Aggregate source optimization method and system based on aggregate interface performance data modeling

Abstract

The invention discloses an aggregate source optimization method and system based on aggregate interface performance data modeling. The method comprises the following steps: acquiring three-dimensional surface texture data, chemical composition data and surface adhesion data of multi-source aggregates with the same lithology; the method comprises the following steps: screening core parameters strongly related to interface adhesion strength in three-dimensional surface texture data, chemical composition data and surface adhesion data of the same-lithology multi-source aggregate through a Pearson correlation analysis method, and carrying out dimensionality reduction on the parameters by adopting a principal component analysis method so as to obtain principal component characteristic parameters; and constructing a multiple regression adhesion performance prediction model, obtaining an interface adhesion strength prediction value of the candidate aggregate by using the multiple regression adhesion performance prediction model and the candidate aggregate, and selecting the candidate aggregate source corresponding to the maximum value as an optimal aggregate source. According to the method, the technical problems that aggregate selection depends on experience, the adhesion performance prediction capability is weak, and a cross-scale data fusion and mapping mechanism is lacked in the prior art are solved.

Description

Technical Field

[0001] This invention relates to the field of road engineering materials technology, specifically to a method and system for optimizing aggregate sources based on aggregate interface performance data modeling. Background Technology

[0002] In modern road engineering, asphalt mixtures serve as the main materials for both structural and surface layers, and their overall performance largely depends on the interfacial adhesion between aggregates and asphalt. Aggregates are not only the main skeleton material in the mixture, but their surface morphology, chemical composition, and other physicochemical properties also directly affect their bond strength with asphalt, thus determining the structural stability and durability of the pavement.

[0003] For a long time, the selection of aggregate sources has mainly relied on engineering experience and traditional indicators (such as crushing value, needle-like and flaky content, apparent density, etc.) for evaluation. This method has obvious limitations: (1) the indicator system is local and lacks multi-scale systematicity; (2) it ignores the intrinsic relationship between aggregate physicochemical properties and interfacial adhesion performance; (3) the testing cycle is long and the cost is high, and the results are often affected by the subjective judgment of personnel, making it difficult to meet the requirements of modern large-scale road engineering for high-performance and sustainable material design.

[0004] Furthermore, as engineering projects become increasingly large-scale and customized, it is often necessary to identify the optimal aggregate source from multiple sources of similar lithological types in the early stages of actual design. For example, even basalt aggregates can exhibit significantly different interfacial adhesion properties with asphalt due to differences in their diagenetic background, weathering degree, and mineral content. Establishing a scientific and quantitative evaluation system during the design phase to help determine which aggregate source offers superior interfacial performance will greatly improve design efficiency and structural reliability.

[0005] In recent years, with the rapid development of multi-scale characterization techniques and materials genomics methods, researchers have begun to analyze the coupling relationship between aggregate characterization parameters and asphalt adhesion properties from the perspective of "gene-performance" mapping. This lays the technical foundation for constructing a quantitative mapping model based on the "gene parameters" of aggregate physicochemical properties and interfacial bonding properties. However, there is currently a lack of a model construction method that is practically applicable to engineering practice and can assist in the selection of aggregates from multiple sources.

[0006] In summary, there is an urgent need for a method and system for aggregate source optimization based on aggregate interface performance data modeling, to support early material comparison and accurate material selection decisions in engineering projects, and to promote the transformation of road engineering material design from traditional experience-based models to performance-oriented and sustainability-oriented models. Summary of the Invention

[0007] To address the aforementioned shortcomings in the prior art, this invention provides a method and system for optimizing aggregate sources based on aggregate interface performance data modeling.

[0008] To achieve the above-mentioned objectives, the technical solution adopted by this invention is as follows:

[0009] A method for optimizing aggregate sources based on aggregate interface performance data modeling includes the following steps:

[0010] We selected homolithological multi-source aggregates and prepared standard plate samples based on them. We used multi-scale equipment to collect and process data from the standard plate samples to obtain three-dimensional surface texture data, chemical composition data and surface adhesion data of the homolithological multi-source aggregates.

[0011] The interfacial adhesion strength of synlithological multi-source aggregates was determined. Pearson correlation analysis was used to screen core parameters that were strongly correlated with interfacial adhesion strength from the three-dimensional surface texture data, chemical composition data, and surface adhesion force data of synlithological multi-source aggregates to obtain initial characteristic parameters. Principal component analysis was then used to reduce the dimensionality of the initial characteristic parameters to obtain principal component characteristic parameters. The principal component characteristic parameters include three parameters that characterize the three-dimensional surface texture characteristics, chemical composition characteristics, and surface adhesion force characteristics of synlithological multi-source aggregates, respectively.

[0012] A multivariate regression adhesion performance prediction model was constructed with principal component characteristic parameters as independent variables and interfacial adhesion strength of multi-source aggregates of the same lithology as dependent variable. The predicted values ​​of interfacial adhesion strength of candidate aggregates were obtained using the multivariate regression adhesion performance prediction model and candidate aggregates, and the candidate aggregate source corresponding to the maximum value was selected as the preferred aggregate source.

[0013] Furthermore, multi-source aggregates of the same lithology are selected, and standard plate samples are prepared based on the multi-source aggregates of the same lithology. The specific process is as follows: multi-source aggregates of the same lithology with obvious differences in source are selected, and the multi-source aggregates of the same lithology are processed into plate samples with flat surfaces and consistent dimensions according to standard procedures to prepare standard plate samples.

[0014] Furthermore, multi-scale equipment was used to acquire and process data from standard plate samples to obtain three-dimensional surface texture data, chemical composition data, and surface adhesion force data of multi-source aggregates of the same lithology, including the following steps:

[0015] A1. A non-contact three-dimensional profilometer was used to collect structural information on the surface of the standard plate sample to obtain the initial three-dimensional surface texture data of the multi-source aggregate of the same lithology. An X-ray fluorescence analyzer was used to detect the chemical composition of the standard plate sample to obtain the chemical composition data of the multi-source aggregate of the same lithology. An atomic force microscope was used to detect the standard plate sample to obtain the surface adhesion force data of the multi-source aggregate of the same lithology.

[0016] A2. Perform small-scale component filtering, contour fitting and removal, and large-scale component filtering on the initial three-dimensional surface texture data of the homolithological multi-source aggregates to extract the height parameters, functional stratification parameters, volume parameters, spatial and mixing parameters of the homolithological multi-source aggregates, so as to obtain the three-dimensional surface texture data of the homolithological multi-source aggregates.

[0017] Furthermore, when testing the standard plate sample using atomic force microscopy, the PeakForce QNM mode was used, with a scanning area of ​​30μm×30μm, a resolution of 512×512, and a probe elastic modulus of 26N / m. The average surface adhesion force obtained by atomic force microscopy was used as the surface adhesion force data of multi-source aggregates of the same lithology.

[0018] Furthermore, when using an X-ray fluorescence analyzer to detect the chemical composition of standard plate samples, the standard plate samples are pretreated by ball milling, drying, and pressing in sequence. The range of detectable elements in the pretreated standard plate samples covers O to U.

[0019] An aggregate source optimization system based on aggregate interface performance data modeling applied to the above method includes a physicochemical parameter acquisition module, a characteristic parameter analysis module, and a decision output module.

[0020] The physicochemical parameter acquisition module is used to select multi-source aggregates of the same lithology, prepare standard plate samples based on the multi-source aggregates of the same lithology, and use multi-scale equipment to acquire and process data on the standard plate samples to obtain three-dimensional surface texture data, chemical composition data and surface adhesion data of the multi-source aggregates of the same lithology.

[0021] The feature parameter analysis module is used to determine the interfacial adhesion strength of synlithological multi-source aggregates. The core parameters that are strongly correlated with the interfacial adhesion strength in the three-dimensional surface texture data, chemical composition data and surface adhesion force data of synlithological multi-source aggregates are screened by Pearson correlation analysis to obtain initial feature parameters. The initial feature parameters are then reduced in dimensionality by principal component analysis to obtain principal component feature parameters. The principal component feature parameters include three parameters that characterize the three-dimensional surface texture features, chemical composition features and surface adhesion force features of synlithological multi-source aggregates, respectively.

[0022] The decision output module is used to construct a multivariate regression adhesion performance prediction model with principal component feature parameters as independent variables and interfacial adhesion strength of multi-source aggregates of the same lithology as dependent variable. It then uses the multivariate regression adhesion performance prediction model and candidate aggregates to obtain the predicted values ​​of interfacial adhesion strength of candidate aggregates, and selects the candidate aggregate source corresponding to the maximum value as the preferred aggregate source.

[0023] The present invention has the following beneficial effects:

[0024] (1) This invention extracts the three-dimensional morphology and chemical composition parameters of aggregates through multi-scale characterization methods, and constructs the mapping relationship between aggregate "gene parameters" and interface adhesion performance by using principal component analysis and multiple linear regression. This can effectively identify the main control factors of aggregate adhesion performance, realize the performance optimization of aggregates of the same type from different sources, and break through the limitations of relying on experience and rough characterization in the traditional aggregate selection process.

[0025] (2) The performance prediction model proposed in this invention integrates the physicochemical characteristics information at the macro, meso, micro and nano scales, and constructs a cross-scale comprehensive parameter system, which avoids the problem that the single-dimensional parameters in the prior art are insufficient to explain the adhesion performance of asphalt, and effectively improves the stability and interpretability of the model.

[0026] (3) The aggregate selection framework established by this invention has good applicability and scalability. It does not rely on a single test index and can be widely applied to the aggregate source comparison and analysis in the actual engineering design stage. It provides data support and decision-making basis for the promotion of materials genome technology in road engineering and helps to promote the transformation from "experience-based design" to "performance-oriented" intelligent design. Attached Figure Description

[0027] Figure 1 A schematic diagram of a method for optimizing aggregate sources based on aggregate interface performance data modeling;

[0028] Figure 2 This is a schematic diagram of a material source optimization system based on material interface performance data modeling. Detailed Implementation

[0029] The specific embodiments of the present invention are described below to enable those skilled in the art to understand the present invention. However, it should be understood that the present invention is not limited to the scope of the specific embodiments. For those skilled in the art, various changes are obvious as long as they are within the spirit and scope of the present invention as defined and determined by the appended claims. All inventions utilizing the concept of the present invention are protected.

[0030] like Figure 1 As shown, a method for optimizing aggregate sources based on aggregate interface performance data modeling includes steps S1-S3, as detailed below:

[0031] S1. Select homolithological multi-source aggregates, prepare standard plate samples based on homolithological multi-source aggregates, and use multi-scale equipment to collect and process data on the standard plate samples to obtain three-dimensional surface texture data, chemical composition data and surface adhesion data of homolithological multi-source aggregates.

[0032] In an optional embodiment of the present invention, the present invention selects multi-source aggregates of the same lithology and prepares standard plate samples based on the multi-source aggregates of the same lithology. The specific process is as follows: select multi-source aggregates of the same lithology with obvious differences in source, and process them into plate samples with flat surfaces and consistent dimensions according to standard procedures to prepare standard plate samples.

[0033] Specifically, this invention selects six types of basalt aggregates from different regions to ensure consistent lithology but different origins. The multi-source aggregates of the same lithology are cut into 150mm×150mm×10mm sample plates, and the surfaces are treated with a bidirectional grinding method to ensure high flatness.

[0034] This invention employs multi-scale equipment to acquire and process data from standard flat plate samples, obtaining three-dimensional surface texture data, chemical composition data, and surface adhesion force data of multi-source aggregates of the same lithology, including the following steps:

[0035] A1. A non-contact three-dimensional profilometer was used to collect structural information on the surface of the standard plate sample to obtain the initial three-dimensional surface texture data of the multi-source aggregate of the same lithology. An X-ray fluorescence analyzer was used to detect the chemical composition of the standard plate sample to obtain the chemical composition data of the multi-source aggregate of the same lithology. An atomic force microscope was used to detect the standard plate sample to obtain the surface adhesion data of the multi-source aggregate of the same lithology.

[0036] In this invention, when using atomic force microscopy to test standard plate samples, the PeakForce QNM mode is employed with a scanning area of ​​30 μm × 30 μm, a resolution of 512 × 512, and a probe elastic modulus of 26 N / m. The average surface adhesion force obtained from the atomic force microscope is used as the surface adhesion force data for multi-source aggregates of the same lithology. When using X-ray fluorescence analysis to detect the chemical composition of standard plate samples, the samples are pretreated sequentially by ball milling, drying, and pelleting. The pretreated standard plate samples cover the range of detectable elements from O to U.

[0037] Specifically, this invention uses a non-contact three-dimensional profilometer to acquire surface texture data with a resolution of 0.28 μm / pixel; this invention uses an X-ray fluorescence analyzer to determine the main chemical components, including SiO2, MgO, and Fe2O3.

[0038] A2. Perform small-scale component filtering, contour fitting and removal, and large-scale component filtering on the initial three-dimensional surface texture data of the homolithological multi-source aggregates to extract the height parameters, functional stratification parameters, volume parameters, spatial and mixing parameters of the homolithological multi-source aggregates, so as to obtain the three-dimensional surface texture data of the homolithological multi-source aggregates.

[0039] Specifically, the height parameters include Sv and Ssk; the functional layering parameters include Svk, Smrk1, and Smrk2; the volume parameter is Vvv; and the spatial and mixing parameters include Sal and Sratio.

[0040] Sv represents the deepest valley depth, specifically the maximum depth downwards from the reference plane (average plane) in the surface profile, reflecting the degree of surface concavity; Ssk represents kurtosis (height distribution skewness), which measures the symmetry of the surface height distribution. When Ssk > 0, it indicates that peaks dominate, and when Ssk < 0, it indicates that valleys dominate; Svk represents the average valley depth, characterizing the average depth of the valleys in the load-bearing curve, affecting oil film retention and adhesion; Smrk1 represents the peak-to-core ratio, specifically the material ratio between the peak area and the core area, reflecting the load-bearing capacity at the high points of the surface. Capacity; Smrk2 is the valley boundary ratio, specifically the material ratio between the valley and core regions, reflecting lubrication retention; Vvv is the valley functional volume, representing the volume below the lower limit of the core region of the load-bearing curve, used to measure the capacity or filling space size; Sal is the autocorrelation length, used to measure the repeatability and directionality of the surface texture pattern, the smaller the value, the more drastic the change in surface roughness; Sratio is the surface heterogeneity ratio, characterizing the uniformity and complexity of the surface in the spatial direction, the higher the value, the more uneven the surface distribution.

[0041] S2. Determine the interfacial adhesion strength of multi-source aggregates of the same lithology. Use Pearson correlation analysis to screen core parameters that are strongly correlated with interfacial adhesion strength from the three-dimensional surface texture data, chemical composition data, and surface adhesion force data of multi-source aggregates of the same lithology to obtain initial characteristic parameters. Then, use principal component analysis to reduce the dimensionality of the initial characteristic parameters to obtain principal component characteristic parameters. The principal component characteristic parameters include three parameters that characterize the three-dimensional surface texture characteristics, chemical composition characteristics, and surface adhesion force characteristics of multi-source aggregates of the same lithology, respectively.

[0042] In an optional embodiment of the present invention, the present invention uses a standard test method for adhesive bond strength to determine the interfacial adhesion strength of multi-source aggregates of the same lithology.

[0043] Specifically, this invention uses Pearson correlation analysis to screen core parameters strongly correlated with interfacial adhesion strength from three-dimensional surface texture data, chemical composition data, and surface adhesion force data of multi-source aggregates of the same lithology. Redundant parameters with linear correlation |P|≥0.95 are eliminated, and representative parameters with the strongest correlation to the interfacial adhesion strength of multi-source aggregates of the same lithology are retained. This invention ultimately screened 12 core parameters, including Ssk, Sv, Svk, Sal, Sratio, Smrk1, Smrk2, Vvv, SiO2, MgO, Fe2O3, and adhesion force, and determined them as initial characteristic parameters. Then, this invention uses principal component analysis to reduce the dimensionality of the above 12 core parameters, extracting three principal component characteristic parameters. The cumulative variance contribution rate of each principal component characteristic parameter is 95.7%, meeting the modeling accuracy requirements.

[0044] S3. Construct a multivariate regression adhesion performance prediction model with principal component characteristic parameters as independent variables and interfacial adhesion strength of multi-source aggregates of the same lithology as dependent variable. Use the multivariate regression adhesion performance prediction model and candidate aggregates to obtain the predicted values ​​of interfacial adhesion strength of candidate aggregates, and select the candidate aggregate source corresponding to the maximum value as the preferred aggregate source.

[0045] In an optional embodiment of the present invention, the present invention constructs a multiple regression adhesion performance prediction model using principal component characteristic parameters as independent variables and interfacial adhesion strength of multi-source aggregates of the same lithology as the dependent variable. The coefficient of determination R of the multiple regression adhesion performance prediction model is... 2 The mean and variance of the residuals are stable at 0.891, indicating that the multivariate regression adhesion performance prediction model has a good fit.

[0046] like Figure 2 As shown, an aggregate source optimization system based on aggregate interface performance data modeling applied to the above method includes a physicochemical parameter acquisition module, a characteristic parameter analysis module, and a decision output module.

[0047] In an optional embodiment of the present invention, the physicochemical parameter acquisition module is used to select homolithological multi-source aggregates, prepare standard plate samples based on homolithological multi-source aggregates, and use multi-scale equipment to acquire and process data on the standard plate samples to obtain three-dimensional surface texture data, chemical composition data and surface adhesion data of homolithological multi-source aggregates.

[0048] In an optional embodiment of the present invention, the feature parameter analysis module is used to determine the interfacial adhesion strength of synlithological multi-source aggregates. The core parameters that are strongly correlated with the interfacial adhesion strength in the three-dimensional surface texture data, chemical composition data and surface adhesion force data of synlithological multi-source aggregates are screened by Pearson correlation analysis to obtain initial feature parameters. The initial feature parameters are then dimensionality-reduced by principal component analysis to obtain principal component feature parameters. The principal component feature parameters include three parameters that characterize the three-dimensional surface texture features, chemical composition features and surface adhesion force features of synlithological multi-source aggregates, respectively.

[0049] In an optional embodiment of the present invention, the decision output module is used to construct a multivariate regression adhesion performance prediction model with principal component feature parameters as independent variables and interfacial adhesion strength of multi-source aggregates of the same lithology as dependent variable, and to obtain the predicted values ​​of interfacial adhesion strength of candidate aggregates using the multivariate regression adhesion performance prediction model and candidate aggregates, and to select the candidate aggregate source corresponding to the maximum value as the preferred aggregate source.

[0050] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0051] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0052] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0053] Specific embodiments have been used to illustrate the principles and implementation methods of this invention. The descriptions of the embodiments above are only for the purpose of helping to understand the method and core ideas of this invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this invention. Therefore, the content of this specification should not be construed as a limitation of this invention.

[0054] Those skilled in the art will recognize that the embodiments described herein are intended to help the reader understand the principles of the invention, and should be understood that the scope of protection of the invention is not limited to such specific statements and embodiments. Those skilled in the art can make various other specific modifications and combinations based on the technical teachings disclosed in this invention without departing from the spirit of the invention, and these modifications and combinations are still within the scope of protection of this invention.

Claims

1. A method for optimal aggregate source selection based on aggregate interface performance data modeling, characterized in that, Includes the following steps: We selected homolithological multi-source aggregates and prepared standard plate samples based on them. We used multi-scale equipment to collect and process data from the standard plate samples to obtain three-dimensional surface texture data, chemical composition data and surface adhesion data of the homolithological multi-source aggregates. The interfacial adhesion strength of synlithological multi-source aggregates was determined. Pearson correlation analysis was used to screen core parameters that were strongly correlated with interfacial adhesion strength from the three-dimensional surface texture data, chemical composition data, and surface adhesion force data of synlithological multi-source aggregates to obtain initial characteristic parameters. Principal component analysis was then used to reduce the dimensionality of the initial characteristic parameters to obtain principal component characteristic parameters. The principal component characteristic parameters include three parameters that characterize the three-dimensional surface texture characteristics, chemical composition characteristics, and surface adhesion force characteristics of synlithological multi-source aggregates, respectively. A multivariate regression adhesion performance prediction model was constructed with principal component characteristic parameters as independent variables and interfacial adhesion strength of multi-source aggregates of the same lithology as dependent variable. The predicted values ​​of interfacial adhesion strength of candidate aggregates were obtained using the multivariate regression adhesion performance prediction model and candidate aggregates, and the candidate aggregate source corresponding to the maximum value was selected as the preferred aggregate source.

2. The method for optimal aggregate source selection based on aggregate interface performance data modeling according to claim 1, characterized in that, Select multi-source aggregates of the same lithology and prepare standard plate samples based on them. The specific process is as follows: Select multi-source aggregates of the same lithology with obvious differences in source and process them into plate samples with flat surfaces and consistent dimensions according to standard procedures to prepare standard plate samples.

3. The method for optimal aggregate source selection based on aggregate interface performance data modeling according to claim 1, characterized in that, Data acquisition and processing were performed on standard plate samples using multi-scale equipment to obtain three-dimensional surface texture data, chemical composition data, and surface adhesion force data of multi-source aggregates of the same lithology. This included the following steps: A1. A non-contact three-dimensional profilometer was used to collect structural information on the surface of the standard plate sample to obtain the initial three-dimensional surface texture data of the multi-source aggregate of the same lithology. An X-ray fluorescence analyzer was used to detect the chemical composition of the standard plate sample to obtain the chemical composition data of the multi-source aggregate of the same lithology. An atomic force microscope was used to detect the standard plate sample to obtain the surface adhesion force data of the multi-source aggregate of the same lithology. A2. Perform small-scale component filtering, contour fitting and removal, and large-scale component filtering on the initial three-dimensional surface texture data of the homolithological multi-source aggregates to extract the height parameters, functional stratification parameters, volume parameters, spatial and mixing parameters of the homolithological multi-source aggregates, so as to obtain the three-dimensional surface texture data of the homolithological multi-source aggregates.

4. The method for optimal aggregate source selection based on aggregate interface performance data modeling according to claim 3, characterized in that, When testing standard flat plate samples using atomic force microscopy, PeakForce QNM mode was used, with a scanning area of ​​30μm×30μm, a resolution of 512×512, and a probe elastic modulus of 26N / m. The average surface adhesion force obtained by atomic force microscopy was used as the surface adhesion force data of multi-source aggregates of the same lithology.

5. The method for optimal aggregate source selection based on aggregate interface performance data modeling according to claim 3, characterized in that, When using an X-ray fluorescence analyzer to detect the chemical composition of standard plate samples, the standard plate samples are pretreated by ball milling, drying and pressing in sequence. The range of detectable elements in the pretreated standard plate samples covers O to U.

6. A material source optimization system based on aggregate interface performance data modeling applied to the method of any one of claims 1-5, characterized in that, It includes a physicochemical parameter acquisition module, a characteristic parameter analysis module, and a decision output module; The physicochemical parameter acquisition module is used to select multi-source aggregates of the same lithology, prepare standard plate samples based on the multi-source aggregates of the same lithology, and use multi-scale equipment to acquire and process data on the standard plate samples to obtain three-dimensional surface texture data, chemical composition data and surface adhesion data of the multi-source aggregates of the same lithology. The feature parameter analysis module is used to determine the interfacial adhesion strength of synlithological multi-source aggregates. The core parameters that are strongly correlated with the interfacial adhesion strength in the three-dimensional surface texture data, chemical composition data and surface adhesion force data of synlithological multi-source aggregates are screened by Pearson correlation analysis to obtain initial feature parameters. The initial feature parameters are then reduced in dimensionality by principal component analysis to obtain principal component feature parameters. The principal component feature parameters include three parameters that characterize the three-dimensional surface texture features, chemical composition features and surface adhesion force features of synlithological multi-source aggregates, respectively. The decision output module is used to construct a multivariate regression adhesion performance prediction model with principal component feature parameters as independent variables and interfacial adhesion strength of multi-source aggregates of the same lithology as dependent variable. It then uses the multivariate regression adhesion performance prediction model and candidate aggregates to obtain the predicted values ​​of interfacial adhesion strength of candidate aggregates, and selects the candidate aggregate source corresponding to the maximum value as the preferred aggregate source.

Images