8 The coating curing degree prediction device described in Example).

[0202] The coating curing degree prediction method, device and system based on the LM iterative optimization algorithm of the above-mentioned embodiment of the present disclosure have high prediction accuracy and reliable function model.

[0203] The coating curing degree prediction method, device and system of the above-mentioned embodiments of the present disclosure can be applied to the coating curing degree detection of the coating used for painting engineering machinery.

[0204] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above embodiments (for example Figure 1 The method for predicting the degree of curing of the coating described in Example 1 is as follows.

[0205] According to another aspect of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and when the instructions are executed by a processor, any of the above embodiments (for example Figure 1 The method for predicting the degree of curing of the coating described in Example 1 is as follows.

[0206] In some embodiments of the present disclosure, the computer-readable storage medium may be a non-transitory computer-readable storage medium.

[0207] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, devices, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present disclosure may take the form of a computer program product implemented on one or more computer-usable non-transient storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0208] The present disclosure is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present disclosure. It should be understood that each process and / or block in the flowchart and / or block diagram and the combination of processes and / or blocks in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0209] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0210] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0211] The coating curing degree prediction device, spectral data acquisition module, sample data acquisition module, curing model determination module and curing degree prediction module described above can be implemented as a general processor, programmable logic controller (PLC), digital signal processor (DSP), application specific integrated circuit (ASIC), field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware component or any appropriate combination thereof for performing the functions described in the present application.

[0212] So far, the present disclosure has been described in detail. In order to avoid obscuring the concept of the present disclosure, some details known in the art are not described. Based on the above description, those skilled in the art can fully understand how to implement the technical solution disclosed here.

[0213] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware, or may be accomplished by instructing the relevant hardware through a program, and the program may be stored in a non-transitory computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0214] The description of the present disclosure is given for the purpose of illustration and description, and is not intended to be exhaustive or to limit the present disclosure to the disclosed form. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiments are selected and described in order to better illustrate the principles and practical applications of the present disclosure, and to enable those of ordinary skill in the art to understand the present disclosure and thereby design various embodiments with various modifications suitable for specific uses.

Claims

1. A method for predicting the degree of curing of a coating, comprising: Obtaining spectral data of the coating to be tested at different times; Processing the spectral data to obtain coating curing degree sample data at different times; Determine the curing degree objective function; Using an iterative optimization method, nonlinear fitting is performed on the coating curing degree sample data to optimize the curing degree objective function and obtain a coating curing degree prediction model; According to the target coating curing time and the coating curing degree prediction model, a coating curing degree prediction value of the target coating curing time is determined.

2. The method for predicting the degree of curing of a coating according to claim 1, wherein: The solidification degree objective function includes model parameters; The method of adopting an iterative optimization method to perform nonlinear fitting on the coating curing degree sample data to optimize the curing degree objective function and obtain a coating curing degree prediction model includes: The iterative optimization method is adopted to optimize the model parameters according to the coating curing degree sample data to obtain a coating curing degree prediction model.

3. The method for predicting the degree of curing of a coating according to claim 2, wherein: The iterative optimization method is used to optimize the model parameters according to the coating curing degree sample data to obtain the coating curing degree prediction model, which includes: Determining the initial value of the model parameter according to the coating curing degree sample data; Adopting the iterative optimization method, optimizing the model parameters according to the coating curing degree sample data; Determine whether the iteration exit condition is met; When the iteration exit condition is met, the current curing degree objective function is used as the coating curing degree prediction model.

4. The method for predicting the degree of curing of a coating according to claim 3, wherein: The method of optimizing the model parameters according to the coating curing degree sample data by adopting an iterative optimization method to obtain a coating curing degree prediction model further includes: In the case where the iteration exit condition is not met, the step of repeatedly optimizing the model parameters according to the coating curing degree sample data by adopting an iterative optimization method to determine whether the iteration exit condition is met is performed.

5. The method for predicting the degree of curing of a coating according to claim 3 or 4, wherein: The iteration exit condition includes at least one of the following conditions: The current number of iterations is greater than or equal to the predetermined number of iterations; The current determination coefficient is greater than or equal to a predetermined value.

6. The method for predicting the coating curing degree according to claim 5, further comprising: Determine the residual sum of squares of the coating curing degree according to the measured value of the coating curing degree and the predicted value of the coating curing degree; Determining the total sum of squares of the coating curing degree according to the measured values ​​and the average value of the measured values; The current determination coefficient is determined according to the residual sum of squares and the total sum of squares.

7. The method for predicting the degree of curing of a coating according to claim 6, wherein: Determining the current determination coefficient according to the residual sum of squares and the total sum of squares includes: Taking the ratio of the residual sum of squares to the total sum of squares as a first ratio; The difference between 1 and the first ratio is used as the current determination coefficient.

8. The method for predicting the degree of curing of a coating according to claim 5, wherein: The predetermined value is 0.

99.

9. The method for predicting the degree of curing of a coating according to any one of claims 2 to 4, wherein: The independent variable of the curing degree objective function is the curing time, and the dependent variable of the curing degree objective function is the curing degree; The model parameters include a curing degree parameter, an amplitude parameter and a curing time parameter.

10. The method for predicting the degree of curing of a coating according to claim 9, wherein: The objective function for determining the degree of solidification comprises: The inverse of the ratio of the degree of cure to the degree of cure parameter is used as a first expression; Using the exponential function of the Euler number as a second expression, wherein the exponent of the Euler number is the first expression; The difference between 1 and the second expression is taken as the third expression; The product of the third expression and the amplitude parameter is taken as a fourth expression; The curing degree objective function is determined by equating the curing degree to the sum of the curing degree parameter and the fourth expression.

11. The method for predicting the degree of curing of a coating according to any one of claims 1 to 4, wherein: The nonlinear fitting of the coating curing degree sample data by adopting an iterative optimization method includes: The steepest descent method combined with the Gauss-Newton method is used to perform nonlinear fitting on the coating curing degree sample data.

12. The method for predicting the degree of curing of a coating according to any one of claims 1 to 4, wherein: The obtaining of spectral data of the coating to be tested at different times comprises: The spectral data is acquired through a data acquisition device, wherein the data acquisition device includes a temperature acquisition module, an in-situ measurement module and a data acquisition module, the temperature acquisition module is used to collect temperature data, the in-situ measurement module includes an electric heating module and a heatable crystal attenuated total reflection module, and the data acquisition module is used to collect the spectral data.

13. A coating curing degree prediction device, comprising: A spectral data acquisition module is configured to acquire spectral data of the coating to be tested at different times; A sample data acquisition module is configured to process the spectral data to obtain sample data of coating curing degree at different times; A solidification model determination module is configured to determine a solidification degree objective function; Using an iterative optimization method, nonlinear fitting is performed on the coating curing degree sample data to optimize the curing degree objective function and obtain a coating curing degree prediction model; The curing degree prediction module is configured to determine a coating curing degree prediction value of the target coating curing time according to the target coating curing time and the coating curing degree prediction model.

14. A coating curing degree prediction device, comprising: a memory configured to store instructions; The processor is configured to execute the instructions so that the coating curing degree prediction device performs the coating curing degree prediction method as described in any one of claims 1-12.

15. A coating curing degree prediction system, comprising a data acquisition device and a coating curing degree prediction device as claimed in claim 13 or 14.

16. A computer-readable storage medium, wherein: The computer-readable storage medium stores computer instructions, and when the instructions are executed by a processor, the method for predicting the coating curing degree according to any one of claims 1 to 12 is implemented.

17. A computer program product comprising a computer program, wherein: When the computer program is executed by a processor, the method for predicting the coating curing degree according to any one of claims 1 to 12 is implemented.