A method and system for predicting the pile-forming quality and optimal construction parameters of jet grouting piles

Abstract

The present invention relates to the technical field of engineering intelligent algorithms, in particular to a method and system for predicting the pile-forming quality and construction optimal parameters of jet grouting piles. The method comprises the following steps: constructing a data sample set based on similar historical engineering cases; classifying the soil bodies of the construction strata of the jet grouting piles to obtain different soil body categories of the strata, and acquiring the construction process sensitive parameters; conducting an orthogonal test to obtain the orthogonal test results, so as to establish a numerical simulation model for the construction of the jet grouting piles to obtain a simulated data sample set; constructing a strength prediction model for the jet grouting piles to obtain the prediction results of the pile-forming quality of the jet grouting piles; establishing constraint conditions, and optimizing the prediction results of the pile-forming quality of the jet grouting piles according to an optimization algorithm to obtain an optimal solution set; and combining the actual construction situation of the jet grouting piles, and obtaining the construction optimal parameters according to an optimal solution screening method. The present invention can quickly and efficiently obtain the construction optimal parameters of the jet grouting pile project, so as to optimize the construction plan, and further ensure the pile-forming quality of the jet grouting piles.

Description

Technical Field

[0001] The present invention relates to the technical field of engineering intelligent algorithms, and in particular to a method and system for predicting the quality of jet grouting piles and the optimal construction parameters. Background Art

[0002] The high-pressure jet grouting pile technology is an efficient foundation reinforcement method, which is widely used in the fields of soft soil foundation treatment, building foundation reinforcement, and tunnel construction control. The high-pressure jet grouting pile technology injects cement slurry into the underground soil layer through high-pressure jet grouting, so that the soil and the cement slurry are fully mixed to form a high-strength cement-soil pile body. The main advantages are flexible construction, which can adapt to complex geological conditions. At the same time, the jet grouting pile has high compressive strength and shear strength, effectively improving the bearing capacity and stability of the foundation. In addition, the jet grouting pile construction has little impact on the environment, and is particularly suitable for urban intensive areas and areas with dense underground facilities.

[0003] However, the quality and strength of the jet grouting pile are affected by various factors, resulting in large discreteness and uncertainty in the strength and impermeability performance of the jet grouting pile. The influencing factors include the jet grouting process itself, the setting of construction parameters, and the on-site formation conditions. In previous technical solutions, the evaluation of the pile body strength and impermeability performance relied on on-site sampling and laboratory testing, which was not only time-consuming and laborious but also had a large engineering cost. Therefore, in existing construction, the determination of jet grouting pile construction parameters mostly uses empirical formulas and simple statistical models, which are difficult to accurately describe the complex non-linear relationship between construction parameters and geological conditions, and may thus lead to an increase in project costs and an increase in construction safety risks.

[0004] In view of this, there is an urgent need for a data-driven intelligent prediction method. The present invention conducts a sensitivity analysis on construction process parameters, constructs a jet grouting pile strength prediction model, and optimizes the prediction results using an optimization algorithm, which can quickly and efficiently obtain the optimal construction parameters of the jet grouting pile, so as to optimize the construction plan and improve the project quality. Summary of the Invention

[0005] Aiming at the defects in the prior art, the present invention provides a method and system for predicting the quality of jet grouting piles and the optimal construction parameters.

[0006] To achieve the above object, in a first aspect, the present invention provides a method for predicting the pile-forming quality and optimal construction parameters of jet grouting piles. The method includes the following steps: constructing a data sample set based on similar historical engineering cases by obtaining construction stratum parameters, construction process parameters, and jet grouting pile evaluation parameters; classifying the construction stratum soil bodies of the jet grouting piles to obtain different stratum soil body categories, and obtaining the construction process sensitive parameters of the different stratum soil body categories; conducting an orthogonal test on the construction process sensitive parameters to obtain orthogonal test results, and establishing a numerical simulation model for jet grouting pile construction to obtain a simulated data sample set; according to the simulated data sample set, respectively constructing jet grouting pile strength prediction models for the different stratum soil body categories, and further obtaining the pile-forming quality prediction results of the jet grouting piles; establishing constraint conditions, and optimizing the pile-forming quality prediction results of the jet grouting piles according to an optimization algorithm to obtain an optimal solution set that meets the constraint conditions; combining the actual jet grouting pile construction situation, and optimizing and screening the optimal solution set according to an optimal solution screening method to obtain the optimal construction parameters. By constructing a data sample set, classifying stratum soil bodies, obtaining sensitive parameters, and establishing a prediction model, the present invention improves the prediction accuracy of the pile-forming quality of jet grouting piles. Based on the prediction results, an optimal solution set that meets the constraint conditions is obtained by using an optimization algorithm, and the optimal construction parameters are obtained, which improves the construction efficiency. At the same time, by adjusting the construction parameters, materials are saved, the foundation bearing capacity is improved, the pile-soil stress distribution is more reasonable, and the overall engineering construction level is significantly improved.

[0007] Optionally, the constructing a data sample set based on similar historical engineering cases by obtaining construction stratum parameters, construction process parameters, and jet grouting pile evaluation parameters includes: the construction stratum parameters include the stratum distribution and soil body characteristics of the soil body in the construction area where the jet grouting pile is located, the soil body characteristics include the physical indexes and mechanical properties of the soil body, the physical indexes include natural density, water content, void ratio, dry density, liquidity index, and standard penetration blow count, and the mechanical properties include compression modulus, shear strength, and Poisson's ratio; the construction process parameters include nozzle diameter, pilot hole diameter, cement content, water-cement ratio, grout injection flow rate, air flow rate, water flow rate, and lifting speed; the jet grouting pile evaluation parameters include the unconfined compressive strength and permeability coefficient after the jet grouting pile is consolidated and formed. By collecting the construction stratum parameters, construction process parameters, and jet grouting pile evaluation parameters of similar historical engineering cases to construct a data sample set, the present invention provides comprehensive and accurate data support for subsequent analysis, helps to improve prediction accuracy, optimize construction parameters, and improve construction efficiency, and shows significant application value in scenarios such as foundation reinforcement and anti-seepage and water-stop.

[0008] Optionally, classifying the soil body of the construction stratum of the jet grouting pile to obtain different soil body categories of the stratum, and obtaining the construction process sensitive parameters of the different soil body categories of the stratum, including: classifying the soil body of the construction stratum to obtain the different soil body categories of the stratum, including silt, silty clay, cohesive soil, plain fill, and sandy soil; performing global sensitivity analysis on the construction process parameters of the different soil body categories based on the jet grouting pile evaluation parameters to obtain the construction process sensitive parameters. The present invention classifies the soil body of the construction stratum of the jet grouting pile, and performs global sensitivity analysis on the construction process parameters of different soil body categories based on the jet grouting pile evaluation parameters to obtain the construction process sensitive parameters, which helps to improve the pertinence and efficiency of construction parameter selection, optimize the construction parameter combination, thereby improving the pile forming quality and construction efficiency of the jet grouting pile; at the same time, by clarifying the sensitive parameters of different soil body categories of the stratum, it provides a more accurate parameter adjustment basis for actual construction.

[0009] Optionally, performing an orthogonal test on the construction process sensitive parameters to obtain an orthogonal test result, and establishing a numerical simulation model for jet grouting pile construction to obtain a simulated data sample set, including: delimiting the value range of the construction process sensitive parameters based on the similar historical engineering cases, using the value range to expand the target unknown parameters, and constructing a simulation test case; performing numerical simulation according to the simulation test case, thereby establishing the numerical simulation model for jet grouting pile construction; obtaining the jet grouting pile evaluation parameters as the simulated data sample set according to the numerical simulation model for jet grouting pile construction. The present invention delimits the parameter value range, expands and constructs the simulation test case, combines numerical simulation modeling, obtains the evaluation parameters as the simulated data sample set, effectively improves the experimental efficiency, and at the same time can comprehensively evaluate the influence of different construction parameter combinations on the pile forming quality and construction efficiency, reveals the interaction between parameters through the orthogonal test, optimizes the parameter combination, and improves the construction effect. In addition, the numerical simulation model provides accurate data support and decision-making basis for subsequent actual construction, enhancing the adaptability and effectiveness of the construction plan.

[0010] Optionally, based on the simulated data sample set, a jet grouting pile strength prediction model is constructed for different strata soil types respectively, and then a prediction result of the jet grouting pile forming quality is obtained, including: normalizing the simulated data sample set to obtain normalized data; acquiring the initialization parameters of the jet grouting pile strength prediction model, and dividing the simulated data sample set into pure subsets through recursive splitting; constructing the jet grouting pile strength prediction model for different strata soil types respectively based on the pure subsets; training and validating the jet grouting pile strength prediction model to obtain the optimal model hyperparameter combination; establishing the corresponding relationship between the construction process parameters and the jet grouting pile evaluation parameters in different strata soil types as the prediction result of the jet grouting pile forming quality. The present invention eliminates the influence of different dimensions and orders of magnitude through data normalization processing, improves the model convergence speed and prediction accuracy; reveals the internal structure and law of the data by dividing pure subsets, providing a basis for model construction; constructs a jet grouting pile strength prediction model, and obtains the optimal hyperparameter combination through model training and validation, improving the prediction performance; establishes the corresponding relationship between the construction process parameters and the evaluation parameters in different strata soil types, providing accurate data reference and decision-making basis for actual construction.

[0011] Optionally, the dividing the simulated data sample set into pure subsets through recursive splitting includes: measuring the purity of the pure subsets by using the Gini index, and the Gini index includes:

[0012] ;

[0013] wherein, is the Gini index of the pure subset is the number of classes, is the class, is the class, is the pure subset in the class sample proportion. The present invention effectively evaluates the purity of the subsets through the Gini index. The smaller the index, the higher the purity, which helps to improve the prediction accuracy of the model, reveals the internal structure and law of the data, enhances the generalization ability of the model, provides accurate data support for constructing the jet grouting pile strength prediction model, optimizes the selection of construction parameters, and is beneficial to improving the construction efficiency.

[0014] Optionally, the constructing the jet grouting pile strength prediction model for different strata soil types respectively includes:

[0015] ;

[0016] wherein, is the classification voting result, Indicates the category that maximizes the function value. is the number of decision trees. is a decision tree. is an indicator function. is the prediction result output by the is the input sample. is the category. The present invention constructs a jet grouting pile strength prediction model for different strata soil categories. Through the ensemble learning of multiple decision trees, the prediction accuracy is improved. The jet grouting pile strength prediction model synthesizes the prediction results of multiple decision trees to obtain the final prediction result, effectively reducing the overfitting risk and enhancing the generalization ability of the model.

[0017] Optionally, the establishment of the constraint conditions optimizes the prediction result of the jet grouting pile forming quality according to the optimization algorithm to obtain the optimal solution set that meets the constraint conditions, including: using the jet grouting pile evaluation parameters as the constraint conditions, including:

[0018] ;

[0019] Among them, and are the constraint conditions. is the minimum unconfined compressive strength obtained based on the jet grouting pile strength prediction model. is the minimum unconfined compressive strength allowed by the project. is the maximum permeability coefficient obtained based on the jet grouting pile strength prediction model. is the maximum permeability coefficient allowed by the project. The present invention ensures that the forming quality of the jet grouting pile meets the project requirements by setting the minimum unconfined compressive strength and the minimum permeability coefficient as the constraint conditions. By continuously iteratively solving the optimal solution through the optimization algorithm, it has the advantages of strong global search ability and high parallel processing ability, can effectively avoid falling into the local optimal solution, and realizes the search for the global optimal solution, providing accurate data support for the optimization of the jet grouting pile construction parameters.

[0020] Optionally, in combination with the actual jet grouting pile construction situation, the optimal solution set is optimized and screened according to the optimal solution screening method to obtain the optimal construction parameters, including: obtaining the corresponding equation between the construction cost of the jet grouting pile and the construction process parameters, including:

[0021] ;

[0022] Among them, is the construction cost of the jet grouting pile. is the quantity of the medium material. is the medium material. is the unit volume cost of the medium material. is the dosage of the medium material; under the above constraints, according to the optimal solution screening method, a step-by-step verification mechanism is adopted to optimize and screen the optimal solution set to obtain the jet grouting pile construction plan with the lowest construction cost, so as to obtain the optimal construction parameters. By establishing an equation between the construction cost of the jet grouting pile and the construction process parameters, the present invention quantifies the construction cost, provides data support for optimizing the construction parameters, and adopts a step-by-step verification mechanism to screen the optimal solution set, ensuring the feasibility and economy of the selected construction parameters, excluding infeasible or uneconomical solutions, and improving the reliability of the optimization results.

[0023] In a second aspect, the present invention provides a system for predicting the quality of the formed jet grouting pile and the optimal construction parameters. The system executes the method for predicting the quality of the formed jet grouting pile and the optimal construction parameters provided by the present invention. The system includes an input device, an output device, a processor, and a memory. The advantages are that: the integrated hardware facilities of the present invention have excellent performance, the input device, the output device, the processor, and the memory are interconnected with each other, and the information transmission between each component is smooth. Through the interaction of multiple hardware facilities, an efficient information processing system is constructed. The present invention dynamically monitors the construction process of the jet grouting pile, provides real-time feedback and adjusts the construction parameters to ensure the pile forming effect and construction quality, and improves the intelligent level of the jet grouting pile construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 is a flowchart of a method for predicting the quality of the formed jet grouting pile and the optimal construction parameters according to an embodiment of the present invention;

[0025] Figure 2 is a schematic diagram of the clustering algorithm process according to an embodiment of the present invention;

[0026] Figure 3 is a schematic diagram of the random forest algorithm process according to an embodiment of the present invention;

[0027] Figure 4 is a schematic diagram of the archived micro-genetic algorithm process according to an embodiment of the present invention;

[0028] Figure 5 is a schematic diagram of the triple-tube method construction process of the jet grouting pile according to an embodiment of the present invention;

[0029] Figure 6 is a framework diagram of a system for predicting the quality of the formed jet grouting pile and the optimal construction parameters according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0030] Specific embodiments of the present invention will be described in detail below. It should be noted that the embodiments described here are only for illustrative purposes and are not intended to limit the present invention. In the following description, in order to provide a thorough understanding of the present invention, a large number of specific details are set forth. However, it is obvious to those of ordinary skill in the art that the present invention does not have to employ these specific details. In other instances, well-known circuits, software, or methods have not been specifically described in order to avoid obscuring the present invention.

[0031] Throughout the specification, the reference to "one embodiment", "an embodiment", "an example", or "an example" means that a particular feature, structure, or characteristic described in connection with the embodiment or example is included in at least one embodiment of the present invention. Thus, the phrases "in one embodiment", "in an embodiment", "an example", or "an example" appearing throughout the specification do not necessarily all refer to the same embodiment or example. In addition, the specific features, structures, or characteristics may be combined in any suitable combination and / or sub-combination in one or more embodiments or examples. In addition, those of ordinary skill in the art should understand that the diagrams provided herein are for illustrative purposes only and are not necessarily drawn to scale.

[0032] Please refer to Figure 1 , an embodiment of the present invention provides a method for predicting the pile-forming quality and construction optimal parameters of jet grouting piles, and the method includes the following steps:

[0033] S1. Based on similar historical engineering cases, obtain construction formation parameters, construction process parameters, and jet grouting pile evaluation parameters to construct a data sample set.

[0034] In this embodiment, by combining previous similar engineering solutions, obtain the construction formation parameters of each construction case, the construction process plan and its related parameters of the jet grouting piles, and the strength and anti-seepage performance after the jet grouting piles are consolidated and formed, to obtain a data sample set. The construction formation parameters include the formation distribution and soil properties of the soil in the construction area where the jet grouting piles are located. The soil properties include the physical indexes and mechanical properties of the soil. The physical indexes include natural density, moisture content, void ratio, dry density, liquidity index, and standard penetration number. The mechanical properties include compression modulus, shear strength, and Poisson's ratio. The construction process parameters include nozzle diameter, pilot hole diameter, cement content, water-cement ratio, grout injection flow rate, air flow rate, water flow rate, and lifting speed. The jet grouting pile evaluation parameters include the unconfined compressive strength and permeability coefficient after the jet grouting piles are consolidated and formed.

[0035] Specifically, setting the air flow rate and water flow rate to 0 indicates that the construction process method is the single-tube method; setting the water flow rate to 0 indicates that the construction process method is the double-tube method.

[0036] Further, by obtaining 2000 data samples of similar historical engineering cases, a data sample set is constructed, as shown in Table 1:

[0037] Table 1

[0038]

[0039] Among them, the ellipsis in the table represents the parameter conditions of similar historical engineering cases between the 4th group and the 1997th group, as well as some construction geographical parameters and process parameters. Due to the large number of similar historical engineering cases, the ellipsis is used to represent these situations.

[0040] S2. Classify the construction stratum soil bodies to obtain different stratum soil body categories, and obtain the construction process sensitive parameters of the different stratum soil body categories.

[0041] Among them, S2 specifically includes the following steps:

[0042] S21. Classify the construction stratum soil bodies to obtain the different stratum soil body categories, including silt, silty clay, clay, plain fill, and sand.

[0043] In this embodiment, the K-medoids clustering algorithm (abbreviated as K-medoids) is selected to classify the construction stratum soil bodies to obtain different stratum soil body categories, including silt, silty clay, clay, plain fill, and sand.

[0044] Please refer to Figure 2 , which is a schematic diagram of the clustering algorithm process; first, input the typical representative parameter samples of the above five different stratum soil body categories as the initial clustering centers; second, establish a partitioning criterion based on the Euclidean distance metric, and assign the remaining samples to the data clusters corresponding to the nearest neighbor clustering centers; finally, for each data cluster, form an iterative optimization process by solving and updating the clustering centers until the convergence condition is met.

[0045] Specifically, for each soil body parameter point in the data sample set of similar historical engineering cases, obtain the distance from the soil body parameter point to the primary clustering centers of different stratum soil body categories, satisfying the following relationship:

[0046]

[0047] Among them, is the Euclidean distance, is the total amount of parameters, is the index variable, is the value of the th parameter in each similar historical engineering case, is the The value of a parameter.

[0048] Furthermore, based on the distances from the soil parameter points of each engineering case to the primary clustering centers of different stratum soil types, the parameter points are classified into the stratum soil types corresponding to the primary clustering centers with the shortest distances. Construct a criterion function to traverse the data points in each soil type, and obtain the data point with the minimum criterion function as the new cluster center; the criterion function satisfies the following relationship:

[0049]

[0050] Where is the criterion function, is the index variable for traversing the data points, is the Euclidean distance.

[0051] Repeat the above method steps to achieve the classification of the sample soil types in the data sample set.

[0052] S22. Based on the jet grouting pile evaluation parameters, perform a global sensitivity analysis on the construction process parameters of the different stratum soil types to obtain the construction process sensitive parameters.

[0053] In this embodiment, different stratum soil types are obtained based on the classification of the construction stratum soil. For the construction process schemes and their related parameters of the jet grouting piles in different stratum soil types, relevant programs of Matrix Laboratory (abbreviated as MATLAB) are called. Based on the unconfined compressive strength and permeability coefficient after the jet grouting pile is consolidated, a global sensitivity analysis of the parameters is performed based on the Probabilistic Analysis of Within-sample Variability and Numerical (abbreviated as PAWN); the parameters with a global sensitivity index less than 0.05 are judged as insensitive parameters, and vice versa as sensitive parameters.

[0054] The sensitivities of the construction process parameters in different stratum soil types are shown in Table 2, where "√" indicates that the parameter is sensitive and "×" indicates that the parameter is insensitive.

[0055] Table 2

[0056]

[0057] Furthermore, according to the differences in the quantity of the original construction data and the parameter accuracy, any other parameter sensitivity analysis method can be used to replace the PAWN global sensitivity analysis method of the parameters.

[0058] S3. Conduct an orthogonal experiment on the sensitive parameters of the construction process to obtain the orthogonal experiment results, and establish a numerical simulation model for jet grouting pile construction to obtain a simulated data sample set.

[0059] In this embodiment, an orthogonal experiment is conducted on the sensitive parameters of the jet grouting pile construction process in different strata soil types. Based on the orthogonal experiment results, a numerical simulation model for jet grouting pile construction is constructed, and the unconfined compressive strength and permeability coefficient after the jet grouting pile is consolidated and formed are obtained as the simulated data sample set.

[0060] Specifically, the orthogonal experiment method is to delimit the value range of the sensitive parameters based on previous construction cases and relevant literature, and use the value range to expand each target unknown parameter to construct a large number of simulated test cases.

[0061] Furthermore, the numerical simulation is carried out based on the software Discrete Lattice Spring Model (DLSM for short) and the large commercial software COMSOL Multiphysics (Comsol for short) respectively, and then a numerical simulation model for jet grouting pile construction is constructed to obtain the unconfined compressive strength and permeability coefficient after the jet grouting pile is consolidated and formed.

[0062] In the numerical simulation, for the insensitive parameters of the jet grouting pile construction process in the stratum, values can be taken based on previous construction cases and relevant construction experience and do not participate in the orthogonal experiment of this stratum.

[0063] In an actual engineering case, if the global sensitivity analysis of the construction process parameters for each stratum shows that the gas flow rate and water flow rate are both insensitive parameters, then the single-tube method with the lowest construction cost is selected for the jet grouting pile construction process. In the numerical simulation, the gas flow rate and water flow rate of the jet grouting pile construction in each stratum are both taken as 0, and the gas flow rate and water flow rate do not participate in the orthogonal experiment; if there is a global sensitivity analysis of the construction process parameters in the stratum type showing that the gas flow rate is a sensitive parameter, while the water flow rate for all stratum soils is an insensitive parameter, then the double-tube method is selected for the jet grouting pile construction process. In the numerical simulation, the water flow rate of the jet grouting pile construction in each stratum is taken as 0 and does not participate in the orthogonal experiment, and the gas flow rate participates in the orthogonal experiment; in other cases, the triple-tube method is default used for construction, and the gas flow rate and water flow rate of the jet grouting pile construction in each stratum participate in the orthogonal experiment.

[0064] In an alternative embodiment, taking the jet grouting pile construction of a certain section of the foundation pit of the Yangtze River Bridge project as an example, the designed pile length is 54.2 m. The K-medoids method is used to classify the 1# stratum as silt, the 2# stratum as silty soil, and the 3# stratum as clay.

[0065] For the 3# stratum of cohesive soil type, both the air flow rate parameter and the water flow rate parameter in the jet grouting pile construction process parameters are sensitive parameters, and both the air flow rate parameter and the water flow rate parameter participate in the orthogonal test in the numerical simulation.

[0066] Specifically, the orthogonal table of the sensitive parameters of the jet grouting pile construction process under different construction strata in the actual construction case is shown in Table 3, where "*" represents the insensitive parameters with default values based on previous construction cases and relevant construction experience.

[0067] Table 3

[0068]

[0069] Specifically, import the relevant construction stratum parameters and the jet grouting pile construction parameters in Table 3 into the numerical simulation model of the jet grouting pile construction. Use the software DLSM to fix the upper surface of the jet grouting pile model and apply a speed of 0.01 m / s from bottom to top to the lower surface to obtain the peak value of the unconfined compressive strength of different jet grouting piles; use the seepage flow extraction function provided by the COMSOL finite element analysis software to calculate the permeability coefficient of different jet grouting piles. Taking the 1# silt stratum as an example, the evaluation parameters of the jet grouting piles under the combination of various construction process parameters in different stratum types are obtained through numerical simulation, as shown in Table 4:

[0070] Table 4

[0071]

[0072] S4. According to the simulated data sample set, respectively construct the jet grouting pile strength prediction model for the different stratum soil categories, and then obtain the prediction result of the jet grouting pile forming quality.

[0073] Among them, S4 specifically includes the following steps:

[0074] S41. Normalize the simulated data sample set to obtain the normalized data.

[0075] Specifically, when normalizing the data, the following relationship is satisfied:

[0076]

[0077] Among them, is the normalized data, is the sample data, is the minimum value of the sample data, is the maximum value of the sample data.

[0078] S42. Obtain the initialization parameters of the jet grouting pile strength prediction model, and divide the simulated data sample set into pure subsets through recursive splitting.

[0079] Specifically, based on the decision tree algorithm, the simulated data sample set is divided into pure subsets in a recursive splitting manner, and the Gini index is used to measure the purity of the pure subsets. The Gini index satisfies the following relationship:

[0080]

[0081] Among them, is the Gini index of the pure subset is the number of categories, is the category, is the category, is the pure subset in the category of the sample proportion.

[0082] S43. Based on the pure subsets, the jet grouting pile strength prediction models are respectively constructed for the different stratum soil types.

[0083] In this embodiment, the random forest algorithm is used to construct the jet grouting pile strength prediction model, and the initialization parameters of the random forest model are selected, including the number of trees, the maximum depth of the trees, and the minimum number of samples required for node splitting.

[0084] Specifically, the jet grouting pile strength prediction model satisfies the following relationship:

[0085]

[0086] Among them, is the classification voting result, represents taking the category that makes the function value the largest, is the number of decision trees, is the decision tree, is the indicator function, is the th prediction result output by the decision tree, is the input sample, is the category.

[0087] Furthermore, based on the jet grouting pile strength prediction model, the corresponding relationship between the construction process parameters of the jet grouting pile and the unconfined compressive strength and permeability coefficient after the jet grouting pile is consolidated and formed in different stratum soil types is established as the prediction result of the jet grouting pile forming quality.

[0088] S44. Train and validate the jet grouting pile strength prediction model to obtain the optimal model hyperparameter combination of the jet grouting pile strength prediction model.

[0089] In this embodiment, the training data set is input into the above jet grouting pile strength prediction model through the input layer to obtain the output result of the output layer. When the prediction accuracy of the jet grouting pile strength prediction model reaches the specified stop condition, the model training is completed. The training data set satisfies the following relationship:

[0090]

[0091] Among them, is the training data set, are the construction process parameters of different stratum soil types, is the unconfined compressive strength after the jet grouting pile is consolidated and formed, is the permeability coefficient after the jet grouting pile is consolidated and formed.

[0092] Furthermore, on the validation set, the trained jet grouting pile strength prediction model is verified using the coefficient of determination to evaluate the accuracy of the jet grouting pile strength prediction model. The coefficient of determination satisfies the following relationship:

[0093]

[0094] Among them, is the coefficient of determination, is the total number of recorded data, is the index variable of the recorded data, is the th predicted value of the recorded data, is the th measured value of the recorded data, is the average value of the recorded data.

[0095] When constructing and training the model, the grid search algorithm is used to repeatedly adjust the model hyperparameters to find the hyperparameter combination that makes the coefficient of determination approach 1. When the preset stop condition is reached, the parameter optimization process ends, and the optimal model hyperparameter combination of the jet grouting pile strength prediction model is obtained.

[0096] Please refer to Figure 3, shown as the schematic diagram of the random forest algorithm process; taking the construction of the jet grouting pile strength prediction model for the 1# silt stratum type as an example, its technical process is as follows: perform outlier detection on the simulated data sample set, remove missing values and outlier samples, divide the processed 500 groups of training data (numbered 1 - 500) and 100 groups of test data (numbered 501 - 600) in a ratio of 5:1, and transform the data into a standard normal distribution through normalization processing; for model training, use the grid search algorithm to optimize the initial weight parameter combination, configure the number of decision trees to be 1000, the upper limit of the tree depth to be 20 layers, and the minimum number of samples for node splitting to be 5. After verification, the prediction accuracy of the constructed jet grouting pile strength prediction model on the test set reaches more than 96%, confirming the reliability of the model. Based on the same modeling process, the jet grouting pile strength prediction models for the 2# silty clay stratum type and the 3# cohesive soil stratum type can be established synchronously.

[0097] S5. Establish constraint conditions, and optimize the prediction results of the jet grouting pile forming quality according to the optimization algorithm to obtain the optimal solution set that meets the constraint conditions.

[0098] In this embodiment, the jet grouting pile evaluation parameters are used as constraint conditions, satisfying the following relationship:

[0099]

[0100]

[0101]

[0102] Among them, and are constraint conditions, is the minimum unconfined compressive strength obtained based on the jet grouting pile strength prediction model, is the minimum unconfined compressive strength allowed by the project, is the maximum permeability coefficient obtained based on the jet grouting pile strength prediction model, is the maximum permeability coefficient allowed by the project, is the unconfined compressive strength of the construction process parameters of this group of jet grouting piles in each stratum obtained based on the jet grouting pile strength prediction model, is the permeability coefficient of the construction process parameters of this group of jet grouting piles in each stratum obtained based on the jet grouting pile strength prediction model.

[0103] It should be noted that the minimum unconfined compressive strength allowed by the project is 1.5 MPa, and the maximum permeability coefficient allowed by the project is 1E - 7 cm / s.

[0104] Furthermore, the Archive-based Micro Genetic Algorithm (AMGA) is used as the optimization algorithm to optimize the prediction results of the jet grouting pile forming quality, and the Pareto optimal solution set that meets the constraint conditions is obtained.

[0105] First, determine the unconfined compressive strength and permeability coefficient of the jet grouting pile after consolidation in each stratum as the constraint conditions, and take the construction cost of the jet grouting pile as the optimization objective; second, select the basic parameters such as the iteration times, population size, crossover and mutation probabilities of the AMGA algorithm, create the initial population and initialize the archive; then, select non-dominated individuals through binary constraint competition; then, in the current archive, screen out non-dominated individuals according to the domination relationship; next, after the AMGA algorithm generates the initial chromosome, dynamically detect the domination relationship between the candidate solution and the archive: if the candidate solution is dominated by the archived individuals, it is eliminated, if there is a non-domination relationship, it is stored in the archive, if the candidate solution dominates the archived individuals, it is stored and the dominated individuals are removed to maintain the high-quality non-dominated solution set of the archive; finally, judge whether the AMGA algorithm reaches the maximum iteration times. If not, return to the previous step. If so, end the algorithm, and the output archive includes the Pareto optimal solution set that meets the constraint conditions.

[0106] According to the construction process parameters of the jet grouting pile, the chromosome of the AMGA algorithm has 6 gene loci, namely the pilot hole diameter, cement content, water-cement ratio, grouting flow rate, air flow rate and water flow rate. The fitness of the chromosome is measured according to the unconfined compressive strength, permeability coefficient and economic optimization objectives of the jet grouting pile after consolidation. The key operating parameters of the genetic algorithm are configured as follows: the population size is 30, the crossover probability is 0.8, the mutation probability is 0.55, and the maximum iteration times is 3000 times.

[0107] Please refer to Figure 4 for the schematic diagram of the archive micro genetic algorithm process; extract the elite individuals in the archive through the domination relationship judgment. If the candidate solution is dominated by the archived individuals, it will be automatically eliminated. If there is a non-domination relationship with the archived individuals, it will be included in the archive. If it dominates the archived individuals, it will replace the dominated items, so as to achieve the efficient update of the archive set; through the iteration termination condition judgment, when the preset maximum iteration times is reached, the output archive set includes the Pareto optimal solution set, and the Pareto optimal solution set is shown in Table 5:

[0108] Table 5

[0109]

[0110] S6. Combining the actual construction situation of the jet grouting pile, optimize and screen the optimal solution set according to the optimal solution screening method to obtain the optimal construction parameters.

[0111] In this embodiment, by referring to relevant similar projects and market research, the corresponding equation between the construction cost of the jet grouting pile and the construction process parameters is obtained and used as the optimization objective, satisfying the following relationship:

[0112]

[0113] Wherein, is the construction cost of the jet grouting pile, is the quantity of the medium material, is the medium material, is the unit volume cost of the medium material, is the consumption of the medium material.

[0114] It should be noted that the medium material includes cement, admixture, accelerator and suspending agent; its unit volume cost includes the cost of the material itself, mechanical cost, labor cost, equipment loss cost and other costs.

[0115] On the premise of meeting the constraint conditions, the construction cost of the jet grouting pile is used as the standard for evaluating the overall performance of the jet grouting pile process method and the selection of relevant parameters. The smaller the function value of the construction cost of the jet grouting pile, the better the method.

[0116] It should be particularly pointed out that under the established construction process and parameter combination, the construction cost of the jet grouting pile can be quantitatively calculated. This cost model has the characteristic of being independent of the formation, and its numerical results are not affected by the change of formation conditions.

[0117] In this embodiment, the relevant parameters in the Pareto optimal solution set are optimized based on the actual construction situation of the jet grouting pile. Specifically, when the parameter values of the air flow rate and the water flow rate both approach zero or are significantly lower than the process threshold, it is determined that the single-tube method construction is applicable; when only the water flow rate parameter approaches zero or is significantly lower than the process threshold, and the air flow rate meets the specification requirements, it is determined that the double-tube method construction process is adopted; for the predrilled hole diameter, rounding up is used.

[0118] In an alternative embodiment, when the water flow rate in the optimal solution is significantly lower than the process threshold and the air flow rate meets the specification requirements, it is determined that the double-tube method construction process is adopted; at the same time, based on the actual engineering parameter values, the predrilled hole diameter is taken as 190 mm; after substituting the obtained construction optimal parameters into the numerical simulation model of the jet grouting pile construction, the output results are the unconfined compressive strength , the permeability coefficient , which does not meet the construction requirements of this example.

[0119] Furthermore, the optimal solution screening method is implemented by a step-by-step verification mechanism to obtain the jet grouting pile construction plan with the lowest cost under the satisfaction of constraint conditions. Specifically, it includes: First, the result after optimizing the global optimal solution in the Pareto optimal solution set is input into the numerical simulation model of jet grouting pile construction for calculation to obtain the response function; Subsequently, a judgment function is constructed based on the constraint conditions to determine whether the optimal solution meets the construction feasibility requirements; If the conditions are not met, the above verification process is iteratively executed in the order of Pareto levels until the first optimized solution that meets the conditions is obtained as the construction optimal parameters.

[0120] Repeat the above step-by-step verification mechanism in the order of Pareto levels, and the first optimized solution that meets the constraint conditions is shown in Table 6:

[0121] Table 6

[0122]

[0123] After substituting the optimized solution in Table 6 into the numerical simulation model of jet grouting pile construction, the result is the unconfined compressive strength , the permeability coefficient , which meets the construction requirements of this example; this optimized solution is the final construction parameter solution and serves as the construction optimal parameters.

[0124] Please refer to Figure 5 , which is a schematic diagram of the construction technology of the triple-tube method for jet grouting piles; when using the triple-tube method for construction, the entire length of the pilot hole is divided into three parts: the overburden layer, the effective reinforcement section, and the ultra-deep pilot hole; a steel casing is set in the overburden layer; in the effective reinforcement section, high-pressure "steam and water" is used for cutting; in the ultra-deep pilot hole, high-pressure mud is used for cutting and stirring; and the construction of the jet grouting pile is achieved through the drill pipe and mud discharge treatment; at this time, the construction cost of a single jet grouting pile is 13,200 yuan.

[0125] Please refer to Figure 6 , in an alternative embodiment, the present invention provides a system for predicting the pile-forming quality and construction optimal parameters of jet grouting piles. The system includes an input device, an output device, a processor, and a memory. The hardware facilities are interconnected with each other. Among them, the memory is used to store computer programs, and the computer programs include program instructions. The processor is configured to call the program instructions to execute the specific steps of the related embodiments of the method for predicting the pile-forming quality and construction optimal parameters of jet grouting piles provided by the present invention. The system for predicting the pile-forming quality and construction optimal parameters of jet grouting piles provided by the present invention has a complete structure, is objective and stable, and improves the overall applicability and practical application ability of the present invention.

[0126] A method and system for predicting the pile-forming quality and construction optimal parameters of jet grouting piles proposed by the present invention have significant advantages, including:

[0127] 1. In view of the fact that geological condition changes will significantly affect the strength and anti-seepage characteristics of jet grouting piles, the present invention uses the K-medoids clustering algorithm to group the formation performance characteristics, and conducts sensitivity quantification and ranking on the formation parameters of each cluster based on the PAWN global sensitivity analysis, extracts the key sensitive parameter set, and thus establishes a partition prediction model. Through the input parameter dimensionality reduction and model structure adaptation mechanism, the prediction accuracy and engineering applicability of the optimized solution of the jet grouting pile process parameters are significantly improved.

[0128] 2. The present invention searches for the optimal hyperparameters of the random forest model based on the grid search algorithm, which can quickly traverse the hyperparameter combinations, avoid the blindness of traditional grid search and random search, effectively overcome the problem of combinatorial explosion of traditional parameter optimization methods in high-dimensional spaces, and further improve the accuracy of the prediction model.

[0129] 3. Based on the AMGA algorithm, the present invention sets the construction cost of the jet grouting pile as the target optimization function, and at the same time sets the strength and anti-seepage performance after the consolidation and formation of the jet grouting pile as the constraint conditions, so as to comprehensively evaluate the rationality of the selection of jet grouting pile construction parameters, ensure that while reducing the cost, the performance of the jet grouting pile meets the requirements of engineering specifications, and thus ensure the stability and safety of the construction.

[0130] 4. The present invention takes into account the coupling relationship between different formations and jet grouting piles in actual engineering, ensures that the optimal process parameter combination is applicable to engineering under the complex geological conditions of multi-layer intercalation, and significantly improves the reliability of predicting the optimal construction parameters of jet grouting piles. At the same time, the Pareto optimal solution set is optimized based on the actual engineering parameter values, and the optimized solution is substituted back into the numerical model for verification, ensuring the feasibility of the prediction solution in actual engineering.

[0131] In summary, the method and system for predicting the pile-forming quality and construction optimal parameters of jet grouting piles provided by the method of the present invention combine sensitivity analysis, random forest and optimization algorithms, improve the scientificity and effectiveness of the jet grouting pile construction process method and related parameter selection in an algorithm-driven manner, thereby enhancing construction safety, reducing construction costs, and improving engineering benefits. The method of the present invention is easy to understand, simple to calculate, has a small workload, is convenient for engineering applications, and provides a theoretical basis and technical support for the further development of engineering intelligent algorithm technology.

[0132] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered within the scope of the claims and the description of the present invention.

Claims

1. A method for predicting the quality of rotary jet grouting piles and the optimal construction parameters, characterized in that, It includes the following steps: Construct a data sample set based on similar historical engineering cases by obtaining construction stratum parameters, construction process parameters, and jet grouting pile evaluation parameters; Classify the construction stratum soil of the jet grouting pile to obtain different stratum soil categories, and obtain the construction process sensitive parameters of the different stratum soil categories; Conduct an orthogonal test on the construction process sensitive parameters to obtain the orthogonal test results, so as to establish a numerical simulation model for jet grouting pile construction to obtain a simulated data sample set; According to the simulated data sample set, respectively construct jet grouting pile strength prediction models for the different stratum soil categories, and then obtain the prediction results of the jet grouting pile forming quality; Establish constraint conditions, and optimize the prediction results of the jet grouting pile forming quality according to the optimization algorithm to obtain an optimal solution set that meets the constraint conditions; Combined with the actual jet grouting pile construction situation, optimize and screen the optimal solution set according to the optimal solution screening method to obtain the optimal construction parameters; The step of respectively constructing jet grouting pile strength prediction models for the different stratum soil categories according to the simulated data sample set, and then obtaining the prediction results of the jet grouting pile forming quality includes: Normalize the simulated data sample set to obtain normalized data; Obtain the initial parameters of the jet grouting pile strength prediction model, and divide the simulated data sample set into pure subsets through recursive splitting; Based on the pure subsets, respectively construct the jet grouting pile strength prediction models for the different stratum soil categories; Train and verify the jet grouting pile strength prediction model to obtain the optimal model hyperparameter combination of the jet grouting pile strength prediction model; Among the different stratum soil categories, establish the corresponding relationship between the construction process parameters and the jet grouting pile evaluation parameters by using the jet grouting pile strength prediction model as the prediction result of the jet grouting pile forming quality.

2. The method for predicting the pile-forming quality and construction optimal parameters of the jet grouting pile according to claim 1, wherein, The step of constructing a data sample set based on similar historical engineering cases by obtaining construction stratum parameters, construction process parameters, and jet grouting pile evaluation parameters includes: The construction stratum parameters include the stratum distribution and soil properties of the soil in the construction area where the jet grouting pile is located. The soil properties include the physical indexes and mechanical properties of the soil. The physical indexes include natural density, moisture content, void ratio, dry density, liquidity index, and standard penetration blow count. The mechanical properties include compression modulus, shear strength, and Poisson's ratio; The construction process parameters include nozzle diameter, pilot hole diameter, cement content, water-cement ratio, grout injection flow rate, air flow rate, water flow rate, and lifting speed; The jet grouting pile evaluation parameters include the unconfined compressive strength and permeability coefficient after the jet grouting pile is consolidated and formed.

3. The jet grouting pile forming quality and construction optimal parameter prediction method according to claim 1, characterized in that, The step of classifying the construction stratum soil of the jet grouting pile to obtain different stratum soil categories, and obtaining the construction process sensitive parameters of the different stratum soil categories includes: Classify the construction stratum soil to obtain the different stratum soil categories, including silt, silty clay, clay, plain fill, and sand; Conduct a global sensitivity analysis on the construction process parameters of the different stratum soil categories based on the jet grouting pile evaluation parameters to obtain the construction process sensitive parameters.

4. The jet grouting pile forming quality and construction optimal parameter prediction method according to claim 1, wherein, Performing an orthogonal experiment on the sensitive parameters of the construction process to obtain orthogonal experiment results, and establishing a numerical simulation model for jet grouting pile construction to obtain a simulated data sample set, including: Defining the value range of the sensitive parameters of the construction process based on the similar historical engineering cases, and using the value range to expand the target unknown parameters to construct a simulation test case; Performing numerical simulation according to the simulation test case, so as to establish the numerical simulation model for jet grouting pile construction; Obtaining the evaluation parameters of the jet grouting pile as the simulated data sample set according to the numerical simulation model for jet grouting pile construction.

5. The jet grouting pile forming quality and construction optimal parameter prediction method according to claim 1, characterized in that Dividing the simulated data sample set into pure subsets by recursive splitting, including: Measuring the purity of the pure subset by using the Gini index, and the Gini index includes: wherein, is the Gini index of the pure subset , is the number of classes is the class is the sample proportion of class in the pure subset .

6. The prediction method for the quality of rotary jet grouting piles and the optimal construction parameters according to claim 1, characterized in that, Constructing the strength prediction model for the jet grouting pile respectively for different stratum soil types, including: in, To categorize the voting results, It means to take the category that makes the function value the largest. is the number of decision trees, For decision tree, is the indicator function, For the The prediction results output by the decision tree are: is the input sample, For category.

7. The prediction method for the quality of rotary jet grouting pile formation and the optimal construction parameters according to claim 1, characterized in that, Establishing the constraint conditions, and optimizing the prediction result of the jet grouting pile forming quality according to the optimization algorithm to obtain the optimal solution set that meets the constraint conditions, including: Taking the evaluation parameters of the jet grouting pile as the constraint conditions, including: Among them, and are constraint conditions, is the minimum unconfined compressive strength obtained from the jet grouting pile strength prediction model, is the minimum unconfined compressive strength allowed by the project, is the maximum permeability coefficient obtained from the jet grouting pile strength prediction model, is the maximum permeability coefficient allowed by the project.

8. The prediction method for the quality of rotary jet grouting pile formation and the optimal construction parameters according to claim 1, characterized in that Combining the actual construction situation of the jet grouting pile, and optimizing and screening the optimal solution set according to the optimal solution screening method to obtain the optimal construction parameters, including: Obtaining the corresponding equation between the construction cost of the jet grouting pile and the construction process parameters, including: Among them, is the construction cost of the jet grouting pile, is the quantity of the medium material, is the medium material, is the unit volume cost of the medium material, is the consumption of the medium material; Under the constraint conditions, according to the optimal solution screening method, using a step-by-step verification mechanism to optimize and screen the optimal solution set to obtain the jet grouting pile construction plan with the lowest construction cost, so as to obtain the optimal construction parameters.

9. A prediction system for the quality of rotary jet grouting piles and the optimal construction parameters, characterized in that The system includes an input device, an output device, a processor and a memory. The input device, the output device, the processor and the memory are interconnected. Among them, the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute the jet grouting pile forming quality and optimal construction parameter prediction method according to any one of claims 1-8.

Images