Method, system and terminal for predicting chloride ion diffusion in cement-based materials based on fuzzy random algorithm

Abstract

The present invention discloses a method, system and terminal for predicting chloride ion diffusion in cement-based materials based on a fuzzy random algorithm. The present invention uses test data of similar materials to supplement limited test data of cement-based materials to determine the confidence interval of age coefficient and chloride ion diffusion coefficient, and then combines expert opinions in the field to express the average values ​​of age coefficient and chloride ion diffusion coefficient as fuzzy variables through fuzzy logic and construct a membership function, and then generates the distribution law of age coefficient and chloride ion diffusion coefficient by Monte Carlo sampling, and finally substitutes the diffusion formula of chloride ions to calculate the diffusion law and durability failure probability. The fuzzy random algorithm proposed by the present invention uses a numerical method to characterize approximate material test data and expert opinions in the field to break through the limitation of insufficient data, and realizes the prediction of chloride ion diffusion law in cement-based materials under sparse data.

Description

Technical Field

[0001] The present invention relates to the technical field of material performance prediction, and in particular to a method, system, terminal and computer-readable storage medium for predicting chloride ion diffusion in cement-based materials based on a fuzzy random algorithm. Background Art

[0002] The durability of reinforced concrete structures is affected by the chloride ion concentration. When the chloride ion concentration reaches the critical concentration, the steel bars in the concrete will rust and the components will begin to fail.

[0003] At present, the mainstream research methods for analyzing chloride ion diffusion in cement-based materials can be divided into three categories: experimental testing, numerical simulation and data-driven methods.

[0004] The test method mainly uses test instruments to directly observe the corrosion inside cement-based composite materials to give the durability of cement-based composites or indirectly test the chloride ion concentration, and then further analyze the durability of cement-based composites. Due to the long time spent on the durability test of cement-based composites and the diversity of composite material ratios, the test analysis method is difficult to adapt to the research needs of a large number of samples or different working conditions, resulting in a scarcity of durability data for cement-based composites.

[0005] The numerical simulation method predicts the performance of composite materials by combining test results with physical methods such as mathematics or mechanics to simulate the time-varying law of chloride ion diffusion in cement-based materials. When data is scarce, the prediction accuracy and reliability of numerical models are limited because the models require accurate material parameters and experimental data for calibration. Insufficient data will make it difficult for the model to capture the actual heterogeneity, microstructural characteristics and damage evolution behavior of the material, affecting the applicability of the model and the credibility of the results.

[0006] The principle of data-driven methods for predicting composite material performance is to use machine learning algorithms (such as neural networks, support vector machines, etc.) to train with a large amount of experimental data to automatically learn the complex nonlinear relationship of chloride ion diffusion in cement-based materials under different conditions. Insufficient data also limits the accuracy of data-driven models, leading to overfitting or underfitting, and reducing the reliability and generalization ability of predictions.

[0007] Therefore, the prior art still needs to be improved and developed. Summary of the invention

[0008] The main purpose of the present invention is to provide a method, system, terminal and computer-readable storage medium for predicting chloride ion diffusion in cement-based materials based on fuzzy random algorithm, aiming to solve the problem of insufficient data in analyzing the durability of composite materials in the prior art, resulting in low prediction accuracy of the durability of composite materials.

[0009] To achieve the above object, the present invention provides a method for predicting chloride ion diffusion in cement-based materials based on fuzzy random algorithm, and the method for predicting chloride ion diffusion in cement-based materials based on fuzzy random algorithm comprises the following steps:

[0010] Sampling cement-based materials and approximate cement-based materials to obtain the average values ​​of age coefficient and initial chloride ion diffusion coefficient, using the collected data to draw a histogram and determine the membership function of the collected data;

[0011] The membership functions of two fuzzy variables, the age coefficient and the average value of the initial chloride ion diffusion coefficient, are projected into the three-dimensional fuzzy space, and the three-dimensional fuzzy spaces of the age coefficient and the average value of the initial chloride ion diffusion coefficient of cement-based materials and approximate cement-based materials are obtained respectively;

[0012] Using α level discretization, the three-dimensional fuzzy space is approximately represented by several discontinuous subsets, and several two-dimensional sections of the age coefficient and the average value of the initial chloride ion diffusion coefficient corresponding to the α value are obtained, and random values ​​are taken on the two-dimensional sections for Monte Carlo random sampling;

[0013] Calculate the spatiotemporal distribution of chloride ion concentration in intact cement mortar and express it with a two-dimensional Gaussian probability density function, and calculate the cumulative density function of chloride ion concentration corresponding to the two-dimensional Gaussian probability density function;

[0014] The cumulative density function of chloride ion concentration is compared with the critical failure concentration to obtain the fuzzy probability of component failure, and the lower and upper limits of the corresponding time failure probability are obtained;

[0015] The horizontal rank method is used to obtain a defuzzified average value of the corresponding failure probability, wherein the defuzzified average value represents the probability of component failure at a set time according to the fuzzy random algorithm.

[0016] Optionally, the method for predicting chloride ion diffusion in cement-based materials based on fuzzy random algorithm, wherein the sampled cement-based materials and the approximate cement-based materials obtain the average value of the age coefficient and the initial chloride ion diffusion coefficient, and the collected data are used to draw a histogram to determine the membership function of the collected data, specifically includes:

[0017] The cement-based materials were sampled to obtain the average age coefficient and initial chloride ion diffusion coefficient, and the approximate cement-based materials were sampled to obtain the average age coefficient and initial chloride ion diffusion coefficient;

[0018] Draw a cement-based material histogram using the age coefficient of the cement-based material and the average value of the initial chloride ion diffusion coefficient, and draw an approximate cement-based material histogram using the age coefficient of the approximate cement-based material and the average value of the initial chloride ion diffusion coefficient;

[0019] According to the cement-based material histogram and the approximate cement-based material histogram, an age coefficient histogram, an age coefficient membership function, an initial chloride ion diffusion coefficient average value histogram and an initial chloride ion diffusion coefficient average value membership function are determined.

[0020] Optionally, in the method for predicting chloride ion diffusion in cement-based materials based on fuzzy random algorithm, the cement-based materials include intact cement mortar and intact ECC; and the approximate cement-based materials include cracked cement mortar and cracked ECC.

[0021] Optionally, the method for predicting chloride ion diffusion in cement-based materials based on fuzzy random algorithm, wherein the α level discretization is adopted, the three-dimensional fuzzy space is approximated by a number of discontinuous subsets, and a number of two-dimensional sections of the age coefficient and the average value of the initial chloride ion diffusion coefficient corresponding to the α value are obtained, and random values ​​are taken on the two-dimensional sections for Monte Carlo random sampling, specifically including:

[0022] By using α level discretization, the three-dimensional fuzzy space composed of the age coefficient and the average value of the initial chloride ion diffusion coefficient of the cement-based material and the approximate cement-based material is approximated by a number of α level subsets, and a number of two-dimensional sections of the age coefficient and the average value of the initial chloride ion diffusion coefficient corresponding to the α value are obtained;

[0023] Random sampling is performed on multiple two-dimensional α sections of intact cement mortar materials. Based on each sampling point, random sampling is performed using Monte Carlo to obtain multiple sampling points. , represents the age coefficient, represents the average value of initial chloride ion diffusion coefficient.

[0024] Optionally, the method for predicting chloride ion diffusion in cement-based materials based on fuzzy random algorithm, wherein the temporal and spatial distribution law of chloride ion concentration in intact cement mortar is calculated and represented by a two-dimensional Gaussian probability density function, and the cumulative density function of chloride ion concentration corresponding to the two-dimensional Gaussian probability density function is calculated, specifically includes:

[0025] The sampling point Substituting into formulas (1)-(5), the spatiotemporal distribution of chloride ion concentration in intact cement mortar is calculated and expressed by a two-dimensional Gaussian probability density function;

[0026] The relationship between the chloride ion concentration in the diffusion zone and time t and space:

[0027] ; (1)

[0028] in, Indicates the chloride ion concentration; Indicates the distance from the surface; Indicates time; Indicates the surface chloride ion concentration; represents the error function; Indicates the depth of the convection zone; It represents the chloride ion diffusion coefficient of cement-based materials;

[0029] ; (2)

[0030] in, represents the environment transfer variable; Represents transfer parameters; Indicates reference time;

[0031] Diffusion of chloride ions within the coating:

[0032] ; (3)

[0033] in, Indicates the chloride ion concentration in cement-based materials; Indicates the chloride ion concentration on the surface of cement-based materials; It represents the chloride ion diffusion coefficient of cement-based materials;

[0034] Diffusion of chloride ions in cement-based materials:

[0035] ; (4)

[0036] in, and Indicates the chloride ion concentration on the surface of cement-based materials; Indicates the thickness of cement-based materials;

[0037] Chloride ion concentration in cement-based materials:

[0038] ; (5)

[0039] in, Indicates the chloride ion concentration in cement-based materials; It represents the chloride ion diffusion coefficient of cement-based materials;

[0040] The Gaussian probability density function of chloride ion concentration at different times corresponding to each α value at the buried depth of steel bars in intact cement mortar was statistically analyzed, and the corresponding cumulative density function of chloride ion concentration was calculated. The Gaussian probability density function of chloride ion concentration at different times in intact ECC, cracked cement mortar and cracked ECC and the corresponding cumulative density function of chloride ion concentration were also calculated.

[0041] Optionally, the method for predicting chloride ion diffusion in cement-based materials based on fuzzy random algorithm, wherein the cumulative density function of the obtained chloride ion concentration is compared with the critical failure concentration to obtain the fuzzy probability of component failure, and obtain the lower limit and upper limit of the corresponding time failure probability, specifically includes:

[0042] The obtained chloride ion concentrations and critical failure concentrations of intact cement mortar, intact ECC, cracked cement mortar and cracked ECC at different times under multiple α values ​​were compared. Substitute into formula (6) to calculate the component failure fuzzy probability , and obtain the lower limit of the corresponding time failure probability and upper limit ;

[0043] ; (6)

[0044] Repeat the calculation to obtain the lower limit of the time failure probability corresponding to each α value and upper limit .

[0045] Optionally, the method for predicting chloride ion diffusion in cement-based materials based on fuzzy random algorithm, wherein the defuzzified average value of the corresponding failure probability is obtained by using the horizontal rank method, specifically includes:

[0046] Lower bounds on failure probabilities at multiple times and upper limit , use the horizontal rank method to obtain the defuzzified failure probability average , repeatedly calculate and obtain the defuzzified average value of the failure probability at different times ;

[0047] Horizontal rank method:

[0048] ; (7)

[0049] in, Indicates the number of α values;

[0050] Repeat the calculation to get the defuzzified average value of the failure probability at different times , the deblurred mean Represents the probability of component failure at time t according to the fuzzy random algorithm.

[0051] In addition, to achieve the above-mentioned purpose, the present invention also provides a chloride ion diffusion prediction system in cement-based materials based on fuzzy random algorithm, wherein the chloride ion diffusion prediction system in cement-based materials based on fuzzy random algorithm comprises:

[0052] A data sampling module is used to sample cement-based materials and approximate cement-based materials to obtain the average values ​​of age coefficients and initial chloride ion diffusion coefficients, draw a histogram using the collected data, and determine the membership function of the collected data;

[0053] A data projection module is used to project the membership functions of two fuzzy variables, namely, the age coefficient and the average value of the initial chloride ion diffusion coefficient, into a three-dimensional fuzzy space to obtain the three-dimensional fuzzy spaces of the age coefficient and the average value of the initial chloride ion diffusion coefficient of the cement-based material and the approximate cement-based material, respectively;

[0054] A data discretization module is used to discretize at the α level, approximate the three-dimensional fuzzy space with a number of discontinuous subsets, obtain a number of two-dimensional sections of the age coefficient and the average value of the initial chloride ion diffusion coefficient corresponding to the α value, and randomly select values ​​on the two-dimensional sections for Monte Carlo random sampling;

[0055] The concentration calculation module is used to calculate the spatiotemporal distribution of chloride ion concentration in intact cement mortar and express it with a two-dimensional Gaussian probability density function, and calculate the cumulative density function of chloride ion concentration corresponding to the two-dimensional Gaussian probability density function;

[0056] A probability calculation module is used to compare the obtained cumulative density function of chloride ion concentration with the critical failure concentration to obtain the fuzzy probability of component failure and obtain the lower limit and upper limit of the corresponding time failure probability;

[0057] The performance prediction module is used to obtain a defuzzified average value of a corresponding failure probability using a horizontal rank method, wherein the defuzzified average value represents the probability of component failure at a set time obtained according to a fuzzy random algorithm.

[0058] In addition, to achieve the above-mentioned purpose, the present invention also provides a terminal, wherein the terminal includes: a memory, a processor, and a chloride ion diffusion prediction program in cement-based materials based on a fuzzy random algorithm stored in the memory and run on the processor, wherein the chloride ion diffusion prediction program in cement-based materials based on a fuzzy random algorithm implements the steps of the chloride ion diffusion prediction method in cement-based materials based on a fuzzy random algorithm as described above when the chloride ion diffusion prediction program in cement-based materials based on a fuzzy random algorithm is executed by the processor.

[0059] In addition, to achieve the above-mentioned purpose, the present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a chloride ion diffusion prediction program in cement-based materials based on a fuzzy random algorithm, and when the chloride ion diffusion prediction program in cement-based materials based on a fuzzy random algorithm is executed by a processor, the steps of the chloride ion diffusion prediction method in cement-based materials based on a fuzzy random algorithm are implemented as described above.

[0060] In the present invention, cement-based materials and approximate cement-based materials are sampled to obtain the age coefficient and the average value of the initial chloride ion diffusion coefficient, and a histogram is drawn using the collected data to determine the membership function of the collected data; the membership function of the two fuzzy variables of the age coefficient and the average value of the initial chloride ion diffusion coefficient is projected into a three-dimensional fuzzy space to obtain the three-dimensional fuzzy space of the age coefficient and the average value of the initial chloride ion diffusion coefficient of the cement-based material and the approximate cement-based material respectively; the α level discretization is adopted to approximate the three-dimensional fuzzy space with a plurality of discontinuous subsets to obtain a plurality of age coefficients and the initial chloride ion diffusion coefficients corresponding to the α value. The coefficient average value is calculated in a two-dimensional section, and the Monte Carlo random sampling is performed on the two-dimensional section at random; the spatiotemporal distribution law of the chloride ion concentration in the intact cement mortar is calculated, and it is expressed by a two-dimensional Gaussian probability density function, and the cumulative density function of the chloride ion concentration corresponding to the two-dimensional Gaussian probability density function is calculated; the cumulative density function of the chloride ion concentration obtained is compared with the critical failure concentration to obtain the fuzzy probability of component failure, and the lower and upper limits of the corresponding time failure probability are obtained; the defuzzified average value of the corresponding failure probability is obtained using the horizontal rank method, and the defuzzified average value represents the probability of component failure at a set time obtained according to the fuzzy random algorithm. The present invention uses the test data of similar materials to supplement the limited test data of cement-based materials to determine the confidence interval of the age coefficient and the chloride ion diffusion coefficient, and then combines the expert opinions in the field to express the average values ​​of the age coefficient and the chloride ion diffusion coefficient as fuzzy variables through fuzzy logic and construct a membership function, and then generates the distribution law of the age coefficient and the chloride ion diffusion coefficient by Monte Carlo sampling, and finally substitutes the diffusion formula of chloride ions to calculate the diffusion law and the durability failure probability. The fuzzy random algorithm proposed in the present invention uses a numerical method to characterize approximate material test data and expert opinions in this field to break through the limitation of insufficient data and realize the prediction of chloride ion diffusion law in cement-based materials under sparse data. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 This is a schematic diagram of chloride ion corrosion of steel bars;

[0062] Figure 2 It is a flow chart of a preferred embodiment of the method for predicting chloride ion diffusion in cement-based materials based on fuzzy random algorithm of the present invention;

[0063] Figure 3 It is a schematic flow chart of a random fuzzy method in a preferred embodiment of the method for predicting chloride ion diffusion in cement-based materials based on a fuzzy random algorithm of the present invention;

[0064] Figure 4 It is an age coefficient histogram and a membership function diagram of a preferred embodiment of the method for predicting chloride ion diffusion in cement-based materials based on fuzzy random algorithm of the present invention;

[0065] Figure 5It is a histogram of the average value of the initial chloride ion diffusion coefficient and a membership function diagram in a preferred embodiment of the method for predicting chloride ion diffusion in cement-based materials based on fuzzy random algorithm of the present invention;

[0066] Figure 6 It is a schematic diagram of a two-dimensional fuzzy space of an age coefficient and an average value of an initial chloride ion diffusion coefficient in a preferred embodiment of the method for predicting chloride ion diffusion in cement-based materials based on a fuzzy random algorithm of the present invention;

[0067] Figure 7 It is a two-dimensional cross-sectional diagram of the average value of the aging coefficient and the initial chloride ion diffusion coefficient in a preferred embodiment of the method for predicting chloride ion diffusion in cement-based materials based on fuzzy random algorithm of the present invention;

[0068] Figure 8 It is a central diagram of the average value of the age coefficient and the initial chloride ion diffusion coefficient in a preferred embodiment of the method for predicting chloride ion diffusion in cement-based materials based on fuzzy random algorithm of the present invention;

[0069] Fig. 9 It is a Gaussian probability density function (PDF) diagram of a preferred embodiment of the method for predicting chloride ion diffusion in cement-based materials based on fuzzy random algorithm of the present invention;

[0070] Fig.10 It is a PDF graph corresponding to each α-level subset and a PDF graph at different times in a preferred embodiment of the method for predicting chloride ion diffusion in cement-based materials based on fuzzy random algorithm of the present invention;

[0071] Fig.11 It is a cumulative density function (CFD) diagram of a preferred embodiment of the method for predicting chloride ion diffusion in cement-based materials based on fuzzy random algorithm of the present invention;

[0072] Fig.12 It is a horizontal rank method diagram of all alpha levels in a preferred embodiment of the method for predicting chloride ion diffusion in cement-based materials based on fuzzy random algorithm of the present invention;

[0073] Fig.13 It is a probability density function diagram of chloride concentration in mortar coating in a preferred embodiment of the method for predicting chloride ion diffusion in cement-based materials based on fuzzy random algorithm of the present invention;

[0074] Fig.14 It is a cumulative density function diagram of chloride concentration in mortar coating in a preferred embodiment of the method for predicting chloride ion diffusion in cement-based materials based on fuzzy random algorithm of the present invention;

[0075] Fig.15 It is a 50-year fuzzy failure probability comparison diagram in a preferred embodiment of the method for predicting chloride ion diffusion in cement-based materials based on fuzzy random algorithm of the present invention;

[0076] Fig.16 It is a structural diagram of a preferred embodiment of the chloride ion diffusion prediction system in cement-based materials based on fuzzy random algorithm of the present invention;

[0077] Fig.17 It is a structural diagram of a preferred embodiment of the terminal of the present invention. DETAILED DESCRIPTION

[0078] In order to make the purpose, technical solution and advantages of the present invention clearer and more specific, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0079] like Figure 1 As shown, it represents a graph of chloride ion corrosion of steel bars. The durability of reinforced concrete structures is affected by the chloride ion concentration, and the diffusion of chloride ions in concrete is affected by the age coefficient and the chloride ion diffusion coefficient. Under the limitation of limited test data, the existing probability statistics method cannot express the distribution law of the age coefficient and the chloride ion diffusion coefficient of cement-based materials and the time-varying law of chloride ion diffusion. The fuzzy random algorithm proposed in the present invention uses a numerical method to characterize approximate material test data and expert opinions in this field to break through the limitation of insufficient data, and realizes the prediction of the chloride ion diffusion law in cement-based materials under sparse data, which is impossible with the existing technology.

[0080] The method for predicting chloride ion diffusion in cement-based materials based on fuzzy random algorithm described in the preferred embodiment of the present invention is as follows: Figure 2 and Figure 3 As shown, the method for predicting chloride ion diffusion in cement-based materials based on fuzzy random algorithm comprises the following steps:

[0081] Step S10: sampling cement-based materials and approximate cement-based materials to obtain the average values ​​of age coefficients and initial chloride ion diffusion coefficients, using the collected data to draw a histogram, and determining the membership function of the collected data.

[0082] Specifically, the cement-based materials include intact cement mortar and intact ECC (Engineered Cementitious Composites, ECC is a composite material with super toughness, composed of randomly distributed short fiber reinforced cement-based materials); the approximate cement-based materials include cracked cement mortar and cracked ECC; that is, the present invention predicts the time-varying law of chloride ion diffusion in four coatings (intact cement mortar, intact ECC, cracked cement mortar and cracked ECC) of prestressed box girders; the cement-based materials are sampled to obtain the age coefficient and the average value of the initial chloride ion diffusion coefficient, and the approximate cement-based materials are sampled to obtain the age coefficient and the average value of the initial chloride ion diffusion coefficient; the cement-based material histogram is drawn using the age coefficient and the average value of the initial chloride ion diffusion coefficient of the cement-based material, and the approximate cement-based material histogram is drawn using the age coefficient and the average value of the initial chloride ion diffusion coefficient of the approximate cement-based material; Figure 4 and Figure 5 As shown, based on the cement-based material histogram and the approximate cement-based material histogram, the age coefficient histogram, the age coefficient membership function, the initial chloride ion diffusion coefficient average value histogram and the initial chloride ion diffusion coefficient average value membership function are determined.

[0083] Regarding the value of the average initial chloride ion diffusion coefficient, the histograms of the four materials were compared horizontally and the existing scientific research knowledge was considered: intact ECC, intact cement mortar, cracked ECC, and cracked cement mortar increased in sequence, and the membership function of the average initial chloride ion diffusion coefficient of the four materials was determined.

[0084] Step S20, projecting the membership functions of the two fuzzy variables of the age coefficient and the average value of the initial chloride ion diffusion coefficient into the three-dimensional fuzzy space, and obtaining the three-dimensional fuzzy spaces of the age coefficient and the average value of the initial chloride ion diffusion coefficient of the cement-based material and the approximate cement-based material respectively.

[0085] Specifically, Figure 6 As shown in the figure, the membership functions of the two fuzzy variables of the age coefficient and the average value of the initial chloride ion diffusion coefficient are projected into the three-dimensional fuzzy space, and the fuzzy spaces of the age coefficient and the average value of the initial chloride ion diffusion coefficient of the four materials (i.e., intact ECC, intact cement mortar, cracked ECC, and cracked cement mortar) are obtained respectively.

[0086] Step S30, using α level discretization, the three-dimensional fuzzy space is approximately represented by several discontinuous subsets, and several two-dimensional sections of the age coefficient and the average value of the initial chloride ion diffusion coefficient corresponding to the α value are obtained, and random values ​​are taken on the two-dimensional sections for Monte Carlo random sampling.

[0087] Specifically, Figure 7As shown, the α level discretization is adopted, and the three-dimensional fuzzy space (three-dimensional continuous fuzzy space) composed of the age coefficient and the average value of the initial chloride ion diffusion coefficient of the cement-based material and the approximate cement-based material is respectively discretized with several α level subsets (for example, α=1, α=0.8, α=0.6, α=0.4 and α=0.2, α is Figure 7 In μ ) is approximated, that is, a number of two-dimensional cross-sections of the age coefficient and the average value of the initial chloride ion diffusion coefficient corresponding to the α value are obtained.

[0088] like Figure 8 As shown, multiple (e.g., 5) two-dimensional α sections of intact cement mortar materials are randomly sampled, for example, 100 points are obtained, the x coordinate is the average value of Dcl,0, the y coordinate is the age coefficient, and the z coordinate is the α value, a total of 500 points. Based on the x coordinate of each sampling point and the variance of 0.3, Monte Carlo is used for random sampling to obtain multiple sampling points , a total of 50,000 points, represents the age coefficient, represents the average value of initial chloride ion diffusion coefficient.

[0089] Step S40, calculating the spatiotemporal distribution law of chloride ion concentration in the intact cement mortar, and expressing it with a two-dimensional Gaussian probability density function, and calculating the cumulative density function of chloride ion concentration corresponding to the two-dimensional Gaussian probability density function.

[0090] Specifically, Fig. 9 As shown in Figure 2, 50,000 (Dcl,0,n) generated by the fuzzy-random algorithm are substituted into formulas (1)-(5) to calculate the spatiotemporal distribution of chloride ion concentration in intact cement mortar and express it with a two-dimensional Gaussian probability density function (PDF).

[0091] The relationship between the chloride ion concentration in the diffusion zone and time t and space:

[0092] ; (1)

[0093] in, Indicates the chloride ion concentration; Indicates the distance from the surface; Indicates time; Indicates the surface chloride ion concentration; represents the error function; Indicates the depth of the convection zone; It represents the chloride ion diffusion coefficient of cement-based materials;

[0094] ; (2)

[0095] in, represents the environment transfer variable; Represents transfer parameters; Indicates reference time;

[0096] Diffusion of chloride ions within the coating:

[0097] ; (3)

[0098] in, Indicates the chloride ion concentration in cement-based materials; Indicates the chloride ion concentration on the surface of cement-based materials; It represents the chloride ion diffusion coefficient of cement-based materials;

[0099] Diffusion of chloride ions in cement-based materials:

[0100] ; (4)

[0101] in, and Indicates the chloride ion concentration on the surface of cement-based materials; Indicates the thickness of cement-based materials;

[0102] Chloride ion concentration in cement-based materials:

[0103] ; (5)

[0104] in, Indicates the chloride ion concentration in cement-based materials; It represents the chloride ion diffusion coefficient of cement-based materials;

[0105] like Fig.10 As shown in the figure, the Gaussian probability density function of chloride ion concentration for unused time (e.g. 10 years, 20 years, 30 years, 40 years and 50 years) corresponding to each α value at the buried depth of steel bars in intact cement mortar is statistically analyzed, and the corresponding cumulative density function (PDF) of chloride ion concentration is calculated. The Gaussian probability density function of chloride ion concentration for unused time (e.g. 10 years, 20 years, 30 years, 40 years and 50 years) of intact ECC, cracked cement mortar and cracked ECC and the corresponding cumulative density function (CDF, ​​Cumulative Density Function) of chloride ion concentration are also calculated.

[0106] Step S50: Use the horizontal rank method to obtain a defuzzified average value of the corresponding fault probability, wherein the defuzzified average value represents the probability of component failure at a set time obtained according to the fuzzy random algorithm.

[0107] Specifically, Fig.11As shown, multiple (100) chloride ion concentrations of intact cement mortar, intact ECC, cracked cement mortar and cracked ECC at different times (e.g., 10 years, 20 years, 30 years, 40 years and 50 years) were obtained and compared with the critical failure concentration Substitute into formula (6) to calculate the component failure fuzzy probability , and obtain the lower limit of the corresponding time failure probability and upper limit ;

[0108] ; (6)

[0109] Repeat the calculation to obtain the lower limit of the time failure probability corresponding to each α value and upper limit .

[0110] Step S60: Use the horizontal rank method to obtain a defuzzified average value of the corresponding fault probability, wherein the defuzzified average value represents the probability of component failure at a set time obtained according to the fuzzy random algorithm.

[0111] Specifically, Fig.12 As shown, the lower bound of the failure probability based on multiple (100) time and upper limit , use the horizontal rank method to obtain the defuzzified failure probability average , repeatedly calculate and obtain the defuzzified average value of the failure probability at different times ;

[0112] Horizontal rank method:

[0113] ; (7)

[0114] in, Indicates the number of α values;

[0115] Repeat the calculation to get the defuzzified average value of the failure probability at different times , the deblurred mean Represents the probability of component failure at time t according to the fuzzy random algorithm.

[0116] Based on the cumulative density function of chloride ion concentration at different times, repeated calculations can be performed to obtain the durability life probability of cement-based materials under chloride ion diffusion within the entire service life.

[0117] like Fig.13 As shown in the figure, the probability density function diagram of the chloride concentration in the mortar coating is as follows: Fig.14 As shown, the cumulative density function diagram of the chloride concentration in the mortar coating is shown in Fig.15 As shown, it is a comparison chart of 50-year fuzzy failure probability.

[0118] The present invention uses test data of similar materials to supplement limited test data of cement-based materials to determine the confidence interval of the age coefficient and the chloride ion diffusion coefficient, and then combines the opinions of experts in the field to express the average values ​​of the age coefficient and the chloride ion diffusion coefficient as fuzzy variables through fuzzy logic and construct a membership function, and then uses Monte Carlo sampling to generate the distribution law of the age coefficient and the chloride ion diffusion coefficient, and finally substitutes them into the diffusion formula of chloride ions to calculate the diffusion law and durability failure probability.

[0119] Furthermore, if Fig.16 As shown, based on the above-mentioned method for predicting chloride ion diffusion in cement-based materials based on fuzzy random algorithm, the present invention also provides a system for predicting chloride ion diffusion in cement-based materials based on fuzzy random algorithm, wherein the system for predicting chloride ion diffusion in cement-based materials based on fuzzy random algorithm comprises:

[0120] A data sampling module 51 is used to sample cement-based materials and approximate cement-based materials to obtain an age coefficient and an average value of an initial chloride ion diffusion coefficient, draw a histogram using the collected data, and determine a membership function of the collected data;

[0121] A data projection module 52 is used to project the membership functions of two fuzzy variables, namely, the age coefficient and the average value of the initial chloride ion diffusion coefficient, into a three-dimensional fuzzy space to obtain the three-dimensional fuzzy spaces of the age coefficient and the average value of the initial chloride ion diffusion coefficient of the cement-based material and the approximate cement-based material, respectively;

[0122] The data discretization module 53 is used to discretize the three-dimensional fuzzy space with a plurality of discontinuous subsets respectively by using the α level, obtain a plurality of two-dimensional sections of the age coefficient and the average value of the initial chloride ion diffusion coefficient corresponding to the α value, and randomly select values ​​on the two-dimensional sections for Monte Carlo random sampling;

[0123] The concentration calculation module 54 is used to calculate the spatiotemporal distribution law of chloride ion concentration in the intact cement mortar, and express it with a two-dimensional Gaussian probability density function, and calculate the cumulative density function of the chloride ion concentration corresponding to the two-dimensional Gaussian probability density function;

[0124] The probability calculation module 55 is used to compare the obtained cumulative density function of chloride ion concentration with the critical failure concentration to obtain the fuzzy probability of component failure and obtain the lower limit and upper limit of the corresponding time failure probability;

[0125] The performance prediction module 56 is used to obtain a defuzzified average value of a corresponding failure probability using a horizontal rank method, wherein the defuzzified average value represents the probability of component failure at a set time obtained according to a fuzzy random algorithm.

[0126] Furthermore, if Fig.17As shown, based on the above-mentioned method and system for predicting chloride ion diffusion in cement-based materials based on fuzzy random algorithm, the present invention also provides a terminal accordingly, and the terminal includes a processor 10, a memory 20 and a display 30. Fig.17 Only some components of the terminal are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0127] In some embodiments, the memory 20 may be an internal storage unit of the terminal, such as a hard disk or memory of the terminal. In other embodiments, the memory 20 may also be an external storage device of the terminal, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the terminal. Further, the memory 20 may also include both an internal storage unit of the terminal and an external storage device. The memory 20 is used to store application software and various types of data installed in the terminal, such as the program code of the installation terminal, etc. The memory 20 may also be used to temporarily store data that has been output or is to be output. In one embodiment, a chloride ion diffusion prediction program 40 in cement-based materials based on a fuzzy random algorithm is stored on the memory 20, and the chloride ion diffusion prediction program 40 in cement-based materials based on a fuzzy random algorithm can be executed by the processor 10, thereby realizing the chloride ion diffusion prediction method in cement-based materials based on a fuzzy random algorithm in the present application.

[0128] In some embodiments, the processor 10 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run the program code or process data stored in the memory 20, such as executing the method for predicting chloride ion diffusion in cement-based materials based on fuzzy random algorithm.

[0129] In some embodiments, the display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 30 is used to display information on the terminal and to display a visual user interface. The processor 10, the memory 20, and the display 30 of the terminal communicate with each other via a system bus.

[0130] In one embodiment, when the processor 10 executes the chloride ion diffusion prediction program 40 in the memory 20 based on the fuzzy random algorithm in cement-based materials, the steps of the above method for predicting chloride ion diffusion in cement-based materials based on the fuzzy random algorithm are implemented.

[0131] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a chloride ion diffusion prediction program in cement-based materials based on a fuzzy random algorithm, and when the chloride ion diffusion prediction program in cement-based materials based on a fuzzy random algorithm is executed by a processor, the steps of the chloride ion diffusion prediction method in cement-based materials based on a fuzzy random algorithm are implemented as described above.

[0132] In summary, the present invention provides a method, system, terminal and computer-readable storage medium for predicting chloride ion diffusion in cement-based materials based on fuzzy random algorithm, the method comprising: projecting the membership function of collected data into a two-dimensional fuzzy space to obtain a two-dimensional fuzzy space; using α level discretization, numerically representing the two-dimensional fuzzy space with several α level subsets respectively, obtaining several two-dimensional sections of the age coefficient and the average value of the initial chloride ion diffusion coefficient corresponding to the α value, and randomly taking values ​​on the two-dimensional section for Monte Carlo simulation; calculating the chloride concentration and representing it with a two-dimensional Gaussian probability density function, calculating the cumulative density function of the chloride ion concentration corresponding to the two-dimensional Gaussian probability density function; calculating according to the chloride ion concentration and the critical chloride ion concentration in the concrete, obtaining the fuzzy probability of component failure, and obtaining the lower limit and upper limit of the corresponding time failure probability; using the horizontal rank method to obtain the defuzzified average value of the corresponding failure probability, the defuzzified average value represents the probability of component failure at a set time obtained according to the fuzzy random algorithm. The present invention uses the test data of similar materials to supplement the limited test data of cement-based materials to determine the confidence interval of the age coefficient and the chloride ion diffusion coefficient, and then combines the expert opinions in the field to express the average values ​​of the age coefficient and the chloride ion diffusion coefficient as fuzzy variables through fuzzy logic and construct a membership function, and then generates the distribution law of the age coefficient and the chloride ion diffusion coefficient by Monte Carlo sampling, and finally substitutes the diffusion formula of chloride ions to calculate the diffusion law and durability failure probability. The fuzzy random algorithm proposed by the present invention uses a numerical method to characterize the approximate material test data and the expert opinions in the field to break through the limitation of insufficient data, and realizes the prediction of the chloride ion diffusion law in cement-based materials under sparse data.

[0133] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or terminal including the element.

[0134] Of course, those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the program can be stored in a computer-readable storage medium that can be read by a computer, and the program can include the processes of the above-mentioned method embodiments when executed. The computer-readable storage medium can be a memory, a disk, an optical disk, etc.

[0135] It should be understood that the application of the present invention is not limited to the above examples. For ordinary technicians in this field, improvements or changes can be made based on the above description. All these improvements and changes should fall within the scope of protection of the claims attached to the present invention.

Claims

1. A method for predicting chloride ion diffusion in cement-based materials based on fuzzy random algorithm, characterized in that: The method for predicting chloride ion diffusion in cement-based materials based on fuzzy random algorithm comprises: Sampling cement-based materials and approximate cement-based materials to obtain the average values ​​of age coefficient and initial chloride ion diffusion coefficient, using the collected data to draw a histogram and determine the membership function of the collected data; The membership functions of two fuzzy variables, the age coefficient and the average value of the initial chloride ion diffusion coefficient, are projected into the three-dimensional fuzzy space, and the three-dimensional fuzzy spaces of the age coefficient and the average value of the initial chloride ion diffusion coefficient of cement-based materials and approximate cement-based materials are obtained respectively; Using α level discretization, the three-dimensional fuzzy space is approximately represented by several discontinuous subsets, and several two-dimensional sections of the age coefficient and the average value of the initial chloride ion diffusion coefficient corresponding to the α value are obtained, and random values ​​are taken on the two-dimensional sections for Monte Carlo random sampling; Calculate the spatiotemporal distribution of chloride ion concentration in intact cement mortar and express it with a two-dimensional Gaussian probability density function, and calculate the cumulative density function of chloride ion concentration corresponding to the two-dimensional Gaussian probability density function; The cumulative density function of chloride ion concentration is compared with the critical failure concentration to obtain the fuzzy probability of component failure, and the lower and upper limits of the corresponding time failure probability are obtained; Using the horizontal rank method to obtain a defuzzified average value of the corresponding failure probability, the defuzzified average value represents the probability of component failure at a set time obtained according to the fuzzy random algorithm; The α level discretization is adopted to approximate the three-dimensional fuzzy space with several discontinuous subsets, to obtain several two-dimensional sections of the age coefficient and the average value of the initial chloride ion diffusion coefficient corresponding to the α value, and to perform Monte Carlo random sampling by randomly taking values ​​on the two-dimensional sections, specifically including: By using α level discretization, the three-dimensional fuzzy space composed of the age coefficient and the average value of the initial chloride ion diffusion coefficient of the cement-based material and the approximate cement-based material is approximated by a number of α level subsets, and a number of two-dimensional sections of the age coefficient and the average value of the initial chloride ion diffusion coefficient corresponding to the α value are obtained; Random sampling is performed on multiple two-dimensional α sections of intact cement mortar materials. Based on each sampling point, random sampling is performed using Monte Carlo to obtain multiple sampling points. , represents the age coefficient, represents the average value of the initial chloride ion diffusion coefficient; The calculating of the spatiotemporal distribution law of chloride ion concentration in the intact cement mortar and expressing it with a two-dimensional Gaussian probability density function, and calculating the cumulative density function of chloride ion concentration corresponding to the two-dimensional Gaussian probability density function, specifically includes: The sampling point Substituting into formulas (1)-(5), the spatiotemporal distribution of chloride ion concentration in intact cement mortar is calculated and expressed by a two-dimensional Gaussian probability density function; The relationship between the chloride ion concentration in the diffusion zone and time t and space: ；（1） in, represents the chloride ion concentration in the diffusion zone; Indicates the distance from the surface; Indicates time; represents the surface chloride ion concentration in the diffusion zone; represents the error function; Indicates the depth of the convection zone; It represents the chloride ion diffusion coefficient of cement-based materials in the diffusion zone; ；（2） in, represents the environment transfer variable; Represents transfer parameters; Indicates reference time; Diffusion of chloride ions within the coating: ；（3） in, Indicates the chloride ion concentration in cement-based material coating; Indicates the chloride ion concentration on the surface of cement-based materials in the coating; Indicates the chloride ion diffusion coefficient of cement-based materials in the coating; Diffusion of chloride ions in cement-based materials: ；（4） in, and Indicates the chloride ion concentration on the surface of cement-based materials; Indicates the thickness of cement-based materials; Chloride ion concentration in cement-based materials: ；（5） in, Indicates the chloride ion concentration in cement-based materials; It represents the chloride ion diffusion coefficient of cement-based materials; The Gaussian probability density function of chloride ion concentration at different times corresponding to each α value at the buried depth of steel bars in intact cement mortar was statistically analyzed, and the corresponding cumulative density function of chloride ion concentration was calculated. The Gaussian probability density function of chloride ion concentration at different times of intact ECC, cracked cement mortar and cracked ECC and the corresponding cumulative density function of chloride ion concentration were also calculated.

2. The method for predicting chloride ion diffusion in cement-based materials based on fuzzy random algorithm according to claim 1 is characterized in that: The sampling of cement-based materials and approximate cement-based materials to obtain the average value of the age coefficient and the initial chloride ion diffusion coefficient, using the collected data to draw a histogram, and determining the membership function of the collected data, specifically includes: The cement-based materials were sampled to obtain the average age coefficient and initial chloride ion diffusion coefficient, and the approximate cement-based materials were sampled to obtain the average age coefficient and initial chloride ion diffusion coefficient; Draw a cement-based material histogram using the age coefficient of the cement-based material and the average value of the initial chloride ion diffusion coefficient, and draw an approximate cement-based material histogram using the age coefficient of the approximate cement-based material and the average value of the initial chloride ion diffusion coefficient; According to the cement-based material histogram and the approximate cement-based material histogram, an age coefficient histogram, an age coefficient membership function, an initial chloride ion diffusion coefficient average value histogram and an initial chloride ion diffusion coefficient average value membership function are determined.

3. The method for predicting chloride ion diffusion in cement-based materials based on fuzzy random algorithm according to claim 2 is characterized in that: The cement-based materials include intact cement mortar and intact ECC; the approximate cement-based materials include cracked cement mortar and cracked ECC.

4. The method for predicting chloride ion diffusion in cement-based materials based on fuzzy random algorithm according to claim 1, characterized in that: The cumulative density function of the chloride ion concentration obtained is compared with the critical failure concentration to obtain the fuzzy probability of component failure, and the lower limit and upper limit of the corresponding time failure probability are obtained, specifically including: The obtained chloride ion concentrations and critical failure concentrations of intact cement mortar, intact ECC, cracked cement mortar and cracked ECC at different times under multiple α values ​​were compared. Substitute into formula (6) to calculate the component failure fuzzy probability , and obtain the lower limit of the corresponding time failure probability and upper limit ; ；（6） Repeat the calculation to obtain the lower limit of the time failure probability corresponding to each α value and upper limit .

5. The method for predicting chloride ion diffusion in cement-based materials based on fuzzy random algorithm according to claim 4 is characterized in that: The method of using the horizontal rank method to obtain the defuzzified average value of the corresponding fault probability specifically includes: Lower bounds on failure probabilities at multiple times and upper limit , use the horizontal rank method to obtain the defuzzified failure probability average , repeatedly calculate and obtain the defuzzified average value of the failure probability at different times ; Horizontal rank method: ；（7） in, Indicates the number of α values; Repeat the calculation to get the defuzzified average value of the failure probability at different times , the deblurred mean Represents the probability of component failure at time t according to the fuzzy random algorithm.

6. A chloride ion diffusion prediction system in cement-based materials based on fuzzy random algorithm, characterized in that: The chloride ion diffusion prediction system in cement-based materials based on fuzzy random algorithm is applied to the chloride ion diffusion prediction method in cement-based materials based on fuzzy random algorithm according to any one of claims 1 to 5, and the chloride ion diffusion prediction system in cement-based materials based on fuzzy random algorithm comprises: A data sampling module is used to sample cement-based materials and approximate cement-based materials to obtain the average values ​​of age coefficients and initial chloride ion diffusion coefficients, draw a histogram using the collected data, and determine the membership function of the collected data; A data projection module is used to project the membership functions of two fuzzy variables, namely, the age coefficient and the average value of the initial chloride ion diffusion coefficient, into a three-dimensional fuzzy space to obtain the three-dimensional fuzzy spaces of the age coefficient and the average value of the initial chloride ion diffusion coefficient of the cement-based material and the approximate cement-based material respectively; A data discretization module is used to discretize at the α level, approximate the three-dimensional fuzzy space with a number of discontinuous subsets, obtain a number of two-dimensional sections of the age coefficient and the average value of the initial chloride ion diffusion coefficient corresponding to the α value, and randomly select values ​​on the two-dimensional sections for Monte Carlo random sampling; The concentration calculation module is used to calculate the spatiotemporal distribution of chloride ion concentration in intact cement mortar and express it with a two-dimensional Gaussian probability density function, and calculate the cumulative density function of chloride ion concentration corresponding to the two-dimensional Gaussian probability density function; A probability calculation module is used to compare the obtained cumulative density function of chloride ion concentration with the critical failure concentration to obtain the fuzzy probability of component failure and obtain the lower limit and upper limit of the corresponding time failure probability; The performance prediction module is used to obtain a defuzzified average value of a corresponding failure probability using a horizontal rank method, wherein the defuzzified average value represents the probability of component failure at a set time obtained according to a fuzzy random algorithm.

7. A terminal, characterized in that: The terminal includes: a memory, a processor, and a chloride ion diffusion prediction program in cement-based materials based on a fuzzy random algorithm stored in the memory and executable on the processor. When the chloride ion diffusion prediction program in cement-based materials based on a fuzzy random algorithm is executed by the processor, the steps of the chloride ion diffusion prediction method in cement-based materials based on a fuzzy random algorithm as described in any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a chloride ion diffusion prediction program in cement-based materials based on a fuzzy random algorithm. When the chloride ion diffusion prediction program in cement-based materials based on a fuzzy random algorithm is executed by a processor, the steps of the chloride ion diffusion prediction method in cement-based materials based on a fuzzy random algorithm as described in any one of claims 1 to 5 are implemented.

Images