Experimental test method and system for accurately detecting multiple parameters of geological sample

Abstract

The invention discloses an experimental test method and system for accurately detecting multiple parameters of a geological sample, and the method comprises the steps: collecting basic parameters of the geological sample, importing the basic parameters into an intelligent geological component analysis and calculation platform, carrying out the data classification and feature extraction, and then calling a rock stratum permeability evolution prediction model and a multispectral mineral phase feature recognition model for prediction and recognition. Deviation is calibrated through an error traceability self-adaptive correction algorithm, and a result is generated through platform multi-parameter coupling analysis and is displayed in a structured mode; wherein the key steps are divided into multiple links to be executed in order, and refinement of data processing is achieved. According to the method and the system, through multi-model deep collaboration, error traceability dynamic correction and step modular splitting, single parameter detection isolation is broken, detection data relevance and accuracy are improved, complex geological conditions are adapted, the method and the system are suitable for the fields of mineral resource exploration, oil and gas reservoir evaluation and the like, and the method and the system have wide application prospects. And an efficient and reliable technical scheme is provided for geological sample multi-parameter detection.

Description

Technical Field

[0001] This invention relates to the field of geological sample testing technology, and in particular to an experimental testing method and system for accurate detection of multiple parameters in geological samples. Background Technology

[0002] Multi-parameter detection of geological samples is a core technical aspect in mineral resource exploration, oil and gas reservoir evaluation, and geological engineering investigation. The accuracy of the detection results directly affects the efficiency of geological resource development and the safety of engineering construction. As geological exploration extends to deeper and more complex strata, the demand for simultaneous detection of multiple parameters such as mineral composition, pore structure, and permeability is becoming increasingly urgent. Traditional methods relying on single detection techniques or isolated model calculations are no longer sufficient to meet the detection needs under complex geological conditions. Core technical challenges such as the evolution of rock permeability, accurate identification of mineral facies characteristics, and multi-parameter coupled analysis are driving the industry's research and development of integrated and intelligent detection methods and systems. The integrated application of intelligent geological component analysis and calculation platforms, multi-model collaborative computation, and error adaptive correction technologies has become a key direction for improving detection accuracy and efficiency.

[0003] Existing technologies suffer from two core drawbacks: First, the integration of detection methods is insufficient. They often use a single model to analyze a single parameter, failing to achieve deep synergy in predicting rock permeability evolution, identifying multispectral mineral facies characteristics, and coupling multi-parameter analysis. This results in a lack of correlation between the detection results of different parameters, making it difficult to comprehensively reflect the overall characteristics of geological samples. Furthermore, a systematic error tracing and dynamic correction mechanism has not been established, and deviation calibration relies on manual intervention, which cannot adapt to the dynamic changes of complex geological parameters. Second, the modular design of the detection system is unreasonable. Data transmission links between functional units are not smooth, and there is a lack of a unified intelligent analytical calculation platform for geological components as the core of data processing. This leads to a disconnect between parameter acquisition, model calculation, and analytical output, failing to form a complete data processing closed loop. Moreover, the allocation of unit functions has not been optimized for the special characteristics of multi-parameter detection of geological samples, affecting the continuity of the detection process and the efficiency of data processing. Summary of the Invention

[0004] In order to overcome the shortcomings and deficiencies of existing technologies, this invention provides an experimental testing method and system for accurate detection of multiple parameters in geological samples.

[0005] The technical solution adopted in this invention is an experimental testing method for accurate detection of multiple parameters in geological samples, comprising the following steps: S1, collecting basic data on mineral composition content, pore structure parameters, particle size distribution, rock density, porosity, and permeability of geological samples using an experimental testing device for accurate detection of multiple parameters in geological samples, and simultaneously recording sampling depth and stratigraphic lithology correlation information; S2, importing the collected basic data into a geological component intelligent analysis and calculation platform, and performing hierarchical division and feature extraction according to geological parameter type through the platform's built-in data classification module; S3, calling the rock stratum permeability evolution prediction model to extrapolate the evolution trend of the divided permeability correlation parameters, and combining it with a multispectral mineral facies feature identification model to target and identify mineral component feature data; S4, using an error source tracing adaptive correction algorithm to calibrate the model output results, tracing the source of the error in the geological parameter correlation and making dynamic adjustments; S5, based on the calibrated feature data, performing multi-parameter coupled analysis of geological samples through the geological component intelligent analysis and calculation platform to generate multi-dimensional parameter analysis results; S6, presenting the analysis results in a structured manner through the output module of the experimental testing device, forming a complete data chain for multi-parameter detection of geological samples.

[0006] Furthermore, the expression for the rock stratum permeability evolution prediction model is as follows: ,in, This is the predicted value of rock permeability. Permeability evolution coefficient, Porosity of geological samples Porosity influence index This refers to the mass fraction of the mineral components. The weights of the components Pore ​​connectivity factor The average pore diameter, For aperture influence index, This is a fluid flow correction factor. It is a function of water saturation. For effective pressure, For the formation temperature, For fluid viscosity, The length is the sample length.

[0007] Furthermore, the expression for the multispectral mineral facies feature identification model is as follows: ,in, These are multispectral characteristic response values. For the first Spectral weighting coefficients of minerals, For the first minerals at wavelength Reflectivity at that location For the first Spectral broadening factor of the mineral, For spectral correction factor, The measured spectral signal, For spectral weighting functions, For the spectral detection wavelength range, This represents the number of mineral types.

[0008] Furthermore, the expression for the error source tracing adaptive correction algorithm is as follows: ,in, This is the corrected error value. This is the initial error value. For the first The error of each parameter affects the weight. For the first Measured values ​​of several geological testing parameters For the first Predicted values ​​from a parameter model For the first The adjustment amount of each parameter, This is the error compensation coefficient. For the first The error sensitivity coefficient of each parameter, This represents the number of parameters involved in error correction.

[0009] Furthermore, the geological parameter coupling analytical model expression of the intelligent analytical calculation platform for geological components is as follows: ,in, The results are based on a comprehensive analysis of geological components. For the first The analytical weights of the components, For the first Characteristic parameter values ​​of the components, For the first Model fit coefficients for each component For the first Weighting factors for each detection parameter, For the first Standardized values ​​of each detection parameter These are the coupling analytical coefficients. To effectively detect the amount of data, For parameters related to component identification accuracy, For data redundancy factor, The number of component types, This represents the number of parameters to be detected.

[0010] Furthermore, the optimized model expression for the experimental test parameters of the geological sample multi-parameter accurate detection is as follows: ,in, For the parameter optimization results, For the first Weighting coefficients for each experimental condition. For the first Measured values ​​of parameters under experimental conditions. For the first The effectiveness factor of each experimental condition. For the first Optimization weights for each parameter, For the first Measured values ​​of each parameter For the first Industry reference values ​​for each parameter. The number of experimental condition groups, This represents the total number of parameters detected.

[0011] Further, step S3 includes the following sub-steps: S31, selecting the porosity, mineral composition content, and particle size distribution parameters of the geological sample as input variables for the rock stratum permeability evolution prediction model, and grouping the input variables according to geological stratification characteristics; S32, substituting the grouped variables into the rock stratum permeability evolution prediction model, and performing multiple rounds of evolution trend deduction through the model's built-in iterative calculation logic to generate a preliminary permeability prediction data sequence; S33, simultaneously extracting the multispectral reflectance signal, absorption signal, and scattering signal of the geological sample, removing environmental interference-related data from the signals, and retaining the mineral facies feature calibration signal; S34, inputting the calibration signal into the multispectral mineral facies feature recognition model, and using the model's feature matching mechanism to target and identify mineral types and content distribution, and outputting mineral facies feature analysis results.

[0012] Further, step S4 includes the following sub-steps: S41, extracting the output data of the rock stratum permeability evolution prediction model and the multispectral mineral facies feature identification model to establish a basic dataset for error analysis; S42, calling the error source tracing adaptive correction algorithm to perform source tracing analysis on the deviation data in the dataset, locating the geological parameter correlation nodes and their degree of influence caused by the error; S43, based on the source tracing results, the algorithm automatically generates a dynamic correction factor sequence and performs hierarchical calibration on the deviation data according to the parameter correlation weight; S44, comparing and analyzing the calibrated data with the original output data to form a complete data comparison chain before and after error correction, providing corrected data support for subsequent analysis.

[0013] Further, S5 includes the following sub-steps: S51, importing the error-corrected permeability prediction data and mineral facies analysis data into the intelligent geological component analysis calculation platform, which automatically assigns them to the corresponding analysis modules according to data type; S52, each analysis module calls the preset component analysis rules to perform multi-dimensional coupled calculations on the mineral composition, pore structure parameters, and physical and mechanical property parameters of the geological sample; S53, during the calculation process, the sampling depth and stratigraphic lithology background information are correlated in real time, and the analysis results are adjusted to adapt to the geological scene; S54, the analysis results of each module are integrated to form a comprehensive multi-parameter analysis report of the geological sample, which includes parameter values, distribution characteristics, and correlation information.

[0014] An experimental testing system for accurate multi-parameter detection of geological samples includes: a geological sample parameter acquisition unit, a multi-dimensional data preprocessing unit, a model calculation and feature recognition unit, an error tracing and correction unit, an intelligent analytical calculation unit, and a result output and storage unit. The geological sample parameter acquisition unit and the multi-dimensional data preprocessing unit are connected via a high-speed data transmission link. The basic parameter data of the geological samples acquired by the acquisition unit is transmitted in real time to the preprocessing unit for classification and organization. The multi-dimensional data preprocessing unit communicates bidirectionally with the model calculation and feature recognition unit. The preprocessed parameter data is input into the model calculation unit, which incorporates a rock stratum permeability evolution prediction model and a multispectral mineral facies feature recognition model. After prediction and identification are completed, the results are fed back to the preprocessing unit for data verification. The model operation and feature recognition unit is electrically connected to the error tracing and correction unit, and the output results are transmitted to the error correction unit. The deviation calibration is completed through the error tracing adaptive correction algorithm. The error tracing and correction unit is connected to the intelligent analysis and calculation unit through a data bus. The calibrated data is imported into the geological component intelligent analysis and calculation platform for multi-parameter coupled analysis. The intelligent analysis and calculation unit is communicatively connected to the result output and storage unit. The analysis results are presented through the output unit after structured processing. At the same time, the storage unit encrypts and stores the data throughout the process. All units work together to perform accurate multi-parameter detection of geological samples.

[0015] The present invention has the following beneficial effects:

[0016] Through deep multi-model collaboration and modular integration across the entire process, this method achieves precise, efficient, and systematic multi-parameter detection of geological samples. Addressing the insufficient integration of existing technologies, this method organically integrates rock stratum permeability evolution prediction, multispectral mineral facies identification, and intelligent geological component analysis. It achieves deep correlation between detection results of different parameters through multi-model collaborative computation. Simultaneously, relying on error tracing and adaptive correction technology, a systematic deviation calibration mechanism is established, enabling error tracing and dynamic adjustment without manual intervention. This comprehensively reflects the integrated characteristics of geological samples and adapts to the dynamic changes of complex geological parameters. Addressing the issue of unreasonable modular design in the detection system, the system constructs a complete data processing closed loop through the orderly connection of six functional units and a high-speed data transmission link. With the intelligent geological component analysis and calculation platform at its core, it achieves seamless integration from parameter acquisition, model computation, error correction, intelligent analysis to result output. Optimizing the functional allocation and collaborative operation logic of each unit ensures the continuity of the detection process and the efficiency of data processing, significantly improving the accuracy and overall efficiency of multi-parameter detection of geological samples, and providing reliable technical support for geological exploration in deep and complex strata. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating the overall process of the method of the present invention.

[0018] Figure 2 This is a flowchart of method step S3 of the present invention;

[0019] Figure 3 This is a flowchart of method step S4 of the present invention;

[0020] Figure 4 This is a flowchart of step S5 of the method of the present invention;

[0021] Figure 5 This is a diagram showing the system unit composition of the present invention. Detailed Implementation

[0022] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. The application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0023] like Figure 1 As shown, an experimental testing method for accurate multi-parameter detection of geological samples includes the following steps:

[0024] S1, through an experimental testing device for precise detection of multiple parameters of geological samples, collects basic data on mineral composition content, pore structure parameters, particle size distribution, rock density, porosity, and permeability of geological samples, and simultaneously records sampling depth and stratigraphic lithology correlation information;

[0025] Specifically, step S1 involves basic data acquisition using a high-precision geological sample multi-parameter detection experimental device. This device integrates a mineral composition analysis module, a pore structure detection module, a particle size testing module, and a physical property detection module. It simultaneously collects core parameters of geological samples, such as mineral composition content, pore structure parameters, particle size distribution, rock density, porosity, and permeability. Among these, the mineral composition content detection covers common geological mineral types such as silicates, carbonates, and oxides. The pore structure parameters include detailed indicators such as pore morphology, connectivity paths, and throat dimensions. The particle size distribution detection range is set to 0.01 to 1000 micrometers. The rock density detection accuracy is controlled within ±0.01 micrometers. The porosity detection covers the range of 0.1% to 40%. The permeability detection range is 0.001 to 10000 micrometers. During the data collection process, sampling depth data is recorded simultaneously with a depth recording accuracy of 0.1 meters. At the same time, stratigraphic lithological information is labeled, including lithological types such as clastic rocks, carbonate rocks, and igneous rocks, as well as auxiliary information such as rock layer thickness and burial depth. All collected data is stored in real time through the device's built-in data recording module, and the storage format adopts a standardized data structure to ensure compatibility with subsequent data processing. This step provides comprehensive and accurate raw data support for the entire detection process and is the basic prerequisite for subsequent model calculations and intelligent analysis.

[0026] S2, import the collected basic data into the intelligent analysis and calculation platform for geological components, and perform hierarchical division and feature extraction according to geological parameter types through the platform's built-in data classification module;

[0027] Specifically, step S2 imports all the basic data collected in step S1 into the intelligent geological component analysis and calculation platform through the data transmission interface. The transmission process uses an encrypted data transmission protocol to ensure data integrity and security. The platform's built-in data classification module divides the data into three levels according to the type of geological parameters. The first level is divided into three major categories: physical property parameters, mineral component parameters, and structural feature parameters. The second level further subdivides each major category into specific parameter subcategories. For example, physical property parameters are divided into density, porosity, and permeability subcategories; mineral component parameters are divided into elemental minerals and compound minerals subcategories; and structural feature parameters are divided into pore structure and particle size subcategories. The third level further subdivides the data according to the parameter detection accuracy and data type. After classification, the platform initiates feature extraction algorithms to extract core feature indicators for different types of parameters. For example, for mineral component parameters, it extracts indicators such as feature peak value, content ratio, and distribution gradient; for pore structure parameters, it extracts indicators such as pore equivalent diameter, connectivity index, and pore distribution uniformity; and for particle size parameters, it extracts indicators such as average particle size, particle size standard deviation, and cumulative distribution percentage. During feature extraction, the correlation mapping relationship between the original data and the feature data is preserved to ensure data traceability. This step realizes the systematic organization of the original data and the extraction of core information, providing standardized and structured data input for subsequent model calls.

[0028] S3, call the rock stratum permeability evolution prediction model to extrapolate the evolution trend of the permeability correlation parameters after division, and combine the multispectral mineral facies feature identification model to target the mineral component feature data;

[0029] Specifically, step S3 activates the model calculation module of the intelligent geological component analysis and calculation platform. First, it calls the rock stratum permeability evolution prediction model, using the permeability-related parameters obtained in step S2 as model input. These parameters include core permeability-related parameters such as porosity, pore structure parameters, particle size distribution, and mineral component content. The model uses multi-parameter coupled calculation logic to extrapolate the permeability evolution trend. The extrapolation process employs a multi-round iterative calculation method, with the number of iterations set to 50 to 200. Each iteration optimizes the parameter weight allocation based on the results of the previous round. Simultaneously, the multispectral mineral facies feature identification model is called, inputting the mineral component feature data extracted in step S2 into the model. The model uses spectral feature matching, feature threshold determination, and component correlation analysis to target and identify the mineral component feature data. During the identification process, it focuses on key indicators such as characteristic spectral peak position, peak intensity, and full width at half maximum (FWHM), accurately distinguishing the differences in spectral characteristics among different minerals. The identification range covers more than 50 common geological mineral types, including major minerals such as quartz, feldspar, calcite, dolomite, and clay minerals, as well as various rare minerals. This step uses dual-model collaborative computation to separately complete the permeability evolution trend projection and ore-facies feature targeted identification, providing preliminary computational results for subsequent error correction and multi-parameter analysis.

[0030] S4, the model output results are calibrated by the error source tracing adaptive correction algorithm, the geological parameters associated with the error are traced and dynamically adjusted;

[0031] Specifically, step S4 invokes the error source tracing adaptive correction algorithm, using the output results of the rock stratum permeability evolution prediction model and the multispectral mineral facies feature identification model from step S3 as input data. The algorithm first constructs an error analysis matrix, comparing the model output with the original detection data collected in step S1 to calculate the deviation values ​​and deviation rates of each parameter. The deviation rate is calculated using a relative deviation calculation method. Subsequently, the algorithm activates the error source tracing mechanism, using parameter correlation analysis, data flow tracking, and reverse calculation of the computation process to trace the geological parameter correlation sources of the errors, identifying the core influencing parameters causing the deviations, including deviations in parameter acquisition accuracy, model parameter adaptability, and multi-parameter coupling interference. After the source tracing is completed, the algorithm automatically generates a dynamic adjustment strategy based on the type and degree of deviation, constructs a sequence of correction factors, and keeps the number of correction factors consistent with the number of parameters involved in the calculation. Each correction factor corresponds to a core detection parameter. The deviation data is calibrated hierarchically according to the parameter association weight. The calibration process adopts a step-by-step iterative correction method. After each round of correction, the deviation rate is recalculated until the deviation rate is reduced to within the set threshold range. This step achieves accurate calibration of the model output results, improves data reliability, and provides a high-quality data foundation for subsequent intelligent analysis.

[0032] S5, based on the calibrated feature data, performs multi-parameter coupled analysis of geological samples through the intelligent analysis and calculation platform for geological components, and generates multi-dimensional parameter analysis results;

[0033] Specifically, step S5, based on the feature data calibrated in step S4, initiates the multi-parameter coupled analysis module of the intelligent geological component analysis calculation platform. The analysis module first integrates the calibrated permeability prediction data and mineral facies analysis data according to parameter type, forming three major datasets: a comprehensive physical property dataset, a comprehensive mineral component dataset, and a comprehensive structural feature dataset. Subsequently, the platform calls preset multi-parameter coupled analysis rules, which include core logic such as parameter correlation analysis, cross-dataset fusion calculation, and geological scene adaptation adjustment. The analysis rules can automatically adapt and adjust to the detection needs of different types of geological samples. For example, for clastic rock samples, the coupling analysis of particle size and pore structure is strengthened; for carbonate rock samples, the correlation analysis of mineral components and permeability is strengthened. During the analysis process, background information such as sampling depth and stratigraphic lithology recorded in step S1 is simultaneously invoked to establish a correlation mapping between the analysis results and the geological scene, generating multi-dimensional parameter analysis results. These results include three dimensions: single-parameter numerical analysis results, multi-parameter correlation analysis results, and geological scene adaptation analysis results. Each dimension includes specific parameter values, distribution characteristics, and variation patterns. This step achieves deep fusion and intelligent analysis of multi-source data, forming comprehensive and systematic detection and analysis results.

[0034] S6 presents the analytical results in a structured manner through the output module of the experimental testing device, forming a complete data chain for multi-parameter detection of geological samples.

[0035] Specifically, step S6 activates the output module of the experimental testing device. This module integrates three functional units: a data structuring processing unit, a result presentation unit, and a data export unit. First, the data structuring processing unit formats the multi-dimensional parameter analysis results generated in step S5, constructing a structured data report according to the detection parameter type, geological scene classification, and data accuracy level. The report includes core content such as parameter names, detection values, characteristic indicators, related parameters, and geological adaptation analysis. Data presentation uses a combination of tables, curves, and distribution maps to ensure the results are intuitive and easy to understand. Subsequently, the result presentation unit provides a visual display, supporting both local display and remote terminal access. Local display uses a high-definition touchscreen, while remote display uses a network communication module for real-time data push. Simultaneously, the data export unit supports exporting data in various formats, including standardized text, table, and image formats, meeting the data usage needs of different application scenarios. Throughout the process, the output module synchronously records auxiliary information such as the output time, data version, and processing personnel, forming a complete data chain for multi-parameter detection of geological samples. The data chain includes raw acquisition data, intermediate processing data, final analysis results, process parameters, and other full-process data. This step enables the systematic presentation and archiving of detection results, providing direct data support for subsequent geological analysis and engineering applications.

[0036] Preferably, the expression for the rock stratum permeability evolution prediction model is:

[0037] ,

[0038] in, This is the predicted value of rock permeability. Permeability evolution coefficient, Porosity of geological samples Porosity influence index This refers to the mass fraction of the mineral components. The weights of the components Pore ​​connectivity factor The average pore diameter, For aperture influence index, This is a fluid flow correction factor. It is a function of water saturation. For effective pressure, For the formation temperature, For fluid viscosity, The length is the sample length.

[0039] Specifically, the rock formation permeability evolution prediction model achieves accurate prediction of rock formation permeability through multi-parameter coupled calculations. During model implementation, core parameters such as geological sample porosity, mineral component mass fraction, average pore diameter, effective pressure, formation temperature, fluid viscosity, and sample length are selected as inputs. Porosity values ​​range from 0.1% to 40%, mineral component mass fractions are precisely measured according to their respective proportions, the average pore diameter is controlled within the range of 0.01 to 100 micrometers, effective pressure is set with gradient values ​​based on actual formation conditions, formation temperature is recorded from 0 to 200 degrees Celsius, fluid viscosity is determined based on the geological fluid type, and sample length is precisely measured according to the actual sample size. During model calculation, the basic characteristics of the internal structure of the geological sample are first reflected through the collaborative calculation of porosity and mineral component mass fraction. The influence of fluid flow path is corrected by combining the average pore diameter and pore connectivity factor. Then, the influence of dynamic environmental parameters such as effective pressure, formation temperature, and fluid viscosity on permeability is incorporated through integral calculations. The number of iterations is set to 50 to 200 to ensure convergence of the calculation results. This model, through the comprehensive integration of multi-dimensional parameters and step-by-step computational logic, accurately depicts the evolution of rock permeability with geological parameters and environmental conditions, providing a scientific and reliable basis for the detection of permeability in geological samples. Its implementation does not require the addition of additional detection equipment and can be directly calculated based on existing experimental test parameters, greatly improving the efficiency and accuracy of permeability detection.

[0040] Preferably, the expression for the multispectral mineral facies feature identification model is:

[0041] ,

[0042] in, These are multispectral characteristic response values. For the first Spectral weighting coefficients of minerals, For the first minerals at wavelength Reflectivity at that location For the first Spectral broadening factor of the mineral, For spectral correction factor, The measured spectral signal, For spectral weighting functions, For the spectral detection wavelength range, This represents the number of mineral types.

[0043] Specifically, the multispectral mineral facies feature identification model achieves targeted identification of mineral components based on spectral feature analysis. During model implementation, the detection wavelength range is first determined, set to 200 to 2500 nanometers, covering the characteristic spectral response range of common geological minerals. Then, measured spectral signals of geological samples within this wavelength range are acquired, and reflectance data of each mineral at different wavelengths are recorded simultaneously, with reflectance measurement accuracy controlled within ±0.001. During model computation, corresponding spectral weighting coefficients and spectral broadening coefficients are first assigned according to mineral type. The spectral weighting coefficients are set to a gradient value of 0.1 to 1.0 based on the intensity differences of mineral characteristic spectra, while the spectral broadening coefficients are set to a range of 0.01 to 0.1 based on the width characteristics of mineral spectral peaks. Then, exponential calculations are used to correct the broadening effect of the spectral signal, reducing the influence of environmental interference on spectral features. Simultaneously, integral calculations are used to weight the measured spectral signals, with the spectral weighting function assigning weights according to the importance of the wavelength range, strengthening the signal response within the characteristic wavelength range. The model covers more than 50 common geological minerals during the identification process. By comparing the calculated spectral characteristic response values ​​with standard mineral spectral library data, it can accurately determine the mineral type and content. The implementation process does not require complicated sample preprocessing and can directly complete the identification based on multispectral detection data, which significantly improves the efficiency and accuracy of mineral phase feature detection.

[0044] Preferably, the expression for the error source tracing adaptive correction algorithm is:

[0045] ,

[0046] in, This is the corrected error value. This is the initial error value. For the first The error of each parameter affects the weight. For the first Measured values ​​of several geological testing parameters For the first Predicted values ​​from a parameter model For the first The adjustment amount of each parameter, This is the error compensation coefficient. For the first The error sensitivity coefficient of each parameter, This represents the number of parameters involved in error correction.

[0047] Specifically, the error source-tracing adaptive correction algorithm corrects the deviation of the model output results through systematic source tracing and dynamic calibration. During algorithm implementation, the output results of the rock strata permeability evolution prediction model and the multispectral mineral facies feature identification model are first collected. Simultaneously, the measured values ​​of geological testing parameters collected in step S1 are retrieved to construct a basic dataset for error analysis, including all core parameters. The number of parameters involved in error correction covers 20 to 50 key parameters such as mineral composition content, porosity, permeability, and spectral reflectance. The algorithm first calculates the initial error value, then analyzes the influence of each parameter on the error through partial derivative calculations, assigns corresponding error influence weights, and sets the weight values ​​to a range of 0.01 to 0.2 according to the degree of influence. Subsequently, the difference between the measured values ​​and the model prediction values ​​of each parameter is calculated as the adjustment amount. By tracing the source of errors through an error source tracing mechanism, specific types of errors are identified, such as parameter acquisition accuracy deviation, model parameter adaptability deviation, and multi-parameter coupling interference deviation. Based on the tracing results, error compensation coefficients are generated, with values ​​ranging from 0.8 to 1.2. Combined with an error sensitivity coefficient, stratified calibration of the deviation data is performed, with the error sensitivity coefficient set to 0.1 to 0.5 according to parameter stability. The calibration process employs a multi-round iterative approach, recalculating the error value after each iteration until the error value is reduced to a set threshold range of 0.001 to 0.01. This algorithm achieves precise error source tracing and dynamic correction, completing deviation calibration without manual intervention and significantly improving data reliability.

[0048] Preferably, the geological parameter coupling analytical model expression of the intelligent analytical calculation platform for geological components is as follows:

[0049] ,

[0050] in, The results are based on a comprehensive analysis of geological components. For the first The analytical weights of the components, For the first Characteristic parameter values ​​of the components, For the first Model fit coefficients for each component For the first Weighting factors for each detection parameter, For the first Standardized values ​​of each detection parameter These are the coupling analytical coefficients. To effectively detect the amount of data, For parameters related to component identification accuracy, For data redundancy factor, The number of component types, This represents the number of parameters to be detected.

[0051] Specifically, the geological parameter coupling analytical model of the intelligent geological component analysis and calculation platform achieves comprehensive analysis of geological components through multi-source data fusion. During model implementation, core parameters such as component characteristic parameter values ​​of geological samples, model adaptation coefficients, standardized values ​​of detection parameters, effective detection data volume, and data redundancy factor are first selected as inputs. The component analysis weights are set to gradient values ​​from 0.1 to 0.3 based on the importance of each component. The model adaptation coefficients are adjusted to a range of 0.8 to 1.2 based on the parameter type. The weight factors for detection parameters are set to 0.05 to 0.2 based on detection accuracy. The effective detection data volume is calculated based on the actual number of effective samples collected, and the data redundancy factor is calculated based on the data repetition rate, ranging from 0.1 to 0.5. During model computation, the basic analytical results for each component are first calculated through weighted summation. Then, the deviation in the multi-parameter coupling process is corrected through square root calculation. The adaptability of the analytical results is adjusted in conjunction with the coupling analytical coefficients, which range from 0.9 to 1.1. Simultaneously, the accuracy of the analytical results is optimized by calculating the ratio of effective detection data volume to the data redundancy factor, reducing the interference of redundant data on the analytical results. The model analysis process covers 10 to 30 types of geological components, integrates multi-dimensional data such as physical properties, mineral composition, and structural features, and generates comprehensive geological component analysis results. Its implementation realizes deep fusion and collaborative analysis of multiple parameters, improves the comprehensiveness and accuracy of geological component detection, and provides a scientific basis for the comprehensive evaluation of geological samples.

[0052] Preferably, the optimized model expression for the experimental test parameters of the geological sample multi-parameter accurate detection is as follows:

[0053] ,

[0054] in, For the parameter optimization results, For the first Weighting coefficients for each experimental condition. For the first Measured values ​​of parameters under experimental conditions. For the first The effectiveness factor of each experimental condition. For the first Optimization weights for each parameter, For the first Measured values ​​of each parameter For the first Industry reference values ​​for each parameter. The number of experimental condition groups, This represents the total number of parameters detected.

[0055] Specifically, the experimental parameter optimization model for precise multi-parameter detection of geological samples optimizes the detection parameters through multi-condition weighting and logarithmic operations. During model implementation, core parameters are first selected, including the weighting coefficients of experimental conditions, measured parameter values, experimental condition validity factors, parameter optimization weights, and industry reference values ​​for parameters. The weighting coefficients of experimental conditions are set to 0.1 to 0.3 based on experimental reliability; measured parameter values ​​are taken from the precise detection data in step S1; the validity factors of experimental conditions are set to 0.7 to 1.0 based on the reliability of the experimental results; the parameter optimization weights are set to 0.05 to 0.25 based on the degree of influence of the parameters on the detection results; and the industry reference values ​​adopt industry-standard data. During model calculation, the basic parameter values ​​under each experimental condition are first calculated through weighted summation. Then, the difference between the measured parameter values ​​and the industry reference values ​​is compared through ratio calculation, and the optimization bias caused by excessive differences is corrected by natural logarithmic operations. The number of experimental condition sets is set to 3 to 10, covering different sampling depths, detection environments, and other conditions. The total number of detection parameters includes 20 to 50 core parameters, encompassing all key detection indicators such as mineral composition, physical properties, and structural characteristics. Through comprehensive calculation and optimization of multiple sets of experimental data, the model outputs the optimal value range and detection conditions for each detection parameter. Its implementation can optimize parameter settings and condition selection in experimental testing, reduce invalid and duplicate detections, improve detection efficiency and data accuracy, and provide standardized parameter setting guidelines for subsequent detection work, thereby reducing detection costs.

[0056] Preferred, such as Figure 2 As shown, step S3 includes the following sub-steps: S31, selecting the porosity, mineral composition content, and particle size distribution parameters of the geological sample as input variables for the rock stratum permeability evolution prediction model, and grouping the input variables according to geological stratification characteristics; S32, substituting the grouped variables into the rock stratum permeability evolution prediction model, and performing multiple rounds of evolution trend deduction through the model's built-in iterative calculation logic to generate a preliminary permeability prediction data sequence; S33, simultaneously extracting the multispectral reflectance signal, absorption signal, and scattering signal of the geological sample, removing environmental interference-related data from the signals, and retaining the mineral facies feature calibration signal; S34, inputting the calibration signal into the multispectral mineral facies feature recognition model, and using the model's feature matching mechanism to target and identify mineral types and content distribution, and outputting mineral facies feature analysis results.

[0057] Specifically, step S3 includes four sub-steps. The implementation process involves model calculation and feature recognition. S31 first selects porosity, mineral composition content, and particle size distribution parameters of geological samples from the parameters classified in step S2 as input variables for the rock layer permeability evolution prediction model. Based on geological stratification characteristics, the input variables are divided into three groups: shallow, middle, and deep layers, with each group including at least 30 sample data points to ensure data coverage of geological characteristics at different strata depths. S32 imports the grouped variables sequentially into the rock layer permeability evolution prediction model. The model activates its built-in iterative calculation logic, performing multiple rounds of evolution trend extrapolation with 50 to 200 iterations. After each iteration, the parameter weight allocation is automatically optimized, ultimately generating an initial model including information such as permeability numerical changes, evolution rate, and trend inflection points. Step 1: Permeability prediction data sequence; Step 2: Simultaneously extract multispectral reflection, absorption, and scattering signals from geological samples using multispectral detection equipment. Signal filtering removes ambient light interference, equipment noise, and other related data, retaining calibration signals directly related to mineral facies characteristics. Signal extraction accuracy is controlled within ±0.001. Step 34: Input the calibration signals into the multispectral mineral facies characteristic identification model in wavelength order. The model activates a feature matching mechanism, comparing the characteristics of the calibration signals with those of a standard mineral spectral library to target and identify mineral types and content distribution. The matching results are updated every 0.1 seconds during the identification process. The final output includes mineral facies characteristic analysis results such as mineral name, content percentage, and spatial distribution location. The orderly connection of each step ensures the accuracy of prediction and identification.

[0058] Preferred, such as Figure 3 As shown, step S4 includes the following sub-steps: S41, extracting the output data of the rock stratum permeability evolution prediction model and the multispectral mineral facies feature identification model to establish a basic dataset for error analysis; S42, calling the error source tracing adaptive correction algorithm to perform source tracing analysis on the deviation data in the dataset, locating the geological parameter correlation nodes and the degree of influence of the error; S43, based on the source tracing results, the algorithm automatically generates a dynamic correction factor sequence and performs hierarchical calibration on the deviation data according to the parameter correlation weight; S44, comparing and analyzing the calibrated data with the original output data to form a complete data comparison chain before and after error correction, providing corrected data support for subsequent analysis.

[0059] Specifically, step S4 includes four sub-steps, during which error tracing and correction are performed. S41 first extracts core data such as predicted permeability and mineral content identification values ​​from the outputs of the rock stratum permeability evolution prediction model and the multispectral mineral facies characteristic identification model. This data is then processed with the original detection data collected in step S1 to construct a basic error analysis dataset containing 20 to 50 key parameters. The dataset is categorized and labeled according to parameter type. S42 calls the error tracing adaptive correction algorithm to perform statistical analysis on the deviation data in the dataset. Through parameter correlation analysis, the relationship between errors and factors such as the accuracy of geological parameter acquisition, model parameter adaptability, and multi-parameter coupling interference is traced to clarify the specific nodes where errors occur and their impact. The degree is quantified and evaluated in a numerical range of 0 to 1; S43 Based on the traceability results, the algorithm automatically generates a dynamic correction factor sequence including 20 to 50 correction factors according to the parameter association weights. The correction factor values ​​range from 0.8 to 1.2. The deviation data is calibrated in layers according to the weight from high to low. After each layer of calibration, the deviation rate is calculated to ensure the targeting of the calibration; S44 The calibrated data is compared with the original output data one by one according to the parameter category. The change in deviation rate is calculated to form a complete data comparison chain including the original data, deviation data, correction data, and change in deviation rate. The comparison chain is sorted and stored by timestamp to provide accurate calibrated data support for subsequent analysis work. Each step is progressive to achieve effective error correction.

[0060] Preferred, such as Figure 4 As shown, step S5 includes the following sub-steps: S51, importing the error-corrected permeability prediction data and mineral facies analysis data into the intelligent geological component analysis calculation platform, which automatically assigns them to the corresponding analysis modules according to data type; S52, each analysis module calls the preset component analysis rules to perform multi-dimensional coupled calculations on the mineral composition, pore structure parameters, and physical and mechanical property parameters of the geological sample; S53, during the calculation process, the sampling depth and stratigraphic lithology background information are correlated in real time, and the analysis results are adjusted to adapt to the geological scene; S54, the analysis results of each module are integrated to form a comprehensive multi-parameter analysis report of the geological sample, which includes parameter values, distribution characteristics, and correlation information.

[0061] Specifically, step S5 includes four sub-steps. During implementation, intelligent analysis is performed. S51 converts the error-corrected permeability prediction data and mineral facies analysis data according to data type, converting them to a data format compatible with the geological component intelligent analysis and calculation platform. This data is then imported into the platform via a high-speed data transmission link. The platform automatically allocates the data to the corresponding three analysis modules according to physical property parameters, mineral composition parameters, and structural characteristic parameters. S52 Each analysis module activates preset component analysis rules. The physical property analysis module performs numerical calibration for parameters such as rock density and porosity; the mineral composition analysis module performs secondary verification of mineral composition and content; and the physical and mechanical property analysis module performs coupling calculations for parameters such as compressive strength and elastic modulus. The calculation process involves data verification after each round of computation. In step S53, background information such as sampling depth and lithology recorded in step S1 is retrieved in real time. A geological scene unit is divided into units with a depth of 1 meter. The analysis results are then adapted and adjusted to match the geological characteristics of the corresponding scene unit. The adjustment range is set to 0.01 to 0.1 based on the lithological differences of the scene unit. In step S54, the analysis results of each analysis module are summarized through the platform's data integration module. The results are then classified and organized according to three dimensions: parameter values, distribution characteristics, and correlation relationships. A structured multi-parameter comprehensive analysis report of geological samples is generated. The report includes complete information such as data source, calculation process, and final results. The collaboration of each step ensures the comprehensiveness and reliability of the analysis results.

[0062] like Figure 5As shown, an experimental testing system for accurate multi-parameter detection of geological samples is described. This system is applied to an experimental testing method for accurate multi-parameter detection of geological samples and includes: a geological sample parameter acquisition unit, a multi-dimensional data preprocessing unit, a model calculation and feature recognition unit, an error tracing and correction unit, an intelligent analytical calculation unit, and a result output and storage unit. The geological sample parameter acquisition unit and the multi-dimensional data preprocessing unit are connected via a high-speed data transmission link. The basic parameter data of the geological samples acquired by the acquisition unit is transmitted in real time to the preprocessing unit for classification and organization. The multi-dimensional data preprocessing unit communicates bidirectionally with the model calculation and feature recognition unit. The preprocessed parameter data is input into the model calculation unit, which has a built-in rock stratum permeability evolution prediction function. The model and multispectral mineral facies feature identification model complete prediction and identification, and then feed the results back to the preprocessing unit for data verification. The model calculation and feature identification unit is electrically connected to the error tracing and correction unit, and the output results are transmitted to the error correction unit. The deviation is calibrated by the error tracing adaptive correction algorithm. The error tracing and correction unit is connected to the intelligent analysis and calculation unit through a data bus. The calibrated data is imported into the geological component intelligent analysis and calculation platform for multi-parameter coupled analysis. The intelligent analysis and calculation unit is communicatively connected to the result output and storage unit. The analysis results are presented through the output unit after structured processing. At the same time, the storage unit encrypts and stores the data throughout the process. All units work together to perform accurate multi-parameter detection of geological samples.

[0063] The formula in this invention enables the fusion calculation of different scalar and vector parameters by constructing a standardized mapping mechanism and dimension adaptation logic based on the essential correlation of geological parameters. Scalar parameters, such as mineral component mass fraction, porosity, and rock density, although lacking directional attributes, directly reflect the basic physicochemical properties of geological samples. Vector parameters, such as multispectral reflectance signal vectors and permeability evolution trend vectors, include both magnitude and direction information, characterizing the dynamic changes or spatial distribution features of the parameters. The formula transforms the directional information of vector parameters into scalar influence weights by introducing targeted adaptation coefficients and weighting factors. For example, in the multispectral mineral facies feature identification model, the vector components of the multispectral reflectance signal are decomposed according to the wavelength dimension, and different wavelength components are assigned corresponding contribution levels through spectral weighting coefficients, thus transforming vector information into calculation units compatible with scalar parameters such as mineral component mass fraction. Meanwhile, the formula establishes a parameter correlation bridge based on the inherent logic of geological processes. For example, in the rock layer permeability evolution prediction model, porosity (scalar) and pore connectivity path vector (vector) are coupled through pore connectivity factor. The direction information of the vector corresponds to the direction characteristics of the connectivity path. After factor transformation, it forms a collaborative calculation relationship with the numerical characteristics of the scalar parameter, ensuring the consistency of different types of parameters in physical meaning and calculation dimension.

[0064] Furthermore, the formula eliminates computational conflicts between different scalar and vector parameters through a hierarchical operational structure and dynamic correction mechanism, ensuring the scientific rigor and accuracy of the fusion calculation. Taking the coupled analytical model of the intelligent analytical calculation platform for geological components as an example, scalar parameters such as the effective detection data volume and data redundancy factor, and vector parameters such as the standardized value vector of detection parameters and the component feature parameter vector, are first normalized in dimension through their respective weight coefficients, so that all parameters are uniformly mapped to the suitable range of [0.1, 1.2]. Subsequently, the formula adopts a step-by-step operational logic, first performing internal aggregation on parameters of the same type, and then achieving cross-operation of different types of parameters through coupling analytical coefficients. For example, scalar parameters such as mineral component mass fraction and porosity are first weighted and summed, while multispectral feature vectors and permeability evolution vectors are vector synthesized. Finally, deep fusion of the two types of parameters is achieved through product or ratio operations. The error source adaptive correction algorithm further dynamically adjusts the calculation weights of different types of parameters through the error sensitivity coefficient, and calibrates the numerical deviation of scalar parameters and the directional deviation of vector parameters respectively, so as to ensure that all types of parameters maintain their own physical meaning in the formula and can work together to output accurate calculation results, thereby realizing the comprehensive quantitative analysis of multi-dimensional parameters of geological samples.

[0065] An experimental testing method and system for accurate multi-parameter detection of geological samples organically integrates rock stratum permeability evolution prediction, multispectral mineral facies identification, and intelligent geological component analysis. This breaks the isolation of single-parameter detection, enabling deep correlation between detection data from different dimensions and comprehensively presenting the integrated characteristics of geological samples. Simultaneously, relying on error source tracing and adaptive correction technology to construct a systematic deviation calibration path, it can automatically trace the parameter correlation source of errors and complete accurate calibration through a dynamic adjustment mechanism. This eliminates reliance on manual intervention, perfectly adapts to the dynamic changes of parameters under complex geological conditions, and solves the problems of one-sided detection results and uncontrollable deviations caused by the lack of collaborative mechanisms and effective correction methods in traditional methods.

[0066] This system is centered around six functional units, which are interconnected and communicate bidirectionally via high-speed data transmission links and a data bus, forming a closed-loop data processing system with an intelligent geological component analysis and calculation platform at its core. From geological sample parameter acquisition, multi-dimensional data processing, model calculation and feature recognition, to error source tracing and correction, intelligent coupling analysis, and finally to result output and storage, each unit has a precise functional allocation and a clear collaborative operation logic, achieving seamless integration throughout the entire process. This design not only ensures the continuity of the detection process and significantly improves the efficiency of data processing, but also ensures data security through an encrypted storage mechanism, completely solving the problems of disconnected connections, poor data transmission, and low processing efficiency in traditional systems.

[0067] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various equivalent changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. An experimental testing method for accurate detection of multiple parameters in geological samples, characterized in that, Includes the following steps: S1. A multi-parameter precision testing device for geological samples is used to collect basic data on mineral composition, pore structure parameters, particle size distribution, rock density, porosity, and permeability of the samples, while simultaneously recording sampling depth and stratigraphic lithology information. S2. The collected basic data is imported into an intelligent geological component analysis and calculation platform. The platform's built-in data classification module performs hierarchical division and feature extraction according to geological parameter types. S3. A rock stratum permeability evolution prediction model is used to extrapolate the evolution trend of the divided permeability-related parameters. A multispectral mineral facies feature identification model is combined to target and identify mineral component feature data. S4. An error-based adaptive correction algorithm is used to calibrate the model output results, tracing the source of errors in the associated geological parameters and making dynamic adjustments. S5, based on the calibrated feature data, performs multi-parameter coupled analysis of geological samples through the intelligent analysis and calculation platform for geological components, generating multi-dimensional parameter analysis results; S6, the analysis results are presented in a structured manner through the output module of the experimental testing device, forming a complete data chain for multi-parameter detection of geological samples.

2. The experimental testing method for accurate detection of multiple parameters in geological samples according to claim 1, characterized in that, The expression for the rock stratum permeability evolution prediction model is as follows: ,in, This is the predicted value of rock permeability. The permeability evolution coefficient, For the porosity of geological samples, Porosity influence index This represents the mass fraction of the mineral components. The weights of the components Pore ​​connectivity factor The average pore diameter, For aperture influence index, This is a fluid flow correction factor. It is a function of water saturation. For effective pressure, For the formation temperature, For fluid viscosity, The length is the sample length.

3. The experimental testing method for accurate detection of multiple parameters in geological samples according to claim 1, characterized in that, The expression for the multispectral mineral facies feature identification model is as follows: ,in, These are multispectral characteristic response values. For the first Spectral weighting coefficients of minerals, For the first minerals at wavelength Reflectivity at that location For the first Spectral broadening factor of the mineral, For spectral correction factor, The measured spectral signal, For spectral weighting functions, For the spectral detection wavelength range, This represents the number of mineral types.

4. The experimental testing method for accurate detection of multiple parameters in geological samples according to claim 1, characterized in that, The expression for the error source tracing adaptive correction algorithm is: ,in, This is the corrected error value. This is the initial error value. For the first The error of each parameter affects the weight. For the first Measured values ​​of several geological testing parameters For the first Predicted values ​​from a parameter model For the first The adjustment amount of each parameter, This is the error compensation coefficient. For the first The error sensitivity coefficient of each parameter, This represents the number of parameters involved in error correction.

5. The experimental testing method for accurate detection of multiple parameters in geological samples according to claim 1, characterized in that, The geological parameter coupling analytical model expression of the intelligent analytical calculation platform for geological components is as follows: ,in, The results are based on a comprehensive analysis of geological components. For the first The analytical weights of the components, For the first Characteristic parameter values ​​of the components, For the first Model fit coefficients for the components For the first Weighting factors for each detection parameter, For the first Standardized values ​​of each detection parameter These are the coupling analytical coefficients. To effectively detect the amount of data, For parameters related to component identification accuracy, For data redundancy factor, The number of component types, This represents the number of parameters to be detected.

6. The experimental testing method for accurate detection of multiple parameters in geological samples according to claim 1, characterized in that, The optimized model expression for the experimental test parameters of the geological sample multi-parameter precision detection is as follows: ,in, For the parameter optimization results, For the first Weighting coefficients for each experimental condition. For the first Measured values ​​of parameters under experimental conditions. For the first The effectiveness factor of each experimental condition. For the first Optimization weights for each parameter, For the first Measured values ​​of each parameter For the first Industry reference values ​​for each parameter. The number of experimental condition groups, This represents the total number of parameters detected.

7. The experimental testing method for accurate detection of multiple parameters in geological samples according to claim 1, characterized in that, S3 includes the following sub-steps: S31, selecting the porosity, mineral composition content, and particle size distribution parameters of geological samples as input variables for the rock stratum permeability evolution prediction model, and grouping the input variables according to geological stratification characteristics; S32, substituting the grouped variables into the rock stratum permeability evolution prediction model, and performing multiple rounds of evolution trend deduction through the model's built-in iterative calculation logic to generate a preliminary permeability prediction data sequence; S33, simultaneously extracting the multispectral reflectance signal, absorption signal, and scattering signal of the geological samples, removing environmental interference-related data from the signals, and retaining the mineral facies feature calibration signal; S34, inputting the calibration signal into the multispectral mineral facies feature recognition model, and using the model's feature matching mechanism to target and identify mineral types and content distribution, and outputting mineral facies feature analysis results.

8. The experimental testing method for accurate detection of multiple parameters in geological samples according to claim 1, characterized in that, S4 includes the following sub-steps: S41, extract the output data of the rock stratum permeability evolution prediction model and the multispectral mineral facies feature identification model, and establish a basic dataset for error analysis; S42, call the error source tracing adaptive correction algorithm to perform source tracing analysis on the deviation data in the dataset, and locate the geological parameter correlation nodes and the degree of influence of the error. S43, Based on the source tracing results, the algorithm automatically generates a dynamic correction factor sequence and performs hierarchical calibration on the deviation data according to the parameter association weight; S44, The calibrated data is compared and analyzed with the original output data to form a complete data comparison chain before and after error correction, providing corrected data support for subsequent analysis.

9. The experimental testing method for accurate detection of multiple parameters in geological samples according to claim 1, characterized in that, S5 includes the following sub-steps: S51, importing the error-corrected permeability prediction data and mineral facies analysis data into the intelligent geological component analysis and calculation platform, which automatically assigns them to the corresponding analysis modules according to data type; S52, each analysis module calls the preset component analysis rules to perform multi-dimensional coupled calculations on the mineral composition, pore structure parameters, and physical and mechanical property parameters of the geological sample; S53, during the calculation process, the sampling depth and stratigraphic lithology background information are correlated in real time, and the analysis results are adjusted to adapt to the geological scene; S54, the analysis results of each module are integrated to form a comprehensive multi-parameter analysis report of the geological sample, which includes parameter values, distribution characteristics, and correlation information.

10. An experimental testing system for precise detection of multiple parameters in geological samples, characterized in that, include: The system comprises a geological sample parameter acquisition unit, a multi-dimensional data preprocessing unit, a model calculation and feature recognition unit, an error tracing and correction unit, an intelligent analytical calculation unit, and a result output and storage unit. The geological sample parameter acquisition unit and the multi-dimensional data preprocessing unit are connected via a high-speed data transmission link. The basic geological sample parameter data acquired by the acquisition unit is transmitted in real-time to the preprocessing unit for classification and organization. The multi-dimensional data preprocessing unit communicates bidirectionally with the model calculation and feature recognition unit. The preprocessed parameter data is input into the model calculation unit, which incorporates a rock stratum permeability evolution prediction model and a multispectral mineral facies feature recognition model. After completing the prediction and recognition, the results are output and stored. The data is fed back to the preprocessing unit for verification; the model calculation and feature recognition unit is electrically connected to the error tracing and correction unit, and the output result is transmitted to the error correction unit, where deviation calibration is completed through the error tracing adaptive correction algorithm; the error tracing and correction unit is connected to the intelligent analysis and calculation unit via a data bus, and the calibrated data is imported into the geological component intelligent analysis and calculation platform for multi-parameter coupled analysis; the intelligent analysis and calculation unit is communicatively connected to the result output and storage unit, and the analysis result is presented through the output unit after structured processing, while the storage unit encrypts and stores the data throughout the process, and all units work together to perform accurate multi-parameter detection of geological samples.

Images