Ecological bag slope protection structure intelligent optimization method and system based on parameter sensitivity

Abstract

The application discloses an ecological bag slope protection structure intelligent optimization method and system based on parameter sensitivity, relates to the technical field of ecological data processing, and comprises the following steps: collecting design parameters of an ecological bag slope protection structure and establishing a finite element numerical model; adopting Bishop method and strength reduction method to calculate overall stability safety factors and fusing to obtain a comprehensive safety factor; performing local sensitivity, global sensitivity and coupling influence degree analysis on the design parameters, calculating comprehensive sensitivity indexes of each parameter, and screening a high-sensitivity parameter set; taking the high-sensitivity parameter set as optimization variables, constructing a multi-objective optimization model, and solving to obtain a Pareto optimal solution set; and constructing a comprehensive decision scoring function, selecting an optimal design scheme from the Pareto optimal solution set, and outputting. The application can quantitatively identify key parameters affecting the safety of the structure, and realize automatic generation of a safety, economy and ecology comprehensive optimal scheme.

Description

Technical Field

[0001] This invention relates to the field of ecological data processing technology, specifically to a method and system for intelligent optimization of eco-bag slope protection structures based on parameter sensitivity. Background Technology

[0002] Eco-bag slope protection structures are a new type of flexible slope protection structure that combines geosynthetic materials with vegetation slope protection technology. They are widely used in river management, highway slope protection, and mine ecological restoration. The stability of this structure is influenced by a combination of factors, including the physical and mechanical parameters of the soil filling within the eco-bag, slope geometric parameters, hydrological parameters, and vegetation parameters.

[0003] Currently, the design of eco-bag slope protection structures mainly relies on engineering analogies and experience to determine preliminary design schemes; limit equilibrium methods or numerical analysis methods are used to verify the safety factor under a single working condition; if the requirements are not met, parameters are adjusted based on design experience and recalculated until the specifications are met. However, this approach has the following shortcomings: the adjustment of design parameters depends excessively on the engineer's personal experience, making it difficult to guarantee the global optimality of the design scheme; the interaction and coupling effects between various design parameters are not quantitatively assessed, leading to unreasonable allocation of design safety redundancy; and the automatic generation of a comprehensive optimal design scheme that integrates safety, economy, and ecology cannot be achieved.

[0004] Therefore, there is an urgent need for a parameter-sensitive intelligent optimization method and system for ecological bag slope protection structures to solve the above problems. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to address the shortcomings of the existing technology by providing an intelligent optimization method and system for ecological bag slope protection structures based on parameter sensitivity.

[0006] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0007] The intelligent optimization method for ecological bag slope protection structure based on parameter sensitivity includes the following steps:

[0008] Step S1: Collect the design parameters of the ecological bag slope protection structure and establish a finite element numerical model;

[0009] Step S2: Calculate the overall stability safety factor of the eco-bag slope protection structure using the Bishop method and the strength reduction method respectively, and combine them to obtain the comprehensive safety factor. Also, calculate the anti-sliding safety factor and anti-overturning safety factor of a single eco-bag in the water level fluctuation zone.

[0010] Step S3: Perform sensitivity analysis on the design parameters of the ecological bag slope protection structure, calculate the comprehensive sensitivity index of each parameter, and select a set of highly sensitive parameters based on the comprehensive sensitivity index.

[0011] Step S4: Using the set of highly sensitive parameters as optimization variables, and with the optimization objectives of maximizing the comprehensive safety factor, minimizing engineering costs, and maximizing ecological benefits, solve to obtain the Pareto optimal solution set;

[0012] Step S5: Normalize the comprehensive safety factor, engineering cost, and ecological benefits of each solution in the Pareto optimal solution set, construct a comprehensive decision scoring function, and select and output the optimal design scheme based on the comprehensive decision score.

[0013] Furthermore, step S1 specifically includes the following steps:

[0014] Step S1.1: Collect the design parameters of the ecological bag slope protection structure, including geometric parameters, material parameters, hydrological parameters and vegetation parameters;

[0015] Step S1.2: Based on the collected design parameters, establish a finite element numerical model of the ecological bag slope protection structure;

[0016] Step S1.3: Mesh the finite element numerical model and set contact elements at the interface between the eco-bag and the soil.

[0017] Furthermore, step S2 specifically includes the following steps:

[0018] Step S2.1: Calculate the overall stability safety factor of the eco-bag slope protection structure using the Bishop method;

[0019] Step S2.2: Calculate the overall stability safety factor of the ecological bag slope protection structure using the strength reduction method. In the finite element numerical analysis, the shear strength parameters of the soil and rock mass are gradually reduced according to the same reduction factor. The reduced strength parameters are substituted into the model for iterative calculation. When the calculation does not converge or the plastic zone is connected, the corresponding reduction factor is the safety factor.

[0020] Step S2.3: Take the safety factor calculated by the Bishop method and the safety factor calculated by the strength reduction method and calculate the weighted average to obtain the comprehensive safety factor, and the sum of the weighting factors is 1.

[0021] Step S2.4: In the water level fluctuation zone of the eco-bag slope protection structure, calculate the anti-sliding safety factor and anti-overturning safety factor of a single eco-bag.

[0022] Furthermore, step S3 specifically includes the following steps:

[0023] Step S3.1: Determine the set of sensitive parameters to be analyzed. The sensitive parameters include soil cohesion, soil internal friction angle, soil unit weight, moisture content, slope height, slope ratio, ecological bag thickness, ecological bag protection range thickness, river flow velocity, vegetation root depth, and vegetation root density.

[0024] Step S3.2: Collect historical data measured on-site in the river section to be treated. Calculate the actual coefficient of variation of each parameter based on the measured historical data. After normalizing each parameter, use it as the independent variable and the comprehensive safety factor as the dependent variable to establish a multiple linear regression equation. Use the least squares method to estimate the standardized regression coefficient of each parameter. Multiply the coefficient of variation with the standardized regression coefficient to obtain the local sensitivity of each parameter.

[0025] Step S3.3: Calculate the global sensitivity of each parameter. The global sensitivity is equal to the comprehensive safety factor when the parameter takes the physical maximum value and the other parameters take the baseline value, minus the comprehensive safety factor when the parameter takes the physical minimum value and the other parameters take the baseline value, and then divided by the comprehensive safety factor when all parameters take the baseline value.

[0026] Step S3.4: Calculate the coupling influence of each parameter. For each parameter, take several value points at equal intervals within its physical feasible domain. For each value point, randomly generate several samples within the physical feasible domains of other parameters and calculate the corresponding comprehensive safety factor. Then, calculate the ratio of the dispersion of the conditional mean of the safety factor to the conditional variance when the parameter takes different values. Use this ratio as the coupling influence.

[0027] Step S3.5: Normalize the local sensitivity, global sensitivity, and coupling influence respectively. Multiply the three normalized values ​​by their corresponding weight coefficients and sum them to obtain the comprehensive sensitivity index of each parameter. The sum of the three weight coefficients is 1.

[0028] Step S3.6: Sort the parameters from largest to smallest according to the comprehensive sensitivity index, and select the parameters whose comprehensive sensitivity index is greater than 1.0 to 1.5 times the average value of all parameters to form a set of high sensitivity parameters.

[0029] Furthermore, step S4 specifically includes the following steps:

[0030] Step S4.1: Use the set of highly sensitive parameters as optimization variables;

[0031] Step S4.2: Construct a multi-objective optimization function with the optimization objectives of maximizing the comprehensive safety factor, minimizing engineering costs, and maximizing ecological benefits;

[0032] Step S4.3: Set constraints, including that the overall safety factor must be greater than or equal to the preset safety threshold, each optimization variable must take values ​​within its physical feasible domain, and each inequality constraint function must meet the requirements.

[0033] Step S4.4: Use a non-dominated sorting genetic algorithm with an elitist strategy to solve the multi-objective optimization function and obtain the Pareto optimal solution set.

[0034] Furthermore, in step S4.2, the project cost includes material cost, construction cost, and transportation cost. The material cost is the sum of the cost of the eco-bags, the cost of the fill soil, the cost of the stone materials, and the cost of the vegetation materials. The construction cost is the product of the total earthwork volume and the unit earthwork construction price. The transportation cost is the product of the total material weight, the transportation distance, and the unit weight unit distance transportation price.

[0035] Furthermore, in step S4.2, the ecological benefits are calculated based on a weighted sum of vegetation coverage, biodiversity, and landscape harmony. The vegetation coverage is calculated exponentially based on the product of vegetation root density and vegetation root depth. The biodiversity is calculated based on the ratio of vegetation root depth to slope height. The harmony is calculated based on the ratio of river flow velocity to ideal flow velocity.

[0036] Furthermore, step S5 specifically includes the following steps:

[0037] Step S5.1: For each solution in the Pareto optimal solution set, normalize the comprehensive safety factor, engineering cost, and ecological benefits according to the maximum and minimum values ​​of each objective in the solution set, and obtain three normalized values ​​for each solution.

[0038] Step S5.2: Construct a comprehensive decision scoring function. Multiply the three normalized values ​​of each solution by the corresponding priority weight coefficients and sum them to obtain a weighted reward term. Introduce a penalty term. When the normalized value of any objective is lower than the preset acceptance threshold, deduct the penalty amount from the comprehensive score of the solution. The penalty amount is the product of the penalty intensity coefficient and the deviation of the normalized value from the acceptance threshold.

[0039] Step S5.3: Select the Pareto solution with the highest comprehensive decision score as the optimal design scheme;

[0040] Step S5.4: Output the values ​​of the optimization variables corresponding to the optimal design scheme, as well as the corresponding comprehensive safety factor, engineering cost, and ecological benefits.

[0041] A parameter-sensitive intelligent optimization system for eco-bag slope protection structures is used to implement any of the parameter-sensitive intelligent optimization methods for eco-bag slope protection structures, including:

[0042] The data acquisition and modeling module is used to collect design parameters of the eco-bag slope protection structure and establish a finite element numerical model.

[0043] The safety factor calculation module is used to calculate the overall stability safety factor using the Bishop method and the strength reduction method respectively, and then combine them to obtain the comprehensive safety factor. It also calculates the anti-sliding safety factor and anti-overturning safety factor of a single ecological bag in the water level fluctuation zone.

[0044] The sensitivity analysis module is used to perform multi-dimensional sensitivity analysis on design parameters, calculate the comprehensive sensitivity index of each parameter, and select a set of highly sensitive parameters based on the comprehensive sensitivity index.

[0045] The multi-objective optimization module is used to solve for the Pareto optimal solution set by taking a set of highly sensitive parameters as optimization variables and taking the optimization objectives of maximizing the comprehensive safety factor, minimizing the engineering cost, and maximizing the ecological benefits.

[0046] The scheme decision output module is used to normalize the comprehensive safety factor, engineering cost and ecological benefits of each solution in the Pareto optimal solution set, construct a comprehensive decision scoring function, select the optimal design scheme based on the comprehensive decision score and output it.

[0047] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the parameter-sensitive intelligent optimization methods for eco-bag slope protection structures.

[0048] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0049] 1. This invention proposes a multi-dimensional sensitivity analysis method that integrates local sensitivity, global sensitivity, and coupling influence. Local sensitivity assesses the actual impact of parameters based on the natural variability of parameters in engineering measured data. Global sensitivity assesses the overall change in the safety factor when parameters change from the physical lower limit to the upper limit. Coupling influence assesses the contribution of the interaction effect between parameters to the safety factor. The three dimensions complement each other and can comprehensively identify key parameters affecting structural safety, providing a scientific basis for optimized design.

[0050] 2. This invention uses multi-dimensional sensitivity analysis to reduce the dimensionality of design parameters, and only includes highly sensitive parameters in the set of optimization variables. This significantly reduces the dimensionality of the multi-objective optimization problem and improves the computational efficiency and convergence speed of the NSGA-II algorithm.

[0051] 3. This invention constructs a mathematical model that includes three optimization objectives: comprehensive safety factor, engineering cost, and ecological benefits. It realizes a quantitative trade-off between engineering safety, economic cost, and ecological benefits, and provides a scientific basis for design decisions.

[0052] 4. This invention adopts a comprehensive decision-making scoring function that combines weighted rewards and penalties. It reflects engineering preferences through priority weights and excludes schemes with low normalized values ​​on any objective dimension through penalty items, ensuring that the final selected design scheme has comprehensive performance that meets engineering preferences. Attached Figure Description

[0053] Other features, objects, and advantages of the invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0054] Figure 1 This is a flowchart illustrating an embodiment of the present invention;

[0055] Figure 2 This is a schematic diagram of the system module structure according to an embodiment of the present invention;

[0056] Figure 3 This is a flowchart illustrating the process of selecting a set of highly sensitive parameters according to an embodiment of the present invention.

[0057] Figure 4 This is a flowchart illustrating the multi-objective optimization and scheme decision-making process according to an embodiment of the present invention. Detailed Implementation

[0058] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0059] like Figure 1 As shown, the intelligent optimization method for ecological bag slope protection structures based on parameter sensitivity includes the following steps:

[0060] Step S1: Collect the design parameters of the ecological bag slope protection structure and establish a finite element numerical model;

[0061] Step S2: Calculate the overall stability safety factor of the eco-bag slope protection structure using the Bishop method and the strength reduction method respectively, and combine them to obtain the comprehensive safety factor. Also, calculate the anti-sliding safety factor and anti-overturning safety factor of a single eco-bag in the water level fluctuation zone.

[0062] Step S3: Perform sensitivity analysis on the design parameters of the ecological bag slope protection structure, calculate the comprehensive sensitivity index of each parameter, and select a set of highly sensitive parameters based on the comprehensive sensitivity index.

[0063] Step S4: Using the set of highly sensitive parameters as optimization variables, and with the optimization objectives of maximizing the comprehensive safety factor, minimizing engineering costs, and maximizing ecological benefits, solve to obtain the Pareto optimal solution set;

[0064] Step S5: Normalize the comprehensive safety factor, engineering cost, and ecological benefits of each solution in the Pareto optimal solution set, construct a comprehensive decision scoring function, and select and output the optimal design scheme based on the comprehensive decision score.

[0065] Step S1 specifically includes the following steps:

[0066] S1.1 Collect the design parameters of the ecological bag slope protection structure, including geometric parameters, material parameters, hydrological parameters and vegetation parameters;

[0067] S1.2 Based on the collected design parameters, a finite element numerical model of the eco-bag slope protection structure is established. The finite element numerical model uses the Mohr-Coulomb constitutive model to describe the mechanical behavior of the eco-bag filling soil and the foundation soil.

[0068] S1.3. Mesh the finite element numerical model and set contact elements at the interface between the eco-bag and the soil to simulate the interfacial friction characteristics between the eco-bag and the soil.

[0069] Step S2 specifically includes the following steps:

[0070] Step S2.1: Calculate the overall stability safety factor of the eco-bag slope protection structure using the Bishop method. The Bishop method is a circular arc sliding surface analysis method based on the limit equilibrium theory. This method assumes that there are only horizontal forces and no vertical shear forces between the soil strips. The sliding body is divided into several vertical soil strips along the potential sliding surface of the slope. Force balance and moment balance equations are established for each soil strip. The overall stability safety factor of the slope is obtained through iterative calculation.

[0071] Step S2.2: Calculate the overall stability safety factor of the ecological bag slope protection structure using the strength reduction method. The basic principle of the strength reduction method is that in the finite element numerical analysis, the shear strength parameters of the soil and rock mass, cohesion and internal friction angle, are gradually reduced according to the same reduction factor. The reduced strength parameters are substituted into the model for iterative calculation. When the calculation does not converge or the plastic zone is connected, the slope reaches the critical failure state. The corresponding reduction factor at this time is the safety factor.

[0072] Step S2.3: Take the safety factor calculated by the Bishop method and the safety factor calculated by the strength reduction method and calculate the weighted average to obtain the comprehensive safety factor, and the sum of the weighting factors is 1.

[0073] Step S2.4: In the water level fluctuation zone of the eco-bag slope protection structure, calculate the anti-sliding safety factor and anti-overturning safety factor of a single eco-bag.

[0074] The specific formula for the comprehensive safety factor is as follows:

[0075]

[0076] in, This represents the overall safety factor. This represents the overall stability safety factor calculated using the Bishop method. This represents the overall stability safety factor calculated using the strength reduction method. This represents the Bishop weighting coefficient, with a value ranging from 0.35 to 0.65, and typically 0.5. This represents the weighting coefficient for the intensity reduction method, with a value ranging from 0.35 to 0.65, and typically 0.5.

[0077] The specific formulas for the anti-slip safety factor and anti-overturning safety factor of a single eco-bag are as follows:

[0078]

[0079] in, This represents the anti-slip safety factor of a single eco-bag, used to assess the likelihood of the eco-bag slipping and failing along the contact surface. A higher value indicates stronger anti-slip capability; the design allowable value should not be less than 1.3. This represents the overturning safety factor of a single eco-bag, used to assess the likelihood of the eco-bag overturning and failing around its front toe. A higher value indicates stronger overturning resistance; the design allowable value should not be less than 1.5. This indicates the weight of the eco-bag itself, in kN. This indicates the weight of the soil filling the eco-bag, in kN. This indicates the buoyancy force acting on the eco-bag, expressed in kN. This represents the coefficient of friction between the eco-bag and the underlying surface. It is dimensionless, determined by the properties of the contact surface material, and ranges from 0.35 to 0.50. This represents the drag force exerted by the water flow on the eco-bag, expressed in kN. This represents the active earth pressure exerted by the backfill soil on the eco-bag, expressed in kN. This represents the horizontal distance from the line of action of the resultant force of the bag's own weight to the front toe. This represents the vertical distance from the point of application of the water's drag force to the front toe. This represents the vertical distance from the point of application of the resultant earth pressure force to the front toe.

[0080] Step S3 specifically includes the following steps:

[0081] Step S3.1: Determine the set of sensitive parameters to be analyzed. The sensitive parameters include soil cohesion, soil internal friction angle, soil unit weight, moisture content, slope height, slope ratio, ecological bag thickness, ecological bag protection range thickness, river flow velocity, vegetation root depth, and vegetation root density.

[0082] Step S3.2: Collect historical data measured on-site in the river section to be treated. Calculate the actual coefficient of variation of each parameter based on the measured historical data. After normalizing each parameter, use it as the independent variable and the comprehensive safety factor as the dependent variable to establish a multiple linear regression equation. Use the least squares method to estimate the standardized regression coefficient of each parameter. Multiply the coefficient of variation with the standardized regression coefficient to obtain the local sensitivity of each parameter.

[0083] Step S3.3: Calculate the global sensitivity of each parameter. The global sensitivity is equal to the comprehensive safety factor when the parameter takes the physical maximum value and the other parameters take the baseline value, minus the comprehensive safety factor when the parameter takes the physical minimum value and the other parameters take the baseline value, and then divided by the comprehensive safety factor when all parameters take the baseline value.

[0084] Step S3.4: Calculate the coupling influence of each parameter. For each parameter, take several value points at equal intervals within its physical feasible domain. For each value point, randomly generate several samples within the physical feasible domains of other parameters and calculate the corresponding comprehensive safety factor. Then, calculate the ratio of the dispersion of the conditional mean of the safety factor to the conditional variance when the parameter takes different values. Use this ratio as the coupling influence.

[0085] Step S3.5: Normalize the local sensitivity, global sensitivity, and coupling influence respectively. Multiply the three normalized values ​​by their corresponding weight coefficients and sum them to obtain the comprehensive sensitivity index of each parameter. The sum of the three weight coefficients is 1.

[0086] Step S3.6: Sort the parameters from largest to smallest according to the comprehensive sensitivity index, and select the parameters whose comprehensive sensitivity index is greater than 1.0 to 1.5 times the average value of all parameters to form a set of high sensitivity parameters.

[0087] Local sensitivity is calculated based on historical data measured on-site in the treated river section. Multiple sets of historical data from on-site measurements in the treated river section are collected for the j-th parameter. The actual coefficient of variation is calculated based on the measured data. The specific formula is as follows:

[0088]

[0089] in, This represents the actual coefficient of variation of the j-th parameter. This represents the standard deviation of the j-th parameter in the measured data. This represents the mean of the j-th parameter in the measured data;

[0090] Based on measured data, a multiple linear regression equation was established by normalizing each parameter and using it as the independent variable, and the comprehensive safety factor as the dependent variable. The standardized regression coefficients of each parameter were estimated using the least squares method. The local sensitivity was calculated by multiplying the coefficient of variation by the standardized regression coefficients. The specific formula is as follows:

[0091]

[0092] in, This represents the local sensitivity of the j-th parameter, reflecting the degree of influence of the parameter on the overall safety factor when it varies within its actual fluctuation range. The larger the value, the more significant the impact of the parameter's actual fluctuation on the overall safety factor at the engineering site. Represents the standardized regression coefficients. Indicates taking the absolute value;

[0093] The specific formulas for the global sensitivity of each parameter are as follows:

[0094]

[0095] in, This represents the global sensitivity of the j-th parameter, reflecting the relative change in the overall safety factor as the parameter changes from the lower physical limit to the upper physical limit. This represents the physical upper limit value of the j-th parameter. This represents the physical lower limit value of the j-th parameter. This means that all parameters except the j-th parameter take their baseline value. This represents the baseline value of the j-th parameter, that is, its typical representative value in engineering practice. This represents the comprehensive safety factor when the j-th parameter takes the maximum physical value and the other parameters take the baseline value. This represents the overall safety factor when the j-th parameter takes the physical minimum value and the other parameters take the baseline value. This represents the overall safety factor when all parameters are taken at baseline values;

[0096] When the numerical model fails to converge at a certain value, it indicates that the slope has become unstable under that parameter combination. In this case, the corresponding comprehensive safety factor is assigned to 0 and included in the statistics.

[0097] For the j-th parameter, N different values ​​are taken at equal intervals within its physical feasible region. For each value, M sets of samples are randomly generated within the physical feasible regions of the other parameters. The comprehensive safety factor corresponding to each set of samples is calculated. Then, the rate of change of the conditional variance of the safety factor when the parameter takes different values ​​is calculated as the coupling influence degree. The specific formula is as follows:

[0098]

[0099] in, This represents the coupling influence of the j-th parameter; a larger value indicates a stronger coupling effect between this parameter and other parameters. This represents the number of possible values ​​within the physically feasible region. This represents the number of samples randomly sampled from the other parameters when the j-th parameter is fixed. This represents the nth value of the j-th parameter. This represents the m-th random sample with all parameters except the j-th parameter. This indicates that the j-th parameter takes... At that time, the conditional mean of the comprehensive safety factor in sample M, This represents the overall mean of the comprehensive safety factor across all N×M sample groups. This indicates that the j-th parameter takes... Other parameters are the comprehensive safety factor corresponding to the m-th sample group. To represent extremely small positive numbers and avoid having a denominator of zero, it is usually taken as 0.00001;

[0100] The comprehensive sensitivity index of each parameter is calculated by combining local sensitivity, global sensitivity, and coupling influence. The specific formula is as follows:

[0101]

[0102] in, This represents the overall sensitivity index of the j-th parameter. This represents the normalized value of the local sensitivity. This represents the normalized value of the global sensitivity. This represents the normalized value of the coupling effect. The weighting coefficient representing local sensitivity ranges from 0.25 to 0.45. The weighting coefficient representing global sensitivity ranges from 0.25 to 0.45. The weighting coefficient, representing the degree of coupling influence, ranges from 0.15 to 0.35.

[0103] according to The parameters are sorted from largest to smallest, and those with a comprehensive sensitivity index greater than 1.0 to 1.5 times the average of all parameters are selected to form a set of highly sensitive parameters.

[0104] Step S4 specifically includes the following steps:

[0105] Step S4.1: Use the set of highly sensitive parameters as optimization variables;

[0106] Step S4.2: Construct a multi-objective optimization function with the optimization objectives of maximizing the comprehensive safety factor, minimizing engineering costs, and maximizing ecological benefits;

[0107] Step S4.3: Set constraints, including that the overall safety factor must be greater than or equal to the preset safety threshold, each optimization variable must take values ​​within its physical feasible domain, and each inequality constraint function must meet the requirements.

[0108] Step S4.4: Use a non-dominated sorting genetic algorithm with an elitist strategy to solve the multi-objective optimization function and obtain the Pareto optimal solution set.

[0109] In step S4.2, the project cost includes material cost, construction cost, and transportation cost. The material cost is the sum of the cost of ecological bags, soil filling, stone materials, and vegetation materials. The construction cost is the product of the total earthwork volume and the unit earthwork construction price. The transportation cost is the product of the total material weight, the transportation distance, and the unit weight unit distance transportation price.

[0110] In step S4.2, the ecological benefits are calculated based on a weighted sum of vegetation coverage, biodiversity, and landscape harmony. The vegetation coverage is calculated exponentially based on the product of vegetation root density and vegetation root depth. The biodiversity is calculated based on the ratio of vegetation root depth to slope height. The harmony is calculated based on the ratio of river flow velocity to ideal flow velocity.

[0111] The specific formula for the multi-objective optimization function is as follows:

[0112]

[0113] in, Represents a multi-objective optimization function vector. Represents the vector of optimization variables. The comprehensive safety factor function is expressed by optimizing variables. The calculation is performed based on the corresponding parameter values. The project cost function, composed of material costs, construction costs, and transportation costs, aims to minimize these costs; therefore, it takes negative values ​​in the objective vector. The ecological benefit function is represented by the following formula:

[0114]

[0115] in, This represents the vegetation cover weighting coefficient, with a value ranging from 0.20 to 0.50, reflecting the importance of vegetation cover in overall ecological benefits. This represents the biodiversity weighting coefficient, with a value ranging from 0.20 to 0.50, reflecting the importance of biodiversity in overall ecological benefits. This represents the coordination weighting coefficient, with a value ranging from 0.20 to 0.50, reflecting the importance of coordination in overall ecological benefits. This represents the root density of vegetation, and is one of the optimization variables. This represents the root depth of vegetation and is one of the optimization variables. The slope height is one of the optimization variables. This represents the river flow velocity, and is one of the optimization variables. The ideal flow velocity value that best harmonizes with the surrounding landscape is represented by the dimensionless numerical values ​​used for the above parameters.

[0116] The constraints include that the overall safety factor must be greater than or equal to the preset safety threshold, each optimization variable must take values ​​within its physical feasible region, and each inequality constraint function must meet the requirements. The preset safety threshold is determined according to the design specifications for dike engineering, and the anti-sliding safety factor of a single ecological bag must be greater than or equal to 1.3, and the anti-overturning safety factor must be greater than or equal to 1.5. The lower and upper limits of the physical feasible region correspond to the minimum and maximum values ​​allowed for each parameter in actual engineering, respectively. The inequality constraint functions include construction feasibility constraints and land occupation restrictions.

[0117] Construction feasibility constraints refer to the comprehensive requirements for mechanical operation space, material supply, construction technology and construction period during the construction process. They are reflected in specific limits such as minimum site width and minimum working area.

[0118] Land use restrictions refer to the fact that the land type, area, and scope occupied by dikes and temporary facilities shall not exceed the permitted land use indicators in the plan. For example, permanent land shall not exceed the planned red line area, and temporary land shall not exceed the maximum permitted area.

[0119] A non-dominated sorting genetic algorithm (NSGA-II) with an elitist strategy is used to solve the multi-objective optimization function. The population size is set to 50-200 individuals, the maximum number of iterations to 100-500, the crossover probability to 0.7-0.9, and the mutation probability to the reciprocal of the number of optimization variables. After randomly initializing the population within the feasible region, the following operations are performed for each generation: calculating the three objective function values ​​for each individual; performing fast non-dominated sorting to divide the population into multiple Pareto levels; calculating the crowding distance between individuals within the same level; using a tournament selection strategy to select parent individuals, prioritizing individuals with low Pareto levels and large crowding distances; performing simulated binary crossover and polynomial mutation on the selected parent individuals to generate the offspring population; merging the parent and offspring generations, and selecting the next generation based on Pareto level and crowding distance for elitism. This process is repeated until the maximum number of iterations is reached, and the final population containing all individuals with a Pareto level of 1 is output as the Pareto optimal solution set.

[0120] Step S5 specifically includes the following steps:

[0121] Step S5.1: For each solution in the Pareto optimal solution set, normalize the comprehensive safety factor, engineering cost, and ecological benefits according to the maximum and minimum values ​​of each objective in the solution set, and obtain three normalized values ​​for each solution.

[0122] Step S5.2: Construct a comprehensive decision scoring function. Multiply the three normalized values ​​of each solution by the corresponding priority weight coefficients and sum them to obtain a weighted reward term. Introduce a penalty term. When the normalized value of any objective is lower than the preset acceptance threshold, deduct the penalty amount from the comprehensive score of the solution. The penalty amount is the product of the penalty intensity coefficient and the deviation of the normalized value from the acceptance threshold.

[0123] Step S5.3: Select the Pareto solution with the highest comprehensive decision score as the optimal design scheme;

[0124] Step S5.4: Output the values ​​of the optimization variables corresponding to the optimal design scheme, as well as the corresponding comprehensive safety factor, engineering cost, and ecological benefits.

[0125] For each solution in the Pareto optimal solution set, its corresponding comprehensive safety factor, engineering cost, and ecological benefit are extracted. Based on the maximum and minimum values ​​of each objective in the Pareto solution set, the three objectives of each solution are normalized. The safety factor is normalized using maximum normalization, which is the solution's safety factor minus the minimum safety factor in the solution set, divided by the range of safety factors in the solution set. The engineering cost is normalized using minimum normalization, which is the maximum cost in the solution set minus the cost of this solution, divided by the range of costs in the solution set. The ecological benefit is normalized using maximum normalization, which is the solution's ecological benefit minus the minimum ecological benefit in the solution set, divided by the range of ecological benefits in the solution set. The values ​​of the three normalization values ​​are all in the range of 0 to 1.

[0126] Construct a comprehensive decision scoring function, the specific formula of which is:

[0127]

[0128] in, This represents the comprehensive decision score of the a-th Pareto solution. Let represent the r-th normalized value of the a-th Pareto solution, where r=1 corresponds to the overall safety factor, r=2 corresponds to the engineering cost, and r=3 corresponds to the ecological benefits. This represents the r-th weighting coefficient. The sum of the three weighting coefficients is 1. It is preset according to the actual needs of the project. When the project has high safety requirements, it is taken as... =0.50~0.60, =0.20~0.30, =0.15~0.25; when project funds are limited and economic efficiency is a high requirement, take... =0.25~0.35, =0.45~0.55, =0.15~0.25; when the project is located in an ecologically sensitive area and has high requirements for environmental protection, take 0.15~0.25. =0.30~0.40, =0.20~0.30, =0.35~0.45; Generally, a balanced weighting is used, taking... =0.40, =0.35, =0.25; This represents the acceptance threshold for the r-th target normalized value, ranging from 0.2 to 0.4. A penalty is triggered when the value falls below this threshold. This threshold differs from the preset safety threshold in step S4.3, which is a hard constraint in the engineering design that all solutions must meet; otherwise, they are directly eliminated. This is a soft acceptance threshold for the post-processing scoring stage; scores below this value only result in point deductions and do not affect the solution's inclusion in the Pareto solution set. This represents the penalty intensity coefficient for the r-th target, with a value ranging from 1.0 to 3.0;

[0129] Select the Pareto solution with the highest comprehensive decision score as the optimal design scheme, and output the values ​​of each optimization variable corresponding to the optimal design scheme, as well as the corresponding comprehensive safety factor, engineering cost and ecological benefits; if the Pareto optimal solution set contains only one solution, then directly use that solution as the optimal design scheme and output it; otherwise, proceed to step S5.1 to perform normalization and subsequent selection process.

[0130] like Figure 2 As shown, the intelligent optimization system for ecological bag slope protection structure based on parameter sensitivity is used to implement any of the intelligent optimization methods for ecological bag slope protection structures based on parameter sensitivity, including:

[0131] The data acquisition and modeling module is used to collect design parameters of the eco-bag slope protection structure and establish a finite element numerical model.

[0132] The safety factor calculation module is used to calculate the overall stability safety factor using the Bishop method and the strength reduction method respectively, and then combine them to obtain the comprehensive safety factor. It also calculates the anti-sliding safety factor and anti-overturning safety factor of a single ecological bag in the water level fluctuation zone.

[0133] The sensitivity analysis module is used to perform multi-dimensional sensitivity analysis on design parameters, calculate the comprehensive sensitivity index of each parameter, and select a set of highly sensitive parameters based on the comprehensive sensitivity index.

[0134] The multi-objective optimization module is used to solve for the Pareto optimal solution set by taking a set of highly sensitive parameters as optimization variables and taking the optimization objectives of maximizing the comprehensive safety factor, minimizing the engineering cost, and maximizing the ecological benefits.

[0135] The scheme decision output module is used to normalize the comprehensive safety factor, engineering cost and ecological benefits of each solution in the Pareto optimal solution set, construct a comprehensive decision scoring function, select the optimal design scheme based on the comprehensive decision score and output it.

[0136] like Figure 3 As shown, the specific process for screening the set of highly sensitive parameters includes: collecting design parameters of the ecological bag slope protection structure, including geometric parameters, material parameters, hydrological parameters, and vegetation parameters, and establishing a finite element numerical model based on the collected parameters to calculate the comprehensive safety factor; then determining the set of sensitive parameters to be analyzed; calculating the sensitivity index of each parameter from three dimensions: calculating the local sensitivity of each parameter through step S3.2, calculating the global sensitivity of each parameter through step S3.3, and calculating the coupling influence degree of each parameter through step S3.4; then normalizing the three sensitivity indices respectively, and then weighting and summing them according to step S3.5 to obtain the comprehensive sensitivity index of each parameter; finally, sorting the parameters according to the comprehensive sensitivity index from largest to smallest, and selecting parameters whose comprehensive sensitivity index is greater than 1.0 to 1.5 times the average value of all parameters to form the set of highly sensitive parameters.

[0137] like Figure 4 As shown, the specific process of multi-objective optimization and scheme decision-making is as follows: A set of highly sensitive parameters is selected as optimization variables. A multi-objective optimization function is then constructed, with three sub-objectives: maximizing the comprehensive safety coefficient, minimizing engineering costs, and maximizing ecological benefits. Constraints are set, including that the comprehensive safety coefficient must be greater than or equal to a preset safety threshold, each optimization variable must take values ​​within its physical feasible domain, and each inequality constraint function must meet requirements. The NSGA-II algorithm is then used to solve the multi-objective optimization problem. Through operations such as population initialization, non-dominated sorting, tournament selection, crossover mutation, and elite retention, the Pareto optimal solution set is obtained after iterating to the maximum number of generations. Finally, for each solution in the Pareto optimal solution set, the comprehensive safety coefficient, engineering cost, and ecological benefits are normalized respectively. A comprehensive decision scoring function is constructed, and the Pareto solution with the largest comprehensive decision score is selected as the optimal design scheme and output.

[0138] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the parameter-sensitive intelligent optimization methods for eco-bag slope protection structures.

[0139] Suppose that the set of sensitivity parameters to be analyzed for a certain eco-bag slope protection project includes: soil cohesion, soil internal friction angle, soil unit weight, moisture content, slope height, slope ratio, eco-bag thickness, eco-bag protection range thickness, river flow velocity, vegetation root depth, and vegetation root density. By calculating the local sensitivity, global sensitivity, and coupling influence of each parameter separately, and then by normalizing and weighting the sum, the comprehensive sensitivity index of each parameter is obtained.

[0140] The overall sensitivity index of each parameter, sorted from largest to smallest, and their specific values ​​are as follows:

[0141] The parameters are: soil cohesion 0.182, slope ratio 0.165, soil internal friction angle 0.148, slope height 0.131, vegetation root density 0.105, ecological bag thickness 0.081, moisture content 0.065, river flow velocity 0.053, soil unit weight 0.035, vegetation root depth 0.026, and ecological bag protection thickness 0.009. The average value of all parameters is 0.091. Taking 1.2 times the average value, i.e., 0.109, as the screening threshold, parameters with a comprehensive sensitivity index greater than 0.109 are selected, including soil cohesion 0.182, slope ratio 0.165, soil internal friction angle 0.148, and slope height 0.131. These four parameters constitute a set of high-sensitivity parameters, which will be used as optimization variables in step S4 to participate in multi-objective optimization and scheme decision-making.

[0142] The examples described herein are merely preferred embodiments of the invention and are not intended to limit the concept and scope of the invention. Any modifications and improvements made by those skilled in the art to the technical solutions of the invention without departing from the design concept of the invention should fall within the protection scope of the invention.

Claims

1. A method for intelligent optimization of eco-bag slope protection structures based on parameter sensitivity, characterized in that, Includes the following steps: Step S1: Collect the design parameters of the ecological bag slope protection structure and establish a finite element numerical model; Step S2: Calculate the overall stability safety factor of the eco-bag slope protection structure using the Bishop method and the strength reduction method respectively, and combine them to obtain the comprehensive safety factor. Also, calculate the anti-sliding safety factor and anti-overturning safety factor of a single eco-bag in the water level fluctuation zone. Step S3: Perform sensitivity analysis on the design parameters of the ecological bag slope protection structure, calculate the comprehensive sensitivity index of each parameter, and select a set of highly sensitive parameters based on the comprehensive sensitivity index. This includes the following steps: Step S3.1: Determine the set of sensitive parameters to be analyzed. The sensitive parameters include soil cohesion, soil internal friction angle, soil unit weight, moisture content, slope height, slope ratio, ecological bag thickness, ecological bag protection range thickness, river flow velocity, vegetation root depth, and vegetation root density. Step S3.2: Collect historical data measured on-site in the river section to be treated. Calculate the actual coefficient of variation of each parameter based on the measured historical data. After normalizing each parameter, use it as the independent variable and the comprehensive safety factor as the dependent variable to establish a multiple linear regression equation. Use the least squares method to estimate the standardized regression coefficient of each parameter. Multiply the coefficient of variation with the standardized regression coefficient to obtain the local sensitivity of each parameter. Step S3.3: Calculate the global sensitivity of each parameter. The global sensitivity is equal to the comprehensive safety factor when the parameter takes the physical maximum value and the other parameters take the baseline value, minus the comprehensive safety factor when the parameter takes the physical minimum value and the other parameters take the baseline value, and then divided by the comprehensive safety factor when all parameters take the baseline value. Step S3.4: Calculate the coupling influence of each parameter. For each parameter, take several value points at equal intervals within its physical feasible domain. For each value point, randomly generate several samples within the physical feasible domains of other parameters and calculate the corresponding comprehensive safety factor. Then, calculate the ratio of the dispersion of the conditional mean of the safety factor to the conditional variance when the parameter takes different values. Use this ratio as the coupling influence. Step S3.5: Normalize the local sensitivity, global sensitivity, and coupling influence respectively. Multiply the three normalized values ​​by their corresponding weight coefficients and sum them to obtain the comprehensive sensitivity index of each parameter. The sum of the three weight coefficients is 1. Step S3.6: Sort the parameters from largest to smallest according to the comprehensive sensitivity index, and select the parameters whose comprehensive sensitivity index is greater than 1.0 to 1.5 times the average value of all parameters to form a set of high sensitivity parameters; Step S4: Using the set of highly sensitive parameters as optimization variables, and with the optimization objectives of maximizing the comprehensive safety factor, minimizing engineering costs, and maximizing ecological benefits, solve to obtain the Pareto optimal solution set; Step S5: Normalize the comprehensive safety factor, engineering cost, and ecological benefits of each solution in the Pareto optimal solution set, construct a comprehensive decision scoring function, and select and output the optimal design scheme based on the comprehensive decision score.

2. The method according to claim 1, characterized in that, Step S1 specifically includes the following steps: Step S1.1: Collect the design parameters of the ecological bag slope protection structure, including geometric parameters, material parameters, hydrological parameters and vegetation parameters; Step S1.2: Based on the collected design parameters, establish a finite element numerical model of the ecological bag slope protection structure; Step S1.3: Mesh the finite element numerical model and set contact elements at the interface between the eco-bag and the soil.

3. The method according to claim 2, characterized in that, Step S2 specifically includes the following steps: Step S2.1: Calculate the overall stability safety factor of the eco-bag slope protection structure using the Bishop method; Step S2.2: Calculate the overall stability safety factor of the ecological bag slope protection structure using the strength reduction method. In the finite element numerical analysis, the shear strength parameters of the soil and rock mass are gradually reduced according to the same reduction factor. The reduced strength parameters are substituted into the model for iterative calculation. When the calculation does not converge or the plastic zone is connected, the corresponding reduction factor is the safety factor. Step S2.3: Take the safety factor calculated by the Bishop method and the safety factor calculated by the strength reduction method and calculate the weighted average to obtain the comprehensive safety factor, and the sum of the weighting factors is 1. Step S2.4: In the water level fluctuation zone of the eco-bag slope protection structure, calculate the anti-sliding safety factor and anti-overturning safety factor of a single eco-bag.

4. The method according to claim 1, characterized in that, Step S4 specifically includes the following steps: Step S4.1: Use the set of highly sensitive parameters as optimization variables; Step S4.2: Construct a multi-objective optimization function with the optimization objectives of maximizing the comprehensive safety factor, minimizing engineering costs, and maximizing ecological benefits; Step S4.3: Set constraints, including that the overall safety factor must be greater than or equal to the preset safety threshold, each optimization variable must take values ​​within its physical feasible domain, and each inequality constraint function must meet the requirements. Step S4.4: Use a non-dominated sorting genetic algorithm with an elitist strategy to solve the multi-objective optimization function and obtain the Pareto optimal solution set.

5. The method according to claim 4, characterized in that, In step S4.2, the project cost includes material cost, construction cost, and transportation cost. The material cost is the sum of the cost of ecological bags, soil filling, stone materials, and vegetation materials. The construction cost is the product of the total earthwork volume and the unit earthwork construction price. The transportation cost is the product of the total material weight, the transportation distance, and the unit weight unit distance transportation price.

6. The method according to claim 5, characterized in that, In step S4.2, the ecological benefits are calculated based on a weighted sum of vegetation coverage, biodiversity, and landscape harmony. The vegetation coverage is calculated exponentially based on the product of vegetation root density and vegetation root depth. The biodiversity is calculated based on the ratio of vegetation root depth to slope height. The harmony is calculated based on the ratio of river flow velocity to ideal flow velocity.

7. The method according to claim 6, characterized in that, Step S5 specifically includes the following steps: Step S5.1: For each solution in the Pareto optimal solution set, normalize the comprehensive safety factor, engineering cost, and ecological benefits according to the maximum and minimum values ​​of each objective in the solution set, and obtain three normalized values ​​for each solution. Step S5.2: Construct a comprehensive decision scoring function. Multiply the three normalized values ​​of each solution by the corresponding priority weight coefficients and sum them to obtain a weighted reward term. Introduce a penalty term. When the normalized value of any objective is lower than the preset acceptance threshold, deduct the penalty amount from the comprehensive score of the solution. The penalty amount is the product of the penalty intensity coefficient and the deviation of the normalized value from the acceptance threshold. Step S5.3: Select the Pareto solution with the highest comprehensive decision score as the optimal design scheme; Step S5.4: Output the values ​​of the optimization variables corresponding to the optimal design scheme, as well as the corresponding comprehensive safety factor, engineering cost, and ecological benefits.

8. A parameter-sensitive intelligent optimization system for eco-bag slope protection structures, used to implement the parameter-sensitive intelligent optimization method for eco-bag slope protection structures as described in any one of claims 1-7, characterized in that, include: The data acquisition and modeling module is used to collect design parameters of the eco-bag slope protection structure and establish a finite element numerical model. The safety factor calculation module is used to calculate the overall stability safety factor using the Bishop method and the strength reduction method respectively, and then combine them to obtain the comprehensive safety factor. It also calculates the anti-sliding safety factor and anti-overturning safety factor of a single ecological bag in the water level fluctuation zone. The sensitivity analysis module is used to perform multi-dimensional sensitivity analysis on design parameters, calculate the comprehensive sensitivity index of each parameter, and select a set of highly sensitive parameters based on the comprehensive sensitivity index. The multi-objective optimization module is used to solve for the Pareto optimal solution set by taking a set of highly sensitive parameters as optimization variables and taking the optimization objectives of maximizing the comprehensive safety factor, minimizing the engineering cost, and maximizing the ecological benefits. The scheme decision output module is used to normalize the comprehensive safety factor, engineering cost and ecological benefits of each solution in the Pareto optimal solution set, construct a comprehensive decision scoring function, select the optimal design scheme based on the comprehensive decision score and output it.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the intelligent optimization method for ecological bag slope protection structure based on parameter sensitivity as described in any one of claims 1 to 7.

Images