Method, device, equipment, storage medium and program product for analyzing corrosion effect of protective coating

Abstract

The application relates to a method and device for analyzing the corrosion effect of a protective coating, equipment, a storage medium and a program product. The method comprises the following steps: acquiring a microorganism test data sequence of the protective coating; the microorganism test data sequence comprises environmental effect data obtained by testing a plurality of microorganism parameters of control groups; the control groups comprise a normal group, an enhancement group and an inhibition group; the environmental effect data is any one of electrochemical impedance, adhesion or light loss rate; first-order differential processing is performed on the microorganism test data sequence according to the environmental prediction model corresponding to each control group, to obtain environmental effect prediction values of the control groups; fitting is performed on the microorganism test data sequence and the environmental effect prediction values, and a corrosion effect value of the microorganism is determined according to a fitting result. By acquiring the environmental effect data of different control groups and using the environmental prediction model to predict the environmental effect data of different control groups, quantitative analysis of the corrosion effect of the microorganism is realized.

Description

Technical Field

[0001] This application relates to the field of protective coating technology, and in particular to a method, apparatus and equipment for analyzing the corrosion effect of protective coatings. Background Technology

[0002] The corrosion failure of equipment materials and their protective coating systems caused by microorganisms has been extensively studied. Common corrosive microorganisms include bacteria, fungi, archaea, and microalgae. Statistics show that direct economic losses due to corrosion worldwide reach as high as US$2.5 trillion annually, of which approximately 20% can be attributed to microbial corrosion. Microbial corrosion is not a single type of corrosion, but rather an electrochemical process caused or accelerated by microorganisms attached to material surfaces and their metabolic activities. As the first line of defense for equipment protection, coating systems face the severe challenge of microbial corrosion in marine and island environments.

[0003] Currently, methods for analyzing the corrosion effects of protective coatings include two approaches: prediction of epoxy coating degradation under the combined influence of multiple environmental factors and prediction and maintenance of corrosion damage by integrating multi-source environmental factors and coating protective effects. The first approach involves designing epoxy coating performance degradation tests and collecting environmental factor data and degradation information data. A random forest model optimized using particle swarm optimization is used to process the acquired data to establish an environmental effect model, which is then trained. A natural environment data model is established based on the natural environment data of the epoxy coating during field service, ultimately predicting the degradation of coating performance under field service conditions. The second approach involves establishing a coating protective effect model, constructing an environmental corrosion evolution model coupled with multi-source time-varying environmental effects, and planning condition-based maintenance control based on corrosion damage prediction.

[0004] However, the two methods mentioned above can only assess the coating degradation results under comprehensive environmental conditions and cannot quantitatively analyze the corrosion effects of microorganisms. Summary of the Invention

[0005] Therefore, it is necessary to provide a method, apparatus, equipment, storage medium, and program product for analyzing the corrosion effect of protective coatings that can achieve quantitative analysis of the corrosion effect of microorganisms, in order to address the above-mentioned technical problems.

[0006] In a first aspect, this application provides a method for analyzing the corrosion effect of a protective coating, including:

[0007] Obtain the microbial test data sequence of the protective coating; the microbial test data sequence includes environmental effect data obtained from tests on microbial parameters of multiple control groups; the control groups include normal group, enhanced group and inhibited group; the environmental effect data is any one of electrochemical impedance, adhesion or gloss loss rate;

[0008] The first-order differential of the microbial experimental data sequence was performed based on the environmental prediction model corresponding to each control group to obtain the predicted environmental effect value of each control group.

[0009] The microbial experimental data sequence and the predicted environmental effects were fitted together, and the corrosion effect value of the microorganisms was determined based on the fitting results.

[0010] In one embodiment, the environmental prediction model includes a cumulative module and a grey differential equation. Based on the environmental prediction model corresponding to each control group, the microbial experimental data sequence is processed using first-order differentials to obtain the predicted environmental effects for each control group, including:

[0011] For each control group's environmental effect data, the environmental effect data is input into the accumulation module, and the environmental effect data is accumulated to obtain a cumulative generation sequence;

[0012] Substitute the accumulated sequence into the gray differential equation to determine the identification parameters;

[0013] The grey differential equation is solved based on the identification parameters to obtain the predicted environmental effects of the control group.

[0014] In one embodiment, fitting the microbial test data sequence and the predicted environmental effects includes:

[0015] The environmental effect data in the microbial experimental data sequence were divided according to a preset threshold to obtain the environmental effect data of each control group;

[0016] For each control group's predicted environmental effect value, the predicted environmental effect value of the control group is fitted with the environmental effect data of the control group to obtain the fitting result of the control group.

[0017] In one embodiment, determining the corrosion effect value of microorganisms based on the fitting results includes:

[0018] Obtain the regression coefficients from the fitting results of each control group;

[0019] The corrosion effect value of microorganisms was determined based on the regression coefficients in the fitting results of each control group.

[0020] In one embodiment, the method further includes:

[0021] For each control group's basic prediction model, historical environmental effect data of the control group are obtained, and the historical environmental effect data of the control group is substituted into the basic prediction model for training to obtain an intermediate prediction model.

[0022] The intermediate prediction model is tested using a preset testing method to obtain the model accuracy of the intermediate prediction model;

[0023] If the model accuracy is greater than the preset accuracy threshold, the intermediate prediction model is determined to be the environmental prediction model corresponding to the control group.

[0024] If the model accuracy is not greater than the preset accuracy threshold, retrain the intermediate prediction model until the model accuracy of the intermediate prediction model is greater than the preset accuracy threshold.

[0025] In one embodiment, the environmental effect data includes test data over multiple time periods, and the method further includes:

[0026] For the experimental data of each time period in the microbial experimental data sequence, the experimental data is compared with the experimental data of the previous time period to obtain the level ratio of the experimental data of the time period;

[0027] If the grade ratio of the test data for a given time period falls within the acceptable coverage range, the test data for that time period will be retained.

[0028] If the grade ratio of the test data for a given time period does not fall within the acceptable coverage range, the test data for that time period is shifted and transformed.

[0029] Secondly, this application also provides a device for analyzing the corrosion effect of a protective coating, comprising:

[0030] The acquisition module is used to acquire the microbial test data sequence of the protective coating; the microbial test data sequence includes environmental effect data obtained from tests on microbial parameters of multiple control groups; the control groups include normal group, enhanced group and inhibited group; the environmental effect data is any one of electrochemical impedance, adhesion or gloss loss rate;

[0031] The prediction module is used to perform first-order differential processing on the microbial experimental data sequence based on the environmental prediction model corresponding to each control group to obtain the predicted environmental effect value of each control group.

[0032] The fitting module is used to fit the microbial experimental data sequence and the predicted values ​​of environmental effects, and to determine the corrosion effect value of the microorganisms based on the fitting results.

[0033] 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 perform the following steps:

[0034] Obtain the microbial test data sequence of the protective coating; the microbial test data sequence includes environmental effect data obtained from tests on microbial parameters of multiple control groups; the control groups include normal group, enhanced group and inhibited group; the environmental effect data is any one of electrochemical impedance, adhesion or gloss loss rate;

[0035] The first-order differential of the microbial experimental data sequence was performed based on the environmental prediction model corresponding to each control group to obtain the predicted environmental effect value of each control group.

[0036] The microbial experimental data sequence and the predicted environmental effects were fitted together, and the corrosion effect value of the microorganisms was determined based on the fitting results.

[0037] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0038] Obtain the microbial test data sequence of the protective coating; the microbial test data sequence includes environmental effect data obtained from tests on microbial parameters of multiple control groups; the control groups include normal group, enhanced group and inhibited group; the environmental effect data is any one of electrochemical impedance, adhesion or gloss loss rate;

[0039] The first-order differential of the microbial experimental data sequence was performed based on the environmental prediction model corresponding to each control group to obtain the predicted environmental effect value of each control group.

[0040] The microbial experimental data sequence and the predicted environmental effects were fitted together, and the corrosion effect value of the microorganisms was determined based on the fitting results.

[0041] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0042] Obtain the microbial test data sequence of the protective coating; the microbial test data sequence includes environmental effect data obtained from tests on microbial parameters of multiple control groups; the control groups include normal group, enhanced group and inhibited group; the environmental effect data is any one of electrochemical impedance, adhesion or gloss loss rate;

[0043] The first-order differential of the microbial experimental data sequence was performed based on the environmental prediction model corresponding to each control group to obtain the predicted environmental effect value of each control group.

[0044] The microbial experimental data sequence and the predicted environmental effects were fitted together, and the corrosion effect value of the microorganisms was determined based on the fitting results.

[0045] The aforementioned method, apparatus, equipment, storage medium, and program products for analyzing the corrosion effects of protective coatings acquire microbial test data sequences of the protective coatings. These microbial test data sequences include environmental effect data obtained from tests using microbial parameters from multiple control groups. The control groups include a normal group, an enhanced group, and an inhibited group. Environmental effect data can be any one of electrochemical impedance, adhesion, or gloss loss rate. The microbial test data sequences are processed using a first-order differential based on the environmental prediction model corresponding to each control group to obtain predicted environmental effect values ​​for each control group. The microbial test data sequences and predicted environmental effect values ​​are fitted together, and the corrosion effect value of the microorganisms is determined based on the fitting results. By acquiring environmental effect data from different control groups, the richness of the corrosion effect analysis data is improved. Furthermore, using an environmental prediction model to specifically predict the environmental effect data of different control groups facilitates accurate analysis of the corrosion effect. Finally, the actual data is fitted to the predicted data, and the corrosion effect value of the microorganisms is directly quantified through the fitting results, achieving quantitative analysis of the microbial corrosion effect and avoiding the problem in existing technologies that can only assess coating degradation results under comprehensive environmental conditions. Attached Figure Description

[0046] 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.

[0047] Figure 1 This is an internal structural diagram of a computer device in one embodiment.

[0048] Figure 2 This is a flowchart illustrating a method for analyzing the corrosion effect of a protective coating in one embodiment;

[0049] Figure 3 This is a schematic diagram of the process of performing first-order differential processing on microbial experimental data sequences based on an environmental prediction model in one embodiment.

[0050] Figure 4 This is a schematic diagram of the process for fitting microbial experimental data sequences and predicted environmental effects in one embodiment;

[0051] Figure 5 This is a schematic diagram of the process for determining the corrosion effect value of microorganisms based on the fitting results in one embodiment;

[0052] Figure 6 This is a flowchart illustrating the process of validating an environmental prediction model in one embodiment.

[0053] Figure 7 This is a schematic diagram of the preprocessing process for microbial test data sequences in one embodiment;

[0054] Figure 8 This is a flowchart illustrating the corrosion effect analysis method for the protective coating in another embodiment;

[0055] Figure 9 This is a schematic diagram illustrating the application of the fitting results of the normal group's light loss rate index in one embodiment.

[0056] Figure 10 This is a schematic diagram illustrating the application of the fitting results of the enhanced group's light loss rate index in one embodiment.

[0057] Figure 11 This is a schematic diagram illustrating the application of the fitting results of the light loss rate index of the inhibition group in one embodiment;

[0058] Figure 12 This is a structural block diagram of a device for analyzing the corrosion effect of a protective coating in one embodiment. Detailed Implementation

[0059] 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.

[0060] 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.

[0061] The corrosion failure of equipment materials and their protective coating systems caused by microorganisms has been extensively studied. Common corrosive microorganisms include bacteria, fungi, archaea, and microalgae. Statistics show that direct economic losses due to corrosion worldwide reach as high as US$2.5 trillion annually, of which approximately 20% can be attributed to microbial corrosion. Microbial corrosion is not a single type of corrosion, but rather an electrochemical process caused or accelerated by microorganisms attached to material surfaces and their metabolic activities. As the first line of defense for equipment protection, coating systems face the severe challenge of microbial corrosion in marine and island environments. Current methods for analyzing the corrosion effects of protective coatings include two approaches: epoxy coating degradation prediction under the combined influence of multiple environmental factors and the prediction and maintenance of corrosion damage by integrating multi-source environmental factors and coating protective effects. The first approach involves designing epoxy coating performance degradation tests and collecting environmental factor data and degradation information data for the epoxy coating; using a random forest model optimized based on particle swarm optimization to process the aforementioned data to establish an environmental effect model, which is then trained; and establishing a natural environment data model based on the natural environment data of the epoxy coating in field service, ultimately predicting the degradation of coating performance under field service conditions. The second approach involves establishing a coating protection effect model and constructing an environmental corrosion evolution model coupled with multi-source time-varying environmental effects, based on condition-based maintenance control planning according to corrosion damage prediction. However, both of these approaches can only assess coating degradation results under comprehensive environmental conditions and cannot quantitatively analyze the corrosion effects of microorganisms.

[0062] In view of the above-mentioned technical problems, this application provides a method for analyzing the corrosion effect of a protective coating that can achieve quantitative analysis of the corrosion effect of microorganisms. The following embodiments will specifically illustrate the method for analyzing the corrosion effect of the protective coating.

[0063] The corrosion effect analysis method for protective coatings provided in this application embodiment can be applied to, for example... Figure 1 The computer device shown may be a server, and its internal structure diagram may be as follows. Figure 1As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O 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, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores microbial parameters from multiple control groups and environmental effect data obtained from experiments. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When executed by the processor, the computer program implements a method for analyzing the corrosion effects of a protective coating.

[0064] Those skilled in the art will understand that Figure 1 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.

[0065] In one exemplary embodiment, such as Figure 2 As shown, a method for analyzing the corrosion effect of a protective coating is provided. This embodiment illustrates the application of this method to a computer device. In this embodiment, the method includes:

[0066] S201, Obtain the microbial test data sequence of the protective coating.

[0067] The microbial test data sequence includes environmental effect data obtained from tests using microbial parameters from multiple control groups. Microbial parameters may include temperature, humidity, salt spray deposition rate, bacterial strain, culture medium, and alcohol. Control groups include a normal group, an enhancement group, and an inhibition group. The normal group consists of coating samples directly tested under natural environmental conditions. The enhancement group involves periodically applying specified bacterial strains and culture medium to the tested samples to increase the concentration of the specified bacterial strains and promote microbial growth. The inhibition group involves spraying alcohol onto the tested samples to inhibit microbial growth. Environmental effect data can be any one of electrochemical impedance spectroscopy, adhesion, or gloss loss rate.

[0068] In the embodiments of this application, the experimental data on the microbial corrosion effect were obtained in advance through exposure tests under a shed at an island and reef test base and stored in a database of a computer device. The test items included electrochemical impedance spectroscopy, adhesion, and gloss loss rate. For each type of coating sample, three samples were selected for each test to measure electrochemical impedance spectroscopy, adhesion, and gloss loss rate. During the 24-month test period, each control group of each coating sample underwent 10 tests. The computer device can arbitrarily select one type of environmental effect data from the experimental data stored in the database to analyze the microbial corrosion effect according to the test requirements. In some embodiments, gloss loss rate, an environmental effect data point, was selected for analysis, and data sequences of gloss loss rates for the normal group, the enhanced group, and the inhibited group were extracted.

[0069] In some embodiments, after acquiring the microbial test data sequence of the protective coating, the computer device can use a missing value identification method to identify the missing values ​​in the microbial test data sequence, thereby obtaining the missing value identification result. The missing value identification method can be any one of the following: isna() / isnull() method, info() method, describe() method, dataset slicing, is.na function, complete.cases function, and regular expressions. If the missing value identification result indicates the presence of missing values, the target imputation method is determined based on the size of the microbial test data sequence; that is, if the sample size of the dataset is large and the proportion of samples containing missing values ​​is small, the method of deleting samples containing missing values ​​is selected. For datasets with small sample sizes or a large proportion of samples containing missing values, the target imputation method is used to process the missing values. The target imputation method can be any one of mean imputation, model-based imputation, maximum likelihood estimation, or multiple imputation. The microbial test data sequence is corrected according to the target imputation method to obtain the corrected microbial test data sequence.

[0070] S202, based on the environmental prediction model corresponding to each control group, the microbial experimental data sequence is processed by first-order differential to obtain the predicted environmental effect value of each control group.

[0071] Among them, the environmental prediction model can be a first-order grey model. In practical applications, the most commonly used model for one-dimensional grey problem modeling is the first-order GM(l,l) differential fitting model with one variable. This model is built by accumulating a data sequence of a certain variable over time, and is a single-sequence first-order linear dynamic model.

[0072] In the embodiments of this application, the computer device's database pre-stores environmental prediction models corresponding to different control groups. After acquiring the microbial experimental data sequence, the computer device can divide the microbial experimental data sequence according to the data distribution to obtain environmental effect data for multiple control groups; the environmental prediction model corresponding to each control group is then used to perform first-order differential processing on the environmental effect data of that control group to obtain the predicted environmental effect value for each control group. The execution process of the environmental prediction model for each control group can be implemented sequentially or in parallel, depending on the requirements of the actual scenario.

[0073] S203 involves fitting the microbial experimental data sequence and the predicted environmental effects, and determining the corrosion effect value of the microorganisms based on the fitting results.

[0074] In the embodiments of this application, the computer device can use the least squares method to fit the microbial test data sequence and the predicted environmental effect value to obtain a fitting curve, analyze the fitting curve to obtain the regression coefficient of the fitting curve, and determine the corrosion effect value of the microorganism based on the regression coefficient of the fitting curve.

[0075] The aforementioned method for analyzing the corrosion effect of protective coatings involves obtaining a sequence of microbial test data for the protective coating. This sequence includes environmental effect data obtained from tests conducted on microbial parameters from multiple control groups. The control groups include a normal group, an enhanced group, and an inhibited group. Environmental effect data can be any one of electrochemical impedance, adhesion, or gloss loss rate. The microbial test data sequence is processed using a first-order differential based on the environmental prediction model corresponding to each control group to obtain the predicted environmental effect value for each control group. The microbial test data sequence and the predicted environmental effect value are then fitted together, and the corrosion effect value of the microorganisms is determined based on the fitting result. By obtaining environmental effect data from different control groups, the richness of the corrosion effect analysis data is improved. Furthermore, using an environmental prediction model to specifically predict the environmental effect data of different control groups facilitates accurate analysis of the corrosion effect. Finally, the actual data is fitted to the predicted data, and the corrosion effect value of the microorganisms is directly quantified through the fitting result, achieving quantitative analysis of the microbial corrosion effect and avoiding the problem in existing technologies that can only assess coating degradation results under comprehensive environmental conditions.

[0076] In one exemplary embodiment, such as Figure 3 As shown, the environmental prediction model includes a cumulative module and a grey differential equation. Based on the environmental prediction model corresponding to each control group, the microbial experimental data sequence is processed using first-order differentials to obtain the predicted environmental effects for each control group, including:

[0077] S301: For the environmental effect data of each control group, input the environmental effect data into the accumulation module, perform accumulation processing on the environmental effect data, and obtain a cumulative generation sequence.

[0078] In the embodiments of this application, for the environmental effect data of each control group, the computer device can segment the environmental effect data of the control group according to the test time to obtain environmental effect data for different time periods. The environmental effect data of different time periods are sequentially input into the accumulation module for accumulation processing to obtain a single accumulation generation sequence corresponding to different time periods.

[0079] In some embodiments, the environmental effect data for each time period can be represented by the following relationship (1):

[0080] (1);

[0081] In the formula, This represents the environmental effect data at the corresponding time point in the time period.

[0082] The sequence generated by a single accumulation can be represented by the following relation (2):

[0083] (2);

[0084] In the formula, .

[0085] For original data that lacks a pattern, cumulative summation generates new data with a more regular pattern, reducing or eliminating the influence of random factors and strengthening the role of deterministic factors in the system. For any non-negative original sequence, a new sequence that is monotonically increasing with a more regular pattern can be obtained after one cumulative summation.

[0086] S302, Substitute the accumulated generation sequence into the gray differential equation to determine the identification parameters.

[0087] In the embodiments of this application, a single-step accumulation generation sequence can determine a set of identification coefficients. The grey differential equation can be expressed by the following relation (3):

[0088] , (3);

[0089] In the formula, a and u are identification parameters. Among them, -a is called the development coefficient, which reflects... and The development trend. u is called the gray action quantity, and its magnitude reflects the changing relationship of environmental effect data.

[0090] S303, based on the identification parameters, solve the grey differential equation to obtain the predicted environmental effect value of the control group.

[0091] In the embodiments of this application, for each control group, the computer device can use the least squares method to solve the identification coefficient, obtain the specific value of the identification coefficient, substitute the specific data of the identification coefficient into the gray differential equation to solve, obtain the cumulative predicted value, and finally restore the cumulative predicted value to obtain the environmental effect predicted value corresponding to the control group.

[0092] In some embodiments, the least squares method for solving the identification coefficients can be expressed by the following relation (4):

[0093] (4);

[0094] In the formula, B is the accumulation matrix. Let them be vectors. Their construction forms can be represented by the following relations (5) and (6), respectively:

[0095] (5);

[0096] (6);

[0097] The cumulative predicted value can be expressed by the following relationship (7):

[0098] (7);

[0099] The predicted environmental effects can be expressed by the following relationships (8) and (9):

[0100] (8);

[0101] (9);

[0102] Targeted prediction of environmental effects data for different control groups using environmental prediction models is beneficial for accurate analysis of corrosion effects.

[0103] In one exemplary embodiment, such as Figure 4 As shown, the fitting of microbial experimental data sequences and predicted environmental effects includes:

[0104] S401, the environmental effect data in the microbial test data sequence is divided according to a preset threshold to obtain the environmental effect data of each control group.

[0105] Each control group has a pre-configured threshold range. The values ​​of the pre-configured threshold ranges for the enhancement group, normal group, and inhibition group decrease sequentially.

[0106] In the embodiments of this application, after acquiring the microbial test data sequence, the computer device matches each environmental effect data with the preset threshold range corresponding to each control group, determines which control group the environmental effect data falls within the preset threshold range, and after a successful match, determines the environmental effect data as the environmental effect data of the corresponding control group.

[0107] S402, for each control group's predicted environmental effect value, fit the predicted environmental effect value of the control group with the control group's environmental effect data to obtain the fitting result of the control group.

[0108] In the embodiments of this application, for each control group's predicted environmental effect value, the computer device extracts environmental effect data at the same time from the control group's environmental effect data, and fits the environmental effect data at the same time with the predicted environmental effect value. During the fitting process, the sum of squared errors between the environmental effect data and the predicted environmental effect value is calculated, and the best fitting curve is obtained when the sum of squared errors is minimized, which is the fitting result for the corresponding control group.

[0109] The above method fits the actual data with the predicted data, and directly quantifies the corrosion effect of microorganisms through the fitting results, thus realizing the quantitative analysis of the corrosion effect of microorganisms and avoiding the problem in the existing technology that can only evaluate the coating degradation results under comprehensive environmental conditions.

[0110] In one exemplary embodiment, such as Figure 5 As shown, the corrosion effect value of microorganisms was determined based on the fitting results, including:

[0111] S501, obtain the regression coefficients from the fitting results of each control group.

[0112] In the embodiments of this application, the computer device can extract regression coefficients from the fitting results of each control group, that is, extract slope parameters from the fitting curves of each control group.

[0113] S502, the corrosion effect value of microorganisms is determined based on the regression coefficients in the fitting results of each control group.

[0114] In the embodiments of this application, after obtaining the regression coefficients in the fitting results of each control group, the computer device performs mean processing on the regression coefficients and determines the mean value of the regression coefficients as the corrosion effect value of microorganisms.

[0115] In some embodiments, the maximum value of the regression coefficient in the fitting results of each control group can be determined and used as the corrosion effect value of the microorganism.

[0116] The above method fits the actual data with the predicted data, and directly quantifies the corrosion effect of microorganisms through the fitting results, thus realizing the quantitative analysis of the corrosion effect of microorganisms.

[0117] In one exemplary embodiment, such as Figure 6 As shown, the method also includes:

[0118] S601: For each control group's basic prediction model, obtain the historical environmental effect data of the control group, substitute the historical environmental effect data of the control group into the basic prediction model for training, and obtain the intermediate prediction model.

[0119] The basic prediction model and the environmental prediction model share the same calculation principle.

[0120] In the embodiments of this application, for each control group's basic prediction model, the computer device inputs the historical environmental effect data of the control group into the basic prediction model for training, and obtains the intermediate prediction model and the residual value of the current round.

[0121] S602, the intermediate prediction model is tested using a preset testing method to obtain the model accuracy of the intermediate prediction model.

[0122] The testing method can be any one of the following: correlation test, residual test, and posterior error test. Model accuracy can be any one of the following accuracy indicators: posterior error ratio, small error probability, root mean square error, or goodness of fit.

[0123] In the embodiments of this application, the computer device selects a target verification method from preset verification methods and uses the target verification method to verify the intermediate prediction model to obtain the model accuracy of the intermediate prediction model. In some embodiments, the computer device can select a posterior error verification method as the target verification method, and substitute the residual value of the current round and the original data sequence into the target verification method for processing to obtain the model accuracy of the intermediate prediction model.

[0124] In some embodiments, the original sequence mean of the posterior difference test can be represented by the following relationship (10):

[0125] (10);

[0126] The root mean square error of the original sequence in the posterior difference test can be expressed by the following relationships (11) and (12):

[0127] (11);

[0128] (12);

[0129] The mean of the residual sequence in the posterior difference test can be expressed by the following relationship (13):

[0130] (13);

[0131] The root mean square error of the residual sequence in the posterior difference test can be expressed by the following relationships (14) and (15):

[0132] (14);

[0133] (15);

[0134] Let the variance ratio (i.e., the posterior error coefficient) be c, and The probability of a small error is denoted as: .

[0135] In some embodiments, the root mean square error and the goodness of fit can be represented by the following relationships (16) and (17), respectively:

[0136] (16);

[0137] (17);

[0138] S603, if the model accuracy is greater than the preset accuracy threshold, determine the intermediate prediction model as the environmental prediction model corresponding to the control group.

[0139] Each model accuracy metric has a corresponding preset accuracy threshold, which can be set according to the actual application scenario; no restrictions are imposed here.

[0140] In the embodiments of this application, after the computer device calculates the model accuracy of multiple indicators of the intermediate prediction model, it arbitrarily selects the model accuracy of one or a combination of indicators, compares the model accuracy with the preset accuracy threshold of the corresponding indicator, and determines the intermediate prediction model as the environmental prediction model corresponding to the control group if the model accuracy is greater than the preset accuracy threshold.

[0141] S604: If the model accuracy is not greater than the preset accuracy threshold, retrain the intermediate prediction model until the model accuracy of the intermediate prediction model is greater than the preset accuracy threshold.

[0142] In the embodiments of this application, if the model accuracy is not greater than a preset accuracy threshold, the current accuracy of the prediction model is too low and needs to be retrained. That is, the environmental effect data of the control group in new historical periods is obtained, and the environmental effect data of the control group in new historical periods is substituted into the basic prediction model for training to obtain an intermediate prediction model. The intermediate prediction model is then tested again, and this process is repeated until the model accuracy of the intermediate prediction model is greater than the preset accuracy threshold. The final intermediate prediction model is then determined to be the environmental prediction model corresponding to the control group.

[0143] In one exemplary embodiment, such as Figure 7 As shown, the environmental effect data includes experimental data from multiple time periods, and the methods also include:

[0144] S701, for each time period in the microbial experimental data sequence, the experimental data is compared with the experimental data of the previous time period to obtain the level ratio of the experimental data for that time period.

[0145] In the embodiments of this application, for the experimental data of each time period in the microbial experimental data sequence, the ratio of the experimental data of that time period (the mean of the environmental effect data of that time period) to the experimental data of the previous time period (the mean of the environmental effect data of the previous time period) is calculated to obtain the level ratio of the experimental data of that time period.

[0146] In some embodiments, for each test data in a microbial test data sequence, the ratio of that test data to the test data in the previous time period is calculated to obtain the level ratio of that test data.

[0147] S702: If the grade ratio of the test data for a given time period falls within the acceptable coverage range, the test data for that time period shall be retained.

[0148] The coverage range is calculated based on the number of data samples.

[0149] In the embodiments of this application, the computer device matches the grade ratio of the test data for the time period with the allowable coverage range. If the grade ratio of the test data for the time period falls within the allowable coverage range, the test data for that time period is retained, that is, the environmental effect data layout for that time period is maintained.

[0150] S703, when the grade ratio of the test data for a time period does not fall within the acceptable coverage range, performs a translation transformation on the test data for that time period.

[0151] In the embodiments of this application, if the grade ratio of the test data for a time period does not fall within the acceptable coverage range, the test data for that time period is shifted and transformed according to a preset shift transformation value. The preset shift transformation value can be set according to the actual application scenario.

[0152] In addition to the methods of all the above embodiments, a method for analyzing the corrosion effect of protective coatings is also provided, such as... Figure 8 As shown, the method includes:

[0153] S801, Obtain the microbial test data sequence of the protective coating; the microbial test data sequence includes environmental effect data obtained from tests on microbial parameters of multiple control groups; the control groups include normal group, enhanced group and inhibited group; the environmental effect data is any one of electrochemical impedance, adhesion or gloss loss rate;

[0154] S802, for the experimental data of each time period in the microbial experimental data sequence, the experimental data is compared with the experimental data of the previous time period to obtain the level ratio of the experimental data of the time period;

[0155] S803, when the grade ratio of the test data for a time period does not fall within the acceptable coverage range, perform a translation transformation on the test data for that time period;

[0156] S804: For the environmental effect data of each control group, the environmental effect data is input into the accumulation module, and the environmental effect data is accumulated to obtain a cumulative generation sequence.

[0157] S805, Substitute the cumulative generation sequence into the gray differential equation to determine the identification parameters;

[0158] S806, solve the grey differential equation based on the identification parameters to obtain the predicted environmental effect value of the control group;

[0159] S807, the environmental effect data in the microbial test data sequence is divided according to a preset threshold to obtain the environmental effect data of each control group;

[0160] S808: For each control group's predicted environmental effect value, the predicted environmental effect value of the control group is fitted with the control group's environmental effect data to obtain the fitting result of the control group.

[0161] S809, obtain the regression coefficients from the fitting results of each control group;

[0162] S810, the corrosion effect value of microorganisms is determined based on the regression coefficients in the fitting results of each control group.

[0163] Each of the above steps has been described in the foregoing embodiments. For details, please refer to the foregoing content. They will not be repeated here.

[0164] The following explanation uses data from a control test of a certain coating as an example. The dataset for this control test includes environmental effect data such as gloss loss rate, adhesion, and electrochemical impedance. After data preprocessing through correlation analysis, the gloss loss rate data shows a certain trend of change over time, reflecting the environmental effect characteristics. Predictive models for the gloss loss rate parameters under time series are presented for the normal group, the enhanced group, and the inhibited group, respectively.

[0165] During the correlation analysis of data preprocessing, a significant positive correlation was found between the gloss loss rate of the coating samples and the test duration, and the same pattern was observed in the three control groups: normal, enhanced, and inhibited. Therefore, a time-series-based prediction method can be used to explore the pattern of coating gloss loss rate changes over time, and a prediction model for the corrosion effect of coating gloss loss rate under the influence of microbial corrosion can be established.

[0166] Analysis of the original dataset reveals it to be a typical small-sample dataset. Generally, data mining algorithms perform better on large-sample datasets, but the grey prediction model shows better performance in time series prediction scenarios with small samples. Therefore, a grey prediction model-based method is used to establish a prediction model for the microbial corrosion effect of coated samples in an island / reef environment.

[0167] A GM(1,1) model was constructed using the normal group's aberration rate data. First, a grade ratio test was performed to determine the applicability of the model to the data series. The grade ratio was calculated as the previous period's data divided by the current period's data. The results are shown in Table 1 below.

[0168] Table 1. GM(1,1) model level ratios in the normal group.

[0169]

[0170] As shown in Table 1 above, the original data did not pass the ratio test. Therefore, a shift transformation was performed, that is, a shift transformation value of 90.00 was added to the original values. Finally, the ratio test values ​​of the shifted data were all within the standard range [0.751, 1.331], which means that this data is suitable for GM(1,1) model construction. The model construction results are shown in Table 2 below.

[0171] Table 2 Results of Grey Prediction Model Construction for Normal Group

[0172]

[0173] As shown in Table 2 above, after model construction, the development coefficient 'a', the grey action amount 'b', the posterior ratio 'C', and the small error probability 'p' were obtained. The posterior ratio 'C' of 0.019 <= 0.35 indicates that the model accuracy is very good. Furthermore, the small error probability 'p' of 1.000 indicates that the model accuracy is also very good.

[0174] After establishing the gray prediction model for the normal group, the gloss loss rate of the coated sample can be predicted based on the model. The prediction results are shown in Table 3 below, and the fitting results of the gloss loss rate index for the normal group are shown in the figure below. Figure 9 As shown.

[0175] Table 3. Prediction results of the grey prediction model for the normal group

[0176]

[0177] For the predicted light loss rate data of the normal group, the accuracy calculation result based on the gray prediction method is as follows: , .

[0178] A GM(1,1) model was constructed based on the light loss rate data of the enhanced group. First, a level ratio test was performed to determine the applicability of the model to the data series. The level ratio is calculated as the previous period's data divided by the current period's data. The results are shown in Table 4 below.

[0179] Table 4. Ratio of GM(1,1) Model Levels for Enhanced Groups

[0180]

[0181] As shown in Table 4 above, the original data did not pass the ratio test. Therefore, a shift transformation was performed, that is, a shift transformation value of 95.00 was added to the original values. Finally, the ratio test values ​​of the shifted data were all within the standard range [0.751, 1.331], which means that this data is suitable for GM(1,1) model construction. The model construction results are shown in Table 5 below.

[0182] Table 5 Results of the construction of the enhanced grey prediction model

[0183]

[0184] As shown in Table 5 above, after model construction, the development coefficient 'a', the grey action amount 'b', the posterior ratio 'C', and the small error probability 'p' were obtained. The posterior ratio 'C' of 0.044 <= 0.35 indicates that the model accuracy is very good. Furthermore, the small error probability 'p' of 1.000 indicates that the model accuracy is also very good.

[0185] After establishing the gray prediction model for the enhanced group, the gloss loss rate of the coated sample can be predicted based on the model. The prediction results are shown in Table 6 below, and the fitting results of the gloss loss rate index for the enhanced group are shown in the figure below. Figure 10 As shown.

[0186] Table 6. Prediction results of the enhanced group grey prediction model

[0187]

[0188] Choose the root mean square error (RMSE) and goodness of fit ( Two accuracy metrics are used to evaluate the model's accuracy. For the luminescence loss prediction data of the enhanced group, the accuracy calculation results based on the grey prediction method are as follows: , .

[0189] A GM(1,1) model was constructed based on the light loss rate data of the suppression group. First, a grade ratio test was performed to determine the applicability of the model to the data series. The grade ratio is calculated as the previous period's data divided by the current period's data. The results are shown in Table 7 below.

[0190] Table 7. Ratio of GM(1,1) model levels in the inhibition group

[0191]

[0192] As shown in Table 7 above, the original data did not pass the ratio test. Therefore, a shift transformation was performed, that is, a shift transformation value of 82.00 was added to the original values. Finally, the ratio test values ​​of the shifted data were all within the standard range [0.751, 1.331], which means that this data is suitable for GM(1,1) model construction. The model construction results are shown in Table 8 below.

[0193] Table 8 Results of Grey Prediction Model Construction for Suppression Group

[0194]

[0195] As shown in Table 8 above, after model construction, the development coefficient 'a', the grey action amount 'b', the posterior ratio 'C', and the small error probability 'p' were obtained. The posterior ratio 'C' of 0.062 <= 0.35 indicates that the model accuracy is very good. Furthermore, the small error probability 'p' of 1.000 indicates that the model accuracy is also very good.

[0196] After establishing the gray prediction model for the enhanced group, the gloss loss rate of the coated sample can be predicted based on the model. The prediction results are shown in Table 9 below, and the fitting results of the gloss loss rate index for the suppressed group are shown in the figure below. Figure 11 As shown.

[0197] Table 9. Prediction results of the grey prediction model for the suppression group.

[0198]

[0199] Choose the root mean square error (RMSE) and goodness of fit ( Two accuracy metrics are used to evaluate the model's accuracy. For the luminescence loss prediction data of the enhanced group, the accuracy calculation results based on the grey prediction method are as follows: , .

[0200] As environmental experiments in island and reef environments continue, the gloss loss rate of epoxy topcoat shows a certain changing pattern with the increase of experimental time. This paper, through preliminary analysis of environmental effect data, identifies the changing trend of gloss loss rate data of each control group (enhanced group, normal group, and inhibited group) over time. Based on the grey prediction model, prediction models for gloss loss rate under the enhanced group, normal group, and inhibited group are established respectively. After testing with posterior ratio and small error probability value, it can be seen that the accuracy of the above models can reach an excellent level, and the models can be used to predict the gloss loss rate of each control group.

[0201] Based on predictions, after 24 months of testing in the natural environment of the island reef, the predicted values ​​of gloss loss rate under each control group can be obtained. Combined with their initial gloss loss rate, the degradation amount of coating gloss loss rate under each control group under the prediction model are as follows:

[0202]

[0203]

[0204]

[0205] The following conclusions can be drawn:

[0206] (1) Under real island and reef natural environment conditions, the difference in gloss rate of the normal group was 50.958, which quantitatively characterized the degree of performance degradation of epoxy topcoat under this environment. However, this degradation was under comprehensive conditions and was not only the result of the influence of microbial corrosion on coating performance.

[0207] (2) The enhanced group was developed by enhancing the propagation of microorganisms during the natural environment test of the coating (by brushing nutrient solution and avoiding ultraviolet light, etc.), which provided good conditions for the propagation of microorganisms on the coating sample. Under the condition of sufficient microbial growth, the gloss loss rate degradation increased by 61.121, which is 10.163 higher than the degradation under real conditions.

[0208] (3) In order to obtain a quantitative characterization of the natural environmental effect of microbial corrosion on the coating under natural environmental test conditions, an inhibition group was set up as one of the control groups. It can be considered that the coating sample under the inhibition group has almost no effect of microbial corrosion. Combined with the test data of 24 months, its gloss rate degradation was 40.794, which was 10.164 lower than the degradation under real conditions. It can be considered that this degradation of 10.164 is due to the degradation of coating performance caused by microbial corrosion.

[0209] It is worth noting that, with the support of the predictive model, the influence trend of microbial corrosion after a 24-month test period can be quantitatively analyzed, or the influence effect of microbial corrosion at a certain non-test point in the middle of the 24 months can be analyzed. This is also the dynamic effect brought by the predictive model for the analysis of microbial corrosion effects.

[0210] It should be understood that although the steps in the flowcharts of the above embodiments 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 above embodiments 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.

[0211] Based on the same inventive concept, this application also provides a protective coating corrosion effect analysis device for implementing the above-described method for analyzing the corrosion effect of protective coatings. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more embodiments of the protective coating corrosion effect analysis device provided below can be found in the limitations of the protective coating corrosion effect analysis method described above, and will not be repeated here.

[0212] In one exemplary embodiment, such as Figure 12 As shown, a device for analyzing the corrosion effect of a protective coating is provided, comprising: an acquisition module 121, a prediction module 122, and a fitting module 123, wherein:

[0213] The acquisition module 121 is used to acquire the microbial test data sequence of the protective coating; the microbial test data sequence includes environmental effect data obtained from tests on the microbial parameters of multiple control groups; the control groups include the normal group, the enhanced group, and the inhibited group; the environmental effect data is any one of electrochemical impedance, adhesion, or gloss loss rate;

[0214] Prediction module 122 is used to perform first-order differential processing on the microbial test data sequence according to the environmental prediction model corresponding to each control group to obtain the predicted environmental effect value of each control group.

[0215] The fitting module 123 is used to fit the microbial experimental data sequence and the predicted values ​​of environmental effects, and to determine the corrosion effect value of the microorganisms based on the fitting results.

[0216] In an exemplary embodiment, the prediction module 122 described above is specifically used for:

[0217] For each control group's environmental effect data, the environmental effect data is input into the accumulation module, and the environmental effect data is accumulated to obtain a cumulative generation sequence;

[0218] Substitute the accumulated sequence into the gray differential equation to determine the identification parameters;

[0219] The grey differential equation is solved based on the identification parameters to obtain the predicted environmental effects of the control group.

[0220] In an exemplary embodiment, the fitting module 123 described above is specifically used for:

[0221] The environmental effect data in the microbial experimental data sequence were divided according to a preset threshold to obtain the environmental effect data of each control group;

[0222] For each control group's predicted environmental effect value, the predicted environmental effect value of the control group is fitted with the environmental effect data of the control group to obtain the fitting result of the control group.

[0223] In an exemplary embodiment, the fitting module 123 described above is specifically used for:

[0224] Obtain the regression coefficients from the fitting results of each control group;

[0225] The corrosion effect value of microorganisms was determined based on the regression coefficients in the fitting results of each control group.

[0226] In one exemplary embodiment, the above-described apparatus further includes a training module, specifically used for:

[0227] For each control group's basic prediction model, historical environmental effect data of the control group are obtained, and the historical environmental effect data of the control group is substituted into the basic prediction model for training to obtain an intermediate prediction model.

[0228] The intermediate prediction model is tested using a preset testing method to obtain the model accuracy of the intermediate prediction model;

[0229] If the model accuracy is greater than the preset accuracy threshold, the intermediate prediction model is determined to be the environmental prediction model corresponding to the control group.

[0230] If the model accuracy is not greater than the preset accuracy threshold, retrain the intermediate prediction model until the model accuracy of the intermediate prediction model is greater than the preset accuracy threshold.

[0231] In an exemplary embodiment, the above-described apparatus further includes a preprocessing module, specifically used for:

[0232] For the experimental data of each time period in the microbial experimental data sequence, the experimental data is compared with the experimental data of the previous time period to obtain the level ratio of the experimental data of the time period;

[0233] If the grade ratio of the test data for a given time period falls within the acceptable coverage range, the test data for that time period will be retained.

[0234] If the grade ratio of the test data for a given time period does not fall within the acceptable coverage range, the test data for that time period is shifted and transformed.

[0235] Each module in the aforementioned corrosion effect analysis device for protective coatings 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 memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0236] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program that, when executed by the processor, implements the steps in the above-described method embodiments.

[0237] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0238] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0239] 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. When executed, the computer program 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.

[0240] 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.

[0241] The above embodiments merely illustrate several implementation methods of this application, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of this application's patent. 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 analyzing the corrosion effect of a protective coating, characterized in that, The method includes: Obtain a microbial test data sequence for the protective coating; the microbial test data sequence includes environmental effect data obtained from tests using microbial parameters from multiple control groups; the control groups include a normal group, an enhanced group, and an inhibited group; the environmental effect data is any one of electrochemical impedance, adhesion, or gloss loss rate; The microbial experimental data sequence was processed by first-order differential based on the environmental prediction model corresponding to each control group to obtain the predicted environmental effect value of each control group. The microbial experimental data sequence and the predicted environmental effects are fitted together, and the corrosion effect value of the microorganisms is determined based on the fitting results.

2. The method according to claim 1, characterized in that, The environmental prediction model includes a cumulative module and a grey differential equation. The step of performing first-order differential processing on the microbial experimental data sequence based on the environmental prediction model corresponding to each control group to obtain the predicted environmental effect value for each control group includes: For each control group's environmental effect data, the environmental effect data is input into the accumulation module, and the environmental effect data is accumulated to obtain a cumulative generation sequence; Substitute the generated sequence of the first accumulation into the gray differential equation to determine the identification parameters; The grey differential equation is solved based on the identification parameters to obtain the predicted environmental effects of the control group.

3. The method according to claim 1, characterized in that, The fitting of the microbial experimental data sequence and the predicted environmental effects includes: The environmental effect data in the microbial test data sequence are divided according to a preset threshold to obtain the environmental effect data of each control group; For each control group's predicted environmental effect value, the predicted environmental effect value of the control group is fitted with the environmental effect data of the control group to obtain the fitting result of the control group.

4. The method according to claim 3, characterized in that, The determination of the corrosion effect value of microorganisms based on the fitting results includes: Obtain the regression coefficients from the fitting results of each control group; The corrosion effect value of the microorganism is determined based on the regression coefficients in the fitting results of each control group.

5. The method according to any one of claims 1-4, characterized in that, The method further includes: For each control group's basic prediction model, historical environmental effect data of the control group is obtained, and the historical environmental effect data of the control group is substituted into the basic prediction model for training to obtain an intermediate prediction model. The intermediate prediction model is tested using a preset testing method to obtain the model accuracy of the intermediate prediction model; If the model accuracy is greater than a preset accuracy threshold, the intermediate prediction model is determined to be the environmental prediction model corresponding to the control group. If the model accuracy is not greater than the preset accuracy threshold, the intermediate prediction model is retrained until the model accuracy of the intermediate prediction model is greater than the preset accuracy threshold.

6. The method according to any one of claims 1-4, characterized in that, The environmental effect data includes experimental data from multiple time periods, and the method further includes: For the experimental data of each time period in the microbial experimental data sequence, the experimental data is compared with the experimental data of the previous time period to obtain the level ratio of the experimental data of that time period; If the grade ratio of the test data for the specified time period falls within the acceptable coverage range, the test data for that time period shall be retained. If the grade ratio of the test data during the specified time period does not fall within the acceptable coverage range, the test data for the specified time period is shifted and transformed.

7. A device for analyzing the corrosion effect of a protective coating, characterized in that, The device includes: The acquisition module is used to acquire the microbial test data sequence of the protective coating; the microbial test data sequence includes environmental effect data obtained from tests on microbial parameters of multiple control groups; the control groups include a normal group, an enhanced group, and an inhibited group; the environmental effect data is any one of electrochemical impedance, adhesion, or gloss loss rate; The prediction module is used to perform first-order differential processing on the microbial test data sequence according to the environmental prediction model corresponding to each control group to obtain the predicted environmental effect value of each control group. The fitting module is used to fit the microbial test data sequence and the predicted environmental effect value, and determine the corrosion effect value of the microorganism based on the fitting result.

8. 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 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images