Multi-attribute target decision evaluation method for enhanced corrosion protection design of bent bolt

Abstract

The application provides a multi-attribute target decision evaluation method for enhanced corrosion resistance design of a bent bolt, which is based on a multi-attribute decision analysis theory, and a support vector regression (SVR) machine learning algorithm is innovatively introduced to solve weight coefficients of various performance evaluation indexes, so as to obtain an objective and accurate comprehensive performance evaluation result. Compared with a traditional subjective weighting method, the biggest advantage of the method is that the method can fully explore index correlation rules and weight distribution characteristics contained in historical evaluation data, and the method realizes adaptive solving from data to weights through the machine learning algorithm, and the method has the characteristics of strong objectivity, good adaptability and strong interpretability. The method can also be widely applied to corrosion resistance performance evaluation of a new coating system, and has important guiding significance for optimization and iteration of a coating formula and process parameters.

Description

Technical Field

[0001] The present invention relates to the technical field of design and evaluation of enhanced anti-corrosion performance of pipeline bent bolts, and in particular to a multi-attribute target decision-making evaluation method for the design of enhanced anti-corrosion performance of pipeline bent bolts. Background Art

[0002] Bent bolts, with their unique bending strength and deformation capacity, play a key role in securing wind turbine towers. They mitigate and absorb external forces acting on the structure, making it safer and more secure. Compared to ordinary bolts, bent bolts have a larger cross-sectional area, which increases the load-bearing capacity of the connection and makes the structure more secure and durable. Furthermore, their bending properties provide a certain degree of loosening resistance and provide excellent seismic resistance and shock absorption properties.

[0003] Corrosion protection technology for bent bolts in concrete wind turbine tower segments is currently undergoing continuous advancement and improvement. To meet the challenges of long-term operation of wind turbine facilities in harsh environmental conditions, particularly in highly corrosive areas like oceans and deserts, modern corrosion protection technology has incorporated a variety of advanced materials, processes, and coating systems to enhance the corrosion resistance of bent bolts, significantly extending their service life and reducing the risk of failure due to corrosion, thereby improving the stability and reliability of the equipment.

[0004] However, due to the harsh operating environment of the fastening bolts used in wind turbine towers, the performance limitations of coating materials in extreme environments remain a major problem. These extreme environments may include high salinity, high humidity, highly corrosive gases, etc. These environmental factors will accelerate the aging, cracking and peeling of the coating, causing the bolts to lose effective protection. This can be solved to a certain extent through moderate oxidation. In addition, the adhesion between the coating and the bolt substrate is also a key issue. If the adhesion is insufficient, the coating will easily peel off, thereby losing its anti-corrosion function. Bolts treated with Dacromet technology have extremely strong corrosion resistance, and the coating is not easy to fall off, but the Dacromet coating contains extremely harmful hexavalent chromium and will cause contact corrosion with stainless steel parts.

[0005] How to effectively evaluate the effects of the above-mentioned solutions on corrosion resistance, so as to seek the best enhanced corrosion resistance design for pipe bend bolts for wind turbine towers under laboratory conditions, is of great significance for the long-term, safe and effective use of pipe bend bolts. Summary of the Invention

[0006] The present invention adopts a corrosion resistance performance evaluation method based on multi-attribute target decision-making to comprehensively evaluate the adhesion and corrosion resistance of pipeline bent bolt samples after anti-corrosion design treatment, and finally obtains more comprehensive and effective evaluation results to guide the design of enhanced corrosion resistance of pipeline bent bolts.

[0007] To achieve the above object, the application provides a multi-attribute target decision evaluation method for enhanced corrosion resistance design of a bent bolt, characterized in that the evaluation method comprises the following steps:

[0008] Step 1: preparing the bent bolt required for the test, and evaluating and detecting the state of the bent bolt;

[0009] Step 2: performing blackening treatment or one kind of Dacromet coating on part of the bent bolts, and performing blackening treatment and then Dacromet coating on part of the bent bolts;

[0010] Step 3: testing the adhesion performance of the coating on the bent bolts treated in step 2, and then scoring and recording the corresponding data according to the test results;

[0011] Step 4: testing the corrosion resistance of the coating on the bent bolts treated in step 2, and then scoring and recording the corresponding data according to the test results;

[0012] Step 5: scoring the comprehensive corrosion resistance of the coating on the bent bolts treated in step 2 and recording the corresponding data;

[0013] Step 6: based on the support vector regression method, using the data recorded in steps 3-5 to solve the index weight of the evaluation index of each performance test in steps 3 and 4 on the evaluation of the corrosion resistance of the coating, to obtain an evaluation model;

[0014] Step 7: using the evaluation model to evaluate the enhanced corrosion resistance design of the bent bolt.

[0015] Further preferably, the adhesion performance test comprises the wiping method, metallographic observation method and physical assembly method.

[0016] Further preferably, the corrosion resistance test comprises the salt spray corrosion method.

[0017] Further preferably, the scores are all five grades of 1-5.

[0018] Further preferably, in step 6, the recorded data and the corresponding performance labels are associated and modeled by using the SVR algorithm, the SVR model adopts a Gaussian radial basis kernel function (RBF), different combinations of a penalty factor C and a kernel function parameter g are traversed by using a grid search combined with cross-validation, the generalization performance on the validation set is evaluated based on a mean square error (MSE) index, and then the optimal parameter combination is determined to train and generate the SVR model.

[0019] Further preferably, the data recorded in steps 3-5 include the following indexes: the wiping adhesion grade x1, the metallographic observation adhesion grade x2, the physical assembly adhesion grade x3, and the salt spray test corrosion resistance grade x4, and the coating comprehensive anti-corrosion performance score y ∈ [1, 5]; if the performance data of n coating samples are collected, an original "feature-label" data set is formed,

[0020] D = {(x1, y1), (x2, y2), …, (x n , y n )}

[0021] wherein xi = [x i1 , x i2 , x i3 , x i4 ] T is the feature vector of the i-th sample, y i is the corresponding comprehensive performance score;

[0022] The index score results are normalized to eliminate the influence of different dimensions, and are uniformly mapped to the interval [0, 1]. Specifically, the maximum and minimum value normalization method is adopted to convert the original feature matrix X = [x1, x2, …, x n ] T ∈ n × 4:

[0023]

[0024] After normalization, the preprocessed feature matrix X ∈ [0, 1] n×4 is obtained.

[0025] Further preferably, based on the preprocessed data set D = {(x1', y1), (x2', y2), …, (x n ', y n )}, an SVR algorithm is used to construct a model. SVR seeks an optimal regression hyperplane f(x) = w T φ(x) + b in the feature space by introducing an ε insensitive loss function, so that the error between the model output f(x i ) and the true label y i is controlled within ε, wherein w, b are model parameters, and φ(·) represents a transformation function that maps the original features to a high-dimensional space;

[0026] A Gaussian radial basis kernel function (RBF) κ(x i , x j ) = exp(-γ‖x i -x j ‖ 2) as the kernel function of the SVR model, where γ>0 is the kernel function width parameter, and the slack variable ξ is introduced i , The objective optimization problem of SVR is expressed as:

[0027]

[0028] Among them, C>0 is the penalty coefficient, which is used to control the complexity of the model and the tolerance to outliers. By solving the dual form of the above convex quadratic programming problem, the optimal decision function of SVR is obtained:

[0029]

[0030] Where, α i , is a Lagrange multiplier satisfying

[0031] In order to obtain the SVR model with the best generalization performance, the SVR model hyperparameters $(C,\gamma)$ are tuned. A method combining grid search and K-fold cross-validation is adopted to traverse different (C,γ) combinations in the parameter space. The optimal parameter configuration is determined by minimizing the mean square error (MSE) on the validation set to guide the training and generation of the SVR model.

[0032] Further preferably, all support vector samples (xs1, ys1), (xs2, ys2), ..., (xsl, ysl) and their corresponding Lagrange multipliers are extracted from the trained SVR model. Calculate the inner product of the support vector and the multiplier to obtain the original weight of the input feature β = [β1,β2,β3,β4] T :

[0033]

[0034] Perform maximum and minimum normalization on β to obtain the relative importance weight of each evaluation index:

[0035]

[0036] At this point, the weight vector w = [w1, w2, w3, w4] of the coating anti-corrosion performance evaluation index is obtained based on the SVR model. T , the scoring results of each index of the coating to be evaluated are x=[x1,x2,x3,x4] T The weighted sum of them with w is the comprehensive evaluation model for the design of enhanced corrosion resistance:

[0037]

[0038] Further preferably, the Dacromet coating layer is divided into acidic conditions and basic conditions.

[0039] The application proposes a novel coating corrosion resistance performance evaluation method, which is based on the multi-attribute decision analysis theory, and innovatively introduces a support vector regression (SVR) machine learning algorithm to solve the weight coefficients of each performance evaluation index, so as to obtain an objective and accurate comprehensive performance evaluation result. Compared with the traditional subjective weighting method, the biggest advantage of the method is that it can fully explore the index correlation law and weight distribution characteristics contained in the historical evaluation data, and realize the adaptive solution from data to weight through the machine learning algorithm, and has the characteristics of strong objectivity, good adaptability and strong interpretability. The method can be widely applied to the corrosion resistance performance evaluation of new coating systems, and has important guiding significance for the optimization and iteration of coating formula and process parameters.

[0040] In the data preprocessing stage, the maximum and minimum value normalization method is adopted to carry out dimensionless processing on the feature data according to the dimension difference of different evaluation indexes, so as to eliminate the influence of dimension.

[0041] In the weight calculation, the SVR algorithm is selected to model the correlation between the normalized feature data and the corresponding performance label. Considering the nonlinear correlation characteristics between the coating corrosion resistance performance evaluation index and the comprehensive performance, the model adopts the Gaussian radial basis kernel function (RBF) to enhance the nonlinear mapping ability. At the same time, in order to seek the optimal parameter configuration of the model, the grid search and cross-validation method are combined to traverse different combinations of the penalty factor C and the kernel function parameter g. Based on the mean square error (MSE) index, the generalization performance on the validation set is evaluated, and then the optimal parameter combination is determined to guide the training and generation of the SVR model. DETAILED DESCRIPTION

[0042] The implementation method of the application will be specifically explained below.

[0043] The multi-attribute target decision evaluation method for enhancing the corrosion resistance performance design of the bent bolt in the application is characterized in that the evaluation method comprises:

[0044] Step 1: Prepare the bent bolt required for the test, and evaluate and detect the state of the bent bolt.

[0045] Step 2: Perform blackening treatment or Dacromet coating on part of the bent bolts, and perform blackening treatment and then Dacromet coating on part of the bent bolts.

[0046] Step 3: Test the adhesion performance of the bent bolt coating after step 2, and then score and record the corresponding data according to the test results.

[0047] Step 4: Perform corrosion resistance test on the bend bolt coating after step 2, then score and record the corresponding data according to the test results;

[0048] Step 5: Perform comprehensive corrosion resistance performance score on the bend bolt coating after step 2 and record the corresponding data;

[0049] Step 6: Based on the support vector regression method, use the data recorded in steps 3-5 to solve the index weight of the evaluation index of each performance test in steps 3 and 4 on the corrosion resistance performance evaluation of the coating, to obtain the evaluation model;

[0050] Step 7: Use the evaluation model to evaluate the enhanced corrosion resistance design of the bend bolt.

[0051] In the specific experiment, the bend bolt sample required for the test in step 1 is specifically:

[0052] Prepare a batch of 40CrNiMo bend bolts for testing, with a thread specification of M36. Perform tensile tests on the bend bolts, and the mechanical properties of the bolt test pieces detected should meet the performance requirements of the bolts for wind power towers in NB / T 31082-2016 High-strength bolt connection pairs for wind turbine towers, to ensure that the test samples can meet the practical needs. Then divide this batch of samples into A, B, C, D, E, and F groups, and perform subsequent steps.

[0053] Step 2.1 Blackening treatment of bend bolt

[0054] Blackening treatment is performed on B, C, and D groups of bolts, with the specific process being:

[0055] Bend bolt cleaning and degreasing → cold water cleaning → pickling → cold water cleaning → oxidation blackening → cold water cleaning → saponification → cold water cleaning (oil immersion) → drying

[0056] 1) Cleaning and degreasing

[0057] In order to remove oil stains attached to the surface of the bolt, the bend bolt needs to be cleaned in the degreasing tank for 20-30 minutes. During the degreasing process, the workpiece must be completely immersed in the degreasing solution, and the pH value of the degreasing solution is generally controlled at 12-1, and the treatment time is usually 10-30 minutes. During the degreasing process, the workpiece surface needs to be shaken up and down several times every 3-5 minutes to ensure that the degreasing solution can uniformly act on the workpiece surface. When the concentration of the solution is lower than pH 12, the degreasing powder needs to be supplemented to maintain the activity of the degreasing solution. The composition and ratio of the degreasing solvent are:

[0058] Table 1 Composition of degreasing solution

[0059] Name Mass percentage Sodium hydroxide 1-3％ Fatty alcohol polyoxyethylene ether 1-5％ Sodium nitrite 0.1-0.5％

[0060] 2) Cold water cleaning

[0061] After degreasing, the bent bolts are cleaned in cold water to remove the degreasing solvent (acid) on the surface.

[0062] 3) Pickling

[0063] The main purpose of pickling is to remove scale, rust, and other impurities from the bolt surface. It also activates the surface of the bent bolt, making it easier for the bolt to form a dense oxide film in the blackening solution. This step requires pickling the bent bolt in 20-30% hydrochloric acid for more than 30 seconds. (The acid solution is sprayed onto the metal surface at high pressure to remove scale and rust. This method is suitable for large and complex-shaped parts and can improve pickling efficiency.)

[0064] 4) Oxidation and blackening

[0065] The main purpose of this step is to form a thin film of oxide or compound on the metal surface. The bent bolts that have been cleaned after pickling are immersed in alkaline blackening liquid and heated to 130°C. They are fully immersed until a uniform black oxide film is formed on the surface of the bent bolts.

[0066] Table 2 Blackening liquid composition and mass (volume) fraction:

[0067] Name Mass percentage Copper sulfate 3％ Silver nitrate 1％ Glass acetic anhydride (volume fraction) 5％ Boric acid 2％ Defatted acid 10％ Sodium sulfite 1％

[0068] 5) Saponification

[0069] This process converts the iron within the micropores of the iron oxide film formed by the blackening of the bent bolts into iron stearate. This conversion results in a passivated surface, thereby improving corrosion resistance. Soak the blackened bent bolts in 2-3% boiling soapy water for 5 minutes.

[0070] 6) Drying

[0071] The saponified and cleaned bent bolts are dried at 150°C to remove surface moisture.

[0072] After the blackening treatment is completed, the bent bolts in group B are retained, and the bent bolts in groups C, D, E, and F are coated with Dacromet coating respectively.

[0073] Step 2.2 The specific process of Dacromet coating on bent bolts is as follows:

[0074] Dipping → Centrifugation → Pre-drying → Sintering → Cooling

[0075] 1) Dip coating

[0076] Immerse the blackened bent bolts in a chromium-free Dacromet solution for 30 seconds to ensure that a complete and uniform chromium-free Dacromet coating is formed on the bolt surface.

[0077] The components and mass percentage of each component of the chromium-free dacromet solution. The roles of silicon dioxide, zinc oxide, and succinic acid are to adjust the pH value.

[0078] After the initial preparation of the dacromet solution, the dacromet solution is divided into two groups ① and ②, and the pH value of each group is adjusted to be weakly alkaline and alkaline respectively. The C and E groups of bent bolts are soaked in the weakly alkaline solution ①, and the D and F groups of bent bolts are soaked in the alkaline solution ②.

[0079] The detailed components and proportions of the dacromet solution are shown in the following table.

[0080] Table 3 Composition of dacromet solution

[0081] Name Mass percentage Polyethylene glycol-400 19％ Zinc powder 22％ Aluminum powder 4.5％ Silane coupling agent KH560 21％ Water 15％ Ethanol 15％ Sodium molybdate 1％ NP-10 2％ Silicon dioxide Less than 0.5% Zinc oxide Less than 0.5% Succinic acid Less than 0.5%

[0082] 2) Centrifugation

[0083] When centrifuging, rotate forward and reverse each twice, for ten to twenty seconds each time, at a speed of 200-300 revolutions per minute. The purpose of this step is to ensure that there is no accumulation of liquid, hanging liquid, bubbles, and missed coating on the parts.

[0084] 3) Pre-baking

[0085] The workpiece of the dacromet wet film needs to be pre-baked at a temperature of 120±20℃ for 10-15 minutes as soon as possible to evaporate the water in the coating liquid and make the flow even.

[0086] 4) Sintering

[0087] The pre-baked bent bolt needs to be sintered at a high temperature of about 300℃ for 20-40 minutes. The purpose of this step is to form a good bonding force between the dacromet coating and the oxide film, and to improve the wear resistance and corrosion resistance of the coating.

[0088] 5) Cooling

[0089] Cool the sintered bolt and prepare for subsequent testing.

[0090] The treatment methods of the bolts in each group are shown in the following table.

[0091] Table 4 Treatment table of bolts in each group

[0092] A No treatment B Blackening treatment C Blackening treatment and Dacromet (weak alkaline) D Dacromet (weak alkaline) E Blackening treatment and Dacromet (alkaline) F Dacromet (alkaline)

[0093] Step 3: Test the adhesion performance of the bent bolt coating

[0094] 1) Use clean white wiping paper to wipe the surface coating of the bent bolt repeatedly and evenly. If no other colors appear on the white paper, the coating quality is excellent; if a small amount of other colors appear on the white paper, the coating quality is average; if a significant amount of other colors appear on the white paper, the coating quality is poor. According to the test results, score the six groups of bolts.

[0095] 2) The six groups of bolts are respectively subjected to metallographic SEM observation, and the state of the surface coating under the microscope is observed. If a dense coating is observed on the surface and no damage is found, the adhesion of the coating is excellent; if the damage of the Dacromet coating is observed, but no exposed metal surface is observed, the adhesion of the coating is good; if the coating is obviously damaged, and the exposed metal surface is observed, the coating quality is poor.

[0096] 3) The six groups of bolts are respectively subjected to manual tightening and disassembly, and the surface coating is visually observed for whether there is peeling, surface scratch, etc. If there is no coating peeling and damage, it indicates that the coating quality is excellent; if the coating surface is found to be damaged, or a small amount of coating peeling occurs, but no exposed metal surface is found, the coating quality is good; if the coating peeling is obvious, and the metal surface is exposed or even damaged, it indicates that the coating quality is poor.

[0097] After the test, the adhesion test of the six groups of bolts is scored and recorded according to the test results, and the scoring results are as follows.

[0098] Table 5 Adhesion ability score

[0099] Serial number Wiping method Metallographic observation Physical assembly A 5.0 1.0 1.0 B 4.0 3.0 3.0 C 5.0 5.0 4.0 D 5.0 5.0 5.0 E 5.0 4.0 4.0 F 5.0 5.0 4.0

[0100] The numbers in the table represent the adhesion grade of the coating, wherein 1 represents poor adhesion, and 5 represents excellent adhesion.

[0101] The six groups of bent bolts are respectively placed in a salt spray test machine for a certain time of salt spray corrosion, and the corrosion results are recorded every certain time. After the test, the corrosion resistance effect of the six groups of bent bolts is scored and recorded according to the salt spray test results, i.e. the corrosion time and the corrosion degree.

[0102] Table 6 Corrosion resistance score

[0103] Serial number Corrosion resistance score A 1.0 B 2.0 C 5.0 D 4.0 E 5.0 F 3.0

[0104] The numbers in the table represent the corrosion resistance grade, wherein 1 represents poor corrosion resistance, and 5 represents excellent corrosion resistance.

[0105] Step 5: Coating comprehensive corrosion resistance performance score

[0106] The six groups of bent bolts are respectively subjected to comprehensive corrosion resistance performance score according to historical experience and expert score, and the specific scoring results are shown in Table 7 below.

[0107] Table 7 Comprehensive corrosion resistance performance score

[0108]

[0109]

[0110] The numbers in the table represent the corrosion resistance grade, 1 represents the comprehensive corrosion resistance grade is poor, and 5 represents the comprehensive corrosion resistance performance is excellent.

[0111] Step 6: Solving the weight of coating corrosion resistance performance evaluation index based on support vector regression

[0112] 6.1 Data preparation and preprocessing

[0113] By testing the adhesion and corrosion resistance of the corrosion-resistant coating processed under different process conditions, a set of performance evaluation data is obtained, which includes the following indicators: scrub adhesion grade x1, metallographic observation adhesion grade x2, physical assembly adhesion grade x3, and salt spray test corrosion resistance grade x4, and coating comprehensive corrosion resistance performance score y∈[1, 5]. Assuming that n coating sample performance data is collected, the original "feature-label" data set is constructed:

[0114] D={(x1,y1),(x2,y2),…,(x n ,y n )}

[0115] Where xi=[x i1 ,x i2 ,x i3 ,x i4 ] T is the feature vector of the ith sample, and y i is the corresponding comprehensive performance score.

[0116] In the data preprocessing stage, first, the index score results are normalized to map them to the interval [0, 1] to eliminate the influence of different dimensions. The maximum and minimum value normalization method is used to convert the original feature matrix X=[x1,x2,···,x n ] T ∈n×4:

[0117]

[0118] After normalization, the preprocessed feature matrix X∈[0, 1] n×4 is obtained.

[0119] 6.2 Construction and training of SVR model

[0120] Based on the preprocessed data set D={(x1',y1),(x2',y2),…,(x n ',y n)}, the SVR algorithm is used to build a comprehensive anti-corrosion performance evaluation model for coatings. SVR introduces an ε-insensitive loss function to seek an optimal regression hyperplane f(x)=w in the feature space. T φ(x)+b, so that the model output f(x i ) and the true label y i The error between them is controlled within ε. Where w and b are model parameters, and φ(·) represents the transformation function that maps the original features to the high-dimensional space.

[0121] Considering the possible complex nonlinear relationship between various performance indicators and comprehensive scores, this paper uses the Gaussian radial basis kernel function (RBF)κ(x i ,x j )=exp(-γ‖x i -x j ‖ 2 ) is used as the kernel function of the SVR model, where γ>0 is the kernel function width parameter. Introducing the slack variable ξ i , The objective optimization problem of SVR can be expressed as:

[0122]

[0123] Among them, C>0 is the penalty coefficient, which is used to control the complexity of the model and the tolerance to outliers. By solving the dual form of the above convex quadratic programming problem, the optimal decision function of SVR can be obtained:

[0124]

[0125] Where, α i , is a Lagrange multiplier satisfying

[0126] To obtain an SVR model with optimal generalization performance, it is necessary to tune the model hyperparameters $(C,\gamma)$. Using a grid search method combined with K-fold cross-validation, we traverse different (C,γ) combinations in the parameter space and determine the optimal parameter configuration by minimizing the mean squared error (MSE) on the validation set. This is used to guide model training and generation.

[0127] 6.3 Solution of evaluation index weights

[0128] Extract all support vector samples (xs1, ys1), (xs2, ys2), ..., (xsl, ysl) and their corresponding Lagrange multipliers from the trained SVR model Calculate the inner product of the support vector and the multiplier to obtain the original weight of the input feature β = [β1,β2,β3,β4] T :

[0129]

[0130] To make the weights comparable, the maximum and minimum value normalization is performed on β to obtain the relative importance weight of each evaluation index:

[0131]

[0132] Thus, the weight vector w = [w1, w2, w3, w4] of the coating corrosion resistance evaluation index is obtained based on the SVR model. T The score results x = [x1, x2, x3, x4] of each index of the coating to be evaluated are weighted and summed with w, respectively, to obtain the comprehensive score of the corrosion resistance performance of the coating: T

[0133]

[0134] Step 7 Summary and Evaluation of the Corrosion Resistance Performance of the Bolt Coating

[0135] The adhesion grade by wiping method, the adhesion grade by metallographic observation method, the adhesion grade by physical assembly method, and the performance grade of the Isaria fumosorosea. To comprehensively evaluate the corrosion resistance performance of the bolts in each group, this paper further comprehensively adopts the multi-attribute decision-making method based on TOPSIS (Technique for Order Preference by Similarity to an Ideal Solution) to weight and integrate the score results of different indexes to obtain the comprehensive score of the corrosion resistance performance of the bolt coating, providing quantitative basis for the optimization of the coating scheme.

[0136] This scheme obtains the adhesion grade by wiping method, the adhesion grade by metallographic observation method, the adhesion grade by physical assembly method, and the performance grade of the Isaria fumosorosea of the six groups of bolts through adhesion tests and salt spray corrosion tests on the bolt samples treated by different processes. To comprehensively evaluate the corrosion resistance performance of the bolts in each group, this paper adopts the multi-attribute decision-making method based on TOPSIS (Technique for Order Preference by Similarity to an Ideal Solution) to weight and integrate the score results of different indexes to obtain the comprehensive score of the corrosion resistance performance of the bolt coating, providing quantitative basis for the optimization of the coating scheme.

[0137] ​TOPSIS method is a commonly used multi-attribute decision-making method. The basic idea is to calculate the distance between each alternative and the positive and negative ideal solutions, establish a relative closeness index, and select the scheme with the smallest positive ideal solution distance and the largest negative ideal solution distance as the optimal choice. In the problem of evaluating the corrosion resistance of coatings, the highest level of each evaluation index can be regarded as the positive ideal solution, and the lowest level as the negative ideal solution. By calculating the weighted Euclidean distance between each coating scheme and the ideal solution, the closeness to the optimal performance can be obtained.

[0138] Suppose there are m groups of coating schemes to be evaluated, and each group has n evaluation indexes. Let the value of the jth index in the ith group of schemes be The implementation steps of TOPSIS method are as follows:

[0139] Step 7.1: Construct the standardized score matrix R = [r ij ] m×n .

[0140] Step 7.2: Calculate the weighted standardized score matrix {V} = [v {ij} ] {m×n} , where

[0141] v ij = w j · r ij , i = 1, 2, …, m; j = 1, 2, …, n

[0142] Step 7.3: Determine the positive and negative ideal solutions:

[0143]

[0144] where,

[0145]

[0146] Step 7.4: Calculate the weighted Euclidean distance between the ith group of schemes and the positive and negative ideal solutions:

[0147]

[0148] Step 7.5: Calculate the relative closeness of the ith group of schemes:

[0149]

[0150] where, 0 ≤ c i ≤ 1, and the closer c i is to 1, the better the comprehensive performance of the ith group of schemes.

[0151] Example

[0152] The scheme provides a method for enhancing the corrosion resistance of a bent bolt and evaluating the corrosion resistance based on multi-attribute target decision, and the specific operation process is as follows:

[0153] (1) Index weight calculation of multi-attribute target evaluation

[0154] i. Historical data collection and preprocessing

[0155] Through the collection and screening of the historical evaluation data of 6 typical anti-corrosion coatings in a certain engineering field, the performance score data of 10 effective samples of each coating formula are obtained, which are used to support the subsequent data analysis and modeling. The original data includes the following attributes: adhesion level by wiping method (1-5 levels), adhesion level by metallographic observation method (1-5 levels), adhesion level by physical assembly method (1-5 levels), corrosion resistance level by salt spray test (1-5 levels), and comprehensive anti-corrosion performance score (1-5 points). The corresponding data matrix is shown below.

[0156] Adhesion level matrix:

[0157]

[0158] Corrosion resistance level vector: [1 2 5 4 5 3]

[0160] Comprehensive performance score vector: [1.5 2.6 4.8 4.5 4.6 3.8]

[0162] The adhesion level matrix and the corrosion resistance level vector are normalized by the maximum and minimum values respectively, and the heterogeneous data is uniformly mapped to the interval [0, 1] to eliminate the dimensional difference. The normalized feature matrix and label vector are as follows:

[0163] Feature matrix:

[0164]

[0165] Label vector: [0.09 0.33 0.97 0.91 0.94 0.70]

[0167] ii. SVR model training and parameter optimization

[0168] Based on the normalized feature matrix and label vector, a "feature-label" data set is constructed for training the SVR model. Considering the small order of magnitude of the given samples, the RBF kernel function is selected to realize the nonlinear transformation of the feature space.

[0169] To obtain the optimal SVR model, the penalty factor C and the kernel function parameter g were taken as the optimization variables, and the grid search method was used to traverse different combinations of C and g. The candidate values of C were set to 10, and the candidate values of g were set to [0.01, 0.1, 1]. The data set was randomly divided into 5 mutually exclusive subsets by 5-fold cross-validation. Four subsets were selected as the training set, and the remaining one subset was selected as the validation set. The generalization performance of the model under each parameter combination was evaluated by the mean square error (MSE) to measure the prediction error on the validation set.

[0170] By comparing the average cross-validation error of different parameter combinations, the optimal parameters were determined as C = 10 and g = 0.1. Based on this parameter combination, the SVR model was retrained using all sample data to obtain the final evaluation model of the coating corrosion resistance.

[0171] iii. Evaluation index weight solving

[0172] The original weight vector of the input features was obtained by matrix multiplication operation from the trained SVR model and the corresponding Lagrange multipliers of all support vector samples. The original weight vector was normalized by maximum and minimum value to scale the weight components to the interval [0, 1]. The normalized weight vector was the relative importance measure of each evaluation index.

[0173] The normalized index weight vector is:

[0174] Wiping method weight: 0.16

[0175] Metallographic observation method weight: 0.21

[0176] Physical assembly method weight: 0.06

[0177] Corrosion resistance weight: 0.57

[0178] (2) Evaluation of corrosion-resistant coating performance of curved bolt based on multi-attribute weight

[0179] According to the test results of the above adhesion test and salt spray test, the multi-attribute objective decision TOPSIS method was used to comprehensively evaluate the final comprehensive corrosion resistance performance according to the following weight ratio.

[0180] Table 8 Weight ratio

[0181] Test method Wiping method Metallographic observation Physical assembly Salt spray corrosion Weight 0.16 0.21 0.06 0.57

Claims

1. A multi-attribute objective decision-making evaluation method for the design of enhanced corrosion resistance of bent bolts, characterized by: The evaluation method includes: Step 1: Prepare the bent bolts required for the test and evaluate and inspect the status of the bent bolts; Step 2: Only blackening treatment or Dacromet coating is performed on some bent bolts, and some bent bolts are first blackened and then Dacromet coating is performed; Step 3: Conduct adhesion performance test on the bent bolt coating treated in step 2, and then score and record the corresponding data based on the test results; Step 4: Conduct corrosion resistance test on the bent bolt coating treated in step 2, and then score and record the corresponding data based on the test results; Step 5: Score the comprehensive corrosion resistance of the bent bolt coating after treatment in step 2 and record the corresponding data; Step 6: Based on the support vector regression method, the data recorded in steps 3-5 are used to solve the weight of the evaluation index of each performance test in steps 3 and 4 that affects the evaluation of the coating's anti-corrosion performance to obtain an evaluation model; Step 7: Use the evaluation model to evaluate the enhanced corrosion resistance design of the bent bolts; The ratings are all on a five-level scale of 1-5; In step 6, the SVR algorithm is used to perform association modeling between the recorded data and its corresponding performance labels. The SVR model uses a Gaussian radial basis kernel function (RBF). Through a combination of grid search and cross-validation, different combinations of penalty factor C and kernel function parameter g are traversed. The generalization performance on the validation set is evaluated based on the mean square error (MSE) indicator, and the optimal parameter combination is determined for training and generating the SVR model. The data recorded in steps 3-5 include the following indicators: adhesion level x1 by wiping method, adhesion level x2 by metallographic observation method, adhesion level x3 by physical assembly method, and corrosion resistance level x4 by salt spray test, as well as the comprehensive corrosion resistance score y∈[1,5]. If the performance data of n coating samples are collected, the original "feature-label" data set is formed. D={(x1,y1),(x2,y2),L,(x n ,y n )} Where, xi=[x i1 ,x i2 ,x i3 ,x i4 ] T is the feature vector of the i-th sample, y i Provide a comprehensive performance score for it; The scoring results of each indicator are normalized and mapped to the interval [0,1] to eliminate the influence of different dimensions. Specifically, the maximum and minimum value normalization method is used to normalize the original feature matrix X = [x1, x2, ···, x n ] T ∈n×4 for conversion: After normalization, the preprocessed feature matrix X∈[0,1] is obtained n×4 ; Based on the preprocessed data set D={(x1',y1),(x2',y2),…,(x n ',y n )}, the SVR algorithm is used to build the model. SVR introduces the ε-insensitive loss function to seek an optimal regression hyperplane f(x)=w in the feature space. T φ(x)+b, so that the model output f(x i ) and the true label y i The error between them is controlled within ε, where w and b are model parameters, and φ(·) represents the transformation function that maps the original features to the high-dimensional space; The Gaussian radial basis kernel function (RBF)κ(x i ,x j )=exp(-γ‖x i -x j ‖ 2 ) is used as the kernel function of the SVR model, where γ>0 is the kernel function width parameter, and the slack variable ξ is introduced. i , The objective optimization problem of SVR is expressed as: s.t. f(x i )-y i ≤ε+ξ Among them, C>0 is the penalty coefficient, which is used to control the complexity of the model and the tolerance to outliers. By solving the dual form of the above convex quadratic programming problem, the optimal decision function of SVR is obtained: Where, α i , is a Lagrange multiplier satisfying To obtain the SVR model with the best generalization performance, the SVR model hyperparameters (C, γ) are tuned. A grid search method combined with K-fold cross-validation is used to traverse different (C, γ) combinations in the parameter space. The optimal parameter configuration is determined by minimizing the mean squared error (MSE) on the validation set to guide the training and generation of the SVR model. Extract all support vector samples (xs1, ys1), (xs2, ys2), L, (xsl, ysl) and their corresponding Lagrange multipliers from the trained SVR model Calculate the inner product of the support vector and the multiplier to obtain the original weight of the input feature β = [β1,β2,β3,β4] T : Perform maximum and minimum normalization on β to obtain the relative importance weight of each evaluation index: At this point, the weight vector w = [w1, w2, w3, w4] of the coating anti-corrosion performance evaluation index is obtained based on the SVR model. T , the scoring results of each index of the coating to be evaluated are x=[x1,x2,x3,x4] T The weighted sum of them with w is the comprehensive evaluation model for the design of enhanced corrosion resistance:

2. The evaluation method according to claim 1, wherein: The adhesion performance test includes a wiping method, a metallographic observation method and a physical assembly method.

3. The evaluation method according to claim 1, wherein: The corrosion resistance test includes a salt spray corrosion method.

4. The evaluation method according to claim 1, wherein: The Dacromet coating is divided into acidic conditions and alkaline conditions.

Images