Methods, apparatus, computer equipment, computer-readable storage media, and computer program products for modeling corrosion effects of protective coatings

Abstract

This application relates to a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for modeling the corrosion effect of protective coatings. The method includes: acquiring independent variable parameters, a first environmental effect characteristic parameter, and a second environmental effect characteristic parameter corresponding to multiple data acquisition time points; obtaining target corrosion effect characteristic parameters based on the first and second environmental effect characteristic parameters; and obtaining a target corrosion effect characteristic model based on the independent variable parameters, the target corrosion effect characteristic parameters, and a preset model. This enables high-precision prediction of the corrosion effect characteristic parameters of protective coatings based on microorganisms and identification of key environmental characteristic parameters, thereby improving the accuracy of predicting the anti-corrosion performance of protective coatings.

Description

Technical Field

[0001] This application relates to the field of protective coating degradation prediction technology, and in particular to a method, apparatus, computer equipment, computer-readable storage medium and computer program product for modeling the corrosion effect of protective coatings. Background Technology

[0002] Protective coatings are a critical barrier ensuring the long-term safe operation of equipment and infrastructure and resisting environmental and microbial corrosion. Therefore, it is necessary to accurately assess and predict the corrosion resistance performance of protective coatings. Specifically, to accurately assess and predict the corrosion resistance performance of protective coatings, it is necessary to accurately evaluate the degree of influence of each factor affecting the corrosion resistance performance of the protective coating on its degradation.

[0003] In existing technologies, when predicting the corrosion resistance of protective coatings, most studies take the natural environment as an influencing factor, such as ultraviolet intensity, temperature, humidity, and salt spray. Few studies take microorganisms as an influencing factor on corrosion resistance, which reduces the accuracy of predicting the corrosion resistance of protective coatings. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for modeling the corrosion effect of protective coatings, which can improve the accuracy of predicting the anti-corrosion performance of protective coatings, in order to address the above-mentioned technical problems.

[0005] Firstly, this application provides a method for modeling the corrosion effect of protective coatings, including:

[0006] The independent variable parameters, first environmental effect characteristic parameters and second environmental effect characteristic parameters corresponding to multiple data collection time points are obtained. The first environmental effect characteristic parameter is the environmental effect characteristic parameter of the protective coating under the first test condition, and the second environmental effect characteristic parameter is the environmental effect characteristic parameter of the protective coating under the second test condition. The microbial information of the first test condition and the second test condition are different. The independent variable parameters include test duration and environmental characteristic parameters.

[0007] The target corrosion effect characteristic parameters are determined based on the first environmental effect characteristic parameters and the second environmental effect characteristic parameters.

[0008] Based on the independent variable parameters, target corrosion effect characteristic parameters, and preset model corresponding to multiple data collection time points, the target corrosion effect characteristic model is obtained.

[0009] In one embodiment, a target corrosion effect characteristic model is obtained based on independent variable parameters corresponding to multiple data acquisition time points, target corrosion effect characteristic parameters, and a preset model, including:

[0010] Based on the independent variable parameters and target corrosion effect characteristic parameters corresponding to multiple data collection time points, the preset model is trained using the preset least squares method to determine the model parameters that minimize the sum of squared errors.

[0011] Based on the model parameters that minimize the sum of squared errors, the characteristic model of the target corrosion effect is obtained.

[0012] In one embodiment, the preset least squares method is the iterative weighted least squares method;

[0013] Based on the independent variable parameters and target corrosion effect characteristic parameters corresponding to multiple data collection time points, a preset model is trained using the preset least squares method to determine the model parameters that minimize the sum of squared errors, including:

[0014] The initial parameters of the preset model are determined based on the preset least squares method;

[0015] Based on the independent variable parameters, target corrosion effect characteristic parameters, and initial parameters corresponding to multiple data collection time points, the parameters of the preset model are optimized multiple times until the parameter convergence condition is met. The current parameters that meet the parameter convergence condition are determined as the model parameters that minimize the sum of squared errors.

[0016] In one embodiment, based on the independent variable parameters, target corrosion effect characteristic parameters, and initial parameters corresponding to multiple data acquisition time points, the parameters of the preset model are optimized multiple times, including:

[0017] Based on the current parameters of the preset model, calculate the current residuals of the independent variable parameters and the target corrosion effect characteristic parameters corresponding to each data acquisition time point;

[0018] The current residual is converted into the current weight value of the independent variable parameter and the target corrosion effect characteristic parameter corresponding to each data acquisition time point according to the loss function of M-estimation. The loss function reduces the weight value of the independent variable parameter and the target corrosion effect characteristic parameter corresponding to the data acquisition time point where the current residual is greater than the preset residual.

[0019] Based on the current weight values, the parameters of the preset model obtained from the previous parameter optimization are optimized to obtain the current parameters of the preset model.

[0020] In one embodiment, determining the target corrosion effect characteristic parameters based on a first environmental effect characteristic parameter and a second environmental effect characteristic parameter includes:

[0021] The initial corrosion effect characteristic parameters are determined based on the difference between the first environmental effect characteristic parameters and the second environmental effect characteristic parameters.

[0022] Data preprocessing is performed on the initial corrosion effect characteristic parameters to obtain the target corrosion effect characteristic parameters.

[0023] In one embodiment, a target corrosion effect characteristic model is obtained based on independent variable parameters corresponding to multiple data acquisition time points, target corrosion effect characteristic parameters, and a preset model, including:

[0024] Based on the independent variable parameters and target corrosion effect characteristic parameters corresponding to multiple data collection points, determine the correlation coefficient between each corrosion effect characteristic parameter and each independent variable parameter;

[0025] Based on the correlation coefficient between each corrosion effect characteristic parameter and each independent variable parameter, as well as the independent variable parameters, target corrosion effect characteristic parameters, and preset model corresponding to multiple data acquisition time points, the target corrosion effect characteristic model is obtained.

[0026] In one embodiment, a target corrosion effect feature model is obtained based on the correlation coefficient between each corrosion effect feature parameter and each independent variable parameter, as well as the independent variable parameters corresponding to multiple data acquisition time points, the target corrosion effect feature parameters, and a preset model. This model includes:

[0027] Based on the correlation coefficient between each corrosion effect characteristic parameter and each independent variable parameter, the independent variable parameters used to determine each corrosion effect characteristic parameter are determined.

[0028] Based on the independent variable parameters, target corrosion effect characteristic parameters, and preset models corresponding to multiple data collection points for determining each corrosion effect characteristic parameter, the target corrosion effect characteristic model corresponding to each corrosion effect characteristic parameter is obtained.

[0029] In one embodiment, a target corrosion effect feature model is obtained based on the correlation coefficient between each corrosion effect feature parameter and each independent variable parameter, as well as the independent variable parameters corresponding to multiple data acquisition time points, the target corrosion effect feature parameters, and a preset model. This model includes:

[0030] Based on the independent variable parameters, target corrosion effect characteristic parameters and preset models corresponding to multiple data collection time points, the initial corrosion effect characteristic model corresponding to each corrosion effect characteristic parameter is obtained;

[0031] Based on the correlation coefficient between each corrosion effect characteristic parameter and each independent variable parameter, the initial corrosion effect characteristic model corresponding to each corrosion effect characteristic parameter is modified to obtain the target corrosion effect characteristic model corresponding to each corrosion effect characteristic parameter.

[0032] Secondly, this application also provides a protective coating corrosion effect modeling device, comprising:

[0033] The first acquisition module is used to acquire independent variable parameters, first environmental effect characteristic parameters and second environmental effect characteristic parameters corresponding to multiple data acquisition time points. The first environmental effect characteristic parameters are the environmental effect characteristic parameters of the protective coating under the first test conditions, and the second environmental effect characteristic parameters are the environmental effect characteristic parameters of the protective coating under the second test conditions. The microbial information of the first test conditions and the second test conditions are different. The independent variable parameters include test duration and environmental characteristic parameters.

[0034] The second acquisition module is used to determine the target corrosion effect characteristic parameters based on the first environmental effect characteristic parameters and the second environmental effect characteristic parameters.

[0035] The modeling module is used to obtain a target corrosion effect characteristic model based on the independent variable parameters, target corrosion effect characteristic parameters, and preset models corresponding to multiple data acquisition time points.

[0036] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method described in any of the first aspects.

[0037] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any of the first aspects.

[0038] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the method described in any of the first aspects.

[0039] The aforementioned method, apparatus, computer equipment, computer-readable storage medium, and computer program product for modeling the corrosion effect of protective coatings acquire independent variable parameters, first environmental effect characteristic parameters, and second environmental effect characteristic parameters corresponding to multiple data acquisition time points. Since the first environmental effect characteristic parameter is the environmental effect characteristic parameter of the protective coating under the first test condition, and the second environmental effect characteristic parameter is the environmental effect characteristic parameter of the protective coating under the second test condition, and the microbial information under the first and second test conditions is different, the difference between the first and second environmental effect characteristic parameters makes the determined target corrosion effect characteristic parameters related to microorganisms. Therefore, based on the independent variable parameters, target corrosion effect characteristic parameters, and preset model corresponding to multiple data acquisition time points, the obtained target corrosion effect characteristic model can reflect the degree of influence of microorganisms on the anti-corrosion performance of the protective coating over time, achieving high-precision prediction of the microbial-based corrosion effect characteristic parameters of the protective coating and identification of the main environmental characteristic parameters. Furthermore, by representing the differences caused by different microbial information through corrosion effect characteristic parameters, the differences in microbial information are expressed in a calculable way, thereby obtaining the target corrosion effect characteristic model. This achieves the goal of predicting the impact of microorganisms on the anti-corrosion performance of protective coatings through mathematical models, solving the problem of the difficulty in predicting the corrosion process of protective coatings by microorganisms, and improving the accuracy of predicting the anti-corrosion performance of protective coatings. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 A flowchart illustrating the corrosion effect modeling of a protective coating provided in an embodiment of this application;

[0042] Figure 2 A flowchart illustrating a method for determining characteristic parameters of a target corrosion effect according to an embodiment of this application;

[0043] Figure 3 A flowchart illustrating a method for constructing a characteristic model of a target corrosion effect according to an embodiment of this application;

[0044] Figure 4 A flowchart illustrating a method for parameter optimization provided in one embodiment of the application;

[0045] Figure 5 A flowchart of a parameter optimization method based on M-estimation provided in one embodiment of the application;

[0046] Figure 6 A flowchart illustrating a method for constructing a characteristic model of a target corrosion effect, provided in another embodiment of this application;

[0047] Figure 7 A flowchart illustrating a method for constructing a target corrosion effect characteristic model by combining correlation coefficients, as provided in an embodiment of this application;

[0048] Figure 8 A flowchart illustrating a method for constructing a target corrosion effect characteristic model by combining correlation coefficients, as provided in another embodiment of this application;

[0049] Figure 9 A flowchart of a method for modeling the corrosion effect of a protective coating provided in yet another embodiment of this application;

[0050] Figure 10 A flowchart illustrating a method for modeling the corrosion effect of a protective coating as provided in another embodiment of this application;

[0051] Figure 11 A schematic diagram of the regression coefficients between the adhesion difference and the independent variable provided in an embodiment of this application;

[0052] Figure 12 A schematic diagram of the structure of a protective coating corrosion effect modeling device provided in an embodiment of this application;

[0053] Figure 13 This is an internal structural diagram of a computer device provided in an embodiment of this application. Detailed Implementation

[0054] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0055] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0056] Because the corrosion resistance of protective coatings is significantly affected by environmental factors, most studies predicting their corrosion resistance focus on the impact of natural environmental factors, neglecting the influence of microorganisms. Furthermore, microbial corrosion involves complex interactions between microorganisms and the protective coating, making its corrosion process more diverse and difficult to predict. Therefore, current research lacks studies on the impact of microorganisms on the corrosion resistance of protective coatings.

[0057] Therefore, this application proposes a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for modeling the corrosion effect of protective coatings. By placing the protective coatings in natural environments with different microbial information, the degree of corrosion of the protective coatings varies due to the different microbial information. This establishes a mapping relationship between the degradation of the environmental effect characteristic parameters of the protective coatings under microbial corrosion conditions and environmental characteristic parameters such as temperature, humidity, and salt spray. The application obtains the degree of influence of the natural environment on the degree of microbial corrosion of the protective coatings, and realizes a high-precision prediction of the corrosion effect characteristic parameters of the protective coatings based on microorganisms and the identification of the main environmental characteristic parameters.

[0058] Figure 1 This is a flowchart illustrating the corrosion effect modeling of a protective coating according to an embodiment of this application. In this embodiment, the method is described using a terminal as an example. It is understood that this method can also be applied to a server, and further to a system including both a terminal and a server, and is implemented through interaction between the terminal and the server. The terminal can be, but is not limited to, various personal computers, laptops, smartphones, and tablets, and the server can be a standalone server or a server cluster composed of multiple servers. Figure 1 As shown, the method in this embodiment includes:

[0059] S101. Obtain the independent variable parameters, first environmental effect characteristic parameters, and second environmental effect characteristic parameters corresponding to multiple data collection time points.

[0060] Among them, the first environmental effect characteristic parameter is the environmental effect characteristic parameter of the protective coating under the first test condition, and the second environmental effect characteristic parameter is the environmental effect characteristic parameter of the protective coating under the second test condition. The microbial information of the first test condition and the second test condition are different. The independent variable parameters include the test duration and environmental characteristic parameters.

[0061] Prepare multiple identical protective coatings, divide the protective coatings into multiple test groups, and then place the multiple test groups under natural conditions, ensuring that the microbial information in the test conditions corresponding to the multiple test groups is different, while other conditions are the same.

[0062] It should be noted that multiple identical protective coatings refer to coatings with the same composition, the same production process specifications, the same appearance and structural state, the same inspection standards, the same final protective performance at the time of leaving the factory, and the same protective performance at the start of the test.

[0063] Microbiological information includes the types and amounts of microorganisms. Different microbiological information means that at least one of the types or amounts of microorganisms is different.

[0064] Other conditions include: light, temperature, humidity, salt spray deposition rate, etc.

[0065] For example, six identical protective coatings are divided into two test groups, each containing three protective coatings. The test group placed directly in the natural environment is designated as the first group, while the second group is placed in the same natural environment but sprayed with substances such as alcohol to inhibit microorganisms. This results in the microbial information of the first experimental conditions corresponding to the first group being different from that of the second group, while other conditions remain the same.

[0066] The independent variable parameter refers to the factor that causes the change in the anti-corrosion performance of the protective coating. In this implementation, the independent variable parameters include: test duration and environmental characteristic parameters. The test duration is the time between the data acquisition time point corresponding to the independent variable parameter and the test start time point, and the test start time point is the time point corresponding to the start of the test.

[0067] The environmental characteristic parameters are selected from other conditions. In this embodiment, the environmental characteristic parameters include: temperature, humidity, and salt spray deposition rate.

[0068] Environmental effect characteristic parameters refer to parameters that can reflect the anti-corrosion performance of the protective coating. In this embodiment, environmental effect characteristic parameters include: electrochemical impedance, adhesion and gloss loss rate.

[0069] For the example above, in order to dynamically monitor the corrosive effect of microorganisms on the protective coating, multiple data acquisition time points are set. At each data acquisition time point, the terminal obtains temperature, humidity, salt spray deposition rate, electrochemical impedance spectroscopy, adhesion, and gloss loss rate from the temperature sensor, humidity sensor, salt spray deposition rate detection device, electrochemical impedance spectroscopy detection device, adhesion detection device, and gloss loss rate detection device, respectively. Alternatively, the user can input temperature, humidity, salt spray deposition rate, electrochemical impedance spectroscopy, adhesion, and gloss loss rate into the terminal.

[0070] It should be noted that since the microbial information of the first and second groups is different, while other conditions are the same, environmental characteristic parameters, namely temperature, humidity, and salt spray deposition, are collected once at each data acquisition time point. For environmental effect characteristic parameters, different environmental effect characteristic parameters are obtained according to the three protective coatings in each group. That is, taking the first group as an example, the electrochemical impedance is obtained using the first protective coating, the adhesion is obtained using the second protective coating, and the gloss loss rate is obtained using the third protective coating.

[0071] S102. Determine the target corrosion effect characteristic parameters based on the first environmental effect characteristic parameters and the second environmental effect characteristic parameters.

[0072] Since the microbial information of the first experimental conditions corresponding to the first group and the first experimental conditions corresponding to the second group are different, while other conditions are the same, there is a difference between the first environmental effect characteristic parameter and the second environmental effect characteristic parameter due to the difference in microbial information. Therefore, the target corrosion effect characteristic parameter is obtained based on the difference between the first environmental effect characteristic parameter and the second environmental effect characteristic parameter.

[0073] The terminal is pre-set with a model for obtaining the characteristic parameters of the target corrosion effect. This model can be the ratio between the first environmental effect characteristic parameter and the second environmental effect characteristic parameter as the characteristic parameter of the target corrosion effect.

[0074] S103. Based on the independent variable parameters, target corrosion effect characteristic parameters, and preset model corresponding to multiple data acquisition time points, obtain the target corrosion effect characteristic model.

[0075] The terminal has pre-set preset models, which can be machine learning models, such as random forests, or statistical models, such as regression models.

[0076] After obtaining the independent variable parameters and the target corrosion effect feature parameters, the terminal uses the independent variable parameters and the target corrosion effect feature parameters corresponding to the same data collection point as a set of target training samples. Based on the target training samples corresponding to multiple data collection time points, the terminal trains the preset model to obtain the target corrosion effect feature model.

[0077] In this embodiment, by acquiring independent variable parameters, a first environmental effect characteristic parameter, and a second environmental effect characteristic parameter corresponding to multiple data acquisition time points, and considering that the first environmental effect characteristic parameter is the environmental effect characteristic parameter of the protective coating under the first test condition, and the second environmental effect characteristic parameter is the environmental effect characteristic parameter of the protective coating under the second test condition, and that the microbial information under the first and second test conditions is different, the difference between the first and second environmental effect characteristic parameters makes the determined target corrosion effect characteristic parameter related to microorganisms. Therefore, based on the independent variable parameters, target corrosion effect characteristic parameters, and a preset model corresponding to multiple data acquisition time points, the obtained target corrosion effect characteristic model can reflect the degree of influence of microorganisms on the anti-corrosion performance of the protective coating over time, achieving high-precision prediction of the corrosion effect characteristic parameters of the protective coating based on microorganisms and identification of key environmental characteristic parameters. Furthermore, by representing the differences caused by different microbial information through corrosion effect characteristic parameters, the differences in microbial information are expressed in a calculable way, thereby obtaining the target corrosion effect characteristic model. This achieves the goal of predicting the influence of microorganisms on the anti-corrosion performance of the protective coating through a mathematical model, solving the problem of the difficulty in predicting the corrosion process of the protective coating by microorganisms and improving the accuracy of predicting the anti-corrosion performance of the protective coating.

[0078] Figure 2 A flowchart illustrating a method for determining characteristic parameters of a target corrosion effect according to an embodiment of this application. Figure 2 It involves how to base on Figure 1 One possible implementation of obtaining the characteristic parameters of the target corrosion effect in S102 is as follows: Figure 2 As shown, the method in this embodiment includes:

[0079] S201. Determine the initial corrosion effect characteristic parameters based on the difference between the first environmental effect characteristic parameters and the second environmental effect characteristic parameters.

[0080] S202. Perform data preprocessing on the initial corrosion effect characteristic parameters to obtain the target corrosion effect characteristic parameters.

[0081] For S201 and S202, since the difference between the first and second group of test conditions lies in the different microbial information, the first environmental effect characteristic parameter and the second environmental effect characteristic parameter are different. The terminal calculates the difference between the first environmental effect characteristic parameter and the second environmental effect characteristic parameter, and uses the difference as the initial corrosion effect characteristic parameter.

[0082] The difference in electrochemical impedance = electrochemical impedance of the second group - electrochemical impedance of the first group;

[0083] The difference in adhesion = adhesion of the second group - adhesion of the first group;

[0084] The difference in light loss rate = Light loss rate of the first group - Light loss rate of the second group;

[0085] It should be noted that, since the second group inhibits microorganisms, the light loss rate of the first group is greater than that of the second group. In order to make the difference in light loss rate greater than 0, the light loss rate of the first group is subtracted from that of the second group to obtain the difference in light loss rate.

[0086] The initial training samples corresponding to the initial corrosion effect feature parameters are shown in Table 1:

[0087] Table 1 Initial training samples corresponding to the initial corrosion effect characteristic parameters

[0088]

[0089] In this study, assuming the experimental design and implementation process are confirmed and the experimental data are reliable, the microbial corrosion effect will, to some extent, increase the degradation of the environmental effect characteristic parameters of the protective coating. Since the second group inhibits microorganisms, the differences in electrochemical impedance, adhesion, and gloss loss rate obtained according to S501 should all be greater than 0. Values ​​less than or equal to 0 will be treated as outliers and processed to ensure that all target corrosion effect characteristic parameters are greater than 0. For example, the adhesion difference for month 1 in Table 1, and the adhesion difference and gloss loss rate difference for month 2, are all negative. These three data points are outliers. Data processing is performed on these three data points by deleting them and using linear interpolation to handle missing values, obtaining the corresponding processed data.

[0090] The target training samples corresponding to the target corrosion effect feature parameters are shown in Table 2:

[0091] Table 2 Target training samples corresponding to the characteristic parameters of the target corrosion effect

[0092]

[0093] In this embodiment, the initial corrosion effect characteristic parameters are determined by the difference between the first environmental effect characteristic parameters and the second environmental effect characteristic parameters. The initial corrosion effect characteristic parameters are then preprocessed to obtain the target corrosion effect characteristic parameters, thereby reducing abnormal data and improving the accuracy of the target corrosion effect characteristic model.

[0094] Figure 3 This is a flowchart illustrating a method for constructing a characteristic model of a target corrosion effect, provided in an embodiment of this application. Figure 2 It involves how to base on Figure 1 One possible implementation of the target corrosion effect characteristic model in S103 is as follows: Figure 3 As shown, the method in this embodiment includes:

[0095] S301. Based on the independent variable parameters and target corrosion effect characteristic parameters corresponding to multiple data collection time points, train the preset model using the preset least squares method to determine the model parameters that minimize the sum of squared errors.

[0096] S302. Obtain the characteristic model of the target corrosion effect based on the model parameters that minimize the sum of squared errors.

[0097] For S301 and S302, the default model is a linear regression model, specifically:

[0098] Formula 1

[0099] Where i represents the i-th target training sample.

[0100] y i Let represent the target corrosion effect feature parameters of the i-th target training sample.

[0101] , represents the independent variable vector of the i-th target training sample, where "1" is a constant term and q is the number of independent variable parameters corresponding to the target training sample. For example, in this embodiment, the independent variable parameters include: test duration and environmental characteristic parameters, and the environmental characteristic parameters include temperature, humidity and salt spray deposition rate. Therefore, the value of q is 4.

[0102] , which is the vector corresponding to the model parameters.

[0103] Let be a random error term, and satisfy independent and identically distributed (i.e., both).

[0104] When the terminal trains the linear regression model corresponding to Formula 1 using the target training samples, it can use a preset least squares method for training. For example, it can use Ordinary Least Squares (OLS) to minimize the sum of squared errors between the predicted values ​​of the corrosion effect feature parameters obtained by the preset model for multiple sets of target training samples and the target corrosion effect feature parameters in the target training samples. At this time, the corresponding model parameters are the model parameters that minimize the sum of squared errors.

[0105] The model parameters that minimize the sum of squared errors are determined as the model parameters of the preset model, thus obtaining the characteristic model of the target corrosion effect. The model type of the characteristic model of the target corrosion effect is a linear regression model.

[0106] In this embodiment, by using the preset least squares method to train the preset model, the requirement for the number of target training samples can be reduced, and a relatively accurate target corrosion effect feature model can be obtained using a small number of target training samples.

[0107] Figure 4 A flowchart illustrating a method for optimizing parameters provided in one embodiment of the application. Figure 4 It involves Figure 3 In the case where the least squares method is an iterative weighted least squares method, how can we obtain the current parameters that satisfy the parameter convergence condition through S301? One possible implementation is as follows: Figure 4 As shown, the method in this embodiment includes:

[0108] S401. Determine the initial parameters of the preset model based on the preset least squares method.

[0109] S402. Based on the independent variable parameters, target corrosion effect characteristic parameters and initial parameters corresponding to multiple data acquisition time points, perform parameter optimization of the preset model multiple times until the parameter convergence condition is met, and determine the current parameters that meet the parameter convergence condition as the model parameters that minimize the sum of squared errors.

[0110] For S401 and S402, the iterative weighted least squares method is used to train the linear regression model. The initial parameters of Formula 1 are determined by the terminal, for example, through OLS, i.e., by pre-setting the initial value of β in Formula 1, or the initial parameters of Formula 1 can be determined randomly. In this embodiment, OLS is used to determine the initial parameters of Formula 1, reducing the number of iterations for parameter optimization.

[0111] After the initial parameters are determined, the model parameters are optimized by iterative weighted least squares. In each iteration, the weights of each target training sample are adjusted by iterative weighted least squares, thereby optimizing the model parameters according to the weights and obtaining the current parameters. Then, the next iteration is performed until the parameter convergence condition is met. The current parameters are then determined as the model parameters that minimize the sum of squared errors.

[0112] The parameter convergence condition can be either the number of iterations reaching a preset number of iterations, or the model parameters converging.

[0113] In this embodiment, by using the iterative weighted least squares method to optimize the model parameters, the impact of abnormal target training samples in the target training samples on the model accuracy can be reduced, thereby improving the accuracy of the target corrosion effect feature model.

[0114] Figure 5 A flowchart of a parameter optimization method based on M-estimation provided for one embodiment of the application. Figure 4 It involves how to pass Figure 4 One possible implementation of S302 for obtaining the current parameters that satisfy the parameter convergence condition is, such as Figure 5 As shown, the method in this embodiment includes:

[0115] S501. Based on the current parameters of the preset model, calculate the current residuals of the independent variable parameters and the target corrosion effect characteristic parameters corresponding to each data acquisition time point.

[0116] S502. Based on the loss function estimated by M, convert the current residual into the current weight values ​​of the independent variable parameters and target corrosion effect characteristic parameters corresponding to each data acquisition time point.

[0117] Among them, the loss function reduces the weight values ​​of the independent variable parameters and the target corrosion effect characteristic parameters corresponding to the data acquisition time point where the current residual is greater than the preset residual;

[0118] S503. Based on the current weight values, optimize the parameters of the preset model obtained from the previous parameter optimization to obtain the current parameters of the preset model.

[0119] For S501-S503, the M-estimation method is used to solve for the model parameters in Equation 1. The core objective is to minimize the robust loss function, and the objective function is:

[0120] Formula 2

[0121] Where, r i =y i -x i T β represents the residual of the i-th target training sample.

[0122] For a robust loss function, this embodiment adopts the Huber loss function, balancing robustness and efficiency:

[0123] Formula 3

[0124] in, , This is a robust scalar estimation.

[0125] The steps to transform the M-estimation into an iterative weighted least squares solution are as follows:

[0126] Step 1: Initial parameter selection, in Figure 3 In the illustrated embodiment, the initial parameters of Formula 1 are determined using OLS: , as the initial value of β in Formula 1 .

[0127] Step 2: Calculate the current residual. k represents the current iteration number.

[0128] Step 3: Calculate the current weight value, differentiate the loss function represented by Formula 3, and obtain the influence function, i.e., the ψ function: Thus, the weights are obtained as follows: .

[0129] Step 4: Update model parameters. ,in , where represents the weight diagonal matrix.

[0130] Step 5: Parameter convergence condition judgment. This is determined when the preset number of iterations is reached, or when the model parameters converge. ( (For the preset threshold), stop the iteration, and... Determine the model parameters that minimize the sum of squared errors; if the number of iterations has not reached the preset number of iterations, or if the model parameters do not converge, repeat steps two to four until the parameter convergence condition is met.

[0131] Taking the adhesion difference of the protective coating as an example, this embodiment uses a robust linear regression method to explore the influencing factors and regression prediction methods affecting the adhesion degradation of the protective coating used in the experiment caused by microbial corrosion. Based on the target training samples in Table 2, the analysis results with adhesion difference as the dependent variable and month, temperature, humidity, and salt spray deposition rate as independent variables are shown in Table 3.

[0132] Table 3 Regression analysis results of adhesion difference

[0133]

[0134] Table 3 shows that by using month (test duration), temperature, humidity, and salt spray deposition rate as independent variables in OLS regression analysis, a characteristic model of the target corrosion effect corresponding to the adhesion difference was obtained. Using the Robust robust standard error regression method, the R-squared value of the model (i.e., the corrosion effect characteristic corresponding to the adhesion difference) is 0.998, meaning that month (test duration), temperature, humidity, and salt spray deposition rate can explain 99.8% of the variation in adhesion difference. The F-test of the model shows that it passes (F=626.138, p=0.030<0.05), indicating that at least one of month (test duration), temperature, humidity, and salt spray deposition rate has an impact on the adhesion difference. The model formula is:

[0135] Adhesion difference = 12.799 + 0.094 * month - 0.198 * temperature - 0.083 * humidity - 0.856 * salt spray

[0136] The final analysis revealed the following: the regression coefficient for month (test duration) was 0.094, with a significance level of 0.01 (t=29.550, p<0.01), indicating a significant positive impact of month (test duration) on adhesion difference. The regression coefficient for temperature was -0.198, with a significance level of 0.01 (t=-10.397, p<0.01), indicating a significant negative impact of temperature on adhesion difference. The regression coefficient for humidity was -0.083, with a significance level of 0.01 (t=-7.263, p=0.000<0.01), indicating a significant negative impact of humidity on adhesion difference. The regression coefficient of salt spray was -0.856, and it was significant at the 0.01 level (t=-16.253, p=0.000<0.01), which means that salt spray has a significant negative impact on the adhesion difference.

[0137] The summary analysis shows that the factors affecting adhesion include month (test duration), temperature, humidity, and salt spray deposition rate. Month (test duration) has a significant positive impact on the adhesion difference, while temperature, humidity, and salt spray have a significant negative impact on the adhesion difference.

[0138] The robust standard error regression method was used to evaluate the target corrosion effect feature model trained by the least squares method based on M-estimation. The model accuracy was found to be up to 99%, which meets the requirement that the accuracy of the fitting model for microbial induced corrosion effect is greater than 80%.

[0139] In addition, such as Figure 11 As shown, taking the adhesion difference as an example of the target corrosion effect characteristic model, it can be seen that the coefficients of the linear regression model can, to a certain extent, represent the influence of various factors on the adhesion difference.

[0140] In this embodiment, the M-estimation is transformed into an iterative weighted least squares solution, making the obtained linear regression model a robust linear regression model and improving the accuracy of the target corrosion effect characteristic model.

[0141] Figure 6 A flowchart illustrating a method for constructing a characteristic model of a target corrosion effect, provided in another embodiment of this application. Figure 6 This involves the correlation coefficient between each corrosion effect characteristic parameter and each independent variable parameter, and how to... Figure 1 Another possible implementation of the target corrosion effect characteristic model is obtained in S103. For example... Figure 6 As shown, the method in this embodiment includes:

[0142] S601. Based on the independent variable parameters and target corrosion effect characteristic parameters corresponding to multiple data collection points, determine the correlation coefficient between each corrosion effect characteristic parameter and each independent variable parameter.

[0143] S602. Based on the correlation coefficient between each corrosion effect characteristic parameter and each independent variable parameter, as well as the independent variable parameters, target corrosion effect characteristic parameters, and preset model corresponding to multiple data acquisition time points, obtain the target corrosion effect characteristic model.

[0144] For S601 and S602, microbial corrosion effects will increase the degradation of the environmental effect characteristic parameters of the protective coating to a certain extent. The contribution of each independent variable parameter to the degradation of these environmental effect characteristic parameters varies, and the degradation of these parameters constitutes the corrosion effect characteristic parameters. For example, humidity has a greater impact on electrochemical impedance than salt spray deposition rate; that is, the degradation of electrochemical impedance caused by humidity is greater than that caused by salt spray deposition rate. Therefore, the target corrosion effect characteristic model can be obtained by combining the contribution of each independent variable parameter to the degradation of the environmental effect characteristic parameters of the protective coating with multiple sets of target training samples.

[0145] The contribution of each independent variable parameter to the degradation of the environmental effect characteristic parameters of the protective coating can be represented by correlation coefficients. This allows us to obtain the correlation coefficients between the electrochemical impedance difference and the test environment, temperature, humidity, and salt spray deposition rate; the adhesion difference and the test environment, temperature, humidity, and salt spray deposition rate; and the gloss loss rate difference and the test environment, temperature, humidity, and salt spray deposition rate. Based on these correlation coefficients and multiple sets of target training samples, a target corrosion effect characteristic model is obtained.

[0146] The terminal has a model for calculating correlation coefficients. The correlation coefficient is obtained through this model. For example, if the characteristic parameter of the corrosion effect is the adhesion difference and the independent variable is temperature, the steps to obtain the correlation coefficient between the adhesion difference and temperature are as follows:

[0147] Step 1: Obtain the variance of multiple adhesion differences corresponding to multiple data collection time points, and the variance corresponding to multiple temperatures;

[0148] Step 2: Obtain the covariance between a sample composed of multiple adhesion differences and a sample composed of multiple temperatures;

[0149] Step 3: Input the variances corresponding to multiple adhesion differences, the variances corresponding to multiple temperatures, and the covariance into the formula. The correlation coefficient between the adhesion difference and temperature was obtained.

[0150] Where X represents a sample of independent variable parameters consisting of multiple independent variable parameters.

[0151] Y represents a sample of corrosion effect characteristic parameters consisting of multiple corrosion effect characteristic parameters.

[0152] S X S Y These represent the variance of the independent variable parameter sample and the variance of the corrosion effect characteristic parameter sample, respectively.

[0153] S XY This represents the covariance between the independent variable parameter sample and the corrosion effect characteristic parameter sample.

[0154] r XY This represents the correlation coefficient between the independent variable parameter and the characteristic parameters of the corrosion effect.

[0155] In this embodiment, the target corrosion effect feature model is obtained by using the correlation coefficient between each corrosion effect feature parameter and each independent variable parameter, as well as multiple sets of target training samples, thereby improving the accuracy of the target corrosion effect feature model.

[0156] It should be noted that the target corrosion effect feature model is obtained by using correlation coefficients combined with multiple sets of target training samples to train the preset model. The preset model can be a linear regression model or other models. Furthermore, the training method used to train the preset model can be the least squares method (including but not limited to OLS, iterative weighted least squares method) or other training methods. This application does not impose any restrictions on this.

[0157] Figure 7 A flowchart illustrating a method for constructing a target corrosion effect characteristic model by combining correlation coefficients, as provided in an embodiment of this application. Figure 7 It involves how to pass Figure 6 This is one possible implementation method for obtaining the target corrosion effect characteristic model in S602. For example... Figure 7 As shown, the method in this embodiment includes:

[0158] S701. Based on the correlation coefficient between each corrosion effect characteristic parameter and each independent variable parameter, determine the independent variable parameter used to determine each corrosion effect characteristic parameter.

[0159] S702. Based on the independent variable parameters, target corrosion effect characteristic parameters and preset models corresponding to multiple data collection points used to determine the characteristic parameters of each corrosion effect, obtain the target corrosion effect characteristic model corresponding to each corrosion effect characteristic parameter.

[0160] For S701 and S702, after obtaining the correlation coefficient between each corrosion effect characteristic parameter and each independent variable parameter, the terminal compares the absolute value of the correlation coefficient with the correlation coefficient threshold. For each corrosion effect characteristic parameter, the independent variable parameter with a correlation coefficient greater than or equal to the correlation coefficient threshold is determined as the independent variable parameter of that corrosion effect characteristic parameter.

[0161] For example, the absolute values ​​of the correlation coefficients between the adhesion difference and the test duration, temperature, humidity, and salt spray deposition rate are all greater than the correlation coefficient threshold. Therefore, the test duration, temperature, humidity, and salt spray deposition rate are all determined as independent variable parameters affecting the adhesion difference.

[0162] For example, if the absolute value of the correlation coefficient between the electrochemical impedance difference and the salt spray deposition rate is less than or equal to the correlation coefficient threshold, and the absolute value of the correlation coefficient between the electrochemical impedance difference and the test duration, temperature, and humidity is greater than the correlation coefficient threshold, then the test duration, temperature, and humidity are determined as independent variable parameters affecting the electrochemical impedance difference.

[0163] The terminal corrects the target training samples used to train the feature model of each target corrosion effect based on the independent variable parameters that affect each corrosion effect feature parameter, as determined by the correlation coefficient. Independent variable parameters with an absolute value of the correlation coefficient less than or equal to the correlation coefficient threshold are removed from the target training samples, resulting in corrected target training samples. A preset model is then trained based on the corrected target training samples to obtain the target corrosion effect feature model corresponding to each corrosion effect feature parameter.

[0164] In this embodiment, the independent variable parameters that affect the characteristic parameters of each corrosion effect are determined by the correlation coefficient, which can reduce the amount of data in each group of target training samples, thereby reducing the amount of computation and improving the model training efficiency.

[0165] Figure 8 A flowchart illustrating a method for constructing a target corrosion effect feature model by combining correlation coefficients, as provided in another embodiment of this application. Figure 8 It involves how to pass Figure 6 Another possible implementation of the target corrosion effect characteristic model is obtained in S602. For example... Figure 8 As shown, the method in this embodiment includes:

[0166] S801. Based on the independent variable parameters, target corrosion effect characteristic parameters and preset model corresponding to multiple data acquisition time points, obtain the initial corrosion effect characteristic model corresponding to each corrosion effect characteristic parameter.

[0167] S802. Based on the correlation coefficient between each corrosion effect characteristic parameter and each independent variable parameter, the initial corrosion effect characteristic model corresponding to each corrosion effect characteristic parameter is modified to obtain the target corrosion effect characteristic model corresponding to each corrosion effect characteristic parameter.

[0168] For S801 and S802, the target corrosion effect feature model corresponding to each corrosion effect feature parameter obtained based on multiple sets of target training samples and preset models will be used as the initial corrosion effect feature model. The initial corrosion effect feature model corresponding to each corrosion effect feature parameter will be corrected according to the correlation coefficient.

[0169] For example, for each characteristic parameter of corrosion effect, the following is adopted: Figure 7 The method in the embodiment obtains the correlation coefficient between the corrosion effect characteristic parameter and each independent variable parameter. Since both the correlation coefficient and the model parameter represent the degree of influence of the independent variable parameter on the corrosion effect characteristic parameter, the accuracy of the model parameters in the initial corrosion effect characteristic model can be evaluated based on the correlation coefficient. Model parameters that have a significant difference from the degree of influence corresponding to the correlation coefficient can be corrected so that the degree of influence represented by the corrected model parameters conforms to the degree of influence of the correlation coefficient.

[0170] In this embodiment, the initial corrosion effect feature model corresponding to each corrosion effect feature parameter is corrected by using the correlation coefficient, thereby improving the accuracy of the target corrosion effect feature model corresponding to each corrosion effect feature parameter.

[0171] Figure 9 A flowchart illustrating a method for modeling the corrosion effect of a protective coating, as provided in another embodiment of this application. Figure 9 As shown, the method in this embodiment includes:

[0172] S901. Obtain the independent variable parameters, first environmental effect characteristic parameters, and second environmental effect characteristic parameters corresponding to multiple data collection time points.

[0173] S902. Determine the initial corrosion effect characteristic parameters based on the difference between the first environmental effect characteristic parameters and the second environmental effect characteristic parameters.

[0174] S903. Perform data preprocessing on the initial corrosion effect characteristic parameters to obtain the target corrosion effect characteristic parameters.

[0175] S904. Based on the independent variable parameters and target corrosion effect characteristic parameters corresponding to multiple data collection points, determine the correlation coefficient between each corrosion effect characteristic parameter and each independent variable parameter.

[0176] S905. Based on the correlation coefficient between each corrosion effect characteristic parameter and each independent variable parameter, determine the independent variable parameter used to determine each corrosion effect characteristic parameter.

[0177] S906. Determine the initial parameters of the preset model based on the preset least squares method.

[0178] S907. Based on the current parameters of the preset model, calculate the current residuals of the independent variable parameters and the target corrosion effect characteristic parameters corresponding to each data acquisition time point, which are used to determine the characteristic parameters of each corrosion effect.

[0179] S908. Based on the loss function estimated by M, convert the current residual into the current weight values ​​of the independent variable parameters and target corrosion effect characteristic parameters corresponding to each data acquisition time point.

[0180] The loss function reduces the weight values ​​of the independent variable parameters and the target corrosion effect characteristic parameters corresponding to the data acquisition time points where the current residual is greater than the preset residual.

[0181] S909. Based on the current weight values, optimize the parameters of the preset model obtained from the previous parameter optimization to obtain the current parameters of the preset model.

[0182] S9010. Repeat S907 to S909 until the parameter convergence condition is met, and determine the current parameter that meets the parameter convergence condition as the model parameter that minimizes the sum of squared errors.

[0183] S9011. Obtain the target corrosion effect characteristic model based on the model parameters that minimize the sum of squared errors.

[0184] Figure 9 For a detailed implementation process of the illustrated embodiment, please refer to [reference needed]. Figures 1-8 This will not be elaborated upon here.

[0185] Figure 10 A flowchart illustrating a method for modeling the corrosion effect of a protective coating, as provided in another embodiment of this application. Figure 10 As shown, the method in this embodiment includes:

[0186] S1001. Obtain the independent variable parameters, first environmental effect characteristic parameters, and second environmental effect characteristic parameters corresponding to multiple data collection time points.

[0187] S1002. Determine the initial corrosion effect characteristic parameters based on the difference between the first environmental effect characteristic parameters and the second environmental effect characteristic parameters.

[0188] S1003. Perform data preprocessing on the initial corrosion effect characteristic parameters to obtain the target corrosion effect characteristic parameters.

[0189] S1004. Determine the initial parameters of the preset model based on the preset least squares method.

[0190] S1005. Based on the current parameters of the preset model, calculate the current residuals of the independent variable parameters and the target corrosion effect characteristic parameters corresponding to each data acquisition time point.

[0191] S1006. Based on the loss function estimated by M, convert the current residual into the current weight values ​​of the independent variable parameters and target corrosion effect characteristic parameters corresponding to each data acquisition time point.

[0192] The loss function reduces the weight values ​​of the independent variable parameters and the target corrosion effect characteristic parameters corresponding to the data acquisition time points where the current residual is greater than the preset residual.

[0193] S1007. Based on the current weight values, optimize the parameters of the preset model obtained from the previous parameter optimization to obtain the current parameters of the preset model.

[0194] S1008. Repeat S1005 to S1007 until the parameter convergence condition is met, and determine the current parameter that meets the parameter convergence condition as the model parameter that minimizes the sum of squared errors.

[0195] S1009. Obtain the initial corrosion effect characteristic model based on the model parameters that minimize the sum of squared errors.

[0196] S1010. Based on the independent variable parameters and target corrosion effect characteristic parameters corresponding to multiple data collection points, determine the correlation coefficient between each corrosion effect characteristic parameter and each independent variable parameter.

[0197] S1011. Based on the correlation coefficient between each corrosion effect characteristic parameter and each independent variable parameter, the initial corrosion effect characteristic model corresponding to each corrosion effect characteristic parameter is modified to obtain the target corrosion effect characteristic model corresponding to each corrosion effect characteristic parameter.

[0198] Figure 10 For a detailed implementation process of the illustrated embodiment, please refer to [reference needed]. Figures 1-8 This will not be elaborated upon here.

[0199] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0200] Based on the same inventive concept, this application also provides a protective coating corrosion effect modeling device for implementing the above-mentioned protective coating corrosion effect modeling method. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more protective coating corrosion effect modeling device embodiments provided below can be found in the limitations of the protective coating corrosion effect modeling method described above, and will not be repeated here.

[0201] In one exemplary embodiment, such as Figure 12 As shown, a protective coating corrosion effect modeling device is provided, comprising: a first acquisition module 1201, a second acquisition module 1202, and a modeling module 1203, wherein:

[0202] The first acquisition module 1201 is used to acquire independent variable parameters, first environmental effect characteristic parameters and second environmental effect characteristic parameters corresponding to multiple data acquisition time points. The first environmental effect characteristic parameters are the environmental effect characteristic parameters of the protective coating under the first test conditions, and the second environmental effect characteristic parameters are the environmental effect characteristic parameters of the protective coating under the second test conditions. The microbial information of the first test conditions and the second test conditions are different. The independent variable parameters include test duration and environmental characteristic parameters.

[0203] The second acquisition module 1202 is used to determine the target corrosion effect characteristic parameters based on the first environmental effect characteristic parameters and the second environmental effect characteristic parameters.

[0204] Modeling module 1203 is used to obtain a target corrosion effect feature model based on the independent variable parameters, target corrosion effect feature parameters, and preset model corresponding to multiple data acquisition time points.

[0205] In one embodiment, the modeling module 1203 is specifically used for:

[0206] Based on the independent variable parameters and target corrosion effect characteristic parameters corresponding to multiple data collection time points, the preset model is trained using the preset least squares method to determine the model parameters that minimize the sum of squared errors.

[0207] Based on the model parameters that minimize the sum of squared errors, the characteristic model of the target corrosion effect is obtained.

[0208] In one embodiment, the preset least squares method is an iterative weighted least squares method; the modeling module 1203 is specifically used for:

[0209] The initial parameters of the preset model are determined based on the preset least squares method;

[0210] Based on the independent variable parameters, target corrosion effect characteristic parameters, and initial parameters corresponding to multiple data collection time points, the parameters of the preset model are optimized multiple times until the parameter convergence condition is met. The current parameters that meet the parameter convergence condition are determined as the model parameters that minimize the sum of squared errors.

[0211] In one embodiment, the modeling module 1203 is specifically used for:

[0212] Based on the current parameters of the preset model, calculate the current residuals of the independent variable parameters and the target corrosion effect characteristic parameters corresponding to each data acquisition time point;

[0213] The current residual is converted into the current weight value of the independent variable parameter and the target corrosion effect characteristic parameter corresponding to each data acquisition time point according to the loss function of M-estimation. The loss function reduces the weight value of the independent variable parameter and the target corrosion effect characteristic parameter corresponding to the data acquisition time point where the current residual is greater than the preset residual.

[0214] Based on the current weight values, the parameters of the preset model obtained from the previous parameter optimization are optimized to obtain the current parameters of the preset model.

[0215] In one embodiment, the second acquisition module 1202 is specifically used for:

[0216] The initial corrosion effect characteristic parameters are determined based on the difference between the first environmental effect characteristic parameters and the second environmental effect characteristic parameters.

[0217] Data preprocessing is performed on the initial corrosion effect characteristic parameters to obtain the target corrosion effect characteristic parameters.

[0218] In one embodiment, the modeling module 1203 is specifically used for:

[0219] Based on the independent variable parameters and target corrosion effect characteristic parameters corresponding to multiple data collection points, determine the correlation coefficient between each corrosion effect characteristic parameter and each independent variable parameter;

[0220] Based on the correlation coefficient between each corrosion effect characteristic parameter and each independent variable parameter, as well as the independent variable parameters, target corrosion effect characteristic parameters, and preset model corresponding to multiple data acquisition time points, the target corrosion effect characteristic model is obtained.

[0221] In one embodiment, the modeling module 1203 is specifically used for:

[0222] Based on the correlation coefficient between each corrosion effect characteristic parameter and each independent variable parameter, the independent variable parameters used to determine each corrosion effect characteristic parameter are determined.

[0223] Based on the independent variable parameters, target corrosion effect characteristic parameters, and preset models corresponding to multiple data collection points for determining each corrosion effect characteristic parameter, the target corrosion effect characteristic model corresponding to each corrosion effect characteristic parameter is obtained.

[0224] In one embodiment, the modeling module 1203 is specifically used for:

[0225] Based on the independent variable parameters, target corrosion effect characteristic parameters and preset models corresponding to multiple data collection time points, the initial corrosion effect characteristic model corresponding to each corrosion effect characteristic parameter is obtained;

[0226] Based on the correlation coefficient between each corrosion effect characteristic parameter and each independent variable parameter, the initial corrosion effect characteristic model corresponding to each corrosion effect characteristic parameter is modified to obtain the target corrosion effect characteristic model corresponding to each corrosion effect characteristic parameter.

[0227] Each module in the aforementioned protective coating corrosion effect modeling device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, so that the processor can call and execute the corresponding operations of each module.

[0228] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 13As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a method for modeling the corrosion effect of a protective coating. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0229] Those skilled in the art will understand that Figure 13 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0230] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the following method for modeling the corrosion effect of protective coatings.

[0231] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements a method for modeling the corrosion effect of a protective coating.

[0232] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0233] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0234] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0235] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for modeling the corrosion effect of protective coatings, characterized in that, The method includes: The independent variable parameters, first environmental effect characteristic parameters, and second environmental effect characteristic parameters corresponding to multiple data collection time points are obtained. The first environmental effect characteristic parameter is the environmental effect characteristic parameter of the protective coating under the first test condition, and the second environmental effect characteristic parameter is the environmental effect characteristic parameter of the protective coating under the second test condition. The microbial information of the first test condition and the second test condition are different. The independent variable parameters include test duration and environmental characteristic parameters. The target corrosion effect characteristic parameters are determined based on the first environmental effect characteristic parameters and the second environmental effect characteristic parameters. Based on the independent variable parameters corresponding to multiple data collection time points, the target corrosion effect characteristic parameters, and the preset model, the target corrosion effect characteristic model is obtained.

2. The method according to claim 1, characterized in that, The step of obtaining the target corrosion effect feature model based on the independent variable parameters corresponding to multiple data acquisition time points, the target corrosion effect feature parameters, and the preset model includes: Based on the independent variable parameters and the target corrosion effect characteristic parameters corresponding to multiple data collection time points, the preset model is trained using the preset least squares method to determine the model parameters that minimize the sum of squared errors. The target corrosion effect characteristic model is obtained based on the model parameters that minimize the sum of squared errors.

3. The method according to claim 2, characterized in that, The preset least squares method is the iterative weighted least squares method; The step of training the preset model based on the independent variable parameters corresponding to multiple data acquisition time points and the target corrosion effect characteristic parameters, using a preset least squares method, to determine the model parameters that minimize the sum of squared errors includes: The initial parameters of the preset model are determined based on the preset least squares method; Based on the independent variable parameters, the target corrosion effect characteristic parameters, and the initial parameters corresponding to multiple data acquisition time points, the parameters of the preset model are optimized multiple times until the parameter convergence condition is met, and the current parameters that meet the parameter convergence condition are determined as the model parameters that minimize the sum of squared errors.

4. The method according to claim 3, characterized in that, The step of optimizing the parameters of the preset model multiple times based on the independent variable parameters, the target corrosion effect characteristic parameters, and the initial parameters corresponding to multiple data acquisition time points includes: Based on the current parameters of the preset model, calculate the current residuals of the independent variable parameters and the target corrosion effect characteristic parameters corresponding to each data acquisition time point; The current residual is converted into the current weight value of the independent variable parameter and the target corrosion effect characteristic parameter corresponding to each data acquisition time point according to the loss function of M-estimation. The loss function reduces the weight value of the independent variable parameter and the target corrosion effect characteristic parameter corresponding to the data acquisition time point where the current residual is greater than the preset residual. Based on the current weight values, the parameters of the preset model obtained from the previous parameter optimization are optimized to obtain the current parameters of the preset model.

5. The method according to claim 1, characterized in that, The step of determining the target corrosion effect characteristic parameters based on the first environmental effect characteristic parameter and the second environmental effect characteristic parameter includes: The initial corrosion effect characteristic parameters are determined based on the difference between the first environmental effect characteristic parameter and the second environmental effect characteristic parameter. The initial corrosion effect characteristic parameters are preprocessed to obtain the target corrosion effect characteristic parameters.

6. The method according to any one of claims 1-5, characterized in that, The step of obtaining the target corrosion effect feature model based on the independent variable parameters corresponding to multiple data acquisition time points, the target corrosion effect feature parameters, and the preset model includes: Based on the independent variable parameters corresponding to multiple data collection points and the target corrosion effect characteristic parameters, determine the correlation coefficient between each corrosion effect characteristic parameter and each independent variable parameter; The target corrosion effect feature model is obtained based on the correlation coefficient between each corrosion effect feature parameter and each independent variable parameter, as well as the independent variable parameters, the target corrosion effect feature parameters, and the preset model corresponding to multiple data acquisition time points.

7. The method according to claim 6, characterized in that, The step of obtaining the target corrosion effect feature model based on the correlation coefficient between each corrosion effect feature parameter and each independent variable parameter, as well as the independent variable parameters corresponding to multiple data acquisition time points, the target corrosion effect feature parameters, and the preset model, includes: The independent variable parameter used to determine the characteristic parameter of each corrosion effect is determined based on the correlation coefficient between each corrosion effect characteristic parameter and each independent variable parameter; Based on the independent variable parameters, target corrosion effect characteristic parameters, and preset model corresponding to multiple data collection points used to determine the characteristic parameters of each corrosion effect, a target corrosion effect characteristic model corresponding to each corrosion effect characteristic parameter is obtained.

8. The method according to claim 6, characterized in that, The step of obtaining the target corrosion effect feature model based on the correlation coefficient between each corrosion effect feature parameter and each independent variable parameter, as well as the independent variable parameters corresponding to multiple data acquisition time points, the target corrosion effect feature parameters, and the preset model, includes: Based on the independent variable parameters, the target corrosion effect characteristic parameters, and the preset model corresponding to the multiple data acquisition time points, an initial corrosion effect characteristic model corresponding to each corrosion effect characteristic parameter is obtained; Based on the correlation coefficient between each corrosion effect characteristic parameter and each independent variable parameter, the initial corrosion effect characteristic model corresponding to each corrosion effect characteristic parameter is modified to obtain the target corrosion effect characteristic model corresponding to each corrosion effect characteristic parameter.

9. A device for modeling the corrosion effect of protective coatings, characterized in that, The device includes: The first acquisition module is used to acquire independent variable parameters, first environmental effect characteristic parameters and second environmental effect characteristic parameters corresponding to multiple data collection time points. The first environmental effect characteristic parameters are the environmental effect characteristic parameters of the protective coating under the first test condition, and the second environmental effect characteristic parameters are the environmental effect characteristic parameters of the protective coating under the second test condition. The microbial information of the first test condition and the second test condition are different. The independent variable parameters include test duration and environmental characteristic parameters. The second acquisition module is used to determine the target corrosion effect characteristic parameters based on the first environmental effect characteristic parameters and the second environmental effect characteristic parameters. The modeling module is used to obtain a target corrosion effect feature model based on the independent variable parameters corresponding to multiple data acquisition time points, the target corrosion effect feature parameters, and a preset model.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1-8.

Images