Method, device and equipment for predicting shear strength of concrete interface and storage medium

Abstract

The application is suitable for the technical field of structural design, and provides a concrete interface shear strength prediction method, device, equipment and storage medium. The method comprises the following steps: obtaining the shear strength and concrete parameters of a concrete interface; establishing an initial LightGBM model, denoted as a first model, and preprocessing the shear strength and concrete parameters to obtain a training set and a test set; optimizing the hyperparameters of the first model based on a collaborative group optimization algorithm and a genetic algorithm to obtain a target hyperparameter set; applying the target hyperparameter set to the first model to obtain a second model, and training the second model based on the training set and the test set to obtain a shear strength prediction model; and inputting the concrete parameters of a target concrete interface into the shear strength prediction model to obtain a shear strength prediction value of the target concrete interface. The application can accurately predict the shear strength of the concrete interface under complex working conditions.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of structural design, and particularly relates to a concrete interface shear strength prediction method, device, equipment and storage medium. BACKGROUND

[0002] With the wide application of prefabricated buildings, bridges and other structures, and the reinforcement and reconstruction of existing buildings, the shear strength prediction problem of new and old concrete interfaces has become an important issue in the field of civil engineering. Existing prediction methods usually rely on empirical formulas or simplified theoretical models, but due to the complexity of the working conditions and the nonlinear relationship between multiple parameters, the accuracy of existing methods is often limited. In recent years, the development of machine learning technology has provided new possibilities for solving this problem. Machine learning can automatically learn complex nonlinear relationships from a large amount of data, and can more effectively handle multiple parameters and complex working conditions, and has been widely used in the field of civil engineering.

[0003] Among various machine learning models, LightGBM (Light Gradient Boosting Machine) has become a powerful tool for predicting the shear strength of new and old concrete interfaces due to its efficient learning mechanism and excellent generalization ability. LightGBM can capture nonlinear features in data through the combination of multiple weak decision trees, and exhibits high prediction accuracy in regression problems. However, the hyperparameters of the LightGBM model have a significant impact on the prediction performance, and if the hyperparameters are not properly selected, the model performance may decrease. Although common grid search and random search methods can optimize hyperparameters to some extent, they have low efficiency and large computational overhead, and cannot fully adapt to the optimization needs of multiple parameters in complex engineering problems. Therefore, traditional methods have many limitations in complex working conditions and nonlinear relationships between multiple parameters. SUMMARY

[0004] The application embodiments provide a concrete interface shear strength prediction method, device, equipment and storage medium to improve the prediction performance of the LightGBM model in predicting shear strength, and can accurately predict the shear strength of the concrete interface under complex working conditions.

[0005] The application is implemented by the following technical solutions:

[0006] In a first aspect, the application embodiments provide a concrete interface shear strength prediction method, comprising:

[0007] Obtaining the shear strength of the concrete interface and the concrete parameters.

[0008] An initial LightGBM model is established, denoted as a first model, and the anti-shear strength and concrete parameters are preprocessed to obtain a training set and a test set.

[0009] Based on the cooperative swarm optimization algorithm and the genetic algorithm, the hyperparameters of the first model are optimized to obtain a target hyperparameter set; the target hyperparameter set is applied to the first model to obtain a second model, and the second model is trained based on the training set and the test set to obtain an anti-shear strength prediction model.

[0010] The concrete parameters of the target concrete interface are input into the anti-shear strength prediction model to obtain the predicted value of the anti-shear strength of the target concrete interface.

[0011] In combination with the first aspect, in some possible implementations, based on the cooperative swarm optimization algorithm and the genetic algorithm, the hyperparameters of the first model are optimized to obtain a target hyperparameter set, including:

[0012] The parameters of the cooperative swarm optimization algorithm, the parameters of the genetic algorithm, and the population parameters are initialized, and the number of hyperparameters of the first model and the upper and lower boundaries are obtained; wherein the fitness function of the cooperative swarm optimization algorithm is the negative mean square error of the first model on the training set.

[0013] Based on the number of hyperparameters of the first model and the upper and lower boundaries, the initial particle positions in the cooperative swarm optimization algorithm are determined to obtain an initial population.

[0014] For each iteration of the population, the particles in the population are iterated based on the cooperative swarm optimization algorithm to obtain updated particles.

[0015] Based on the fitness value of the optimal particle in the updated particles, the selection probability of the genetic algorithm is determined.

[0016] Based on the selection probability, the parent particles of the genetic algorithm are determined.

[0017] The parent particles are iterated based on the genetic algorithm to obtain child particles.

[0018] The child particles and the updated particles are combined to form a new population, denoted as a first population.

[0019] The particles in the first population are sorted according to the fitness values, and a preset number of particles are selected as a second population.

[0020] The global best position is updated according to the particle with the smallest fitness value in the second population, and when the current iteration number does not reach a maximum iteration number, the second population is used as the population for the next iteration.

[0021] After the current iteration number reaches the maximum iteration number, the iteration is stopped, and the global best position at this time is taken as the target hyperparameter set.

[0022] In some possible implementation ways, based on the fitness value of the optimal particle in the updated particles, the selection probability of the genetic algorithm is determined, including:

[0023] The selection probability of the genetic algorithm is determined based on the fitness value of the optimal particle in the updated particles and the first formula.

[0024] The first formula is:

[0025]

[0026] wherein, Pi represents the selection probability, N represents the number of particles, f j represents the fitness value of the particle j, and f represents the fitness value of the optimal particle.

[0027] In some possible implementation ways, the parameters of the cooperative swarm optimization algorithm, the parameters of the genetic algorithm and the population parameters are initialized, including:

[0028] The particle velocity, the personal best position, the personal best fitness value, the global best position, the global best fitness value, the population size, the maximum number of iterations, the initial inertia weight, the inertia weight reduction rate, the acceleration coefficient, the crossover probability and the mutation probability are initialized.

[0029] In some possible implementation ways, the second model is trained based on the training set and the test set, and an anti-shear strength prediction model is obtained, including:

[0030] The second model is trained based on the training set, and a trained model is obtained.

[0031] The accuracy of the trained model is verified based on the test set, the mean square error and the mean absolute error.

[0032] If the accuracy of the trained model meets a preset condition, the trained model is taken as the anti-shear strength prediction model.

[0033] In some possible implementation ways, the anti-shear strength and the concrete parameters are preprocessed to obtain the training set and the test set, including:

[0034] It is judged whether there is missing data in the anti-shear strength and the concrete parameters.

[0035] The missing data is completed based on the K-nearest neighbor algorithm.

[0036] Based on the first model, the importance scores of various types of concrete parameters in the completed concrete parameters are calculated.

[0037] The importance score of each type of concrete parameter is scored, if the importance score is greater than a preset threshold, the data of the type of concrete parameter is retained, if the importance score is less than or equal to the preset threshold, the data of the type of concrete parameter is deleted, and a completed data set is obtained.

[0038] The completed data set is divided into a training set and a test set according to a preset ratio.

[0039] In combination with the first aspect, in some possible implementation manners, based on the first model, the importance score of each type of concrete parameter in the completed concrete parameter is calculated, including:

[0040] Based on the first model, the importance score of each type of concrete parameter in the completed concrete parameter is calculated in combination with the second formula.

[0041] The second formula is:

[0042]

[0043] wherein, I j represents the importance score of the j type of concrete parameter, T represents the total number of decision trees in the first model, S t,j represents a set of all split nodes using the j type of concrete parameter in the decision tree t, Gain S represents the information gain of the node s.

[0044] In the second aspect, the embodiments of the present application provide a concrete interface shear strength prediction device, including:

[0045] The data acquisition module is configured to acquire the shear strength of the concrete interface and the concrete parameters.

[0046] The data processing module is configured to establish an initial LightGBM model, denoted as a first model, and preprocess the shear strength and the concrete parameters to obtain a training set and a test set.

[0047] The first modeling module is configured to optimize hyperparameters of the first model based on a cooperative swarm optimization algorithm and a genetic algorithm to obtain a target hyperparameter set, apply the target hyperparameter set to the first model to obtain a second model, and train the second model based on the training set and the test set to obtain a shear strength prediction model.

[0048] The result prediction module is configured to input the concrete parameters of the target concrete interface into the shear strength prediction model to obtain a shear strength prediction value of the target concrete interface.

[0049] In a third aspect, an embodiment of the present application provides a terminal device, comprising a processor and a memory, the memory being configured to store a computer program, and the processor being configured to execute the computer program to implement the method for predicting the shear strength of the concrete interface according to any one of the first aspect.

[0050] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, the computer readable storage medium storing a computer program, and the computer program being configured to be executed by a processor to implement the method for predicting the shear strength of the concrete interface according to any one of the first aspect.

[0051] It can be understood that the beneficial effects of the second aspect to the fourth aspect described above can be referred to the related description in the first aspect, and will not be repeated here.

[0052] Compared with the prior art, the embodiment of the present application has the following beneficial effects:

[0053] The present application uses the Social Spider Optimization Algorithm (SSOA) for global search. The SSOA can efficiently explore a wide range of parameter spaces and find a preliminary high-quality hyperparameter combination by simulating group cooperation and information exchange between individuals. Subsequently, the Genetic Algorithm (GA) takes over the solution obtained by the SSOA, further optimizes the hyperparameters through crossover and mutation operations, enhances the diversity of the population, and promotes more comprehensive solution space exploration. The hybrid optimization strategy combining the SSOA and the GA not only speeds up the convergence speed of hyperparameter optimization and significantly shortens the model training time, but also effectively avoids the problem of single optimization algorithm falling into local optimum, improves the prediction performance of the LightGBM model, and ensures accurate prediction of the shear strength of the concrete interface under complex working conditions.

[0054] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and cannot limit the present specification. BRIEF DESCRIPTION OF DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0056] Figure 1 is a flowchart of the method for predicting the shear strength of the concrete interface provided by an embodiment of the present application;

[0057] Figure 2 is a structural schematic diagram of a concrete interface shear strength prediction device provided by an embodiment of the present application.

[0058] Figure 3 is a structural schematic diagram of a terminal device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0059] In the following description, for the purposes of explanation and not limitation, specific details are set forth, such as particular system configurations, techniques, etc., in order to provide a thorough understanding of the embodiments of the application. However, it will be apparent to those skilled in the art that the present application can be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known methods, devices, circuits, and

[0060] It should be understood that the term "comprises" when used in this specification and the appended claims, specifies the presence of stated features, integers, steps, operations, elements, and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0061] It should also be understood that the term "and / or" when used in this specification and the appended claims, means any one or more of the associated listed items can be present, and includes multiples of any item, and permutations of those multiples.

[0062] As used in this specification and the appended claims, the term "if" can be interpreted as meaning "when," or "once," or "in response to determining," or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [a described condition or event] is detected" can be interpreted to mean "once it is determined," or "in response to determining," or "once [the described condition or event] is detected," or "in response to detecting [the described condition or event]," depending on the context.

[0063] In addition, in the description of the specification and the appended claims, the terms "first," "second," "third," etc. are used merely to distinguish descriptions, and cannot be understood as indicating or implying relative importance.

[0064] Reference within the specification of this application to "one embodiment" or "some embodiments" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the application. The appearances of the phrase "in one embodiment" or "in some embodiments" in various places within specified

[0065] The embodiment of the application provides a method for predicting the shear strength of a concrete interface, Figure 1 is a flowchart of a method for predicting the shear strength of a concrete interface provided by an embodiment of the application, with reference to Figure 1 The details of the method for predicting the shear strength of the concrete interface are as follows:

[0066] Step 101: Obtain the shear strength of the concrete interface and concrete parameters.

[0067] Specifically, the concrete parameters can include the compressive strength of the first poured concrete, the compressive strength of the second poured concrete, the material type of the second poured concrete, the length along the shear surface, the area of the shear surface, the interface treatment method, the interface roughness, the interface stress, the rebar rate, the rebar depth, the rebar yield strength, and the rebar diameter.

[0068] Step 102: Establish an initial LightGBM model, denoted as a first model, and preprocess the shear strength and the concrete parameters to obtain a training set and a test set.

[0069] Illustratively, the preprocessing of the shear strength and the concrete parameters to obtain the training set and the test set can include:

[0070] Determine the missing data in the shear strength and the concrete parameters.

[0071] Complete the missing data based on the K-nearest neighbor algorithm.

[0072] Based on the first model, calculate the importance scores of each type of concrete parameter in the completed concrete parameters.

[0073] For the importance score of each type of concrete parameter, if the importance score is greater than a preset threshold, the data of the type of concrete parameter is retained, and if the importance score is less than or equal to the preset threshold, the data of the type of concrete parameter is deleted, to obtain a completed data set.

[0074] The data set after completion of processing is divided into a training set and a test set according to a preset proportion.

[0075] Specifically, the preset threshold can be 0.1, and the preset proportion corresponding to the training set and the test set can be 8:2. In some specific embodiments, the importance scores of the two types of concrete parameters, i.e., the diameter of the anchor rod and the depth of the anchor rod, are both less than 0.1. In order to reduce the data dimension and reduce the complexity of the model, the feature item is deleted in the subsequent training.

[0076] Specifically, the K-nearest neighbor (KNN) algorithm is introduced to fill in the missing values, especially for the missing of the concrete parameters, so as to ensure the integrity and quality of the data set and avoid the prediction deviation caused by the missing data. Through the preprocessing of the data, the relevance and reliability of the data are further improved, thereby providing a solid foundation for the model training.

[0077] For example, based on the first model, the importance scores of the various types of concrete parameters in the completed concrete parameters can include:

[0078] Based on the first model, the importance scores of the various types of concrete parameters in the completed concrete parameters are calculated in combination with the second formula.

[0079] The second formula can be:

[0080]

[0081] wherein I j represents the importance score of the j-type concrete parameter, T represents the total number of decision trees in the first model, S t,j represents a set of all split nodes using the j-type concrete parameter in the decision tree t, Gain S represents the information gain of the node s.

[0082] For example, in some embodiments, the process of judging the missing data in the shear strength and the concrete parameters and filling in the missing data based on the K-nearest neighbor algorithm can include the following process:

[0083] Step S1, the acquired shear strength and concrete parameters of the concrete interface are defined as a data set wherein x i represents the feature vector of the i-th sample, y i represents the shear strength of the i-th sample, and n represents the number of samples. For the feature vector x i of a sample, x i ={x i1 , x i2 , x i3 ,......, x imm represents the number of concrete parameter types.

[0084] Step S2, find the data set with missing data: D 缺失 The missing data in the data set with missing data is generally a concrete parameter. If the missing data is shear strength, the data set corresponding to the shear strength is directly excluded.

[0085] Step S3, after finding the data set with missing data, calculate the Euclidean distance from the data set with complete data to the data set with missing data, select the nearest 10 data sets in the Euclidean distance as the neighbors of the data set with missing data, determine the type of missing data, and complete the missing data using the mean value of the type data of the 10 neighbors.

[0086] Specifically, in order to more clearly illustrate the calculation method of the Euclidean distance, define x1={x 11 , x 12 , x 13 ,..., x 1m} and x2={x 21 , x 22 , x 23 ,..., x 2m}, and assume that x 11 is missing data, then the calculation formula of the Euclidean distance is: In short, it is to calculate the distance between two vectors according to the data other than the missing data type.

[0087] Specifically, in some embodiments, the first model can be a LightGBM regression model M:

[0088] M = LightGBMRegressor(Θ)

[0089] Where Regressor represents a regression model, and Θ represents an initial hyperparameter set of the first model.

[0090] Step 103, based on the cooperative group optimization algorithm and the genetic algorithm, the hyperparameters of the first model are optimized to obtain a target hyperparameter set; the target hyperparameter set is applied to the first model to obtain a second model, and the second model is trained based on the training set and the test set to obtain a shear strength prediction model.

[0091] For example, based on the cooperative group optimization algorithm and the genetic algorithm, the hyperparameters of the first model are optimized to obtain a target hyperparameter set, which can include:

[0092] parameters of the cooperative group optimization algorithm, parameters of the genetic algorithm and population parameters are initialized, and the number of hyperparameters of the first model and upper and lower boundaries are obtained; wherein, the fitness function of the cooperative group optimization algorithm is the negative mean square error of the first model on the training set.

[0093] Based on the number of hyperparameters of the first model and the upper and lower boundaries, the initial particle position in the cooperative group optimization algorithm is determined, and the initial population is obtained.

[0094] For each iteration of the population, the particles in the population are iterated based on the cooperative group optimization algorithm, and the updated particles are obtained.

[0095] Based on the fitness value of the optimal particle in the updated particle, the selection probability of the genetic algorithm is determined.

[0096] Based on the selection probability, the parent particles of the genetic algorithm are determined.

[0097] Based on the genetic algorithm, the parent particles are iterated to obtain the child particles.

[0098] The child particles and the updated particles are combined to form a new population, denoted as the first population.

[0099] The particles in the first population are sorted according to the fitness value, and a predetermined number of particles are selected as the second population.

[0100] According to the particle with the smallest fitness value in the second population, the global best position is updated, and when the current iteration number does not reach the maximum iteration number, the second population is used as the population for the next iteration.

[0101] After the current iteration number reaches the maximum iteration number, the iteration is stopped, and the global best position at this time is taken as the target hyperparameter set.

[0102] Illustratively, based on the fitness value of the optimal particle in the updated particle, the selection probability of the genetic algorithm can include:

[0103] Based on the fitness value of the optimal particle in the updated particle, the selection probability of the genetic algorithm is determined in combination with the first formula.

[0104] The first formula can be:

[0105]

[0106] Wherein, Pi represents the selection probability, N represents the number of particles, f j represents the fitness value of particle j, and f represents the fitness value of the optimal particle.

[0107] Illustratively, initializing the parameters of the cooperative group optimization algorithm, the parameters of the genetic algorithm and the population parameters can include:

[0108] Initialize particle velocities, personal best positions, personal best fitness values, global best position, global best fitness value, population size, maximum number of iterations, initial inertia weight, inertia weight reduction rate, acceleration coefficients, crossover probability, and mutation probability.

[0109] Exemplarily, the parameters need to be initialized before using the cooperative swarm optimization algorithm and the genetic algorithm, specifically including:

[0110] 1.1 Parameter setting

[0111] Population size: Set the number of particles N = 50.

[0112] Maximum number of iterations: Set the number of iterations T = 100.

[0113] Problem dimension: The number of hyperparameters Dim = 11.

[0114] Upper and lower bounds of hyperparameters: Set the upper and lower bounds LB and UB for each hyperparameter.

[0115] Inertia weight parameter: Initial inertia weight w(0) = 0.9, inertia weight reduction rate k = 0.5.

[0116] Acceleration coefficient: c1 = c2 = 2.

[0117] Genetic algorithm parameters: Crossover probability Pc = 0.8, mutation probability Pm = 0.1.

[0118] 1.2 Initialize particle position

[0119] Randomly generate an initial position X i for each particle between the upper and lower bounds of each dimension.

[0120] X i = LB + rand(Dim) * (UB - LB) i = 1, 2,,, N

[0121] Where rand(Dim) generates a random vector of dimension Dim, with elements between [0, 1].

[0122] 1.3 Initialize particle velocity

[0123] Set the initial velocity of all particles to zero vector v i = 0.

[0124] 1.4 Calculate initial fitness value

[0125] For each particle X i , calculate its fitness value f(X i ).

[0126] 30% of the training set is taken as the validation set, and the fitness function takes the negative mean square error (MSE) of the model on the validation set as the fitness value:

[0127]

[0128] where l is the number of validation set samples, y i is the actual value of the shear strength in the validation set, is the predicted value of the second model.

[0129] 1.5, initialize the personal best position and fitness value

[0130] Take the current position of each particle as its personal best position:

[0131] p besti = X i

[0132] Take the fitness value of each particle as its personal best fitness value:

[0133] f pbesti = f(X i )

[0134] 1.6, initialize the global best position and fitness value

[0135] Find the particle with the maximum fitness value in the current population, and set it as the global best position:

[0136] g best = X g ,

[0137] f gbest = f(X g )

[0138] In the iterative optimization phase of the algorithm, for each generation (from t = 1 to T), the following steps are performed:

[0139] 2.1, update the inertia weight

[0140] Use the adaptive update formula of the inertia weight:

[0141] w(t+1) = w(t) x (1-e -k×t )

[0142] where w(0) is the initial inertia weight.

[0143] 2.2, for each particle i (from i = 1 to N), perform the following operations:

[0144] Generate a random number: generate a random vector between [0, 1]

[0145] r1, r2, r3, r4, r5 ∈ [0, 1]

[0146] Inertia weight term (IWV):

[0147] IWV i = w(t) x v i

[0148] Personal best term (PBC):

[0149] PBC i = r1 x (e x rand(pbest i ) - X i )

[0150] where e represents a very small constant to introduce a small perturbation, and rand(pbest i ) represents a random perturbation to the personal best position.

[0151] Global best term (GBC):

[0152] GBC i = r2 x (g best - X i )

[0153] Dynamic attraction term (DAC):

[0154]

[0155] The specific process of calculating attract i includes: determining the neighborhood, setting the neighborhood size H = 5, for particle i, selecting the nearest H particles to form the neighborhood Ni according to the Euclidean distance between particles, finding the particle with the maximum fitness value in Ni, and the position is attract i .

[0156] Adaptive neighborhood interaction term (ANIC):

[0157] Let neighborbest i = attract i , then

[0158] ANIC i = r4 x (neighborbest i - X i )

[0159] Diversity maintenance term (DMC):

[0160] DMC i = c2 x r5 x (diversity i - Xi )

[0161] diversity i = X i + b x (X center - X i )

[0162]

[0163] where b is a random number in the interval [0, 1].

[0164] 2.3, Update velocity

[0165] Adding the above terms, the update velocity is:

[0166] v i = I W V i + P B C i + G B C i + D A C i + A N I C i + D M C i

[0167] Update position: update the position of the particle

[0168] X i = X i + v i

[0169] Boundary handling: if X i exceeds the lower and upper bounds LB and UB, boundary handling is performed:

[0170] If X i < LB, then X i = LB.

[0171] If X i > UB, then X i = UB.

[0172] 2.4, Calculate fitness value

[0173] Calculate the new fitness value of the particle: f(X i )

[0174] 2.5, Update personal best position and fitness value

[0175] If the current fitness value of the particle is better than its personal best fitness value, then update:

[0176] p besti = X i

[0177] f pbesti = f(Xi )

[0178] In particular, the specific process of the genetic algorithm is as follows:

[0179] 3.1, selection operation

[0180] The selection probability Pi is calculated based on the fitness value:

[0181]

[0182] Using the roulette method, the parent particles are selected according to Pi to form a mating pool.

[0183] 3.2, crossover operation

[0184] The particles in the mating pool are subjected to crossover operation with a crossover probability Pc.

[0185] Single-point crossover is adopted:

[0186] For each pair of parent particles, a crossover point c is randomly selected (between [1, Dim-1]). Two offspring particles are generated:

[0187] offspring1 = [parent1(1:c), parent2(1+c:Dim)]

[0188] offspring2 = [parent2(1:c), parent1(1+c:Dim)]

[0189] Where parent represents the parent, and offspring represents the offspring.

[0190] 3.3, mutation operation

[0191] Each dimension of the offspring particle is subjected to mutation with a mutation probability Pm.

[0192] Mutation method:

[0193] For each dimension j of the particle, mutation is performed with a probability of Pm:

[0194] Calculate the mutation amplitude:

[0195] O j = 0.1(UB j -LB j ), j = 1, 2, 3, …, Dim

[0196] Generate a random disturbance:

[0197] T = randn() × O j

[0198] where randn() is a random number generation function of standard normal distribution.

[0199] Update offspring i，j = offspring i，j + T.

[0200] 3.4, Boundary processing

[0201] For the mutated offspring particles, check whether they exceed the boundary and perform boundary processing.

[0202] 3.5, Fitness evaluation

[0203] For the mutated offspring particles, calculate their fitness values f(offspring i ).

[0204] Repeat the above iteration multiple times, and when the number of iterations reaches the maximum number of iterations, take the global best position as the target hyperparameter set. After applying the target hyperparameter set to the first model, the second model can be obtained.

[0205] Illustratively, training the second model based on the training set and the test set to obtain the shear strength prediction model can include:

[0206] Training the second model based on the training set to obtain the trained model.

[0207] Based on the test set, the mean square error and the mean absolute error, the accuracy of the trained model is verified.

[0208] If the accuracy of the trained model meets the preset condition, the trained model is taken as the shear strength prediction model.

[0209] Illustratively, after obtaining the shear strength prediction model, the key features affecting the shear strength of the concrete interface can also be output according to the shear strength prediction model, and the specific process is as follows:

[0210] Step S1, calculate the SHAP value of each concrete parameter according to the third formula; wherein the SHAP value of each type of concrete parameter represents the contribution of the feature to the prediction result.

[0211] The third formula can be:

[0212]

[0213] where Φ iSHAP value representing feature i, N represents the set of all features, S represents any feature subset not containing feature i, |S| represents the number of features in set S, v(S) represents the contribution of feature set S to the model prediction output, and v(S∪{i}) represents the contribution of feature set S∪{i} containing feature i to the model prediction output.

[0214] In step S2, the key features affecting the shear strength of the concrete interface are determined according to the size of each SHAP value.

[0215] In this embodiment, the SHAP analysis method is combined to perform interpretive analysis on the shear strength prediction model, to deeply understand the contribution of each input feature to the prediction of the shear strength, to enhance the interpretability of the shear strength prediction model and the transparency of the engineering application, to solve many limitations of the traditional method under complex working conditions and multi-dimensional parameter nonlinear relationship, and to have important theoretical significance and wide engineering application prospect.

[0216] In step 104, the concrete parameters of the target concrete interface are input into the shear strength prediction model to obtain the shear strength prediction value of the target concrete interface.

[0217] The above-mentioned concrete interface shear strength prediction method uses the Social Spider Optimization Algorithm (SSOA) for global search. The SSOA can efficiently explore a wide parameter space and find a preliminary high-quality hyperparameter combination by simulating group cooperation and information exchange between individuals. Then, the Genetic Algorithm (GA) takes over the solution obtained by the SSOA, further optimizes the hyperparameters through crossover and mutation operations, enhances the diversity of the population, and promotes more comprehensive solution space exploration. The hybrid optimization strategy combining the SSOA and the GA not only speeds up the convergence speed of hyperparameter optimization and significantly shortens the model training time, but also effectively avoids the problem of single optimization algorithm falling into local optimum, improves the prediction performance of the LightGBM model, and ensures accurate prediction of the shear strength of the concrete interface under complex working conditions.

[0218] It should be understood that the size of the serial number of each step in the above-mentioned embodiments does not mean the order of execution, and the execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0219] corresponding to the concrete interface shear strength prediction method described in the above embodiments, Figure 2 A structural block diagram of a concrete interface shear strength prediction device provided by an embodiment of the present application is shown. For ease of illustration, only parts related to the embodiments of the present application are shown.

[0220] Referring to Figure 2 The concrete interface shear strength prediction device in the embodiments of the present applicationapplicationinclude:

[0221] The data acquisition module 201 is configured to acquire the shear strength of the concrete interface and the concrete parameters.

[0222] The data processing module 202 is configured to establish an initial LightGBM model, denoted as a first model, and preprocess the shear strength and the concrete parameters to obtain a training set and a test set.

[0223] The first modeling module 203 is configured to optimize the hyperparameters of the first model based on a cooperative swarm optimization algorithm and a genetic algorithm to obtain a target hyperparameter set; apply the target hyperparameter set to the first model to obtain a second model, and train the second model based on the training set and the test set to obtain a shear strength prediction model.

[0224] The result prediction module 204 is configured to input the concrete parameters of the target concrete interface into the shear strength prediction model to obtain a shear strength prediction value of the target concrete interface.

[0225] For example, the data processing module 202applicationbe configured to:

[0226] Initialize the parameters of the cooperative swarm optimization algorithm, the parameters of the genetic algorithm, and the population parameters, and acquire the number of hyperparameters of the first model and the upper and lower boundaries; wherein the fitness function of the cooperative swarm optimization algorithm is the negative mean square error of the first model on the training set.

[0227] Based on the number of hyperparameters of the first model and the upper and lower boundaries, the initial particle positions in the cooperative swarm optimization algorithm are determined to obtain an initial population.

[0228] For each iteration of the population, the particles in the population are iterated based on the cooperative swarm optimization algorithm to obtain updated particles.

[0229] Based on the fitness value of the optimal particle in the updated particles, the selection probability of the genetic algorithm is determined.

[0230] Based on the selection probability, the parent particles of the genetic algorithm are determined.

[0231] The parent particles are iterated based on the genetic algorithm to obtain child particles.

[0232] The child particles and the updated particles are combined to form a new population, denoted as a first population.

[0233] The particles in the first population are sorted according to the fitness values, and a preset number of particles are selected as a second population.

[0234] The global optimal position is updated according to the particle with the minimum fitness value in the second population, and the second population is used as the population for the next iteration when the current iteration number does not reach the maximum iteration number.

[0235] After the current iteration number reaches the maximum iteration number, the iteration is stopped, and the global optimal position at this time is used as the target hyperparameter set.

[0236] The data processing module 202 can also be used for:

[0237] Based on the fitness value of the optimal particle in the updated particle, the selection probability of the genetic algorithm is determined in combination with the first formula.

[0238] The first formula can be:

[0239]

[0240] Wherein, Pi represents the selection probability, N represents the number of particles, f j represents the fitness value of particle j, and f represents the fitness value of the optimal particle.

[0241] The parameters of the cooperative swarm optimization algorithm, the parameters of the genetic algorithm, and the population parameters are initialized, including:

[0242] The particle velocity, the personal optimal position, the personal optimal fitness value, the global optimal position, the global optimal fitness value, the population size, the maximum iteration number, the initial inertia weight, the inertia weight reduction rate, the acceleration coefficient, the crossover probability, and the mutation probability are initialized.

[0243] The first modeling module 203 can be used for:

[0244] The second model is trained based on the training set to obtain a trained model.

[0245] The accuracy of the trained model is verified based on the test set, the mean square error, and the mean absolute error.

[0246] If the accuracy of the trained model meets the preset condition, the trained model is used as the shear strength prediction model.

[0247] The data processing module 202 can be used for:

[0248] The missing data in the shear strength and the concrete parameters is determined.

[0249] The missing data is completed based on the K-nearest neighbor algorithm.

[0250] Based on the first model, the importance score of each type of concrete parameter in the completed concrete parameters is calculated.

[0251] The importance score of each type of concrete parameter is scored, if the importance score is greater than a preset threshold, the data of the type of concrete parameter is retained, if the importance score is less than or equal to the preset threshold, the data of the type of concrete parameter is deleted, and a completed data set is obtained.

[0252] The completed data set is divided into a training set and a test set according to a preset ratio.

[0253] For example, the data processing module 202 can also be used to:

[0254] Based on the first model, the importance score of each type of concrete parameter in the completed concrete parameter is calculated based on the second formula.

[0255] The second formula can be:

[0256]

[0257] Wherein, I j represents the importance score of the j type of concrete parameter, T represents the total number of decision trees in the first model, S t,j represents a set of all split nodes using the j type of concrete parameter in the decision tree t, Gain S represents the information gain of node s.

[0258] It should be noted that the information interaction, execution process and the like between the above devices / units are based on the same concept as the method embodiments of the present application, and the specific functions and technical effects brought about can be referred to the method embodiments part, which will not be repeated here.

[0259] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above division of functional units and modules is exemplified, and in actual application, the above functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or software. In addition, the specific names of each functional unit and module are only for easy distinction, and do not limit the protection scope of the present application. The specific working process of the units and modules in the system can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0260] The present application also provides a terminal device, which is described with reference to Figure 3The terminal device 300 can include at least one processor 310, a memory 320 configured to store a computer program 321, and the processor 310 configured to invoke and execute the computer program 321 stored in the memory 320 to implement the steps in any of the above method embodiments, for example Figure 1 the steps 101 to 104 in the illustrated embodiment. Alternatively, the processor 310 implements the functions of each module / unit in the above apparatus embodiments when executing the computer program, for example Figure 2 the functions of each module illustrated.

[0261] By way of example, the computer program 321 can be segmented into one or more modules / units, one or more of which are stored in the memory 320 and executed by the processor 310 to complete the present application. The one or more modules / units can be a series of computer program segments capable of completing a specific function, which are used to describe the execution process of the computer program in the terminal device 300.

[0262] Those skilled in the art can understand that Figure 3 is merely an example of a terminal device and does not constitute a limitation on the terminal device, which can include more or fewer components than shown, or combine some components, or different components, for example, input / output devices, network access devices, buses, etc.

[0263] The processor 310 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic components, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0264] The memory 320 can be an internal storage unit of the terminal device, or an external storage device of the terminal device, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. The memory 320 is used to store the computer program and other programs and data required by the terminal device. The memory 320 can also be used to temporarily store data that has been output or will be output.

[0265] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, the bus in the drawings of the present application does not limit to only one bus or one type of bus.

[0266] The concrete interface shear strength prediction method provided by the embodiments of the present application can be applied to a terminal device such as a computer, a wearable device, a vehicle-mounted device, a tablet computer, a notebook computer, a netbook, and the like. The embodiments of the present application do not limit the specific type of the terminal device.

[0267] The embodiments of the present application further provide a computer readable storage medium, which stores a computer program. The computer program is executed by a processor to implement the steps in each of the embodiments of the concrete interface shear strength prediction method.

[0268] The embodiments of the present application provide a computer program product. When the computer program product is run on a mobile terminal, the mobile terminal is caused to implement the steps in each of the embodiments of the concrete interface shear strength prediction method.

[0269] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the embodiments of the method described above can be completed by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. The computer program is executed by a processor to implement the steps of each method embodiment described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or some intermediate forms. The computer readable medium at least includes any entity or device capable of carrying the computer program code to the photographing device / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunications signal, and a software distribution medium. For example, a U disk, a mobile hard disk, a magnetic disk or an optical disk, and the like.

[0270] In the above embodiments, the description of each embodiment focuses on different aspects, and the parts not described or recorded in a certain embodiment can be referred to the relevant description of other embodiments.

[0271] Those skilled in the art can understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0272] In the embodiments provided in the present application, it should be understood that the disclosed apparatus / network device and method can be implemented in other ways. For example, the apparatus / network device embodiments described above are merely schematic, for example, the division of the modules or units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed units can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0273] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.

[0274] The above described embodiments are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A method for predicting the interfacial shear strength of concrete, characterized in that, include: Obtain the shear strength and concrete parameters of the concrete interface; An initial LightGBM model is established, denoted as the first model, and the shear strength and concrete parameters are preprocessed to obtain the training set and the test set. Based on the cooperative group optimization algorithm and the genetic algorithm, the hyperparameters of the first model are optimized to obtain a target hyperparameter set; the target hyperparameter set is applied to the first model to obtain a second model, and the second model is trained based on the training set and the test set to obtain a shear strength prediction model; The concrete parameters of the target concrete interface are input into the shear strength prediction model to obtain the predicted shear strength value of the target concrete interface. The concrete parameters include: compressive strength of pre-cast concrete, compressive strength of post-cast concrete, material type of post-cast concrete, length along the shear plane, shear plane area, interface treatment method, interface roughness, interface stress, rebar anchoring ratio, rebar embedment depth, rebar yield strength, and rebar diameter. The importance scores for both rebar diameter and rebar embedment depth are less than 0.

1. To reduce data dimensionality and model complexity, these feature terms will be removed in future training. The preprocessing of the shear strength and the concrete parameters to obtain the training set and the test set includes: Determine the missing data in the shear strength and concrete parameters; The missing data is filled in using the K-nearest neighbor algorithm; Based on the first model, the importance score of each type of concrete parameter in the completed concrete parameters is calculated; For each type of concrete parameter, if the importance score is greater than a preset threshold, the data for that type of concrete parameter is retained; if the importance score is less than or equal to the preset threshold, the data for that type of concrete parameter is deleted, resulting in a completed dataset. The processed dataset is divided into the training set and the test set according to a preset ratio.

2. The method for predicting the interfacial shear strength of concrete as described in claim 1, characterized in that, The hyperparameters of the first model are optimized using the cooperative group optimization algorithm and the genetic algorithm to obtain a target hyperparameter set, including: Initialize the parameters of the cooperative swarm optimization algorithm, the parameters of the genetic algorithm, and the population parameters, and obtain the number and upper and lower boundaries of the hyperparameters of the first model; wherein, the fitness function of the cooperative swarm optimization algorithm is the negative mean square error of the first model on the training set; Based on the number of hyperparameters and upper and lower boundaries of the first model, the initial particle positions in the cooperative swarm optimization algorithm are determined to obtain the initial population. For each iteration of the population, the particles in the population are iterated based on the cooperative group optimization algorithm to obtain the updated particles; Based on the fitness value of the best particle in the updated particles, the selection probability of the genetic algorithm is determined; Based on the selection probability, the parent particles of the genetic algorithm are determined; The parent particles are iterated based on the genetic algorithm to obtain the offspring particles; The offspring particles and the updated particles are combined to form a new population, denoted as the first population. The particles in the first population are sorted according to their fitness values, and a preset number of particles are selected as the second population. The global optimal position is updated based on the particle with the smallest fitness value in the second population, and the second population is used as the population for the next iteration if the current iteration number has not reached the maximum iteration number. After the current iteration count reaches the maximum iteration count, the iteration stops, and the current global optimal position is taken as the target hyperparameter set.

3. The method for predicting the interfacial shear strength of concrete as described in claim 2, characterized in that, Determining the selection probability of the genetic algorithm based on the fitness value of the best particle among the updated particles includes: Based on the fitness value of the best particle in the updated particles, and in conjunction with the first formula, the selection probability of the genetic algorithm is determined. The first formula is: in, This represents the selection probability. Indicates the number of particles. Represents particles fitness value, This represents the fitness value of the optimal particle.

4. The method for predicting the shear strength of concrete interfaces as described in claim 2, characterized in that, The parameters for initializing the cooperative group optimization algorithm, the parameters for the genetic algorithm, and the population parameters include: Initialize particle velocity, individual best position, individual best fitness value, global best position, global best fitness value, population size, maximum number of iterations, initial inertia weight, inertia weight decrease rate, acceleration coefficient, crossover probability, and mutation probability.

5. The method for predicting the interfacial shear strength of concrete as described in claim 1, characterized in that, The process of training the second model based on the training set and the test set to obtain the shear strength prediction model includes: The second model is trained based on the training set to obtain the trained model; The accuracy of the trained model is verified based on the test set, mean squared error, and mean absolute error. If the accuracy of the trained model meets the preset conditions, then the trained model will be used as the shear strength prediction model.

6. The method for predicting the interfacial shear strength of concrete as described in claim 1, characterized in that, Based on the first model, the importance score of each type of concrete parameter in the completed concrete parameters is calculated, including: Based on the first model and combined with the second formula, the importance score of each type of concrete parameter in the completed concrete parameters is calculated. The second formula is: in, express The importance score of concrete type parameters This represents the total number of decision trees in the first model. Representation of decision tree Use The set of all split nodes for the type of concrete parameter. Represents a node Information gain.

7. A terminal device, comprising: A processor and a memory, wherein the memory stores a computer program executable on the processor, characterized in that, when the processor executes the computer program, it implements the concrete interface shear strength prediction method as described in any one of claims 1 to 6.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the concrete interface shear strength prediction method as described in any one of claims 1 to 6.

Images