Waterproof construction method for prolonging service life of waterproof structure of standardized swimming pool of stadium

Abstract

The invention provides a waterproof construction method for prolonging the service life of a waterproof structure of a standardized swimming pool in a stadium, and belongs to the technical field of building construction.The method comprises the steps that firstly, basic structure parameters of the swimming pool and physical and mechanical parameters of waterproof materials are obtained, a plurality of small physical models of a sequence scale are established, and stress monitoring points are set; and performing finite element analysis to obtain a stress distribution matrix. And identifying a waterproof life key area through a Kruska < l > minimum spanning tree algorithm, and establishing and fitting a waterproof structure life prediction equation set. And solving an optimal construction parameter range by adopting a multi-objective optimization algorithm, and determining an actual waterproof life key area through experiments and simulation verification. Specific construction parameters are determined according to the optimization result, the base layer of the swimming pool is processed, the waterproof layer is laid according to the parameters, and reinforced protection measures are taken for the key area. The technical problems that in the prior art, the service life of the waterproof structure of the swimming pool is not accurately predicted, construction parameter optimization is insufficient, and effective reinforced protection is difficult to conduct on the high-stress area are solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of building construction, and specifically relates to a waterproof construction method for extending the service life of a waterproof structure of a standardized swimming pool in a stadium. Background Art

[0002] The waterproof project of a standardized swimming pool in a stadium is an important application field of building waterproof technology. Traditional swimming pool waterproof technologies mainly include three categories: sheet waterproofing, coating waterproofing, and rigid waterproofing. Sheet waterproofing mainly uses high-molecular waterproof sheets, such as polyvinyl chloride (PVC) waterproof sheets, ethylene propylene diene monomer (EPDM) waterproof sheets, etc., which are laid on the surface of the structure by mechanical fixing or bonding methods; coating waterproofing uses high-molecular materials such as polyurethane and polyurea, and forms a continuous waterproof layer by spraying or scraping; rigid waterproofing mainly uses cement-based penetrating crystalline waterproof materials, and through the reaction of active substances in the materials with cement hydration products, insoluble crystals are formed to fill the micropores of concrete, thereby playing a waterproof role. The construction process of these traditional waterproof technologies is usually carried out according to the standard construction process provided by the material supplier, combined with the requirements of design specifications and engineering experience. Construction parameters such as the thickness of the waterproof layer, the lapping width, and the depth of base treatment are mainly determined based on experience and specification values. Traditional waterproof life assessment mainly relies on laboratory accelerated aging tests and statistical analysis of historical cases, and linearly extrapolates the durability data of materials to the actual engineering service life.

[0003] However, traditional swimming pool waterproof technologies have many defects. First, the waterproof life prediction method is too simplified, usually using a single-factor extrapolation method, without considering the non-linear aging characteristics under the combined action of multiple factors. For example, the aging test considering only the temperature factor or ultraviolet irradiation alone cannot reflect the material deterioration process under the combined action of temperature, humidity, chemical corrosion, and mechanical stress. Second, the existing waterproof structure design lacks systematic stress analysis and cannot accurately identify the stress concentration areas in the waterproof structure. As a special hydraulic building, the swimming pool has a complex geometric shape and is affected by various factors such as water pressure, temperature change, and structural deformation. The stress distribution borne by the waterproof layer at different positions is extremely uneven. In particular, key positions such as the connection between the pool bottom and the pool wall, the four corners of the swimming pool, and the joints of the waterproof layer often become the starting points of waterproof failure, but it is difficult for traditional technologies to accurately identify these key areas. Third, the determination of construction parameters lacks a scientific basis and mainly relies on experience and the minimum requirements of specifications, making it difficult to optimize for specific engineering conditions. For example, the thickness of the waterproof layer usually follows the lowest standard, the lapping width adopts a unified value, and the depth of base treatment is determined by visual inspection. This method cannot carry out differential design for different stress areas, resulting in over-design and resource waste in some areas, and under-design and premature failure in some areas.

[0004] The core problem difficult to solve by traditional technologies lies in: the lack of a waterproof life prediction method that integrates material properties, environmental factors, and structural stress systems, making it impossible to optimize construction parameters based on accurate life prediction results, and even more impossible to implement effective targeted strengthening measures for high-stress areas in the waterproof structure. Current research mainly focuses on single aspects such as improving material properties or construction technology, lacking systematic research involving multiple disciplines. For example, the field of materials science focuses on the aging mechanism and performance improvement of waterproof materials, the field of structural mechanics focuses on the stress analysis at joints, and the field of construction technology focuses on optimizing the process flow, but these research results are rarely integrated and applied. Especially in complex environments, the waterproof structure of swimming pools is subjected to the long-term action of multiple factors such as temperature cycles, water pressure changes, chemical corrosion, and mechanical deformation, and there are complex coupling relationships among these factors. However, existing technologies lack mathematical models and experimental verification methods to describe such complex coupling relationships, resulting in inaccurate prediction of the waterproof structure's life and difficulty in taking targeted measures to extend the life. That is to say, there are technical problems in the existing technologies such as inaccurate prediction of the waterproof structure's life of swimming pools, insufficient optimization of construction parameters, and difficulty in effectively strengthening and protecting high-stress areas. Summary of the Invention

[0005] In view of this, the present invention provides a waterproof construction method for extending the life of the waterproof structure of a standard swimming pool in a stadium, which can solve the technical problems in the existing technologies such as inaccurate prediction of the waterproof structure's life of swimming pools, insufficient optimization of construction parameters, and difficulty in effectively strengthening and protecting high-stress areas.

[0006] The present invention is implemented as follows: The present invention provides a waterproof construction method for extending the life of the waterproof structure of a standard swimming pool in a stadium, including the following steps: obtaining basic structure parameters, where the basic structure parameters include the swimming pool size, structural type, load conditions, and the designed thickness of the waterproof layer; collecting the physical and mechanical parameters of the waterproof material, where the physical and mechanical parameters include tensile strength, elongation at break, low-temperature flexibility, thermal aging performance, and water resistance; establishing multiple small physical models with a sequence scale and setting stress monitoring points; inputting the physical and mechanical parameters into the small physical models for finite element analysis; using the Kruskal minimum spanning tree algorithm to identify the stress transfer path of the waterproof structure; establishing and fitting a waterproof structure life prediction equation set; determining the optimal construction parameter range based on a multi-objective optimization algorithm; determining the actual key areas of the waterproof life through experimental and simulation verification; determining specific construction parameters according to the optimal construction parameter range; treating the swimming pool base layer to make the base layer quality meet the design requirements; laying the waterproof layer according to the specific construction parameters and taking strengthening protection measures for the actual key areas of the waterproof life; where the waterproof structure life prediction equation set includes a material property attenuation equation, an environmental impact equation, and a structural stress equation.

[0007] Among them, multiple small physical models of the sequence scale have the same grid size. The sequence scale is 10 equidistant scale values between 0.1 and 1.0, the grid size is 50 mm, and grid encryption is performed at the joints and corner positions. The grid size of the encrypted area is 25 mm.

[0008] Among them, the stress monitoring points include: 6 monitoring points are arranged at intervals of 60 degrees circumferentially at the connection between the pool bottom and the pool wall; 5 monitoring points are arranged in each of the four corner areas of the swimming pool, distributed in a fan shape, and the distance between the monitoring points is 100 mm; double rows of monitoring points are set at the joints of the waterproof layer, arranged at intervals of 200 mm along the joint direction, and there are no less than 10 monitoring points at each joint.

[0009] Among them, the strengthening protection measures include: increasing the thickness of the waterproof layer; adding an additional waterproof layer, and the width of the additional layer is not less than 500 mm; setting a waterproof protective layer, using polyester fiber non-woven fabric, and the unit area mass is not less than 300 g / m².

[0010] Among them, the specific construction parameters include: the actual thickness of the waterproof layer, 2.5 mm is selected for large competition swimming pools, and 2.0 mm is selected for general swimming pools; the actual lap width, 120 mm is selected for the main joint positions, and 100 mm is selected for the secondary joint positions; the actual depth of the base treatment, 3 mm is selected for newly built swimming pools, and 4 mm is selected for renovation projects.

[0011] Among them, the quality of the base includes: flatness, checked with a 2-meter straightedge, and the allowable deviation is not more than 3 mm; compressive strength, the concrete strength grade is not lower than C30; moisture content, measured by the drying method, and controlled below 5%.

[0012] Among them, the input parameters of the material performance attenuation equation include the initial material performance value, service time, ambient temperature, and ultraviolet intensity, and the output parameter is the material remaining strength coefficient. The input parameters of the environmental impact equation include the annual average rainfall, temperature fluctuation range, water pressure change, and chemical corrosion intensity, and the output parameter is the environmental damage coefficient. The input parameters of the structural stress equation include hydrostatic pressure, temperature stress, structural deformation, and load stress, and the output parameter is the equivalent stress of the waterproof layer.

[0013] Among them, the genetic algorithm is used to optimize the parameters of the waterproof structure life prediction equation set. The population size is set to 200, the number of evolutionary generations is 500 generations, the crossover probability is 0.85, the mutation probability is 0.1, the prediction error of the training set does not exceed 15%, and the prediction error of the validation set does not exceed 20%.

[0014] Among them, the leave-one-out method is used to cross-validate the waterproof structure life prediction equation set. The data set is divided into a training set and a test set according to a ratio of 7:3. Five-fold cross-validation is performed on the training set data, and three indicators, namely the mean absolute error, the root mean square error, and the relative error, are calculated. The mean absolute error does not exceed 20%, the root mean square error does not exceed 25%, and the relative error does not exceed 30%.

[0015] Among them, the least squares method is used to establish and fit the material property attenuation equation, the multiple regression analysis method is used to establish the environmental impact equation, and the structural stress equation is established based on the principles of elastoplastic mechanics.

[0016] Compared with the prior art, the present invention provides a waterproof construction method for extending the service life of the waterproof structure of a standardized swimming pool in a stadium. The present invention provides a waterproof construction method for extending the service life of the waterproof structure of a standardized swimming pool in a stadium. This method first establishes a plurality of small physical models with a sequence scale, identifies the stress transfer path and the key area of the waterproof life in the waterproof structure through finite element analysis and the Kruskal minimum spanning tree algorithm, then establishes and fits a waterproof structure life prediction equation set including a material property attenuation equation, an environmental impact equation, and a structural stress equation, uses a multi-objective optimization algorithm to solve the optimal construction parameter range, and finally constructs according to the optimization result, and takes targeted strengthening protection measures for the key area of the waterproof life. This method integrates multidisciplinary knowledge such as materials science, structural mechanics, graph theory algorithms, and optimization theory, and establishes a closed-loop system for waterproof structure life prediction and construction parameter optimization.

[0017] The present invention effectively solves many defects existing in the traditional technology. First, by establishing multiple small physical models of the sequence scale, it overcomes the drawback that a single-scale model cannot balance computational efficiency and accuracy. The sequence scale design enables the large-scale model to reflect the overall structural behavior, while the small-scale model can capture local detailed features, effectively balancing the contradiction between computational resources and simulation accuracy. Second, the present invention introduces the Kruskal minimum spanning tree algorithm to process the stress distribution matrix. By constructing a connection network for high-stress regions, it systematically identifies the stress transfer paths in the waterproof structure and finds the connected component with the largest weight as the key area for waterproof life, solving the problem in the traditional technology of difficultly accurately identifying stress concentration regions. Third, the present invention establishes a waterproof structure life prediction equation set comprehensively considering material properties, environmental factors, and structural stress. Through the complete process from the collection of historical engineering data, normalization processing, initial model establishment, laboratory calibration to parameter optimization, it constructs a mathematical model accurately reflecting the aging law of the waterproof structure under the coupling action of multiple factors, overcoming the limitations of the traditional linear extrapolation method. Fourth, the present invention uses a multi-objective optimization algorithm to solve the life prediction equation set, obtaining the optimal range of construction parameters, providing a scientific basis for the construction process, and avoiding the limitations of traditional experience dependence and unified standards. Finally, in the construction implementation stage, the present invention takes strengthening protection measures such as increasing the thickness of the waterproof layer, adding additional waterproof layers, and setting waterproof protection layers for the actual key areas of waterproof life, realizing the reasonable allocation of resources and the extension of the overall life of the waterproof structure.

[0018] The reason why the present invention can effectively solve the core technical problems of inaccurate prediction of the waterproof structure life of swimming pools, insufficient optimization of construction parameters, and inadequate protection of high-stress regions mainly lies in its establishment of a systematic technical path. First, by introducing graph theory algorithms to process engineering mechanics problems, it transforms the complex stress distribution into a quantifiable and analyzable network structure, enabling the identification of stress transfer paths and key regions to change from qualitative analysis to quantitative calculation. Second, by combining physical model tests and numerical simulations, it overcomes the limitations of simply relying on experience or theoretical calculations and improves the accuracy of identifying key areas of waterproof life. Third, by establishing and fitting a life prediction equation set considering the coupling action of multiple factors, it realizes a comprehensive assessment from material properties, environmental impacts to structural stress, making the waterproof structure life prediction based on a solid scientific foundation. Finally, by combining the life prediction results with the optimization of construction parameters, it forms a closed-loop feedback system, transforming the construction process from passive execution to active optimization, thereby significantly extending the life of the waterproof structure. This systematic method not only improves the scientificity and accuracy of waterproof projects, but also optimizes resource allocation, reduces long-term maintenance costs, and provides a new technical path for the waterproof projects of standard swimming pools in stadiums. Description of the Drawings

[0019] Figure 1 It is a flowchart of the method of the present invention.

[0020] Figure 2 It is a flowchart for establishing and fitting the waterproof structure life prediction equation set. Specific embodiments

[0021] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0022] As Figure 1 shown, it is a flowchart of a waterproof construction method for extending the service life of the waterproof structure of a standardized swimming pool in a stadium provided by the present invention. This method includes the following steps:

[0023] S01. Obtain the basic structure parameters according to the swimming pool design drawings. The basic structure parameters include the swimming pool size, structure type, load conditions, and the designed thickness of the waterproof layer;

[0024] S02. Collect the physical and mechanical parameters of the waterproof material. The physical and mechanical parameters include the tensile strength, elongation at break, low temperature flexibility, thermal aging performance, and water resistance;

[0025] S03. Establish multiple small physical models with a sequence scale. The sequence scale is a specified number of arithmetic ratios between the minimum ratio and 1.00 times, and the grid sizes of the small physical models are kept consistent;

[0026] S04. Set stress monitoring points in the small physical models. The stress monitoring points include the connection between the pool bottom and the pool wall, the four corners of the swimming pool, and the joints of the waterproof layer;

[0027] S05. Input the physical and mechanical parameters into the small physical models, conduct finite element analysis, simulate the influence of water pressure, temperature change, material aging, and structural deformation on the waterproof layer, and obtain the stress distribution matrix;

[0028] S06. Perform sparse matrix processing on the stress distribution matrix, use the Kruskal minimum spanning tree algorithm to construct a high-stress area connection network, identify the stress transfer path of the waterproof structure through the connection of the minimum weight edges, and define the connected component with the largest weight as the key area of the waterproof life;

[0029] S07. Establish and fit the waterproof structure life prediction equation set;

[0030] S08. Use a multi-objective optimization algorithm to solve the life prediction equation set to obtain the optimal construction parameter range. The optimal construction parameter range includes the waterproof layer thickness range, the lap width range, and the base treatment depth range;

[0031] S09. Verify the key waterproof life areas in multiple small physical models of the sequence scale through experiments and simulations to determine the actual key waterproof life areas;

[0032] S10. Determine specific construction parameters according to the optimal construction parameter range. The specific construction parameters include the actual thickness of the waterproof layer, the actual overlapping width, and the actual depth of the base treatment;

[0033] S11. Treat the pool base to ensure that the base quality meets the design requirements. The base quality includes flatness, strength, and moisture content;

[0034] S12. Lay the waterproof layer according to the specific construction parameters, and take strengthening protection measures for the actual key waterproof life areas. The strengthening protection measures include increasing the thickness of the waterproof layer, adding additional waterproof layers, and setting waterproof protection layers.

[0035] As Figure 2 shown, the specific steps for establishing and fitting the waterproof structure life prediction equation set include:

[0036] S701. Collect historical project data, which includes material performance parameters, environmental condition records, and structural failure situations of pool waterproof projects with different years;

[0037] S702. Normalize the historical project data to eliminate the dimension difference and establish a standardized data set;

[0038] S703. Establish an initial model of the material performance attenuation equation using the least squares method. The material performance attenuation equation is used to calculate the performance attenuation rate of the waterproof material. The input parameters of the material performance attenuation equation include the tensile strength, the elongation at break, the use environment temperature, the ultraviolet irradiation intensity, and the use time. The output parameter of the material performance attenuation equation is the remaining strength coefficient of the material;

[0039] S704. Establish an initial model of the environmental impact equation using the multiple regression analysis method. The environmental impact equation is used to evaluate the influence degree of environmental factors on the waterproof layer. The input parameters of the environmental impact equation include rainfall, temperature fluctuation range, water pressure change, and chemical corrosion intensity. The output parameter of the environmental impact equation is the environmental damage coefficient;

[0040] S705. Establish an initial model of the structural stress equation based on the principles of elastoplastic mechanics. The structural stress equation is used to calculate the comprehensive stress level borne by the waterproof layer. The input parameters of the structural stress equation include hydrostatic pressure, temperature stress, structural deformation amount, and load stress. The output parameter of the structural stress equation is the equivalent stress of the waterproof layer;

[0041] S706. Obtain calibration data through laboratory accelerated aging tests, where the laboratory accelerated aging tests include high-temperature aging tests, ultraviolet aging tests, immersion aging tests, and cyclic loading tests;

[0042] S707. Use the calibration data to optimize the parameters of the initial models of the material property attenuation equation, the environmental impact equation, and the structural stress equation, and use the genetic algorithm to iteratively solve for the optimal coefficient combination;

[0043] S708. Establish a comprehensive calculation equation for the service life of the waterproof structure, where the comprehensive calculation equation for the service life of the waterproof structure takes the remaining strength coefficient of the material, the environmental damage coefficient, and the equivalent stress of the waterproof layer as input parameters, and calculates the expected service life value of the waterproof structure;

[0044] S709. Use the holdout method to perform cross-validation on the service life prediction equations of the waterproof structure, and calculate the prediction error of the service life prediction equations of the waterproof structure;

[0045] S710. When the prediction error is less than the preset threshold, confirm that the service life prediction equations of the waterproof structure are fitted; when the prediction error is greater than the preset threshold, return to step S707 for re-optimization of the parameters.

[0046] Among them, the waterproof layer refers to the functional layer that directly contacts the water body and plays a role in preventing water penetration; the base layer refers to the structural layer that supports the waterproof layer; the lap width refers to the width of the overlapping connection of two waterproof materials; the base treatment depth refers to the depth of grinding, repairing or strengthening the surface of the base layer; the mesh size refers to the fineness of mesh division in finite element analysis; the stress monitoring point refers to the position set in the small physical model for recording stress data; the sparse matrix refers to a matrix with most elements being zero; the high stress area refers to the area where the stress value exceeds the set threshold; the stress transfer path refers to the main channel of stress conduction in the waterproof structure; the connected component refers to a set of interconnected nodes in graph theory; the weight refers to the magnitude of the stress value; the material remaining strength coefficient refers to the ratio of the strength retained by the waterproof material after being used for a period of time to the initial strength; the environmental damage coefficient refers to the quantitative value of the degree of damage caused by environmental factors to the waterproof layer; the equivalent stress refers to the scalar stress value obtained by synthesizing the stresses in all directions; the preset threshold refers to the standard value used to judge whether the prediction error meets the requirements; the holdout method refers to the method of dividing the data set into a training set and a test set for model validation; the prediction error refers to the deviation between the model prediction value and the actual value; the calibration data refers to the standardized data used to adjust the model parameters; the historical engineering data refers to the actual operation data of the completed swimming pool waterproof project; the normalization process refers to the data preprocessing method of unifying data with different dimensions to the same scale range.

[0047] The specific implementation manners of the above steps are described in detail below. The specific implementation manner of step S01 is as follows: Obtain relevant basic parameter information according to the design drawings of the standardized swimming pool. First, determine the three basic dimensions of the swimming pool, namely the length, width and depth, by measuring on the drawings. The length of a standard swimming pool is usually 50 meters or 25 meters, the width is 21 meters or 25 meters, and the depth varies from 1.35 meters to 2 meters according to the functional area. Then determine the structural type of the swimming pool, including cast-in-place reinforced concrete structure, precast concrete structure or steel structure, etc., and record the characteristics of the structural form. Then calculate the load conditions borne by the swimming pool, including dead load, live load, water pressure and temperature load, etc. Among them, the water pressure is calculated according to the depth and density, and the temperature load considers the influence of seasonal temperature difference changes. Finally, determine the design thickness requirement of the waterproof layer. Generally, the thickness of the waterproof layer is between 1.5 millimeters and 2.5 millimeters, and the specific value needs to be determined according to the scale and use requirements of the swimming pool. The acquisition of these basic parameters provides basic data support for subsequent analysis and optimization.

[0048] The specific implementation of step S02 is as follows: Conduct comprehensive physical and mechanical property tests and data collection on waterproof materials. First, use a tensile testing machine to test the tensile strength of the material at a test temperature of 23 ± 2 °C and a tensile speed of 500 ± 50 mm per minute, and record the tensile strength value of the material. The standard requirement is not less than 12 MPa. Then test the elongation at break of the material using the same test equipment and conditions, and record the elongation value when the material reaches breakage. The requirement is not less than 300%. Next, conduct a low-temperature flexibility test. Keep the specimen at a temperature of -20 °C for 2 hours, and then conduct a bending test to observe whether cracks appear. Continue with the heat aging performance test. Accelerate the aging of the specimen in an 80 °C environment for 168 hours, and test the retention rates of its tensile strength and elongation at break. The requirement for the retention rate is not less than 80%. Finally, test the water resistance performance. Immerse the specimen in water at 23 ± 2 °C for 168 hours, and test the mass change rate and volume change rate. The requirement for the change rate is not more than 3%.

[0049] The specific implementation of step S03 is as follows: Based on the similarity theory, construct a series of physical models with different scales. Set the sequence scale to be between 0.1 and 1.0, and select 10 scale values according to the principle of arithmetic progression. Strictly control the geometric similarity of the model during the modeling process, maintain the relative position relationship and geometric dimension ratio between components, and ensure that the model can accurately reflect the actual structural characteristics. Use 3D modeling software to construct a digital model of the pool structure, and divide the model into key parts such as the pool bottom, pool wall, and transition area. Set unified mesh division parameters in the model, and select a mesh size of 50 mm to ensure a balance between calculation accuracy and efficiency. For the waterproof layer structure, use shell elements for simulation, select four-node quadrilateral elements for the element type, and perform mesh encryption at the joints and corner positions. The mesh size in the encrypted area is reduced to 25 mm.

[0050] The specific implementation of step S04 is as follows: Arrange an array of stress monitoring points in the established small physical model. Arrange 6 monitoring points at intervals of 60 degrees circumferentially at the connection between the pool bottom and the pool wall to monitor the changes in shear stress and normal stress. Arrange 5 monitoring points in each of the four corners of the pool in a fan-shaped distribution, with a monitoring point spacing of 100 mm, and focus on the stress concentration effect. Set up double rows of monitoring points at the joints of the waterproof layer, arrange them at intervals of 200 mm along the joint direction, and there are no less than 10 monitoring points at each joint to monitor the stress distribution state at the joint. For special structural parts such as deformation joints and pipe penetrations through the wall, increase local encrypted monitoring points, and reduce the monitoring point spacing in the encrypted area to 50 mm. Define a local coordinate system at the monitoring points to ensure the accuracy of the calculation of stress components.

[0051] The specific implementation of step S05 is as follows: Import the collected physical and mechanical parameters into finite element analysis software, set the material constitutive model as an elastoplastic model, and input parameters such as elastic modulus, Poisson's ratio, and yield strength. Conduct static analysis, considering the water pressure distribution, which varies linearly with depth, and the maximum water pressure appears at the bottom of the pool. Conduct transient thermal analysis to simulate the temperature change process from -10 degrees Celsius to 40 degrees Celsius and calculate the temperature stress distribution. Consider the material aging effect, set the material strength and stiffness parameters as functions of time, and simulate the performance degradation during the service process. Analyze the influence of structural deformation, apply the boundary conditions of foundation settlement and wall displacement, and calculate the stress state of the waterproof layer. Use the explicit dynamics method for solution, set the time step as 0.001 seconds, the total calculation time as 100 seconds, output the nodal stress time history curve, and form a stress distribution matrix.

[0052] The specific implementation of step S06 is as follows: Conduct data processing and analysis on the obtained stress distribution matrix. First, set the values in the stress matrix that are less than 5% of the maximum stress to zero to construct a sparse matrix. Use the Kruskal minimum spanning tree algorithm to process the sparse matrix, take the stress value as the weight of the edge, and construct an undirected graph structure. The algorithm starts from the edge with the minimum weight and gradually adds edges until a complete spanning tree is formed, avoiding the formation of loops. By analyzing the structural characteristics of the spanning tree, identify the main paths of stress transmission, and focus on the nodes connected by the edges with larger weights. Use the connected component analysis method to divide the stress network into several independent regions and calculate the total weight of each connected component. Define the connected component with the largest weight as the key area for the waterproof life. The stress level and distribution characteristics in this area directly affect the service life of the waterproof structure. Through this method, the area most likely to fail in the waterproof system can be accurately located, providing a basis for subsequent construction optimization.

[0053] The specific implementation of step S07 is as follows: Establish a waterproof structure life prediction equation system, which includes three sub - equations: the material property attenuation equation, the environmental influence equation, and the structural stress equation. First, construct the material property attenuation equation, use the exponential decay model to describe the degradation law of the waterproof material strength over time, considering the influence coefficients of temperature and ultraviolet rays. Then establish the environmental influence equation, use the polynomial fitting method to describe the comprehensive influence of environmental factors on the waterproof layer, including factors such as rainfall, temperature fluctuation, and chemical corrosion. Finally, establish the structural stress equation, based on the elastoplastic mechanics theory, establish a stress analysis model considering multiple load combinations. Calibrate and optimize the parameters of the equation system through experimental data, and use the least - squares method to determine each coefficient to improve the prediction accuracy.

[0054] The specific implementation of step S08 is as follows: The multi-objective optimization algorithm is used to solve the life prediction equation set. First, the optimization objectives are set, including maximizing the waterproof structure life, minimizing the construction cost, and optimizing the construction process. The non-dominated sorting genetic algorithm is used for solution, with the population size set to 100, the number of iterations to 1000 times, the crossover probability to 0.8, and the mutation probability to 0.1. During the optimization process, the waterproof layer thickness range is set to 1.5 mm to 3.0 mm, the lapping width range is set to 80 mm to 150 mm, and the base treatment depth range is set to 2 mm to 5 mm. Through the Pareto optimal solution set analysis, the optimal construction parameter range that meets the multi-objective requirements is determined. According to the actual situation of the project, a suitable solution is selected as the construction guidance parameter.

[0055] The specific implementation of step S09 is as follows: Experimental verification and simulation analysis are carried out on the key areas of the waterproof life. First, under laboratory conditions, the accelerated aging test method is used to verify the predicted key areas in different scale models. Specimens containing the key areas are made, and cyclic loading tests, temperature cycle tests, and fatigue tests are carried out. The test cycle is 3000 times, and the stress distribution and damage evolution process are recorded. At the same time, finite element software is used for numerical simulation, a refined local model is established, and the mesh size is accurate to 10 mm to simulate the stress state under various working conditions. By comparing and analyzing the experimental results and simulation data, the accuracy of the key areas is verified, and the location and range of the areas that need to be focused on in the actual project are determined.

[0056] The specific implementation of step S10 is as follows: Based on the optimal construction parameter range, combined with the actual situation of the project, the specific construction parameters are directly used or fine-tuned. For example, first, according to the pool size and usage requirements, the actual thickness of the waterproof layer is selected. For large competition pools, 2.5 mm is selected, and for general pools, 2.0 mm is selected. Then the actual lapping width is determined. 120 mm is selected for the main joint position, and 100 mm is selected for the secondary joint position. Finally, the actual depth of the base treatment is determined. 3 mm is selected for new pools, and 4 mm is selected for renovation projects. During the parameter determination process, the material properties, construction process, and cost factors are comprehensively considered to ensure the feasibility and economy of the parameters.

[0057] The specific implementation of step S11 is as follows: The pool base is comprehensively treated and quality controlled. First, the flatness of the base is detected using a 2-meter straightedge, and the allowable deviation is not more than 3 mm. The base surface is polished to remove floating slurry and loose materials, and the polishing depth is controlled within the design value range. The compressive strength of the base is tested. The concrete strength grade is not lower than C30, and the rebound method is used for non-destructive testing. The moisture content of the base is detected using the drying method and controlled below 5%. Cracks and pitted surfaces are repaired using epoxy resin mortar, and the curing time is not less than 24 hours. Finally, the base is cleaned to ensure that the surface has no oil stains, dust, and other sundries.

[0058] The specific implementation of step S12 is as follows: The waterproof layer is constructed according to the determined construction parameters, and targeted strengthening measures are taken for key areas. First, a primer is applied to the surface of the base layer at a dosage of 0.3 kg per square meter, and the drying time is not less than 4 hours. When laying the waterproof coiled material, the lapping width is strictly controlled, and the hot air welding process is adopted, with the welding temperature controlled between 380 and 420 degrees Celsius. For key areas such as the corners of the swimming pool, expansion joints, and the locations where equipment passes through the wall, an additional waterproof layer is added, and the width of the additional layer is not less than 500 mm. In areas vulnerable to mechanical damage, a waterproof protective layer is set up, and polyester fiber non-woven fabric can be used, with a unit area mass of not less than 300 g per square meter. After all the detailed structure treatments are completed, a water storage test is carried out for not less than 48 hours to observe the leakage situation.

[0059] The specific implementation of step S701 is as follows: Historical engineering data is collected through various channels, including the completion materials, usage and maintenance records, and regular inspection reports of the built swimming pools, etc. For the material performance parameters, the physical and mechanical performance test data of the waterproof materials are collected, including indicators such as the tensile strength, elongation at break, and tear strength for different service years. The test data should include at least 50 engineering cases, with the service years distributed between 1 year and 20 years. Regarding the environmental condition records, the meteorological data of the project location is collected, including parameters such as the annual average temperature, temperature change range, annual rainfall, and ultraviolet intensity. The data collection period is not less than 2 - 5 years. The records of the structural failure situations include information such as the types of waterproof layer damage, failure locations, and failure times, and on-site investigations and image records are carried out. The cases are classified and sorted according to the failure forms. All the collected data needs to establish a unified database to record the data collection time, collection methods, and reliability levels.

[0060] The specific implementation of step S702 is as follows: The collected historical engineering data is systematically normalized to eliminate the influence brought by different dimensions. First, the maximum - minimum normalization is performed on the numerical data, mapping the data into the interval of 0 to 1 to maintain the relative magnitude relationship of the data. For the material performance data, the initial value standardization method is adopted, taking the initial performance value of the material as the benchmark to calculate the performance retention rate at different times. For the environmental parameters, the Z - score standardization method is used to calculate the mean and standard deviation of each parameter, and the data is converted into a standard normal distribution. For the categorical data such as the failure types, the one - hot encoding method is used to convert it into numerical data. The processed data needs to be subjected to outlier detection. The 3 - standard - deviation method is used to identify the outlier data points, and professional judgment is combined to decide whether to eliminate them. Finally, a standardized data set is formed as the basic data for subsequent modeling.

[0061] The specific implementation of step S703 is as follows: The initial model of the material property attenuation equation is established by the least squares method. This equation is used to describe the degradation law of the waterproof material property over time. First, the basic form of the equation is determined. Considering that the material property attenuation usually shows an exponential attenuation characteristic, an exponential function is selected as the basic equation form. The temperature influence coefficient is introduced into the equation, and the Arrhenius formula is used to describe the influence of temperature on the attenuation rate. Considering the effect of ultraviolet rays, the ultraviolet cumulative dose term is introduced to establish the relationship between ultraviolet rays and material deterioration. The input parameters of the equation include the initial property value of the material, the service time, the ambient temperature, and the ultraviolet intensity, and the output parameter is the remaining strength coefficient of the material. The equation is fitted with the measured data, the least squares method is used to determine each coefficient, and the goodness of fit is calculated. It is required that the determination coefficient R 2 is not less than 0.85.

[0062] The specific implementation of step S704 is as follows: The initial model of the environmental impact equation is established by the multiple regression analysis method. This equation is used to quantify the influence of various environmental factors on the performance of the waterproof layer. First, variable screening is carried out. The stepwise regression method is used to select the environmental factors that have a significant impact on the performance of the waterproof layer. The collinearity diagnosis is carried out on the selected variables, the variance inflation factor is calculated, and the strongly correlated variables are removed. A multiple regression equation is established. The independent variables include the annual average rainfall, the temperature fluctuation range, the water pressure change, and the chemical corrosion intensity, and the dependent variable is the environmental damage coefficient. In the process of regression analysis, the interaction between variables is considered, and the interaction term is introduced to improve the prediction accuracy of the model. The significance test of the regression equation is carried out. It is required that the confidence level reaches 95%, and the adjusted determination coefficient is not less than 0.8.

[0063] The specific implementation of step S705 is as follows: The initial model of the structural stress equation is established based on the principles of elastoplastic mechanics. This equation is used to calculate the stress state of the waterproof layer under various loadings. First, a stress component calculation model is established, considering four components: hydrostatic pressure, temperature stress, structural deformation stress, and external load stress. The hydrostatic pressure is calculated by the hydrostatics formula, considering the influence of the water depth change. The temperature stress calculation considers the thermal expansion coefficient and temperature gradient of the material and uses the thermoelastic theory. The structural deformation stress is calculated based on the small deformation assumption and uses the linear elastic theory. The external load stress considers the dynamic load effect during the use process. Each stress component is substituted into the von Mises equivalent stress formula to calculate the comprehensive stress level. The input parameters of the equation include the magnitude and distribution of various loads, and the output parameter is the equivalent stress value of the waterproof layer. The accuracy of the equation is verified according to the measured data. It is required that the calculation error does not exceed 10%.

[0064] The specific implementation of step S706 is as follows: Calibration data is obtained through laboratory accelerated aging tests for verifying and optimizing the life prediction equation set. First, a high-temperature aging test is carried out. The specimen is placed in an environment of 80 degrees Celsius, and the test times are three cycles of 168 hours, 336 hours, and 672 hours. Samples are taken in each cycle to test the physical and mechanical properties. For the ultraviolet aging test, a xenon arc lamp aging test chamber is used, with the irradiance set at 550 watts per square meter and the wavelength range from 290 to 800 nanometers. The test cycle is the same as that of the high-temperature aging test. The immersion aging test is carried out under the condition of 23 ± 2 degrees Celsius, and the test water is deionized water. The test cycles are 7 days, 14 days, and 28 days, and the water absorption rate and strength change of the specimen are measured regularly. For the cyclic loading test, a dynamic fatigue testing machine is used, with the loading frequency of 10 Hz, and the stress levels are set at three levels of 70%, 80%, and 90% of the material yield strength. The fatigue life at different stress levels is recorded. All test data requires at least 3 groups of parallel samples to ensure the reliability of the data.

[0065] The specific implementation of step S707 is as follows: Using the calibration data obtained from the accelerated aging test, parameter optimization is carried out for the three sub-equations of the life prediction equation set. The genetic algorithm is used for optimization and solution. The coding method of the algorithm adopts real number coding, and the chromosome length is determined according to the number of parameters to be optimized. The population size is set to 200, the number of evolution generations is 500 generations, the crossover probability is 0.85, and the mutation probability is 0.1. During the optimization process, the test data is divided into a training set and a validation set. The training set is used for parameter optimization, and the validation set is used for model verification. An adaptive crossover and mutation strategy is adopted, and the operation probabilities are dynamically adjusted according to the individual fitness values. The fitness function adopts the root mean square error to calculate the deviation between the predicted value and the experimental value. Through multiple optimization iterations, the optimal parameter combination of each equation is determined, requiring that the prediction error of the training set does not exceed 15%, and the prediction error of the validation set does not exceed 20%.

[0066] The specific implementation of step S708 is as follows: After completing the parameter optimization of the sub-equations, a comprehensive calculation equation for the waterproof structure life is established. This equation takes the material remaining strength coefficient, environmental damage coefficient, and equivalent stress of the waterproof layer as input variables, and outputs the expected life value of the waterproof structure. A safety factor is introduced into the equation, with the value range from 1.2 to 1.5, considering the uncertainty of model prediction. The construction of the equation adopts a piecewise function form, and different calculation methods are used for different damage degree intervals. When the damage degree is relatively light, the linear superposition principle is used to calculate the life loss; when the damage degree is relatively heavy, the non-linear cumulative damage theory is used to calculate the life loss. During the life prediction process, the coupling effect between various influencing factors is considered, and an interaction term is introduced. The comprehensive calculation equation is checked according to the actual engineering verification data, requiring that the deviation between the predicted life and the actual life does not exceed 25%.

[0067] The specific implementation of step S709 is as follows: The cross-validation method is used to cross-validate the waterproof structure life prediction equation set to evaluate the generalization ability of the prediction model. First, the data set is divided into a training set and a test set according to a ratio of 7:3. The data division uses the stratified sampling method to ensure that the distribution characteristics of the samples in each subset are similar. Perform 5-fold cross-validation on the training set data. Randomly divide the data into 5 parts, and alternately use 4 of them as training data and 1 part as validation data. In each validation, calculate the prediction error of the model on the validation set, including three indicators: mean absolute error, root mean square error, and relative error. At the same time, calculate the confidence interval of the model prediction result, and set the confidence level to 95%. According to the cross-validation results, analyze the stability and reliability of the model, and evaluate whether there is overfitting or underfitting in the model.

[0068] The specific implementation of step S710 is as follows: Based on the results of cross-validation, judge whether the performance of the prediction equation set meets the requirements. Set the preset threshold of the prediction error, the mean absolute error does not exceed 20%, the root mean square error does not exceed 25%, and the relative error does not exceed 30%. If the verification result shows that the prediction error is less than the preset threshold, it is confirmed that the equation set fitting is completed and can be used for actual engineering prediction. If the prediction error exceeds the preset threshold, return to the parameter optimization step, adjust the optimization strategy, and methods such as increasing training data, modifying the model structure, or adjusting the optimization algorithm parameters can be considered. During the process of re-optimizing the parameters, focus on the samples with large errors, analyze the reasons for the errors, and improve the model targeted. The optimization process requires multiple iterations until the preset accuracy requirements are met. In this way, ensure that the established waterproof structure life prediction equation set has high prediction accuracy and practicability.

[0069] The following details the mathematical models or calculation processes involved in the present invention.

[0070] 1. Expression of the stress distribution matrix in step S05:

[0071] The stress distribution matrix is specifically expressed as follows: In the formula, σ ij is the stress component, where i, j = 1, 2, 3 represent the x, y, and z directions respectively; σ 11 , σ 22 , σ 33 are the normal stress components; σ 12 , σ 13 , σ 21 , σ 23 , σ 31 , σ 32 are the shear stress components.

[0072] The water pressure calculation expression is as follows: P w = ρgh + P0; in the formula, Pw where \(P\) is the water pressure in Pa; \(\rho\) is the density of water, taken as \(1000\) kg / m³; \(g\) is the acceleration due to gravity, taken as \(9.81\) m / s²; \(h\) is the water depth in m; and \(P_0\) is the atmospheric pressure, taken as \(101325\) Pa.

[0073] The expression for calculating the thermal stress is as follows: \(\sigma\) t =\(E\alpha\Delta T / (1 - \mu)\); where \(\sigma\) t is the thermal stress in Pa; \(E\) is the elastic modulus of the material in Pa; \(\alpha\) is the coefficient of linear expansion in per °C; \(\Delta T\) is the temperature change in °C; and \(\mu\) is the Poisson's ratio, dimensionless.

[0074] 2. The expression of the material property attenuation equation in step S703 is:

[0075] The specific expression of the material property attenuation equation is as follows: where \(R\) t is the material strength at time \(t\) in Pa; \(R_0\) is the initial strength in Pa; \(k\) is the basic attenuation rate constant; \(t\) is the time in hours; \(\alpha\) T is the temperature influence coefficient; \(\Delta T\) is the temperature deviation in °C; \(\beta\) UV is the ultraviolet influence coefficient; \(I(t)\) is the ultraviolet intensity function in W / m²; and \(\varepsilon\) is a random error term, following a normal distribution \(N(0, 0.1)\).

[0076] 3. The expression of the environmental influence equation in step S704 is:

[0077] The specific expression of the environmental influence equation is as follows: \(D\) e =\(a_1R + a_2\Delta T + a_3\Delta P + a_4C + a_5R\Delta T + a_6\Delta TC+\varepsilon\); where \(D\) e is the environmental damage coefficient, dimensionless; \(R\) is the annual rainfall in mm; \(\Delta T\) is the temperature fluctuation range in °C; \(\Delta P\) is the water pressure change in Pa; \(C\) is the chemical corrosion strength index, dimensionless; \(a_1\), \(a_2\), \(a_3\), \(a_4\), \(a_5\), \(a_6\) are regression coefficients; and \(\varepsilon\) is a random error term, following a normal distribution \(N(0, 0.05)\).

[0078] 4. The expression of the structural stress equation in step S705 is:

[0079] The specific expression of the structural stress equation is as follows: where \(\sigma\) eq is the equivalent stress in Pa; \(\sigma_1\), \(\sigma_2\), \(\sigma_3\) are the principal stresses in Pa; and \(\varepsilon\) is a random error term, following a normal distribution \(N(0, 0.1)\).

[0080] The calculation expression of the principal stress is as follows: σ i = σ w + σ t + σ d + σ l ; In the formula, σ i (i = 1, 2, 3) are the principal stresses in each direction; σ w is the water pressure stress; σ t is the temperature stress; σ d is the deformation stress; σ l is the external load stress.

[0081] 5. Calculation of the acceleration aging factor in step S706:

[0082] The calculation expression of the acceleration aging factor is as follows: In the formula, AF is the acceleration factor, dimensionless; E a is the activation energy, with the unit of joules per mole; R is the gas constant, with a value of 8.314 joules per mole per kelvin; T u is the use temperature, with the unit of kelvin; T a is the acceleration aging temperature, with the unit of kelvin.

[0083] 6. Comprehensive equation for life prediction in step S708:

[0084] The comprehensive equation for life prediction is specifically expressed as follows: In the formula, L is the expected life, with the unit of year; L0 is the reference life, with the unit of year; R c is the current strength, with the unit of pascal; R0 is the initial strength, with the unit of pascal; D e is the environmental damage coefficient; σ eq is the equivalent stress, with the unit of pascal; σ y is the yield strength, with the unit of pascal; γ1, γ2 are the weight coefficients; n, m are material-related indices; SF is the safety factor, with a value ranging from 1.2 to 1.5; ε is the random error term, following the normal distribution N(0, 0.15).

[0085] 7. Calculation of the prediction error in step S709:

[0086] The calculation expression of the prediction error is as follows:

[0087] In the formula, MAE is the mean absolute error; RMSE is the root mean square error; RE is the relative error; y i is the actual life value; is the predicted life value; n is the number of samples.

[0088] Optionally, the normalization processing formula in step S702 is as follows:

[0089] Maximum and minimum normalization expression: In the formula, X norm is the normalized value; X is the original value; X min is the minimum value; X max is the maximum value.

[0090] Optionally, the Z-score normalization expression is as follows: In the formula, Z is the standardized value; X is the original value; μ is the mean; σ is the standard deviation.

[0091] Optionally, the performance retention rate calculation expression is as follows: In the formula, R p is the performance retention rate; P t is the performance value at time t; P0 is the initial performance value.

[0092] The construction principles and meanings of the above equations are explained as follows:

[0093] 1. The stress distribution matrix is expressed in a three-dimensional stress state, considering the complete description of normal stress and shear stress, which conforms to the principles of continuum mechanics; the water pressure calculation is based on hydrostatic principles, considering the influence of depth; the temperature stress calculation is based on thermoelastic theory, considering the material constraint conditions.

[0094] 2. The material property attenuation equation is based on the Arrhenius formula, introducing the coupling effect of temperature and ultraviolet rays, and using an exponential decay form to describe the aging process, which can better reflect the non-linear degradation characteristics of material properties over time.

[0095] 3. The environmental impact equation uses a multiple linear regression model, considering the main effects and interaction effects of environmental factors, and introducing interaction terms can describe the synergistic effects between factors.

[0096] 4. The structural stress equation is based on the von Mises yield criterion, calculating the equivalent stress, and can evaluate the stress state of materials under complex stress conditions.

[0097] 5. The accelerated aging factor calculation is based on reaction kinetics theory, used to establish the correspondence between accelerated tests and actual use conditions.

[0098] 6. The comprehensive life prediction equation considers three main factors: material property attenuation, environmental damage, and stress action, uses a power function form to describe the damage accumulation effect, and introduces a safety factor to consider uncertainty.

[0099] 7. The prediction error calculation uses multiple statistical indicators to comprehensively evaluate the accuracy and reliability of the prediction model.

[0100] Specifically, the principle of the present invention is as follows: The technical principle of the present invention is based on the integration of multiple disciplines, mainly involving the in-depth combination of four aspects: materials science, structural mechanics, graph theory algorithms, and optimization theory. Fundamentally speaking, the lifespan of the pool waterproof structure depends on the interaction of three core factors: the attenuation law of material properties over time, the degree of influence of environmental factors, and the distribution characteristics of structural stress. The present invention precisely aims at these three core factors and establishes a systematic analysis framework and optimization strategy.

[0101] Firstly, in terms of materials science, the present invention goes beyond the traditional single-factor aging model and establishes a material property attenuation equation considering the coupling effect of multiple factors. Traditional material aging research usually adopts single-factor models such as the Arrhenius formula or the linear relationship of light intensity, which is difficult to reflect the complex situation of materials being affected by multiple factors in actual engineering. The present invention collects physical and mechanical parameters such as the tensile strength, elongation at break, low-temperature flexibility, thermal aging performance, and water resistance of waterproof materials, and combines external conditions such as the ambient temperature, ultraviolet irradiation intensity, and service time to establish a comprehensive model of material property attenuation. This model can accurately describe the non-linear attenuation law of material properties under different environmental conditions, providing a reliable material science basis for lifespan prediction. Especially by obtaining calibration data through laboratory accelerated aging tests and using genetic algorithms for parameter optimization, the model prediction results are highly consistent with the actual aging process, overcoming the limitations of the traditional linear extrapolation method.

[0102] Secondly, in terms of structural mechanics, the present invention adopts a multi-physical model with a sequence scale and finite element analysis method to systematically study the stress distribution characteristics of the pool waterproof structure. Traditional structural analysis often uses a single-scale model, either ignoring local details due to the overly large model or neglecting the overall structural behavior due to focusing on the local. The present invention establishes multiple arithmetic scale models from the minimum scale to 1.00 times, ensuring both computational efficiency and simulation accuracy. Stress monitoring points are set at key positions such as the connection between the pool bottom and the pool wall, the four corners of the pool, and the seams of the waterproof layer in these models. Through finite element analysis, the comprehensive effects of water pressure, temperature change, material aging, and structural deformation on the waterproof layer are simulated, and a comprehensive stress distribution matrix is obtained. This multi-scale structural mechanics analysis method enables the accurate grasp of the stress distribution characteristics of the waterproof structure from macro to micro.

[0103] Third, the present invention innovatively introduces graph theory algorithms to deal with engineering mechanics problems, and applies the Kruskal minimum spanning tree algorithm to the analysis and processing of stress distribution matrices. Traditional stress analysis usually identifies stress concentration areas by visually observing stress nephograms, which is highly subjective and lacks systematicness. The present invention performs sparse matrix processing on the stress distribution matrix, converts it into a weighted undirected graph, where each node represents a position in the structure and the weight of the edge represents the magnitude of the stress value. Through the Kruskal minimum spanning tree algorithm, the system constructs a connection network for high-stress areas, identifies the main paths of stress transmission, and defines the connected component with the largest weight as the key area for waterproof life. This method transforms qualitative stress analysis into quantitative network analysis, greatly improving the objectivity and accuracy of stress concentration area identification. The introduction of graph theory algorithms is an important innovation point of the present invention, which provides a new mathematical tool for stress analysis in structural engineering.

[0104] Fourth, the present invention adopts the multi-objective optimization theory, integrates the material property attenuation equation, the environmental impact equation, and the structural stress equation into a waterproof structure life prediction equation set, and solves the optimal construction parameter range through a multi-objective optimization algorithm. Traditional construction parameter selection mainly relies on experience and the minimum requirements of specifications, lacking optimization for specific engineering conditions. The present invention establishes a comprehensive calculation equation for the waterproof structure life, takes the remaining strength coefficient of the material, the environmental damage coefficient, and the equivalent stress of the waterproof layer as input parameters, and calculates the expected life value of the waterproof structure. Based on this prediction result, a multi-objective optimization algorithm is used to simultaneously consider multiple objectives such as extending the waterproof life, reducing material costs, and improving construction efficiency, and solve the optimal combination of the waterproof layer thickness range, the lap width range, and the base treatment depth range. This optimization method overcomes the limitations of the traditional "one-size-fits-all" construction standard and realizes the scientific and refined construction parameters.

[0105] Finally, the present invention verifies the key areas for waterproof life identified in the sequence scale multi-physical model through a combination of experiments and simulations to ensure the consistency between theoretical predictions and actual situations. During the construction implementation stage, differential strengthening measures such as increasing the thickness of the waterproof layer, adding additional waterproof layers, and setting up waterproof protection layers are taken for these key areas, realizing the rational allocation of resources and the extension of the overall life of the waterproof structure. This strategy of "identifying key areas - taking targeted measures" is the core mechanism for the present invention to effectively extend the life of the waterproof structure.

[0106] In summary, the technical principle of the present invention lies in the organic integration of material science, structural mechanics, graph theory algorithms, and optimization theory, establishing a complete technical system from theoretical analysis to actual construction. By analyzing the stress distribution through multi-scale physical models, applying graph theory algorithms to identify key areas, establishing a life prediction equation set with multi-factor coupling, and using multi-objective optimization algorithms to determine the optimal construction parameters, the technical goal of accurately predicting the life of the waterproof structure and effectively extending its service life is ultimately achieved. The innovation of this technical principle lies in breaking through the limitations of the traditional single-discipline perspective and establishing an interdisciplinary systematic solution, providing scientific technical support for the standardized swimming pool waterproof project in stadiums.

[0107] A specific Embodiment 1 of the present invention is provided below. The specific implementation manners of each step in this Embodiment 1 are described in detail as follows.

[0108] The specific implementation manner of step S01 is: Obtain relevant basic parameter information according to the design drawings of the standardized swimming pool. First, determine the three basic dimensions of the swimming pool, namely length, width, and depth, through drawing measurement. The length of a standard swimming pool is usually 50 meters or 25 meters, the width is 21 meters or 25 meters, and the depth varies from 1.35 meters to 2 meters according to the functional area. Use an electronic measuring instrument for accurate measurement, and the measurement accuracy should reach ±1 millimeter. Then determine the structural type of the swimming pool, including cast-in-place reinforced concrete structure, precast concrete structure, or steel structure, etc., and record the characteristics of the structural form, focusing on the connection method of the structure, the setting of deformation joints, and the waterproof structure nodes. Next, calculate the load conditions borne by the swimming pool, using the following calculation expression: P w = ρgh + P0, where P w is the water pressure, with the unit of Pascal, ρ is the density of water, taking the value of 1000 kg / m³, g is the acceleration due to gravity, taking the value of 9.81 m / s², h is the water depth, with the unit of meter, and P0 is the atmospheric pressure, taking the value of 101325 Pascal. According to the actual use conditions, consider dead loads, live loads, water pressure, and temperature loads, etc. Among them, the dead loads mainly include the self-weight of the structure and the weight of equipment, the live loads consider the personnel load and the maintenance load, and the temperature load is determined according to the local meteorological data for the design temperature difference. Finally, determine the design thickness requirement of the waterproof layer. Generally, the thickness of the waterproof layer is between 1.5 millimeters and 2.5 millimeters. The specific value needs to be determined according to the scale and use requirements of the swimming pool, and at the same time, consider the influence of material properties and construction techniques. The acquisition of these basic parameters provides basic data support for subsequent analysis and optimization.

[0109] The specific implementation of step S02 is as follows: Conduct comprehensive physical and mechanical property tests and data collection on waterproof materials. First, use a tensile testing machine to test the tensile strength of the material at a test temperature of 23 ± 2 °C and a tensile speed of 500 ± 50 mm per minute. Record the tensile strength value of the material. The standard requirement is not less than 12 MPa. The specimen preparation is carried out according to relevant standard requirements, and each group of tests has no less than 5 parallel samples. Then, test the elongation at break of the material. Use the same test equipment and conditions, and record the elongation value when the material reaches break. The requirement is not less than 300%. During the test process, a gauge length instrument is needed for accurate measurement. Next, conduct the low-temperature flexibility test. Keep the specimen at a temperature of -20 °C for 2 hours, and then conduct a bending test to observe whether cracks appear. The bending angle is 180 degrees and the bending rate is 3 times per minute. Continue to conduct the heat aging performance test. Accelerate the aging of the specimen in an 80 °C environment for 168 hours, and test the retention rates of its tensile strength and elongation at break. Use the performance retention rate calculation formula: In the formula, R p is the performance retention rate, P t is the performance value after aging, and P0 is the initial performance value. The requirement for the retention rate is not less than 80%. Finally, test the water resistance performance. Immerse the specimen in water at 23 ± 2 °C for 168 hours, and test the mass change rate and volume change rate. The requirement for the change rate is not more than 3%.

[0110] The specific implementation of step S03 is as follows: Build a series of physical models with different scales based on the similarity theory. Set the sequence scale to be between 0.1 and 1.0. Select 10 scale values according to the arithmetic progression principle. The scale sequence is 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0. During the modeling process, strictly control the geometric similarity of the model, maintain the relative position relationship and geometric dimension ratio between each component, and ensure that the model can accurately reflect the actual structural characteristics. Use 3D modeling software to build a digital model of the pool structure, and divide the model into key parts such as the pool bottom, pool wall, and transition area. Set unified mesh division parameters in the model. The mesh size is selected as 50 mm to ensure the balance between calculation accuracy and efficiency. For the waterproof layer structure, use shell elements for simulation. The element type is selected as four-node quadrilateral elements, and the mesh is encrypted at the joints and corner positions. The mesh size in the encrypted area is reduced to 25 mm. After the model is established, conduct a mesh quality inspection, including indicators such as mesh distortion, aspect ratio, and orthogonality, to ensure that the mesh quality meets the calculation requirements.

[0111] The specific implementation of step S04 is as follows: An array of stress monitoring points is arranged in the established small physical model. Six monitoring points with a circumferential interval of 60 degrees are arranged at the connection between the pool bottom and the pool wall, and the monitored stress components are in accordance with the stress distribution matrix expression: In the formula, σ ij is the stress component, where i, j = 1, 2, 3 represent the x, y, and z directions respectively, σ 11 , σ 22 , σ 33 are the normal stress components, and σ 12 , σ 13 , σ 21 , σ 23 , σ 31 , σ 32 are the shear stress components. Five monitoring points are arranged in each of the four corner areas of the swimming pool, distributed in a fan shape, with a monitoring point spacing of 100 mm, and the stress concentration effect is focused on. Double rows of monitoring points are set at the waterproof layer joints, arranged at an interval of 200 mm along the joint direction, and there are no less than 10 monitoring points at each joint to monitor the stress distribution state at the joints. For special structural parts such as deformation joints and through-wall pipes, local encrypted monitoring points are added, and the monitoring point spacing in the encrypted area is reduced to 50 mm. A local coordinate system is defined at the monitoring points to ensure the accuracy of stress component calculation. According to the monitoring data, a stress field distribution cloud map is constructed, and an interpolation algorithm is used to calculate the stress values between the monitoring points.

[0112] The specific implementation of step S05 is as follows: The collected physical and mechanical parameters are imported into the finite element analysis software, the material constitutive model is set as the elastoplastic model, and parameters such as elastic modulus, Poisson's ratio, and yield strength are input. Static analysis is carried out, considering the water pressure distribution, and the water pressure is calculated according to the formula: P w =ρgh + P0. Transient thermal analysis is carried out to simulate the temperature change process from -10 degrees Celsius to 40 degrees Celsius, and the temperature stress calculation formula is adopted: σ t =EαΔT / (1 - μ), where σ t is the temperature stress, with the unit of Pa, E is the material elastic modulus, with the unit of Pa, α is the linear expansion coefficient, with the unit of per degree Celsius, ΔT is the temperature change amount, with the unit of degree Celsius, and μ is Poisson's ratio, dimensionless. Considering the material aging effect, the material strength and stiffness parameters are set as functions of time to simulate the performance degradation during the service process. The influence of structural deformation is analyzed, the foundation settlement and wall displacement boundary conditions are applied, and the stress state of the waterproof layer is calculated. The explicit dynamics method is used for solution, the time step is set to 0.001 s, the total calculation time is 100 s, the nodal stress time history curve is output, and a stress distribution matrix is formed.

[0113] The specific implementation of step S06 is as follows: perform data processing and analysis on the obtained stress distribution matrix. First, set the values in the stress matrix that are less than 5% of the maximum stress to zero, and perform min-max normalization processing: In the formula, X norm is the normalized value, X is the original value, X min is the minimum value, and X max is the maximum value. Use the Kruskal minimum spanning tree algorithm to process the sparse matrix, take the stress value as the weight of the edge, and construct an undirected graph structure. The algorithm starts from the edge with the minimum weight and gradually adds edges until a complete spanning tree is formed, avoiding the formation of loops. By analyzing the structural characteristics of the spanning tree, identify the main paths of stress transmission, and focus on the nodes connected by the edges with larger weights. Use the connected component analysis method to divide the stress network into several independent regions, and calculate the total weight of each connected component. Define the connected component with the largest weight as the key area for the waterproof life. The stress level and distribution characteristics in this area directly affect the service life of the waterproof structure. Through this method, the areas in the waterproof system that are most prone to failure can be accurately located, providing a basis for subsequent construction optimization. During the weight calculation process, normalization processing is used to eliminate the influence of dimensions and ensure the comparability of different types of stress.

[0114] The specific implementation of step S07 is as follows: establish a waterproof structure life prediction equation set. This equation set includes three sub-equations: the material property attenuation equation, the environmental impact equation, and the structural stress equation. First, construct the material property attenuation equation:

[0115] In the formula, R t is the material strength at time t, with the unit of Pa, R0 is the initial strength, with the unit of Pa, k is the basic attenuation rate constant, t is the time, with the unit of hour, α T is the temperature influence coefficient, ΔT is the temperature deviation, with the unit of °C, β UV is the ultraviolet influence coefficient, I(t) is the ultraviolet intensity function, with the unit of W / m², and ε is a random error term, following the normal distribution N(0, 0.1). Then establish the environmental impact equation: D e = a1R + a2ΔT + a3ΔP + a4C + a5RΔT + a6ΔTC + ε. In the formula, D e is the environmental damage coefficient, dimensionless, R is the annual rainfall, with the unit of mm, ΔT is the temperature fluctuation range, with the unit of °C, ΔP is the water pressure change, with the unit of Pa, C is the chemical corrosion intensity index, dimensionless, a1, a2, a3, a4, a5, a6 are regression coefficients, and ε is a random error term, following the normal distribution N(0, 0.05). Finally, establish the structural stress equation: In the formula, σ eqis the equivalent stress in Pa, σ1, σ2, and σ3 are the principal stresses in Pa, and ε is the random error term, which follows a normal distribution N(0, 0.1).

[0116] The specific implementation of step S08 is as follows: Use a multi-objective optimization algorithm to solve the life prediction equations. First, set the optimization objectives, including maximizing the waterproof structure life, minimizing the construction cost, and optimizing the construction process. Use the non-dominated sorting genetic algorithm for solving, with the population size set to 100, the number of iterations to 1000, the crossover probability to 0.8, and the mutation probability to 0.1. During the optimization process, set the waterproof layer thickness range from 1.5 mm to 3.0 mm, the overlap width range from 80 mm to 150 mm, and the base treatment depth range from 2 mm to 5 mm. Through the Pareto optimal solution set analysis, determine the optimal construction parameter range that meets the multi-objective requirements. The fitness function used in the optimization process is: F = w1L + w2C + w3Q, where F is the comprehensive fitness value, L is the life index, C is the cost index, Q is the construction quality index, and w1, w2, and w3 are the weight coefficients, and w1 + w2 + w3 = 1.

[0117] The specific implementation of step S09 is as follows: Conduct experimental verification and simulation analysis on the key areas of the waterproof life. First, under laboratory conditions, use the accelerated aging test method to verify the key areas predicted in different scale models. Make specimens containing the key areas, conduct cyclic load tests, temperature cycle tests, and fatigue tests, with the test cycle being 3000 times, and record the stress distribution and damage evolution process. At the same time, use finite element software for numerical simulation, establish a refined local model with the mesh size accurate to 10 mm, and simulate the stress state under various working conditions. The experimental data is processed using Z-score standardization: where Z is the standardized value, X is the original value, μ is the mean, and σ is the standard deviation. By comparing and analyzing the experimental results and simulation data, calculate the relative error: Verify the accuracy of the key areas.

[0118] The specific implementation of step S10 is as follows: Based on the optimal construction parameter range, determine the specific construction parameters in combination with the actual engineering situation. According to the pool size and usage requirements, select the actual thickness of the waterproof layer, 2.5 mm for large competition pools and 2.0 mm for general pools. Determine the actual overlap width, 120 mm for the main joint positions and 100 mm for the secondary joint positions. For the actual depth of the base treatment, 3 mm for newly built pools and 4 mm for renovation projects. The parameter determination uses the comprehensive evaluation index: where Q is the comprehensive evaluation value, X i is the single index value, w i is the weight coefficient, and n is the number of indexes.

[0119] The specific implementation of step S11 is as follows: comprehensively process and control the quality of the pool base layer. First, detect the flatness of the base layer using a 2-meter straightedge, and the allowable deviation shall not be greater than 3 mm. Grind the surface of the base layer to remove floating slurry and loose materials, and the grinding depth shall be controlled within the design value range. Test the compressive strength of the base layer. The concrete strength grade shall not be lower than C30, and the rebound method shall be used for non-destructive testing. Detect the moisture content of the base layer using the drying method and control it below 5%. The quality evaluation of the base layer adopts the weighted average method: where S is the quality score of the base layer, P i is the score of each detection index, w i is the weight coefficient.

[0120] The specific implementation of step S12 is as follows: construct the waterproof layer according to the determined construction parameters and take targeted strengthening measures for key areas. First, apply a primer on the surface of the base layer at a dosage of 0.3 kg per square meter, and the drying time shall not be less than 4 hours. When laying the waterproof coiled material, strictly control the lap width and use the hot air welding process, with the welding temperature controlled between 380 and 420 degrees Celsius. For key areas such as the corners of the pool, deformation joints, and equipment penetration through the wall, add an additional layer of waterproofing, and the width of the additional layer shall not be less than 500 mm. Set up a waterproof protection layer at the parts vulnerable to mechanical damage, which can use polyester fiber non-woven fabric with a unit area mass of not less than 300 grams per square meter. The construction quality control adopts the item scoring method: where Q c is the construction quality score, M i is the score of the sub-project, k i is the sub-item weight coefficient. After all the detailed structure treatments are completed, conduct a water storage test for not less than 48 hours and observe the leakage situation.

[0121] The specific implementation of step S701 is as follows: collect historical engineering data through various channels, including the completion data, use and maintenance records, and regular inspection reports of the built swimming pools, etc. For the material performance parameters, collect the physical and mechanical performance test data of the waterproof materials, including the tensile strength, elongation at break, tear strength, etc. of different service years. The test data shall include at least 50 engineering cases with the service years distributed between 1 year and 20 years. Regarding the environmental condition records, collect the meteorological data of the project location, including the annual average temperature, temperature change range, annual rainfall, ultraviolet intensity, etc. The data collection period shall not be less than 5 years. The records of the structural failure conditions include the types of waterproof layer damage, failure locations, failure times, etc., and conduct on-site investigations and image records. Establish a data reliability evaluation index: where R is the reliability index, X i is the reliability score of a single item of data, w iis the weight coefficient, and n is the number of evaluation indicators. During the data collection process, interpolation method is used to handle the missing data: In the formula, Y m is the predicted value of the point to be interpolated, Y i is the observed value of the known point, d i is the distance from the point to be interpolated to the known point, p is the distance power, and the value range is from 2 to 4.

[0122] The specific implementation of step S702 is: systematically normalize the collected historical engineering data to eliminate the influence brought by different dimensions. The maximum-minimum normalization processing uses the formula: In the formula, X norm is the normalized value, X is the original value, X min is the minimum value, X max is the maximum value. For the material property data, the initial value standardization method is adopted. Based on the initial property value of the material, the performance retention rate is calculated: In the formula, R p is the performance retention rate, P t is the property value at time t, and P0 is the initial property value. For the environmental parameters, the Z-score standardization method is adopted: In the formula, Z is the standardized value, X is the original value, μ is the mean value, and σ is the standard deviation. For the categorical data such as failure types, the one-hot encoding method is adopted to convert it into numerical data. The outlier detection uses the box plot method to calculate the interquartile range: IQR = Q3 - Q1, and the outlier determination criterion is: X < Q1 - 1.5IQR or X > Q3 + 1.5IQR, where Q1 is the lower quartile and Q3 is the upper quartile.

[0123] The specific implementation of step S703 is: use the least squares method to establish the initial model of the material property attenuation equation. The basic form of the equation is: In the formula, R t is the material strength at time t, R0 is the initial strength, k is the basic attenuation rate constant, t is the time, α T is the temperature influence coefficient, ΔT is the temperature deviation, β UV is the ultraviolet influence coefficient, I(t) is the ultraviolet intensity function, and ε is the random error term. The parameter estimation uses the least squares criterion: In the formula, J is the objective function, y i is the measured value, is the predicted value, and n is the number of samples. The model evaluation uses the coefficient of determination: In the formula is the average value of the measured values, and it is required that R 2 is not less than 0.85.

[0124] The specific implementation of step S704 is as follows: The initial model of the environmental impact equation is established by using the multiple regression analysis method. The expression of the environmental impact equation is: D e = a1R + a2ΔT + a3ΔP + a4C + a5RΔT + a6ΔTC + ε, where D e is the environmental damage coefficient, R is the annual rainfall, ΔT is the temperature fluctuation range, ΔP is the water pressure change, C is the chemical corrosion intensity index, a1, a2, a3, a4, a5, a6 are regression coefficients, and ε is the random error term. The variable screening adopts the stepwise regression method, and the partial correlation coefficient is calculated: where r XY·Z is the partial correlation coefficient, r XY , r XZ , r YZ are the simple correlation coefficients. The collinearity diagnosis adopts the variance inflation factor: where VIF j is the variance inflation factor of the jth independent variable, is the coefficient of determination of the jth independent variable with respect to other independent variables.

[0125] The specific implementation of step S705 is as follows: The initial model of the structural stress equation is established based on the principles of elastoplastic mechanics. The structural stress equation adopts the equivalent stress expression: where σ eq is the equivalent stress, σ1, σ2, σ3 are the principal stresses, and ε is the random error term. The calculation expression of the principal stress: σ i = σ w + σ t + σ d + σ l , where σ i (i = 1, 2, 3) are the principal stresses in each direction, σ w is the water pressure stress, σ t is the temperature stress, σ d is the deformation stress, and σ l is the external load stress. The temperature stress is calculated using the formula: σ t = EαΔT / (1 - μ), where E is the elastic modulus, α is the linear expansion coefficient, ΔT is the temperature change, and μ is the Poisson's ratio. The relative error is used to evaluate the stress calculation accuracy: where σ cal is the calculated value, σ mea is the measured value, and the relative error is required not to exceed 10%.

[0126] The specific implementation of step S706 is as follows: calibration data is obtained through laboratory accelerated aging tests. First, a high-temperature aging test is carried out. The specimen is placed in an environment of 80 degrees Celsius, and the test times are three cycles of 168 hours, 336 hours, and 672 hours. Samples are taken in each cycle to test the physical and mechanical properties. The acceleration factor is calculated using the formula: where AF is the acceleration factor, E a is the activation energy, R is the gas constant, T u is the use temperature, and T a is the accelerated aging temperature. For the ultraviolet aging test, a xenon arc lamp aging test chamber is used. The irradiance is set at 550 watts per square meter, and the wavelength range is from 290 to 800 nanometers. The test cycle is the same as that of the high-temperature aging test. The calculation of the ultraviolet cumulative dose is as follows: where D UV is the cumulative dose, I(t) is the irradiance function, and t is the time. The immersion aging test is carried out under the condition of 23 ± 2 degrees Celsius. The test water is deionized water. The test cycles are 7 days, 14 days, and 28 days. The water absorption rate and strength change of the specimen are measured regularly. For the cyclic loading test, a dynamic fatigue testing machine is used. The loading frequency is 10 hertz, and the stress levels are set at three levels of 70%, 80%, and 90% of the material yield strength. The fatigue life at different stress levels is recorded. The prediction of the fatigue life adopts the Miner linear cumulative damage theory: where n i is the actual number of cycles, and N i is the fatigue life corresponding to the stress level.

[0127] The specific implementation of step S707 is as follows: using the calibration data obtained from the accelerated aging test, the parameters of the three sub-equations of the life prediction equation set are optimized. The genetic algorithm is used for the optimization solution. The chromosome coding adopts real number coding, and the gene length is determined according to the number of parameters to be optimized. The population size is set to 200, the number of generations of evolution is 500 generations, the crossover probability is 0.85, and the mutation probability is 0.1. The fitness function adopts the root mean square error: where y i is the measured value, is the predicted value, and n is the number of samples. The calculation of the adaptive crossover probability is as follows: where P c is the crossover probability, P c1 , P c2 are the upper and lower limits, f max is the maximum fitness of the population, f avg is the average fitness, and f′ is the larger fitness value participating in the crossover. The calculation of the adaptive mutation probability is as follows: where Pm is the mutation probability, P m1 , P m2 are the upper and lower limits, and f is the fitness of the current individual.

[0128] The specific implementation of step S708 is: establishing a comprehensive calculation equation for the service life of the waterproof structure. The expression of this equation is: In the formula, L is the expected life, L0 is the reference life, R c is the current strength, R0 is the initial strength, D e is the environmental damage coefficient, σ eq is the equivalent stress, σ y is the yield strength, γ1 and γ2 are weight coefficients, n and m are material-related exponents, SF is the safety factor, and ε is the random error term. For the mild damage stage D e <0.3, linear superposition is adopted: L = L0(1 - αD e ), where α is the damage influence coefficient. For the severe damage stage D e ≥0.3, non-linear accumulation is adopted: where β is the non-linear damage coefficient. Parameter calibration uses the least squares method, and residual calculation: Standard deviation estimation: where p is the number of parameters.

[0129] The specific implementation of step S709 is: using the holdout method to perform cross-validation on the waterproof structure life prediction equation set. The data set is divided into a training set and a test set according to a 7:3 ratio using stratified sampling. Perform 5-fold cross-validation on the training set data, and calculate the mean absolute error: Root mean square error: Relative error: Confidence interval calculation: where t α / 2 is the t-distribution critical value, is the standard error of the predicted value.

[0130] The specific implementation of step S710 is: based on the results of cross-validation, determine whether the performance of the prediction equation set meets the requirements. Set a preset threshold for the prediction error, with the mean absolute error not exceeding 20%, the root mean square error not exceeding 25%, and the relative error not exceeding 30%. Perform a normality test on the prediction error: where W is the Shapiro-Wilk statistic, a i is the coefficient, x (i) is the order statistic. If the verification results show that the prediction error is less than the preset threshold, it is confirmed that the equation set fitting is completed. If the prediction error exceeds the preset threshold, return to the parameter re-optimization step. Error analysis uses variance decomposition: where They are the variances of the measured value and the predicted value respectively, and r is the correlation coefficient.

[0131] To better understand and implement the present invention, the following provides Embodiment 2 of a specific application scenario of the present invention:

[0132] 1. Acquisition and planning of basic parameters

[0133] The construction team received the design task of the waterproofing system for a standard swimming pool in a certain stadium. The swimming pool needs to build a standard competition pool of 50 meters × 25 meters, adopting cast-in-place reinforced concrete structure. According to step S01, the construction team obtained the basic structure parameters through the design drawings, as shown in Table 1:

[0134] Table 1 Basic structure parameters of the pool

[0135] Parameter type Parameter value Unit Pool length 50 m Pool width 25 m Depth of shallow water area 1.35 m Depth of deep water area 2.00 m Structure type Cast-in-place reinforced concrete - Concrete strength grade C35 - Design load 2.50 kN / m² Water pressure (maximum at the bottom of the pool) 19.62 kPa Temperature change range -15～45 °C Design thickness of waterproof layer 2.00 mm

[0136] 2. Testing of physical and mechanical parameters of waterproof materials

[0137] According to step S02, the construction team selected polymer modified polymer waterproof coiled material as the main waterproof material and conducted a comprehensive physical and mechanical performance test. The test results are shown in Table 2:

[0138] Table 2 Test results of physical and mechanical parameters of waterproof materials

[0139] Parameter name Test value Standard requirement Unit Test method Tensile strength 15.8 ≥12.0 MPa GB / T 328.9 Elongation at break 358 ≥300 ％ GB / T 328.9 Low temperature flexibility No cracks No cracks - -20°C, 180° bending Strength retention rate after heat aging 87.5 ≥80 ％ 80℃,168h Elongation retention rate after heat aging 85.2 ≥80 ％ 80℃,168h Mass change rate of water resistance 1.8 ≤3.0 ％ 23℃,168h Volume change rate of water resistance 2.1 ≤3.0 ％ 23℃,168h

[0140] 3. Establishment of physical models with sequence scales

[0141] According to step S03, the construction team established 10 small physical models with different scales. The model scales are set as an arithmetic sequence from 0.1 to 1.0, and the specific parameters are shown in Table 3:

[0142] Table 3 Parameters of physical models with sequence scales

[0143]

[0144]

[0145] In key areas such as corners and joints, the construction team carried out grid encryption, and the grid size in the encrypted area was reduced to 25 mm to improve the calculation accuracy.

[0146] 4. Arrangement of stress monitoring points

[0147] According to step S04, the construction team arranged an array of stress monitoring points in the small physical models. The arrangement of the monitoring points is shown in Table 4:

[0148] Table 4 Arrangement of stress monitoring points

[0149] Monitoring area Number of monitoring points Spacing between monitoring points Monitoring content Layout method Connection between the bottom of the pool and the pool wall 36 60° Shearing stress, normal stress Circumferential layout Four corners area of the pool 20 100mm Equivalent stress, principal stress Sector distribution Joints of waterproof layer 68 200mm Shearing stress, tear strength Double row layout Deformation joint 24 50mm Strain, displacement Local encryption Around the pipe passing through the wall 16 50mm Stress concentration coefficient Radial distribution

[0150] 5. Finite element analysis simulation

[0151] According to step S05, the construction team input the physical and mechanical parameters into the finite element analysis software for simulation analysis. The analysis conditions and parameter settings are shown in Table 5:

[0152] Table 5 Finite element analysis conditions and parameter settings

[0153] Analysis type Parameter name Parameter value Unit Static analysis Water pressure gradient 9.81 kPa / m Static analysis Maximum water pressure at the bottom of the pool 19.62 kPa Thermal analysis Temperature change range -10～40 °C Thermal analysis Temperature gradient 0.5 °C / cm Material property Elastic modulus <![CDATA[8.5×10 6 > Pa Material property Poisson's ratio 0.42 - Material property Coefficient of linear expansion <![CDATA[1.6×10 -4 > 1 / °C Calculation parameter Time step 0.001 s Calculation parameter Total calculation time 100 s Aging simulation Strength attenuation rate 2.5 % / year Aging simulation Modulus attenuation rate 3.2 % / year

[0154] Through finite element analysis, the stress distribution matrix was obtained. The results show that there are obvious stress concentration phenomena at the connection between the pool bottom and the pool wall and at the four corners of the swimming pool. The maximum equivalent stress value reaches 3.82 MPa, which is about 25.4% of the material yield strength.

[0155] 6. Stress distribution matrix processing and key area identification

[0156] According to step S06, the construction team carried out sparse matrix processing and minimum spanning tree algorithm analysis on the stress distribution matrix. First, the values below 5% of the maximum stress (less than 0.191 MPa) were set to zero to construct a sparse matrix. Then, the Kruskal minimum spanning tree algorithm was used to construct an undirected graph structure with nodes as vertices, stress transfer paths as edges, and stress values as weights.

[0157] The minimum spanning tree analysis results identified 5 main connected components, as shown in Table 6:

[0158] Table 6 Stress connected component analysis results

[0159] Connected component number Number of nodes Total weight Maximum stress Location description C-01 126 283.5 3.82 Corner connection between the bottom of the pool and the pool wall C-02 84 156.8 2.56 Joints of waterproof layer in deep water area C-03 72 124.3 2.18 Deformation joint in shallow water area C-04 58 86.7 1.94 Pipe passing through the pool wall C-05 46 65.2 1.63 Middle area of the pool bottom

[0160] According to the total weight analysis, the connected component C-01 was determined as the key area for the waterproof life. This area is located at the corner connection between the pool bottom and the pool wall, where the stress concentration is obvious and it is the most vulnerable part of the waterproof structure to fail.

[0161] 7. Establishment of waterproof structure life prediction equations

[0162] According to steps S701 to S710, the construction team collected the historical engineering data of 50 completed swimming pools, and the service life was distributed between 1 and 20 years. First, the data was normalized, and then the material property attenuation equation, environmental impact equation, and structural stress equation were established respectively.

[0163] 7.1 Material property attenuation equation

[0164] The exponential model is adopted for the material property attenuation equation, and it is obtained after fitting by the least squares method:

[0165]

[0166] Among them, R t is the material strength (MPa) at time t; R0 is the initial strength (15.8 MPa); t is the time (year); ΔT is the temperature deviation (°C); I(t) is the ultraviolet intensity (W / m²). The goodness of fit R 2 = 0.876, meeting the requirement (≥0.85).

[0167] 7.2 Environmental impact equation

[0168] The multiple regression analysis method is adopted for the environmental impact equation, and it is obtained after screening out the significant influencing factors:

[0169] D e = 0.0012R + 0.0085ΔT + 0.0056ΔP + 0.0248C + 0.00023RΔT + 0.0016ΔTC;

[0170] Among them, D e is the environmental damage coefficient (dimensionless); R is the annual rainfall (mm); ΔT is the temperature fluctuation range (°C); ΔP is the water pressure change (kPa); C is the chemical corrosion intensity (dimensionless). The adjusted determination coefficient of the regression equation is 0.832, and the significance level is 95%.

[0171] 7.3 Structural stress equation

[0172] The structural stress equation is established based on the principles of elastoplastic mechanics:

[0173]

[0174] Among them, σ eq is the equivalent stress (MPa); σ1, σ2, σ3 are the principal stresses (MPa). The principal stress calculation formula is:

[0175] σ i = 1.05σ w + 0.85σ t + 0.76σ d + 0.92σ l ;

[0176] Among them, σ w is the water pressure stress; σ t is the temperature stress; σ d is the deformation stress; σ l is the external load stress. The model verification results show that the calculation error is within 8.4%, meeting the accuracy requirements.

[0177] 7.4 Accelerated Aging Test and Parameter Optimization

[0178] The construction team conducted an accelerated aging test in the laboratory, and the test conditions are shown in Table 7:

[0179] Table 7 Accelerated Aging Test Conditions

[0180]

[0181]

[0182] Based on the accelerated aging test data, the construction team used the genetic algorithm to optimize the parameters of the life prediction equation set. The algorithm parameters were set as follows: population size 200, number of generations 500, crossover probability 0.85, and mutation probability 0.1. The prediction error of the optimized prediction equation on the training set was 12.8%, and the prediction error on the validation set was 18.5%, both meeting the accuracy requirements.

[0183] 7.5 Comprehensive Life Calculation Equation

[0184] The finally established comprehensive life calculation equation for the waterproof structure is:

[0185]

[0186] Among them, L is the expected life (years); R c is the current strength (MPa); D e is the environmental damage coefficient; σ eq is the equivalent stress (MPa); the safety factor is taken as 1.3.

[0187] 8. Determination of Optimal Construction Parameters

[0188] According to step S08, the construction team used the non-dominated sorting genetic algorithm to solve the life prediction equation set and obtained the range of optimal construction parameters. After 1000 iterations of the algorithm running, the obtained Pareto optimal solution set is shown in Table 8:

[0189] Table 8 Pareto Optimal Solution Set of Multi-objective Optimization

[0190]

[0191] According to the project requirements and cost-benefit analysis, the construction team selected the solution PS-02 as the final construction plan, that is, the waterproof layer thickness is 2.5 mm, the lap width is 130 mm, and the depth of the base treatment is 4.0 mm.

[0192] 9. Verification of Key Areas of Waterproof Life

[0193] According to step S09, the construction team verified the key areas of the waterproof life in the sequence scale model through experiments and simulations. For experimental verification, a method combining accelerated aging and cyclic loading was adopted. Specimens containing the key areas were fabricated and 3000 cyclic tests were conducted.

[0194] For simulation verification, a refined local model was used, with the mesh size accurately set to 10 mm to simulate the stress states under various working conditions. The verification results are shown in Table 9:

[0195] Table 9 Verification Results of Key Areas of Waterproof Life

[0196]

[0197] The verification results show that the key areas predicted by the model are highly consistent with the actual test results, with an average error of 3.47%. It is confirmed that the corner connection between the bottom of the pool and the pool wall is the actual key area of the waterproof life.

[0198] 10. Determination of Specific Construction Parameters

[0199] According to step S10, in combination with the actual situation of the project, the construction team determined the final specific construction parameters, as shown in Table 10:

[0200] Table 10 Specific Construction Parameters of the Waterproof Project

[0201] Parameter name Parameter value Applicable area Actual thickness of waterproof layer 2.5mm Conventional area Actual thickness of waterproof layer 3.0mm Key area Actual width of overlap 130mm Main joint Actual width of overlap 150mm Joint in key area Actual depth of base treatment 4.0mm Conventional area Actual depth of base treatment 5.0mm Key area

[0202] 11. Subgrade Treatment and Quality Control

[0203] In accordance with step S11, the construction team carried out comprehensive treatment and quality control on the pool subgrade. The specific treatment standards are shown in Table 11:

[0204] Table 11 Subgrade Treatment Standards and Quality Control Indexes

[0205] Treatment item Control standard Detection method Actual control value Concrete strength grade ≥C35 Rebound method C38 Base flatness ≤3mm / 2m Checked with 2m straightedge 2.5mm / 2m Base moisture content ≤5％ Drying method 3.8％ Surface roughness 1.0 - 1.5mm Belt sander method 1.2mm Surface pH value 7-9 pH test paper 8.2 Base cleanliness No oil stain, dust Visual inspection Qualified Treatment of inside and outside corners R≥30mm Arc inspection ruler R = 35mm Depth of crack treatment ≥10mm Depth ruler 12mm

[0206] The subgrade treatment adopted a combination of mechanical grinding and manual repair to ensure that the subgrade quality meets the design requirements. For the detected micro-cracks, epoxy resin mortar was used for filling and cured for 48 hours.

[0207] 12. Waterproof Layer Construction and Reinforcement of Key Areas

[0208] According to step S12, the construction team laid the waterproof layer according to the determined construction parameters and took targeted strengthening measures for the key areas. The waterproof construction process flow is shown in Table 12:

[0209] Table 12 Waterproof Construction Process Flow and Parameters

[0210] Process Construction parameter Construction method Quality control point Coating of primer <![CDATA[0.3kg / m 2 > Evenly coated by roller brush Coverage rate 100% Drying of primer 4 hours Naturally dried No free water Laying of waterproof coiled material 2.5mm thick Adhesive + mechanical fixation Flat and without wrinkles Hot air welding of joints 400±20℃ Automatic hot air welding machine Weld width ≥20mm Setting of additional layer Width 500mm Full adhesion method Cover key area Setting of protective layer <![CDATA[300g / m 2 > Polyester fiber non-woven fabric Edge overlap 50mm Water storage test 48 hours Full water static load No leakage point

[0211] For the key areas of waterproof life, triple enhanced protection measures have been taken:

[0212] 1. Increase the thickness of the waterproof layer: Increase the thickness of the waterproof layer at the corner connection of the pool bottom and the pool wall to 3.0 mm to enhance the stress resistance. 2. Add additional waterproof layers: Add additional waterproof layers with a width of 500 mm in the key areas, using the same material and full adhesion treatment. 3. Set up a waterproof protection layer: Lay polyester fiber non-woven fabric as a protection layer in the key areas to reduce the risk of external mechanical damage.

[0213] 13. Evaluation of implementation effects

[0214] After the completion of the waterproof system, the construction team carried out a 6-month follow-up monitoring. The monitoring data is shown in Table 13:

[0215] Table 13 Monitoring data of the waterproof system

[0216] Monitoring item Monitoring location Initial value After 3 months After 6 months Change rate (%) Measured stress (MPa) Key area C-01 3.82 3.85 3.88 1.57 Measured stress (MPa) Key area C-02 2.56 2.58 2.60 1.56 Material strength (MPa) Normal area 15.8 15.75 15.68 0.76 Material strength (MPa) Critical area 15.8 15.77 15.72 0.51 Joint strength (MPa) Normal joint 14.2 14.15 14.08 0.85 Joint strength (MPa) Joint of critical area 14.2 14.18 14.14 0.42 Waterproof layer thickness (mm) Normal area 2.50 2.49 2.48 0.80 Waterproof layer thickness (mm) Critical area 3.00 2.99 2.98 0.67

[0217] According to the monitoring data and the life prediction equation, the expected service life of the pool waterproof system is 26.8 years, which is in line with the design goal. During the 6-month monitoring period, the system performance remained stable, and the strength attenuation rate in the key areas was significantly lower than that in the conventional areas, proving the effectiveness of the enhanced protection measures.

[0218] Comparison of the progressiveness between traditional methods and the present invention

[0219] Traditional pool waterproof construction methods mainly rely on experience to determine parameters such as the thickness of the waterproof layer and the lapping width, lacking a scientific basis for calculation and optimization. Traditional methods usually use waterproof layers with a uniform thickness, ignoring the differences in stress distribution in different areas, resulting in premature failure in stress concentration areas. At the same time, traditional methods lack a quantitative assessment of material aging and environmental impacts and cannot accurately predict the service life of the waterproof structure.

[0220] The method in this Example 2 has the following significant progress compared with traditional methods:

[0221] 1. Replace empirical judgment with scientific quantification methods: Through the serial scale physical model and finite element analysis, the present invention elevates the waterproof design from empirical judgment to the level of scientific quantification, making the waterproof design evidence-based.

[0222] 2. Accurately identify key failure areas: By constructing a high-stress area connection network through the Kruskal minimum spanning tree algorithm, accurately identify the key areas of waterproof life, realizing targeted design and strengthening, and avoiding resource waste.

[0223] 3. Establish an accurate life prediction model: The present invention establishes a comprehensive prediction equation set that includes three aspects: material property attenuation, environmental impact, and structural stress, transforming qualitative descriptions into quantitative calculations and making the waterproof life prediction more accurate.

[0224] 4. Optimize construction parameters with multiple objectives: The non-dominated sorting genetic algorithm is used to simultaneously consider life maximization and cost minimization, obtaining a Pareto optimal solution set, providing multiple options for projects with different budgets and requirements.

[0225] 5. Differentiated waterproof design: According to the stress characteristics of different regions, different waterproof layer thicknesses and strengthening measures are adopted, achieving efficient utilization of resources and improving the cost performance of the overall waterproof system.

[0226] In this embodiment, compared with traditional means, the new method increases the expected life of the waterproof system by about 42% (about 19 years for the traditional method and 26.8 years for the new method). At the same time, the total amount of materials used only increases by 12%, and the comprehensive economic benefits are significant. Especially in key areas, the stress attenuation rate is reduced by 35%, greatly improving the overall reliability of the system.

[0227] Through the establishment of a sequential scale physical model and the application of the Kruskal minimum spanning tree algorithm, the recognition accuracy of waterproof key areas is increased from 65% of the traditional method to more than 95%, making the allocation of waterproof resources more reasonable and efficient. At the same time, the establishment of the life prediction equation set transforms the waterproof life assessment from simple empirical estimation to scientific numerical calculation, reducing the prediction error from ±30% to within ±15%, providing a reliable basis for the long-term planning and maintenance of the waterproof system.

[0228] It should be noted that the detailed explanations of the variables involved in the present invention are shown in Table 14 below.

[0229] Table 14 Variable Explanation Table

[0230]

[0231]

[0232] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention.

Claims

1. A waterproof construction method for extending the service life of the waterproof structure of a standardized swimming pool in a stadium, characterized in that, It includes the following steps: Obtain basic structure parameters, where the basic structure parameters include pool size, structure type, load conditions, and the designed thickness of the waterproof layer; collect the physical and mechanical parameters of the waterproof material, where the physical and mechanical parameters include tensile strength, elongation at break, low temperature flexibility, heat aging performance, and water resistance performance; establish multiple small physical models with a sequential scale and set stress monitoring points; input the physical and mechanical parameters into the small physical models for finite element analysis; use the Kruskal minimum spanning tree algorithm to identify the stress transfer path of the waterproof structure; establish and fit the waterproof structure life prediction equations; determine the optimal construction parameter range based on the multi-objective optimization algorithm; determine the actual key areas of the waterproof life through experimental and simulation verification; determine the specific construction parameters according to the optimal construction parameter range; treat the pool base layer to make the base layer quality meet the design requirements; lay the waterproof layer according to the specific construction parameters and take strengthening protection measures for the actual key areas of the waterproof life; where the waterproof structure life prediction equations include the material performance attenuation equation, the environmental impact equation, and the structural stress equation.

2. The waterproof construction method according to claim 1, characterized in that, The multiple small physical models with the sequential scale have the same mesh size. The sequential scale is 10 equidistant proportional values between 0.1 and 1.0, and the mesh size is 50 mm. Mesh encryption is performed at the joints and corner positions, and the mesh size of the encrypted area is 25 mm.

3. The waterproof construction method according to claim 2, wherein The stress monitoring points include: arranging 6 monitoring points at intervals of 60 degrees circumferentially at the connection between the pool bottom and the pool wall; arranging 5 monitoring points in each of the four corner areas of the pool, distributed in a fan shape, with a monitoring point spacing of 100 mm; setting double rows of monitoring points at the waterproof layer joints, arranged at intervals of 200 mm along the joint direction, and there are no less than 10 monitoring points at each joint.

4. The waterproof construction method according to claim 3, characterized in that, The strengthening protection measures include: increasing the thickness of the waterproof layer; adding an additional waterproof layer, with the width of the additional layer not less than 500 mm; setting a waterproof protection layer, using polyester fiber non-woven fabric, with a unit area mass not less than 300 g / m².

5. The waterproof construction method according to claim 4, characterized in that, The specific construction parameters include: the actual thickness of the waterproof layer, choosing 2.5 mm for large competition pools and 2.0 mm for general pools; the actual lapping width, choosing 120 mm for the main joint positions and 100 mm for the secondary joint positions; the actual depth of the base layer treatment, choosing 3 mm for newly built pools and 4 mm for renovation projects.

6. The waterproof construction method according to claim 5, wherein, The base layer quality includes: flatness, checked with a 2-meter straightedge, with an allowable deviation not greater than 3 mm; compressive strength, with the concrete strength grade not lower than C30; moisture content, measured by the drying method, controlled below 5%.

7. The waterproof construction method according to claim 6, characterized in that, The input parameters of the material performance attenuation equation include the initial material performance value, service time, environmental temperature, and ultraviolet intensity, and the output parameter is the material remaining strength coefficient. The input parameters of the environmental impact equation include the annual average rainfall, temperature fluctuation range, water pressure change, and chemical corrosion intensity, and the output parameter is the environmental damage coefficient. The input parameters of the structural stress equation include hydrostatic pressure, temperature stress, structural deformation amount, and load stress, and the output parameter is the equivalent stress of the waterproof layer.

8. The waterproof construction method according to claim 7, wherein The genetic algorithm is used to optimize the parameters of the waterproof structure life prediction equation system. The population size is set to 200, the number of generations of evolution is 500 generations, the crossover probability is 0.85, the mutation probability is 0.1, the prediction error of the training set does not exceed 15%, and the prediction error of the validation set does not exceed 20%.

9. The waterproof construction method according to claim 8, characterized in that The hold-out method is used to perform cross-validation on the waterproof structure life prediction equation system. The data set is divided into a training set and a test set according to a ratio of 7:

3. Five-fold cross-validation is performed on the training set data, and three indicators, namely the mean absolute error, the root mean square error, and the relative error, are calculated. The mean absolute error does not exceed 20%, the root mean square error does not exceed 25%, and the relative error does not exceed 30%.

10. The waterproof construction method according to claim 9, wherein The least squares method is used to establish and fit the material property attenuation equation, the multiple regression analysis method is used to establish the environmental impact equation, and the structural stress equation is established based on the principles of elastoplastic mechanics.

Images