Performance prediction method for ceramic powder-doped pervious concrete based on mesoscopic model reconstruction

Abstract

The invention provides a ceramic powder-doped pervious concrete performance prediction method based on mesoscopic model reconstruction, and relates to the technical field of concretes.The method comprises the specific steps that variable parameters influencing performance are collected, different combinations are constructed, sample groups are prepared, initial performance parameters are tested after maintenance, untested samples are scanned, and pore characteristic parameters are obtained. Obtaining a final performance parameter through an environmental adaptability test, training an initial performance prediction model and a final performance prediction model through a variable parameter combination, a pore characteristic parameter and an initial performance parameter, obtaining an environmental condition coefficient based on environmental data, and obtaining a stability index in combination with a performance parameter variation amplitude. And predicting the stability of the ceramic powder doped pervious concrete. According to the method, the variable parameters and the pore characteristic parameters are collected and incorporated into the model for training, the complete association among the preparation parameters, the pore characteristics and the material performance is established, the influence of multiple factors on the performance of the pervious concrete is accurately captured, and the performance prediction accuracy is greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of concrete, and particularly to a method for predicting the performance of permeable concrete mixed with ceramic powder based on mesoscopic model reconstruction. Background Art

[0002] The most prominent characteristic of permeable concrete mixed with ceramic powder is its good water permeability. Its unique internal pore structure can quickly absorb and infiltrate rainwater on the ground surface into the ground like a sponge absorbs water. In the urban environment, this characteristic plays a huge role. During heavy rain, it can effectively alleviate the urban waterlogging problem and avoid the troubles caused by a large amount of water accumulation to traffic and the lives of citizens. At the same time, by introducing rainwater into the ground, it can also supplement the increasingly scarce groundwater, maintain the soil humidity, provide good environmental conditions for the growth of plants in the urban ecosystem, and promote the stability of the ecological balance. Permeable concrete mixed with ceramic powder has been widely used in many fields.

[0003] In the prior art, a method and system for predicting the performance of permeable concrete based on mesoscopic model reconstruction provided by the publication number CN109543350B includes the following steps: obtaining a tomographic image of coarse aggregate; extracting the distribution area of coarse aggregate in the tomographic image of coarse aggregate; calculating the maximum thickness of the coating layer; using a morphological operation method to add a cement-based coating layer with a preset thickness on the surface of the coarse aggregate in the distribution area of coarse aggregate to obtain an image after adding the coating layer; using a three-dimensional reconstruction method to perform three-dimensional reconstruction on the image after adding the coating layer to obtain a three-dimensional model of permeable concrete; extracting the pore distribution area in the image after adding the coating layer; using a three-dimensional reconstruction method to perform three-dimensional reconstruction on the pore distribution area to obtain a three-dimensional model of pores; predicting the performance parameters of the permeable concrete corresponding to the three-dimensional model of permeable concrete. This method can not only predict the pore characteristics, but also predict the water permeability and strength, and has high reliability.

[0004] However, there are still the following deficiencies. From the above statement, predicting the performance of permeable concrete based on mesoscopic model reconstruction mainly extracts information from images to construct the model. It neither collects and analyzes the variable parameters in material preparation (such as ceramic powder parameters, aggregate and cement-based related parameters), nor deeply analyzes the influence mechanism of preparation parameters on the formation of pore characteristics. Variable parameters are the basis for the formation of pore characteristics. The same parameter combination may result in different pore structures and performances due to different processes; and different preparation parameters may produce similar pore characteristics, but other performances vary due to the preparation process. This technology does not establish a complete association among preparation parameters, pore characteristics and material performance, making it difficult to accurately reflect the true performance of the material, explore the root causes of performance differences, is not conducive to performance optimization and regulation, and cannot comprehensively and accurately grasp the performance influencing factors and evolution laws.

[0005] The above information disclosed in the background section is only used to enhance the understanding of the background of the present disclosure, and thus it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0006] An object of the present invention is to provide a method for predicting the performance of ceramic powder-doped permeable concrete based on mesoscopic model reconstruction to solve the problems raised in the above background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions: A method for predicting the performance of ceramic powder-doped permeable concrete based on mesoscopic model reconstruction, the specific steps include: S1. Collect variable parameters affecting the performance of ceramic powder-doped permeable concrete, construct multiple groups of different variable parameter combinations, and based on different variable parameter combinations, prepare different groups of ceramic powder-doped permeable concrete specimens; S2. After the specimens in the specimen group are cured for a period of T, perform a performance test on one specimen in the specimen group to obtain the initial performance parameters of the specimen; S3. Scan one specimen in the specimen group that has not undergone a performance test to obtain image information of different internal layers of the specimen. Based on the image information of different internal layers of the specimen, obtain a fault image under the condition of coarse aggregate accumulation. Through image processing technology, identify and extract the distribution area of coarse aggregates and perform three-dimensional reconstruction to obtain a three-dimensional model of coarse aggregates; S4. Add a cement-based coating layer on the surface of the three-dimensional model of coarse aggregates and perform three-dimensional reconstruction to obtain a three-dimensional model of permeable concrete. Through image processing technology, identify and extract the distribution area of pores and perform three-dimensional reconstruction to obtain a three-dimensional model of pores, and obtain the pore characteristic parameters of the specimen based on the three-dimensional model of pores; S5. Apply different environmental data to each specimen group for environmental adaptability tests. After the tests are completed, perform a performance test on another specimen in the specimen group again to obtain the final performance parameters of the specimen; S6. Use the variable parameter combination and the corresponding pore characteristic parameters of the specimen as inputs, and the corresponding initial performance parameters as labels for training. After training, output an initial performance prediction model. Collect the variable parameter combination and the corresponding pore characteristic parameters of the concrete to be predicted, and use the initial performance prediction model to predict the initial performance parameters; S7. Use the initial performance parameters and environmental data of the specimen as inputs, and the corresponding final performance parameters as labels for training. After training, output a final performance prediction model. Collect the initial performance parameters and environmental data of the concrete to be predicted, and use the final performance prediction model to predict the final performance parameters; S8. Based on the environmental data from the environmental adaptability test, obtain the environmental condition coefficient for evaluating the environmental situation. Based on the initial performance parameters and final performance parameters of the concrete to be predicted, obtain the change range of the performance parameters. Comprehensively analyze the change range of the performance parameters, the initial performance parameters, and the environmental condition coefficient of the concrete to be predicted, and obtain the stability index of each performance parameter of the concrete to be predicted when the environmental conditions change. Compare the stability index of each performance parameter of the concrete to be predicted with the preset threshold to predict the stability quality of the permeable concrete mixed with ceramic powder.

[0008] Further, the variable parameters include the type, dosage, particle size, density of the ceramic powder, the bulk density and gradation of the coarse aggregate, and the mix ratio of the cement-based material; The environmental data includes the immersion time, freezing temperature, melting temperature, static load level, and dynamic load amplitude; The initial performance parameters include the initial water permeability, initial compressive strength, and initial flexural strength; The final performance parameters include the final water permeability, final compressive strength, and final flexural strength; The pore characteristic parameters include the porosity, connected porosity, pore uniformity, internal surface area of the pores, and pore size distribution width.

[0009] Further, based on the environmental data from the environmental adaptability test, obtain the environmental condition coefficient for evaluating the environmental situation, and the formula is as follows: ; ; Where, is the environmental condition coefficient of the environmental adaptability test, and the environmental condition coefficient is used to evaluate the environmental situation of the environmental adaptability test by combining five indicators: immersion time, freezing temperature, melting temperature, static load level, and dynamic load amplitude; In the formula, is the distance from the appropriate immersion time, is the immersion time, is the lower limit value of the appropriate immersion time, is the upper limit value of the appropriate immersion time, is the distance from the appropriate freezing temperature, is the freezing temperature, is the lower limit value of the appropriate freezing temperature, is the upper limit value of the appropriate freezing temperature, is the distance from the appropriate melting temperature, is the melting temperature, is the lower limit value of the appropriate melting temperature, is the upper limit value of the appropriate melting temperature, is the distance from the appropriate static load level, is the static load level, is the lower limit value of the appropriate static load level, is the upper limit value of the appropriate static load level, is the distance from the appropriate dynamic load amplitude, is the dynamic load amplitude, is the lower limit value of the appropriate dynamic load amplitude, is the upper limit value of the appropriate dynamic load amplitude; In the formula, is the weight coefficient of the distance from the appropriate immersion time, is the weight coefficient of the distance from the appropriate freezing temperature, is the weight coefficient of the distance from the appropriate melting temperature, is the weight coefficient of the distance from the appropriate static load level, is the weight coefficient of the distance from the appropriate dynamic load amplitude. Based on let .

[0010] Furthermore, obtain the stability index of the concrete water permeability to be predicted when the environmental conditions change. The formula is as follows: ; Among them, is the stability index of the concrete water permeability to be predicted. The stability index of water permeability is used to comprehensively evaluate the stability of the concrete water permeability to be predicted by combining the change range of water permeability, the initial water permeability, and the environmental condition coefficient; In the formula, is the environmental condition coefficient of the environmental adaptability test, is the initial water permeability of the concrete to be predicted, is the final water permeability of the concrete to be predicted.

[0011] Furthermore, obtain the stability index of the concrete compressive strength to be predicted when the environmental conditions change. The formula is as follows: ; Among them, is the stability index of the concrete compressive strength to be predicted. The stability index of compressive strength is used to comprehensively evaluate the stability of the concrete compressive strength to be predicted by combining the change range of compressive strength, the initial compressive strength, and the environmental condition coefficient; In the formula, is the environmental condition coefficient of the environmental adaptability test, is the initial compressive strength of the concrete to be predicted, is the final compressive strength of the concrete to be predicted.

[0012] Furthermore, obtain the stability index of the flexural strength of the concrete to be predicted when the environmental conditions change. The formula is as follows: ; Wherein, is the stability index of the flexural strength of the concrete to be predicted. The stability index of the flexural strength is used to comprehensively evaluate the stability of the flexural strength of the concrete to be predicted by combining the change range of the flexural strength, the initial flexural strength, and the environmental condition coefficient; In the formula, is the environmental condition coefficient of the environmental adaptability test, is the initial flexural strength of the concrete to be predicted, is the final flexural strength of the concrete to be predicted.

[0013] Furthermore, compare the stability index of each performance parameter of the concrete to be predicted with a preset threshold value to predict the stability of the pervious concrete mixed with ceramic powder. The specific process is as follows: When the stability index of all performances is not greater than the threshold value, that is, and and , it is considered that the stability of the pervious concrete mixed with ceramic powder is good; When the stability index of any one performance is greater than the threshold value, that is, or or , it is considered that the stability of the pervious concrete mixed with ceramic powder is poor; Wherein, , , are the stability indexes of the water permeability, compressive strength, and flexural strength of the concrete to be predicted respectively, is the threshold value of the stability index of the water permeability, is the threshold value of the stability index of the compressive strength, is the threshold value of the stability index of the flexural strength.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention collects variable parameters such as ceramic powder parameters, aggregate and cement-based related parameters, constructs multiple groups of different combinations to prepare specimens, comprehensively covers the key parameters in the material preparation process, scans, performs image processing and three-dimensional reconstruction on the specimens to obtain pore characteristic parameters, and uses the variable parameter combination and pore characteristic parameters as inputs for training. This process enables the model to learn how the preparation parameters affect the formation of pore characteristics and the relationship between pore characteristics and material properties. When facing performance differences, the model obtained based on the training can trace back to the changes in the preparation parameters and pore characteristics, providing a direction and basis for performance optimization and regulation; By incorporating variable parameters, pore characteristic parameters, initial performance parameters, and environmental data into model training, a complete correlation system covering material preparation, structural characteristics, performance, and environmental factors is formed. Combining the environmental condition coefficient and the range of change in performance parameters, the stability of material performance under environmental changes is further analyzed. Such a comprehensive correlation system enables the improved technology to accurately reflect the performance evolution law of materials under different preparation parameters and environmental conditions, meeting the requirements for accurate prediction and optimization of material performance, and achieving significant improvements in comprehensiveness and practicality. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a flowchart of the overall solution of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] To make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to specific embodiments.

[0017] It should be noted that unless otherwise defined, the technical terms or scientific terms used in the present invention should have the ordinary meanings understood by those of ordinary skill in the field to which the present invention belongs. The "first", "second", and similar terms used in the present invention do not denote any order, quantity, or importance, but are only used to distinguish different components. The terms such as "include" or "comprise" mean that the elements or objects appearing before this term cover the elements or objects listed after this term and their equivalents, without excluding other elements or objects. The terms such as "connect" or "couple" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The terms such as "upper", "lower", "left", "right", etc. are only used to represent relative positional relationships, and when the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0018] Example 1: Please refer to Figure 1 , the present invention provides a technical solution: A method for predicting the performance of ceramic powder-doped permeable concrete based on mesoscopic model reconstruction, the specific steps include: S1. Collect variable parameters affecting the performance of ceramic powder-doped permeable concrete, construct multiple groups of different variable parameter combinations, and prepare different groups of ceramic powder-doped permeable concrete specimens based on different variable parameter combinations; On the basis of the above embodiments, the variable parameters include the type, dosage, particle size, density of the ceramic powder, the bulk density and gradation of the coarse aggregate, and the mix ratio of the cement-based material.

[0019] Type of ceramic powder: ordinary ceramic powder, industrial waste ceramic powder; Ceramic powder content: between 5% and 30% of the cement quality, with gradient settings such as 10%, 15%, 20%, 25%, etc.; Particle size of ceramic powder: 0.075 mm - 2.0 mm; Density of ceramic powder: 2.5 g / cm³ - 3.0 g / cm³; Bulk density of coarse aggregate: 1400 kg / m³ - 1600 kg / m³; Gradation of coarse aggregate: Particle size of continuously graded aggregate, 5 mm - 20 mm; Mix ratio of cement-based material: Cement dosage is about 300 kg / m³ - 400 kg / m³, water-cement ratio is between 0.3 and 0.5, and the dosage of water reducer is between 0.5% and 2.0% of the cement quality.

[0020] S2. After the specimen group is cured for T hours, perform performance tests on one specimen in the specimen group to obtain the initial performance parameters of the specimen; On the basis of the above embodiments, the initial performance parameters include initial water permeability, initial compressive strength, and initial flexural strength.

[0021] On the basis of the above embodiments, water permeability, compressive strength, and flexural strength are the key indicators for measuring the performance of permeable concrete mixed with ceramic powder, and are of great significance for evaluating the performance and applicability of materials. Specifically as follows: Water permeability is a direct indicator for measuring the water permeability ability of permeable concrete, which determines whether the material can effectively achieve functions such as rainwater infiltration and alleviating urban waterlogging in actual applications. Different application scenarios have different requirements for the permeability coefficient. For example, the requirements for the permeability coefficient of sidewalks, parking lots, etc. may vary. By measuring the permeability coefficient, it can be evaluated whether the permeable concrete mixed with ceramic powder meets the water permeability performance requirements of specific scenarios.

[0022] Compressive strength is an indicator reflecting the ability of concrete to resist pressure failure, and it is crucial for evaluating the stability and durability of permeable concrete mixed with ceramic powder under various loadings. In actual engineering, whether it is the foundation of a building, the road surface, or other structural components, they all need to have sufficient compressive strength to bear their own weight and various external forces that may be applied. If the compressive strength is insufficient, it may lead to structural deformation, cracking, or even failure, affecting the safety and service life of the entire project. By performing compressive strength tests on permeable concrete mixed with ceramic powder, it can be determined whether it can meet the bearing requirements of different engineering parts.

[0023] Flexural strength is a key indicator to measure the ability of concrete to resist bending failure. For some structures that are easily subjected to bending forces, such as the bridge deck and airport runway, flexural strength is particularly important. In these application scenarios, concrete needs to withstand the bending stress generated by vehicle driving, aircraft takeoff and landing, etc. If the flexural strength is insufficient, cracks may appear on the concrete surface. Over time, the cracks will gradually expand, and ultimately may lead to structural failure. Therefore, evaluating the flexural strength of permeable concrete mixed with ceramic powder helps to judge its applicability in these specific application scenarios and ensure the reliability and safety of the structure.

[0024] On the basis of the above embodiments, a performance test is carried out on one specimen in the specimen group to obtain the initial performance parameters of the specimen. The specific process is as follows: Select specimens with side lengths in the range of 2 - 5 cm from the prepared permeable concrete specimens mixed with ceramic powder; The permeable concrete mixed with ceramic powder has relatively large water permeability, that is, the amount of water passing through the specimen per unit time is relatively large. The constant head permeability test is adopted; Place the specimen in the specimen cylinder of the permeameter, place permeable stones or filter screens at both the upper and lower ends of the specimen, and then seal the specimen cylinder well; Connect the water supply system of the permeameter to the constant temperature water bath device, adjust the water temperature to the set value, generally 20℃±2℃, open the water supply valve, and let the water slowly flow into the specimen cylinder. At the same time, discharge the air in the specimen and the specimen cylinder until the specimen is completely saturated and the water surface is stable at a certain height to form a constant head; When the specimen reaches saturation and the water flow is stable, start recording the amount of water passing through the specimen within a certain period of time, and take the average value after multiple measurements; According to Darcy's law, the calculation formula for water permeability is , where is the time the amount of water passing through the specimen within is the length (or height) of the specimen, is the cross-sectional area of the specimen, is the constant head height; Place the specimen at the center position of the lower platen of the compression testing machine, and make the axis of the specimen coincide with the axis of the testing machine; According to the predicted failure load of the specimen, select the loading speed. For the permeable concrete specimens mixed with ceramic powder, the loading speed is controlled at 0.3MPa / s - 0.5MPa / s. Start the compression testing machine and start uniform loading. At the same time, closely observe the deformation of the specimen and the load display value of the testing machine; When the specimen shows signs of failure, such as crack expansion, abnormal sound, etc., continue to load until the specimen is completely damaged, the load display value of the testing machine reaches the maximum value and starts to decline, and record the maximum load value displayed by the testing machine at this time; Calculate the compressive strength according to the size of the test specimen and the maximum load it bears. Place the test specimen on the supports of the flexural testing machine with the tensile surface of the specimen facing upward, and align the positions of the supports and the indenter with the marked positions. Select the loading speed according to the expected flexural failure load of the test specimen. The loading speed is controlled at 0.05 MPa / s - 0.15 MPa / s. Start the flexural testing machine and begin to load slowly and evenly. At the same time, observe the deformation of the test specimen, the load display value of the testing machine, and the readings of the dial gauge or displacement sensor. When cracks appear in the test specimen and gradually expand to failure, record the maximum load value displayed by the testing machine. Calculate the flexural strength according to the size of the test specimen and the maximum load it bears.

[0025] S3. Scan one test specimen in the test specimen group that has not undergone performance testing to obtain image information of different internal layers of the test specimen. Based on the image information of different internal layers of the test specimen, obtain the tomographic image under the condition of coarse aggregate accumulation. Through image processing technology, identify and extract the coarse aggregate distribution area and perform three-dimensional reconstruction to obtain the three-dimensional model of the coarse aggregate. On the basis of the above embodiments, the specific process of step S3 is as follows: Place the permeable concrete test specimen mixed with ceramic powder to be scanned on the scanning table of the scanner, and adjust the position and angle of the test specimen so that it can be scanned completely. Start the X-ray tomographic scanner and perform scanning according to the preset parameters. During the scanning process, the X-ray penetrates the test specimen from different angles, and the detector records the X-ray intensity information after passing through the test specimen. Use special image reconstruction software to process the scanned data, and convert the X-ray intensity data into a tomographic image through the filtered back-projection algorithm. Use algorithms such as threshold segmentation, edge detection, and region growing in image processing technology to analyze the preprocessed tomographic image. First, through threshold segmentation, based on the difference in gray values between coarse aggregates and cement matrix, pores, etc., the coarse aggregate area is initially separated from the image. Then, use the edge detection algorithm to further refine the edge contour of the coarse aggregate. Finally, adopt the region growing algorithm to merge adjacent pixel points with similar gray values and extract the coarse aggregate distribution area. Stack the coarse aggregate distribution areas in multiple tomographic images extracted according to their spatial position relationships in the test specimen, and use the three-dimensional reconstruction algorithm to convert the two-dimensional coarse aggregate distribution area into a geometric model in three-dimensional space to generate the three-dimensional model of the coarse aggregate.

[0026] S4. Add a cement-based coating on the surface of the three-dimensional model of coarse aggregates and perform three-dimensional reconstruction to obtain a three-dimensional model of permeable concrete. Through image processing technology, identify and extract the pore distribution area and perform three-dimensional reconstruction to obtain a three-dimensional pore model. Based on the three-dimensional pore model, obtain the pore characteristic parameters of the specimen. Take the average value of multiple groups of pore characteristic parameters corresponding to the same variable parameter combination, and use the obtained average value as the pore characteristic parameter under this combination.

[0027] Based on the above embodiments, the specific process of step S4 is as follows: On the surface of the constructed three-dimensional model of coarse aggregates, set appropriate thickness parameters of the cement-based coating according to the actual material ratio and process conditions. Through operations such as inflation and offset in three-dimensional modeling software, evenly add a cement-based coating on the surface of the coarse aggregates, and perform a Boolean operation fusion on the coarse aggregates and the coating. Once again, use three-dimensional reconstruction technology to process the fused model to generate a complete three-dimensional model of permeable concrete; Perform meshing on the three-dimensional model of permeable concrete, divide the model into multiple small unit bodies, and use pore recognition algorithms in image processing technology (such as threshold-based pore segmentation algorithm, morphological pore extraction algorithm). Based on the differences in density, gray value, etc. between pores and solid materials, identify and mark the pore parts in the model. By performing connectivity analysis on the marked pore parts, remove isolated noise points and extract continuous and complete pore distribution areas; Apply a three-dimensional reconstruction algorithm similar to the reconstruction of the three-dimensional model of coarse aggregates to the extracted pore distribution area, convert it from a two-dimensional area to a geometric model in three-dimensional space, and construct a three-dimensional pore model; Based on the constructed three-dimensional pore model, use relevant geometric calculations and statistical analysis methods to obtain the pore characteristic parameters of each specimen.

[0028] Based on the above embodiments, the pore characteristic parameters include porosity, connected porosity, pore uniformity, internal surface area of pores, and pore size distribution width.

[0029] Based on the above embodiments, the specific methods for obtaining porosity, connected porosity, internal surface area of pores, and pore size distribution width are as follows: Porosity refers to the percentage of the pore volume inside the material in the total volume of the material; For materials with regular shapes, first measure their external dimensions to calculate the total volume, then immerse the material in water to allow the pores to fully absorb water. By measuring the mass change of the material before and after water absorption and combining with the density of water, calculate the volume of water absorbed in the pores, and then obtain the pore volume. Finally, calculate the porosity; for materials with irregular shapes, the drainage method can be used to measure their total volume, and then the pore volume can be measured by a similar water absorption method.

[0030] The connected porosity refers to the percentage of the volume of interconnected pores in the material to the total volume of the material; Mark all the connected pores in the three-dimensional pore model through image analysis software. Use the region growing algorithm based on seed points. Starting from a known pore point, expand according to eight-neighbor connectivity to mark all the pores connected to it, and calculate the volume of the marked connected pores (by voxelizing the pore model, counting the number of voxels contained in the connected pores, and then converting it into volume according to the actual size of the voxels); divide the volume of the connected pores by the total volume of the test block (obtained by scanning data or model dimensions) to obtain the connected porosity.

[0031] The internal surface area of the pores refers to the sum of the surface areas of all the pores inside the material; Divide the three-dimensional volume data into numerous small cubes, each cube containing 8 voxels. Based on the value of each voxel, judge the intersection situation between the cube and the pore surface, and then generate triangular patches to approximately represent the surface; Traverse each cube in the three-dimensional volume data. For each cube, according to the values of its 8 voxels, query the pre-defined lookup table to clarify the intersection situation of the cube with the surface, so as to obtain the corresponding triangular patch vertices. Combine the triangular patches generated by all the cubes to obtain the surface model of the pores; For a triangular patch, given the coordinates of its three vertices, use the method of vector cross product to calculate the area of the triangular patch, and add up the areas of all the triangular patches to obtain the internal surface area of the pores.

[0032] The pore size distribution width represents the degree of dispersion of the pore size; Assume that the cross-sectional shape of a certain pore is circular, and calculate the equivalent circular diameter according to the area formula of the circle; Determine the grouping intervals of the pore sizes, traverse the equivalent pore diameters of all the pores, count the number of pores in each interval, and calculate the frequency of the number of pores in each interval to the total number of pores; Use the pore size interval as the abscissa and the number of pores or frequency as the ordinate to draw a pore size distribution histogram; According to the pore size distribution histogram, calculate the average value and standard deviation of the equivalent pore diameters of all the pores, and use the standard deviation to represent the pore size distribution width.

[0033] S5. Apply different environmental data to each specimen group for environmental adaptability tests. After the tests are completed, perform performance tests on another specimen in the specimen group again to obtain the final performance parameters of the specimen; On the basis of the above embodiments, the environmental data include immersion time, freezing temperature, melting temperature, static load level, and dynamic load amplitude; The final performance parameters include final water permeability, final compressive strength, and final flexural strength.

[0034] On the basis of the above embodiments, the process and calculation formula for obtaining the final water permeability, compressive strength, and flexural strength after the environmental test are the same as those for obtaining the initial water permeability, compressive strength, and flexural strength.

[0035] On the basis of the above embodiments, after collecting the water permeability, compressive strength, flexural strength, soaking time, freezing temperature, melting temperature, static load level, and dynamic load amplitude, perform maximum-minimum normalization processing on these parameters respectively, and then use the normalized data for the subsequent analysis and processing, so that in the subsequent analysis and processing process, various data can be analyzed and processed under the same dimension, avoiding the problem that some data are ignored due to different dimensions.

[0036] Before and after the environmental test, the measured water permeability, compressive strength, and flexural strength are collected multiple times (such as 3 groups), and the same type of data is averaged. The finally obtained average value is used as the corresponding data for the water permeability, compressive strength, and flexural strength. The water permeability, compressive strength, and flexural strength calculated later are all the data after averaging.

[0037] S6. Use the variable parameter combinations and corresponding pore characteristic parameters of the specimen as inputs, and the corresponding initial performance parameters as labels for training. After the training is completed, output the initial performance prediction model. Collect the variable parameter combinations and corresponding pore characteristic parameters of the concrete to be predicted, and use the initial performance prediction model to predict the initial performance parameters; Use the variable parameter combinations and corresponding pore characteristic parameters of the test block as inputs, and output the corresponding initial performance parameters as labels to train the initial performance prediction model. Compared with only using the variable parameter combinations or corresponding pore characteristic parameters of the test block as inputs, the achieved technical effects are as follows: As the final manifestation of the internal structure of the material, the pore characteristic parameters can only reflect the static structural properties of the material and cannot trace its formation mechanism. The variable parameters cover the types, dosages, particle sizes, densities of ceramic powders, as well as preparation elements such as aggregate gradation and water-cement ratio. These parameters are the direct inducements for the formation of the pore structure. Combining the two and inputting them can construct a complete causal chain of "preparation parameters - pore structure - material properties" in the model, avoiding the cognitive fragmentation of the performance influencing factors caused by single-parameter input. For example, even if test blocks with similar porosities are formed by different preparation parameter combinations, the difference in the activity of ceramic powders will affect the cement-based strength through the hydration reaction process, ultimately resulting in significant differences in compressive strength. This mechanism cannot be revealed only by relying on pore parameters.

[0038] When a single pore characteristic parameter is input, the model is vulnerable to the interference of the "isomorphic heterogeneity" phenomenon, that is, materials with the same pore structure show different performances due to different preparation processes. For example, for permeable concrete prepared by vibration molding and static pressure molding processes, even if the porosity and pore size distribution are similar, there are significant differences in connectivity and the quality of the interfacial transition zone, which in turn affect water permeability and durability. The collaborative input of variable parameters and pore parameters enables the model to capture such hidden differences, reduce the prediction variance, and improve the accuracy of prediction results.

[0039] As a process variable, there is a two-way coupling relationship between the variable parameter and the pore characteristic parameter (result variable). When only pore parameters are input, the model lacks the dynamic response ability to regulate material properties and cannot quantify the chain effect of changes in preparation parameters on pore structure and performance. The joint input enables the trained model to master the mapping law of "parameter adjustment - pore evolution - performance optimization", for example, to clarify the non-linear relationship between the increase in ceramic powder content and pore refinement, reduced connectivity, and improved compressive strength, providing quantitative guidance for material formulation optimization.

[0040] In actual engineering, it is often necessary to balance multiple performance indicators such as water permeability, strength, and durability of permeable concrete. The joint input of variable parameters and pore parameters enables the model to analyze the cross-influence of different parameters on multiple performances. For example, although reducing the coarse aggregate particle size can improve strength, it may reduce pore connectivity and affect water permeability efficiency; while increasing the activity of ceramic powder can enhance interfacial bonding while maintaining water permeability performance. Through multi-parameter collaborative training, the model can output an optimal parameter combination scheme that takes multiple objectives into account.

[0041] Based on the above embodiments, the initial performance prediction model is composed of a deep learning network based on a multi-layer perceptron. The deep neural network of the multi-layer perceptron includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer, and an output layer. The first hidden layer, the second hidden layer, and the third hidden layer all have at least two neurons and all use ReLU (Rectified Linear Unit) as the activation function; In the initial performance prediction model, the input features of the deep learning network of the multi-layer perceptron include: the type, content, particle size, density of ceramic powder, the bulk density and gradation of coarse aggregate, the mix ratio of cement-based materials, connected porosity, pore uniformity, the internal surface area of pores, and the pore size distribution width, a total of 11 features.

[0042] The structure of the deep learning network of the multi-layer perceptron is as follows: Input layer: Receives the input of 11 features; First hidden layer: Has 128 neurons and uses ReLU as the activation function; Second hidden layer: Has 64 neurons and also uses the ReLU activation function; Third hidden layer: It has 32 neurons and uses the ReLU activation function; Output layer: It has 1 neuron and outputs the initial performance parameters of the concrete to be predicted.

[0043] The process of training the initial performance prediction model is as follows: Using the variable parameter combinations of the specimens and the corresponding pore characteristic parameters as inputs, and the corresponding initial performance parameters as labels for training, and using the mean squared error as the loss function. When the mean squared error is within the specified range, the training of the initial performance prediction model is completed.

[0044] S7. Using the initial performance parameters of the specimens and the environmental data as inputs, and the corresponding final performance parameters as labels for training. After the training is completed, the final performance prediction model is output. The initial performance parameters and environmental data of the concrete to be predicted are collected, and the final performance parameters are predicted using the final performance prediction model; Based on the above embodiments, the final performance prediction model is composed of a deep learning network based on a multi-layer perceptron. The deep neural network of the multi-layer perceptron includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer, and an output layer. The first hidden layer, the second hidden layer, and the third hidden layer all have at least two neurons and all use ReLU as the activation function; In the initial performance prediction model, the input features of the deep learning network of the multi-layer perceptron include: initial water permeability, initial compressive strength, initial flexural strength, number of temperature and humidity cycles, number of dry and wet cycles, number of freeze-thaw cycles, immersion time, freezing temperature, melting temperature, static load level, and dynamic load amplitude, a total of 12 features.

[0045] The structure of the deep learning network of the multi-layer perceptron is as follows: Input layer: Receives the input of 12 features; First hidden layer: It has 128 neurons and uses ReLU as the activation function; Second hidden layer: It has 64 neurons and also uses the ReLU activation function; Third hidden layer: It has 32 neurons and uses the ReLU activation function; Output layer: It has 1 neuron and outputs the final performance parameters of the concrete to be predicted.

[0046] The process of training the final performance prediction model is as follows: Using the initial performance parameters of the specimens and the environmental data as inputs, and the corresponding final performance parameters as labels for training, and using the mean squared error as the loss function. When the mean squared error is within the specified range, the training of the final performance prediction model is completed.

[0047] S8. Based on the environmental data from the environmental adaptability test, obtain the environmental condition coefficient for evaluating the environmental situation. Based on the initial performance parameters and final performance parameters of the concrete to be predicted, obtain the change range of the performance parameters. Comprehensively analyze the change range of the performance parameters, the initial performance parameters, and the environmental condition coefficient of the concrete to be predicted, and obtain the stability index of each performance parameter of the concrete to be predicted when the environmental conditions change. Compare the stability index of each performance parameter of the concrete to be predicted with a preset threshold to predict the stability quality of the permeable concrete mixed with ceramic powder.

[0048] Table 1 shows the variation of the environmental condition coefficient with the environmental data ; Based on the data in Table 1 in the above embodiment, it can be seen that when other deviation distances are 0, as the distance from the appropriate immersion time increases from 0 to 22, the environmental condition coefficient increases from 0 to 9.65, indicating that the larger the value of the distance from the appropriate immersion time, the larger the environmental condition coefficient. Therefore, the distance from the appropriate immersion time and the environmental condition coefficient are positively correlated.

[0049] When other deviation distances are 0, as the distance from the appropriate freezing temperature increases from 0 to 18, the environmental condition coefficient increases from 0 to 9.65, indicating that the larger the value of the distance from the appropriate freezing temperature, the larger the environmental condition coefficient. Therefore, the distance from the appropriate freezing temperature and the environmental condition coefficient are positively correlated.

[0050] When other deviation distances are 0, as the distance from the appropriate melting temperature increases from 0 to 9, the environmental condition coefficient increases from 0 to 9.65, meaning that the larger the value of the distance from the appropriate melting temperature, the larger the environmental condition coefficient. Therefore, the distance from the appropriate melting temperature and the environmental condition coefficient are positively correlated.

[0051] When the remaining deviation distances are 0, as the distance from the appropriate static load level increases from 0 to 11, the environmental condition coefficient increases from 0 to 9.65, that is, the larger the value of the distance from the appropriate static load level, the larger the environmental condition coefficient. Therefore, the distance from the appropriate static load level and the environmental condition coefficient are positively correlated.

[0052] When other conditions are fixed at 0, as the distance from the appropriate dynamic load amplitude increases from 0 to 11, the environmental condition coefficient increases from 0 to 9.65, reflecting that the larger the value of the distance from the appropriate dynamic load amplitude, the larger the environmental condition coefficient. Therefore, the distance from the appropriate dynamic load amplitude and the environmental condition coefficient are positively correlated.

[0053] Based on the above embodiment, the environmental data is processed and analyzed for correlation to generate the environmental condition coefficient. The formula is as follows: ; ; Among them, is the environmental condition coefficient of the environmental adaptability test. The environmental condition coefficient is used to evaluate the environmental condition of the environmental adaptability test by combining five indicators: immersion time, freezing temperature, melting temperature, static load level, and dynamic load amplitude. And the larger the environmental condition coefficient, the more severe the environmental condition of the environmental adaptability test; In the formula, is the distance from the appropriate immersion time, is the immersion time, is the lower limit value of the appropriate immersion time, is the upper limit value of the appropriate immersion time, is the distance from the appropriate freezing temperature, is the freezing temperature, is the lower limit value of the appropriate freezing temperature, is the upper limit value of the appropriate freezing temperature, is the distance from the appropriate melting temperature, is the melting temperature, is the lower limit value of the appropriate melting temperature, is the upper limit value of the appropriate melting temperature, is the distance from the appropriate static load level, is the static load level, is the lower limit value of the appropriate static load level, is the upper limit value of the appropriate static load level, is the distance from the appropriate dynamic load amplitude, is the dynamic load amplitude, is the lower limit value of the appropriate dynamic load amplitude, is the upper limit value of the appropriate dynamic load amplitude; On this basis, it should be noted that: the distance from the appropriate immersion time increases, which means that the actual immersion time is either too long or too short, which will cause the specimen to be affected by water beyond the reasonable range, thus having a more significant adverse impact on its performance, and the severity of the environmental condition of the environmental test increases. Therefore, the environmental condition coefficient increases; the distance from the appropriate freezing temperature increases, which means that the deviation between the actual freezing temperature and the standard value is greater. If the actual freezing temperature is too low, the expansion stress generated by the freezing of pore water in the specimen will far exceed the normal level, causing more and larger microcracks inside the specimen and accelerating the failure of the specimen. If the actual freezing temperature is too high, the purpose of simulating a severe freezing environment cannot be achieved, and the frost resistance of the specimen cannot be accurately tested. The severity of the environmental condition of the environmental test increases. Therefore, the environmental condition coefficient Increase; distance from the appropriate melting temperature Increase. When the actual melting temperature is too high, the moisture inside the specimen evaporates rapidly, generating large shrinkage stresses that may cause cracks or even spalling on the surface of the specimen. When the actual melting temperature is too low, the melting process of the specimen is slow, and the temperature gradient change may generate additional stresses inside the specimen, affecting the structural stability of the specimen. As the severity of the environmental conditions in the environmental test increases, the environmental condition coefficient Increase; distance from the appropriate static load level Increase. If the actual static load level is too high, the specimen will bear pressures beyond its designed capacity, accelerating the damage and failure of its internal structure and shortening its service life. If the actual static load level is too low, the load conditions that the specimen experiences in actual use cannot be accurately simulated, and the bearing performance of the specimen cannot be effectively evaluated. As the severity of the environmental conditions in the environmental test increases, the environmental condition coefficient Increase; distance from the appropriate dynamic load amplitude Increase. When the actual dynamic load amplitude is too large, the specimen will be subjected to stronger impacts and vibrations, and its internal structure is more likely to suffer fatigue damage, reducing its durability. If the actual dynamic load amplitude is too small, the dynamic effect on the specimen is not obvious, and its performance under actual dynamic load conditions cannot be truly reflected. As the severity of the environmental conditions in the environmental test increases, the environmental condition coefficient Increase.

[0054] In summary, the environmental condition coefficient and the distance from the appropriate immersion time 、the distance from the appropriate freezing temperature 、the distance from the appropriate melting temperature 、the distance from the appropriate static load level 、the distance from the appropriate dynamic load amplitude are all positively correlated.

[0055] The effects of different environmental parameters on the performance of permeable concrete do not exist independently but have a synergistic effect. Taking the deviation from the appropriate immersion time and dynamic load amplitude as an example, when the actual immersion time is too long, the pores inside the concrete are filled with water. At this time, if the dynamic load amplitude is large, the extrusion and impact of the water in the pores will be intensified, making it easier to cause damage to the internal structure of the concrete. The combined effect of the two on the performance of the concrete is much greater than the sum of their individual effects. By adding multiple parameters, the synergistic effect can be reflected through coefficient adjustment to make the environmental condition coefficient more truly reflect the actual impact degree of the environment on the performance of the concrete.

[0056] Therefore, the above weighted summation formula is used to characterize the environmental condition coefficient and , , , , The functional relationship among them.

[0057] In the formula, is the weight coefficient of the distance deviating from the appropriate immersion time, is the weight coefficient of the distance deviating from the appropriate freezing temperature, is the weight coefficient of the distance deviating from the appropriate melting temperature, is the weight coefficient of the distance deviating from the appropriate static load level, is the weight coefficient of the distance deviating from the appropriate dynamic load amplitude; When the dynamic load amplitude is too large, the material will be subjected to stronger impacts and vibrations, and its internal structure is more likely to suffer fatigue damage. Fatigue failure is a relatively sudden and dangerous form of failure, which may lead to structural failure without obvious signs, seriously affecting the safety and durability of the structure; although static load will also cause deformation and damage to the structure, it usually does not trigger fatigue failure as quickly as dynamic load. Therefore, the influence of dynamic load amplitude is more critical. ; Static load is directly related to the bearing capacity and stability of the structure. The structure is designed according to a specific static load level during design. If the actual static load level is too high, the specimen will bear a pressure exceeding the designed bearing capacity, accelerating the damage and failure of its internal structure, and may even cause the structure to fail immediately, posing a direct threat to the safety of the structure. The influence of freezing temperature on the structure is mainly achieved indirectly by affecting the physical properties of the material. Although freezing temperature deviation may cause microcracks and other damages inside the test block, the development of this kind of damage is relatively slow and will not cause structural failure as quickly as excessive static load. Therefore, ; The expansion stress generated by the freezing of pore water during the freezing process is an important factor leading to material damage. Too low freezing temperature will make this expansion stress far exceed the normal level, generating a large number of microcracks inside the material. These microcracks will continue to expand during subsequent use, seriously weakening the performance of the material. Although melting temperature will also affect the material, such as rapid evaporation of water due to too high temperature generating shrinkage stress, or slow melting process due to too low temperature generating additional stress, generally speaking, the freezing process is more critical to the initial damage of the internal structure of the material, and the melting process is more about further developing and influencing the existing damage. Therefore, ; The influence of temperature on material properties is relatively common and fundamental. Whether it is the melting temperature or the freezing temperature, deviation from the ideal value will have a direct or indirect impact on the physical and mechanical properties of the material, involving various mechanisms such as changes in the internal microstructure of the material and the generation of thermal stress. The immersion time mainly affects a series of physical and chemical processes after the material comes into contact with water. For some materials with good water resistance, the influence of the immersion time is relatively small. Even if the immersion time deviates from the standard value, its impact on material properties is often not as direct and significant as that of the temperature factor. Therefore 。

[0058] In summary, on the basis of , let 。

[0059] As an implementation method has a value range of 0 - 0.1, has a value range of 0.2 - 0.25, has a value range of 0.1 - 0.2, has a value range of 0.25 - 0.3, has a value range of 0.3 - 0.35. The specific values are set by technicians according to the actual situation and are not limited here.

[0060] Table 2 shows the variation of the stability index of water permeability with the variation range of water permeability, the initial water permeability, and the environmental condition coefficient ; Based on the data in Table 2 in the above embodiments, it can be seen that when the initial water permeability and the environmental condition coefficient change relatively stably, as the variation range of water permeability gradually increases from 0.4 to 2, the stability index of water permeability increases from 0.0347 to 1.5625. That is, the greater the variation range of water permeability, the greater the stability index of water permeability. Therefore, the variation range of water permeability and the stability index of water permeability are positively correlated.

[0061] When the variation range of water permeability and the environmental condition coefficient change regularly, the initial water permeability increases from 1.6 to 4.8, and the stability index of water permeability decreases from 1.5625 to 0.0347, indicating that the greater the initial water permeability, the smaller the stability index of water permeability. Therefore, the initial water permeability and the stability index of water permeability are negatively correlated.

[0062] When the variation range of water permeability and the initial water permeability change regularly, the environmental condition coefficient increases from 0.8 to 2.4, and the stability index of water permeability decreases from 1.5625 to 0.0347, meaning that the greater the environmental condition coefficient, the smaller the stability index of water permeability. Therefore, the environmental condition coefficient and the stability index of water permeability are negatively correlated.

[0063] Based on the above embodiments, the change range of the water permeability of the concrete to be predicted and the environmental condition coefficient are numerically calculated to obtain the stability index of the water permeability of the concrete to be predicted when the environmental conditions change. The formula is as follows: ; Wherein, is the stability index of the water permeability of the concrete to be predicted. The stability index of the water permeability is used to comprehensively evaluate the stability of the water permeability of the concrete to be predicted by combining the change range of the water permeability, the initial water permeability and the environmental condition coefficient; In the formula, is the initial water permeability of the concrete to be predicted, is the final water permeability of the concrete to be predicted.

[0064] In the formula, reflects the absolute range of the change in water permeability. Whether it gets better or worse, the larger this value is, the more obvious the change degree of the water permeability before and after the test is; Divide the change range by the initial water permeability , in order to evaluate the relative degree of influence. For example, if the water permeability changes by a certain value, if the initial water permeability itself is relatively large, then relatively speaking, this change range may not be so "significant"; if the initial water permeability is small, the same change value will appear more "prominent"; The larger it is, the more severe the environmental condition is. Multiply it by as the denominator, which means that under harsh environmental conditions, if the change range of the concrete water permeability is the same, then the more severe the environmental condition is, the smaller the performance index is, indicating that the concrete can maintain the stability of the water permeability under harsh environments, that is, the change range of the water permeability is relatively small, and the stability of the water permeability is better.

[0065] Table 3 shows the change of the stability index of the compressive strength with the change range of the compressive strength, the initial compressive strength and the environmental condition coefficient ; Based on the above embodiments, according to the data in Table 3, when the initial compressive strength and the environmental condition coefficient change regularly, as the change range of the compressive strength gradually decreases from 0.5 to 2.4, the stability index of the compressive strength increases from 0.0203 to 0.1, that is, the larger the change range of the compressive strength is, the larger the stability index of the compressive strength is. Therefore, the change range of the compressive strength and the stability index of the compressive strength are positively correlated.

[0066] When the variation range of the compressive strength and the environmental condition coefficient vary regularly, the initial compressive strength increases from 5 to 24, and the stability index of the compressive strength decreases from 0.1 to 0.0203, indicating that the greater the initial compressive strength, the smaller the stability index of the compressive strength. Therefore, the initial compressive strength and the stability index of the compressive strength are negatively correlated.

[0067] When the variation range of the compressive strength and the initial compressive strength vary regularly, the environmental condition coefficient increases from 1 to 4.8, and the stability index of the compressive strength decreases from 0.1 to 0.0203, meaning that the greater the environmental condition coefficient, the smaller the stability index of the compressive strength. Therefore, the environmental condition coefficient and the stability index of the compressive strength are negatively correlated.

[0068] Based on the above embodiments, the stability index of the compressive strength of the concrete to be predicted when the environmental conditions change is obtained according to the following formula: ; Wherein, is the stability index of the compressive strength of the concrete to be predicted. The stability index of the compressive strength is used to comprehensively evaluate the stability of the compressive strength of the concrete to be predicted by combining the variation range of the compressive strength, the initial compressive strength and the environmental condition coefficient; In the formula, is the initial compressive strength of the concrete to be predicted, is the final compressive strength of the concrete to be predicted.

[0069] Similarly, in the formula, intuitively shows the absolute range of the change in compressive strength. Whether the compressive strength increases or decreases during the test, the larger this value, the more significant the change in compressive strength before and after the test; dividing the variation range of the compressive strength by the initial compressive strength is to evaluate the relative degree of influence. For example, when the absolute value of the change in compressive strength is the same, if the initial compressive strength is higher, then the influence of this variation range is relatively smaller; conversely, if the initial compressive strength is lower, the same variation range will be more prominent; the environmental condition coefficient the larger it is, the more severe the environmental conditions are. Multiplying it with as the denominator indicates that under harsh environmental conditions, if the variation range of the concrete compressive strength is the same, then the more severe the environment, the smaller the stability index of the compressive strength, indicating that the concrete can maintain the stability of the compressive strength in a harsh environment, that is, the variation range of the compressive strength is relatively small, and the stability of the compressive strength is better.

[0070] Table 4 shows the variation of the stability index of the flexural strength with the variation range of the flexural strength, the initial flexural strength and the environmental condition coefficient ; Based on the above embodiments, according to the data in Table 4, it can be seen that when the initial flexural strength and the environmental condition coefficient change regularly, as the change range of the flexural strength increases from 0.2 to 2.1, the stability index of the flexural strength increases from 0.0116 to 0.42. That is, the greater the change range of the flexural strength, the greater the stability index of the flexural strength. Therefore, the change range of the flexural strength is positively correlated with the stability index of the flexural strength.

[0071] When the change range of the flexural strength and the environmental condition coefficient change regularly, the initial flexural strength increases from 5 to 8.8, and the stability index of the flexural strength decreases from 0.42 to 0.0116, indicating that the greater the initial flexural strength, the smaller the stability index of the flexural strength. Therefore, the initial flexural strength is negatively correlated with the stability index of the flexural strength.

[0072] When the change range of the flexural strength and the initial flexural strength change regularly, the environmental condition coefficient increases from 1 to 1.95, and the stability index of the flexural strength decreases from 0.42 to 0.0116, meaning that the greater the environmental condition coefficient, the smaller the stability index of the flexural strength. Therefore, the environmental condition coefficient is negatively correlated with the stability index of the flexural strength.

[0073] Based on the above embodiments, the formula for obtaining the stability index of the flexural strength of the concrete to be predicted when the environmental conditions change is as follows: ; Wherein, is the stability index of the flexural strength of the concrete to be predicted. The stability index of the flexural strength is used to comprehensively evaluate the stability of the flexural strength of the concrete to be predicted by combining the change range of the flexural strength, the initial flexural strength, and the environmental condition coefficient; In the formula, is the initial flexural strength of the concrete to be predicted, is the final flexural strength of the concrete to be predicted.

[0074] Similarly, reflects the absolute range of the change in the flexural strength. Regardless of whether the flexural strength increases or decreases during the test, the larger this value, the more obvious the change in the flexural strength before and after the test. Divide the change range of the flexural strength by the initial flexural strength , and conduct relative quantitative analysis. For example, for the same change amount of the flexural strength, when the initial flexural strength is higher, the relative influence is smaller; while when the initial flexural strength is lower, the relative influence is larger; the environmental condition coefficient the larger it is, the more severe the environmental conditions are. Combine it with Multiplication as the denominator means that in a harsh environment, if the flexural strength of concrete changes by the same amount, the harsher the environmental conditions, the smaller the stability index of the flexural strength. This indicates that the concrete can better maintain the stability of its flexural strength in a harsh environment, that is, the change range of the flexural strength is relatively small, and the stability of the flexural strength is better.

[0075] Based on the above embodiments, compare the stability indices of the performance parameters of the concrete to be predicted with the preset thresholds to predict the stability of the permeable concrete mixed with ceramic powder. The specific process is as follows: When the stability indices of all performances are not greater than the threshold, that is and and , it is considered that the stability of the permeable concrete mixed with ceramic powder is good; When the stability index of any one performance is greater than the threshold, that is or or , it is considered that the stability of the permeable concrete mixed with ceramic powder is poor; Among them, is the threshold of the stability index of water permeability, is the threshold of the stability index of compressive strength, is the threshold of the stability index of flexural strength.

[0076] , and By analyzing the past experimental data, find the stability indices of each performance of the permeable concrete mixed with ceramic powder under different environmental conditions, calculate and analyze the performance indices, calculate the quantiles of the stability indices of each performance, and based on the data distribution, select a reasonable threshold. The median can be considered as the threshold.

[0077] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the real situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0078] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by, electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0079] The unit described as a separating component may or may not be physically separated. The component shown as a unit may or may not be a physical unit, and it may be located in one place or distributed across multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0080] As described above, the specific implementation manners of the present application are only described, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application.

Claims

1. A performance prediction method for ceramic powder-doped permeable concrete based on mesoscopic model reconstruction, characterized in that: The specific steps include: S1. Collect the variable parameters that affect the performance of ceramic powder - doped permeable concrete, construct multiple groups of different variable parameter combinations, and prepare different groups of ceramic powder - doped permeable concrete specimens based on different variable parameter combinations; S2. After the specimens in the specimen group are cured for a period of T, conduct performance tests on one specimen in the specimen group to obtain the initial performance parameters of the specimen; S3. Scan one specimen in the specimen group that has not undergone performance tests to obtain the image information of different internal layers of the specimen. Based on the image information of different internal layers of the specimen, obtain the fault image under the condition of coarse aggregate accumulation. Through image - processing technology, identify and extract the distribution area of coarse aggregates and three - dimensionally reconstruct to obtain the three - dimensional model of coarse aggregates; S4. Add a cement - based coating on the surface of the three - dimensional model of coarse aggregates and three - dimensionally reconstruct to obtain the three - dimensional model of permeable concrete. Through image - processing technology, identify and extract the pore distribution area and three - dimensionally reconstruct to obtain the three - dimensional model of pores. Based on the three - dimensional model of pores, obtain the pore characteristic parameters of the specimen; S5. Apply different environmental data to each specimen group for environmental adaptability tests. After the tests are completed, conduct performance tests on another specimen in the specimen group again to obtain the final performance parameters of the specimen; S6. Use the variable parameter combinations and corresponding pore characteristic parameters of the specimens as inputs, and the corresponding initial performance parameters as labels for training. After training, output the initial performance prediction model. Collect the variable parameter combinations and corresponding pore characteristic parameters of the concrete to be predicted, and use the initial performance prediction model to predict the initial performance parameters; S7. Use the initial performance parameters and environmental data of the specimens as inputs, and the corresponding final performance parameters as labels for training. After training, output the final performance prediction model. Collect the initial performance parameters and environmental data of the concrete to be predicted, and use the final performance prediction model to predict the final performance parameters; S8. Based on the environmental data of the environmental adaptability test, obtain the environmental condition coefficient for evaluating the environmental condition. Based on the initial performance parameters and final performance parameters of the concrete to be predicted, obtain the change range of the performance parameters. Comprehensively analyze the change range of the performance parameters, the initial performance parameters, and the environmental condition coefficient of the concrete to be predicted to obtain the stability index of each performance parameter of the concrete to be predicted when the environmental condition changes. Compare the stability index of each performance parameter of the concrete to be predicted with the preset threshold to predict the stability quality of the ceramic powder - doped permeable concrete.

2. The performance prediction method for ceramic powder-doped permeable concrete based on mesoscopic model reconstruction according to claim 1, characterized in that: The variable parameters include the type, dosage, particle size, density of the ceramic powder, the bulk density and gradation of the coarse aggregate, and the mix ratio of the cement - based material; The environmental data includes the immersion time, freezing temperature, melting temperature, static load level, and dynamic load amplitude; The initial performance parameters include the initial water permeability, initial compressive strength, and initial flexural strength; The final performance parameters include the final water permeability, final compressive strength, and final flexural strength; The pore characteristic parameters include the porosity, connected porosity, pore uniformity, internal surface area of pores, and pore size distribution width.

3. The performance prediction method for ceramic powder-doped permeable concrete based on mesoscopic model reconstruction according to claim 2, characterized in that: Based on the environmental data of the environmental adaptability test, obtain the environmental condition coefficient for evaluating the environmental condition. The formula is as follows: ； ； Among them, is the environmental condition coefficient of the environmental adaptability test. The environmental condition coefficient is used to evaluate the environmental conditions of the environmental adaptability test by combining five indicators: immersion time, freezing temperature, melting temperature, static load level, and dynamic load amplitude. Wherein, is the distance deviating from the appropriate immersion time, is the immersion time, is the lower limit value of the appropriate immersion time, is the upper limit value of the appropriate immersion time, is the distance deviating from the appropriate freezing temperature, is the freezing temperature, is the lower limit value of the appropriate freezing temperature, is the upper limit value of the appropriate freezing temperature, is the distance deviating from the appropriate melting temperature, is the melting temperature, is the lower limit value of the appropriate melting temperature, is the upper limit value of the appropriate melting temperature, is the distance deviating from the appropriate static load level, is the static load level, is the lower limit value of the appropriate static load level, is the upper limit value of the appropriate static load level, is the distance deviating from the appropriate dynamic load amplitude, is the dynamic load amplitude, is the lower limit value of the appropriate dynamic load amplitude, is the upper limit value of the appropriate dynamic load amplitude; In the formula, is the weight coefficient of the distance deviating from the appropriate immersion time, is the weight coefficient of the distance deviating from the appropriate freezing temperature, is the weight coefficient of the distance deviating from the appropriate melting temperature, is the weight coefficient of the distance deviating from the appropriate static load level, is the weight coefficient of the distance deviating from the appropriate dynamic load amplitude. On the basis of , let .

4. The performance prediction method for ceramic powder-doped permeable concrete based on mesoscopic model reconstruction according to claim 2, characterized in that: Obtain the stability index of the water permeability of the concrete to be predicted when the environmental conditions change. The formula is as follows: ； Among them, is the stability index of the water permeability of the concrete to be predicted. The stability index of the water permeability is used to comprehensively evaluate the stability of the water permeability of the concrete to be predicted by combining the change range of the water permeability, the initial water permeability, and the environmental condition coefficient; In the formula, is the environmental condition coefficient of the environmental adaptability test, is the initial water permeability of the concrete to be predicted, is the final water permeability of the concrete to be predicted.

5. The performance prediction method for ceramic powder-doped permeable concrete based on mesoscopic model reconstruction according to claim 2, characterized in that: Obtain the stability index of the compressive strength of the concrete to be predicted when the environmental conditions change. The formula is as follows: ； Among them, is the stability index of the concrete compressive strength to be predicted. The stability index of the compressive strength is used to comprehensively evaluate the stability of the concrete compressive strength to be predicted by combining the change range of the compressive strength, the initial compressive strength, and the environmental condition coefficient. In the formula, is the environmental condition coefficient of the environmental adaptability test, is the initial compressive strength of the concrete to be predicted, is the final compressive strength of the concrete to be predicted.

6. The performance prediction method for ceramic powder-doped permeable concrete based on mesoscopic model reconstruction according to claim 2, characterized in that: Obtain the stability index of the flexural strength of the concrete to be predicted when the environmental conditions change. The formula is as follows: ； Among them, is the stability index of the flexural strength of the concrete to be predicted. The stability index of the flexural strength is used to comprehensively evaluate the stability of the flexural strength of the concrete to be predicted by combining the change range of the flexural strength, the initial flexural strength, and the environmental condition coefficient. In the formula, is the environmental condition coefficient of the environmental adaptability test, is the initial flexural strength of the concrete to be predicted, is the final flexural strength of the concrete to be predicted.

7. The performance prediction method of ceramic powder-doped permeable concrete reconstructed based on the mesoscopic model according to claim 1, characterized in that: Compare the stability index of each performance parameter of the concrete to be predicted with the preset threshold value to predict the stability quality of the permeable concrete mixed with ceramic powder. The specific process is as follows: When the stability indices of all properties are not greater than the threshold, that is and and , it is considered that the stability of the permeable concrete mixed with ceramic powder is good; When the stability index of any one performance is greater than the threshold, that is or or , it is considered that the stability of the permeable concrete mixed with ceramic powder is poor; Among them, , , are the stability indices of the water permeability, compressive strength, and flexural strength of the concrete to be predicted, respectively, is the threshold value of the stability index of the water permeability, is the threshold value of the stability index of the compressive strength, is the threshold value of the stability index of the flexural strength.

Images