70 results about "Multiple linear regression analysis" patented technology

Disclosed in the present invention are a method and system for predicting a hematoma expansion event of a stroke patient. The method comprises: collecting patient data information, and performing data preprocessing; using an XG-Boost model to calculate the SHAP average value and the contribution degrees of different types of data, and extracting a feature quantity with the highest contribution degree from each type of data; performing multivariate linear regression analysis to obtain the weight of the effect of each type of data on hematoma expansion, and weighting all the feature quantities on the basis of the weight to obtain weighted feature quantities; using an extreme learning machine to predict a hematoma expansion probability; and using a northern goshawk optimization algorithm to search predicted values for the boundary of occurrence of a hematoma expansion event, and verifying the prediction accuracy. The present invention can accurately analyze and predict the expansion risk of hematoma after hemorrhagic stroke, which is crucial to early diagnosis and timely treatment.

The invention discloses a large-particle pneumatic conveying pipeline optimal wind speed calculation method based on digital twinning and machine learning, and the method comprises the steps: S1, carrying out the digital twinning modeling of a gas fluid region and large-volume particles, including an overall pipeline fluid model, fluid region grid division, a large-particle model, and a large-particle transportation volume fraction algorithm; s2, a gas-solid coupling numerical simulation experiment is carried out to calculate simulation data, and the optimal conveying wind speed for conveying spherical particles with different volumes and masses is obtained; and S3, fitting simulation data by adopting multiple linear regression analysis in machine learning, establishing a pipeline optimal wind speed calculation model, and determining a high-order term order of an independent variable. According to the method, digital twinborn modeling is conducted on the pneumatic conveying pipeline and the large-size particles, the optimal conveying wind speed for conveying the spherical particles of different sizes and masses is obtained through a gas-solid coupling numerical simulation experiment, and it is avoided that data are obtained through complex, tedious and even difficult-to-execute actual experiments.

Various embodiments include systems and methods to implement predictive scan engine runtime durations by a security platform to predict runtime durations associated with computing resources. Predictive scan engine runtime durations may be determined by training a prediction model using a multiple linear regression analysis. For example, the security platform may determine a prediction model using training data that associates runtime durations with configuration inputs associated with a security service that operates with respect to a computing resource. Based on the prediction model, the security platform may determine a runtime estimate for a security service run that is configured similarly to a previous security service run used to train the prediction model.

The invention discloses a reactive power rapid tracking optimization method and system for a wind power plant in the field of electric power systems. The method comprises the following steps: constructing a power data set comprising a power change rate, the power of the current time period and the actual power value of the next time period by collecting ultra-short-term power data of a wind turbine generator; performing two-dimensional segmentation on the data according to the power size and the change rate, fitting a power predicted value of a next time period based on multiple linear regression analysis, and calculating a confidence interval of the power predicted value; dynamically correcting a voltage margin by combining an active-voltage sensitivity matrix obtained by Jacobian matrix inversion and a power confidence interval; and inputting the actually measured power of each wind turbine generator into the trained SAC decision model to obtain an optimized reactive equipment control strategy, converting into a Markov decision process through an SAC reinforcement learning algorithm to carry out offline training and online rolling optimization to generate a reactor and converter group control strategy, and updating an iteration model. According to the invention, second-level reactive dynamic regulation is realized, the voltage stability is improved, and the network loss is reduced.

The invention relates to the technical field of electric power, in particular to an electricity price fluctuation quantification method, device, equipment and medium based on regression analysis, and the method comprises the steps: taking electric power price fluctuation in peak load of electric power as a dependent variable, and taking new energy power generation, thermal power generation, electric power demand, generating capacity and capacity electricity price as independent variables; establishing a multiple linear regression model; verifying whether the independent variable and the dependent variable have a linear relationship or not, preliminarily carrying out multiple linear regression analysis, finding an optimal regression coefficient by minimizing a residual sum of squares, and carrying out multiple linear problem judgment; a ridge regression analysis method is adopted, a regularization item is added into a loss function to limit the size of a regression coefficient, overfitting of the model is reduced, and a ridge function is confirmed through cross validation; performing overall significance test and regression coefficient significance test on the multiple linear regression model, and analyzing the fitting degree; and performing quantitative analysis on electricity price fluctuation by using the fitted multiple linear regression model.

The invention relates to the field of food with dysphagia, in particular to a method for constructing a swallowing characteristic evaluation model of food with dysphagia. Comprising the following steps: firstly, determining swallowing characteristic indexes such as oral transfer time, epiglottis time, tensile length, oropharyngeal residual quantity, swallowing grade, residual volume of needle tubing, sensory swallowing evaluation score and the like of food with dysphagia; the physical property indexes such as yield stress, consistency coefficient, flow index, zero shear viscosity, apparent viscosity, friction coefficient, density and surface tension in rheological properties are subjected to correlation analysis on the swallowing property indexes and the physical property indexes, and then multiple linear regression analysis is carried out; according to the method, a physical characteristic index-based swallowing characteristic evaluation model is established, a predicted value obtained by the evaluation model is compared with a measured value for verification, and the model has very high fitting precision and can better describe the swallowing characteristics of food with dysphagia.

The invention discloses an oil storage and transportation intelligent management system based on the Internet, belongs to the technical field of energy storage and transportation management, and aims to solve the problem that an existing oil storage and transportation system cannot predict inventory use time. According to the invention, through integration of the business management module, the vehicle management module, the metering management module, the data analysis and prediction module and the user management and report module, intelligent management of the whole oil storage and transportation process is realized; through combination of an ARIMA model and high-order statistic calculation of the oil price fluctuation analysis unit, multiple linear regression analysis of the oil consumption increase prediction unit and grey prediction and particle swarm optimization algorithms of the remaining oil prediction unit, the remaining oil usage time and the change trend can be accurately predicted, the inventory management level is improved, and the economic benefit is improved. The problem that an existing oil product storage and transportation system cannot predict market demands and inventory use time is effectively solved, the oil product storage and transportation management and control capability of enterprises is enhanced, the operation efficiency is improved, and the cost is reduced.

The application discloses a kind of based on cylindrical surface variable pose spray coating thickness prediction modeling method, it is related to signal processing technical field.Step one: establish three-dimensional model of spray gun cap and control domain based on cylindrical surface static spraying, carry out numerical simulation experiment and collect numerical simulation experimental data;Step two: data analysis, analyze the coating film thickness law under the variable pose spraying of different cylindrical diameter, obtain the adjustable range of variable pose spray gun;Step three: establish spray gun mathematical model, combined with the adjustable range of spray gun pose, carry out spraying experiment;Step four: collect experimental coating data, according to variable pose spray gun mathematical model, using Trust-Region optimization algorithm is fitted to experimental data, obtains cylindrical surface variable pose model to be identified parameter, carries out multiple linear regression analysis, obtains cylindrical surface variable pose spraying coating film thickness prediction model.

The invention discloses a sensitivity analysis method and system for influence factors of moisture redistribution of an aeration zone in a subsidence area, and relates to the technical field of protection and utilization of water resources in ecologically fragile mining areas in northwest. The method comprises the following steps: carrying out a soil-water characteristic curve test under a disturbance stress path in a coal mining collapse subsidence area; a VG soil-water characteristic curve model suitable for the coal mining collapse subsidence area is obtained; determining the moisture redistribution condition of the vadose zone of the settlement area under coal mining collapse disturbance under each working condition, wherein the moisture redistribution condition is represented by saturation; based on a range analysis method and a multiple linear regression analysis method, sensitivity analysis is carried out on all main influence factors influencing moisture redistribution of the aeration zone of the subsidence zone under coal mining collapse disturbance, and sensitivity of all the main influence factors is ranked. According to the method, the accurate water redistribution rule of the aeration zone in the coal mining collapse subsidence area can be obtained through calculation, the sensitivity of the influence factors of the water redistribution of the aeration zone is reasonably analyzed, and an important theoretical basis is provided for rapid repair of the coal mining collapse subsidence area.

The application relates to the technical field of data compression storage, and provides a high-throughput genome sequencing quality score data parallel compression method.The method comprises the following steps: segmenting an original gene sequencing file; performing random sampling and k-mer analysis on the sampling data to obtain statistical characteristic information and establish a parallel sequence partition model for binary classification; splicing two partition files obtained through binary classification according to splicing parameters; predicting the to-be-compressed file through a multivariate linear regression analysis prediction method to obtain compression rate gain and establish a parallel four-level run prediction mapping model for data redundancy elimination; and performing context modeling on two redundancy-eliminated subfiles through a multi-core processor cluster, and performing cascade compression in combination with arithmetic coding to obtain a final compressed file.Under the premise of significantly reducing quality score data compression time and peak memory overhead, the application also improves the quality score data compression rate, reduces the size of to-be-compressed storage files, and saves the construction cost of basic storage facilities.

From the perspective of mathematical models, the present invention uses a method combining multiple linear regression analysis (MLR) and response surface optimization (RSM), and realizes the mitigation of MBR membrane pollution and promotes the further application of DAA in MBR systems by applying D-amino acids (DAA) to the intelligent regulation and optimization prediction of operating condition parameters in the MBR sewage treatment process, which can provide a new and effective control strategy for solving the problem of MBR membrane biofouling. The present invention performs fitting optimization analysis on the relationship between operating conditions and membrane fouling rate in DAA-MBR, quantitatively evaluates the degree of influence of each operating condition on the membrane fouling rate, and determines the optimal combination process parameters of the operating conditions. At the same time, the numerical values ​​and trends of DAA-MBR membrane fouling rates under operating conditions of various levels within and outside the test range are effectively predicted. The present invention can not only achieve the mitigation of DAA-MBR membrane pollution through intelligent regulation and optimization of operating conditions, and promote the application of DAA in MBR, but also has simple calculation and strong practicality, and can provide guidance for process optimization in membrane biofouling control.

The present invention discloses a sand body seismic intelligent prediction method based on RF-GAM, comprising the following steps: S1: collecting drilling data and seismic data of a target block, extracting sand-to-formation ratio information from the drilling data, and extracting seismic attribute information from the seismic data; S2: analyzing the correlation between the two types of information and screening relevant factors of the sand-to-formation ratio; S3: using a multivariate linear regression analysis method to predict sand bodies and obtain preliminary sand body prediction results; S4: based on the preliminary sand body prediction results, screening locations where the relevant factors match the sand-to-formation ratio, and using the seismic attribute information at these locations as influencing factors of the sand-to-formation ratio; S5: using a random forest to screen and obtain important influencing factors; S6: using a generalized additive model to perform attribute fusion, and visualizing the results of the attribute fusion to obtain the final sand body prediction results. The present invention can predict more accurate sand body prediction results, providing technical support for oil and gas field exploration and development.

The present application belongs to the field of oil and gas field development, and particularly relates to a method for characterizing the characteristics of gravel around a horizontal well in a conglomerate reservoir. The method comprises the following steps: (1) using a conglomerate reservoir gravel characteristic identification and analysis software to process FMI imaging logging images and extract gravel parameters; (2) using a multiple linear regression analysis method to carry out sensitivity analysis of the gravel parameters and logging data, and to determine the statistical relationship between the gravel parameters and logging curves; and (3) establishing a model of the logging curves and the gravel parameters, and substituting the logging curve data to measure the gravel characteristics. The present application solves the problem of characterizing conglomerate reservoir gravel, and for the first time realizes the use of conventional logging curves to characterize the gravel parameters around a horizontal well section, thereby providing an optimization direction for multi-cluster volume fracturing technology in a horizontal well section.

This invention relates to the field of cement building materials technology, specifically disclosing a method for improving the strength of silicate clinker based on mineral and crystal composition analysis. The method involves collecting 3-day and 28-day compressive strength test data of silicate clinker and quantitatively analyzing the mineral and crystal composition data using XRD. A mineral composition and strength zoning statistical method is employed to obtain appropriate C3S or C2S content to maintain a relatively good overall level of 3-day and 28-day compressive strength of the clinker. Then, a stepwise multiple linear regression analysis is used to establish the relationship between the 3-day and 28-day compressive strength of the clinker, clinker liter weight, f-CaO, the content of other chemical components, and the mineral composition and crystal content of the clinker. Specific analytical methods are used to determine optimization measures, further optimizing and improving the clinker strength. Using the above method, the 3-day and 28-day compressive strength of silicate clinker can be improved simultaneously.

The invention discloses a plate chemical component optimization method which comprises the following steps: S1, utilizing multiple linear regression analysis to obtain chemical elements which have small influence on yield strength and tensile strength of steel; s2, constructing a BP neural network model by taking the chemical elements with small influence as input variables and taking the yield strength and tensile strength of the steel as output variables; s3, the chemical elements with small influences serve as input variables, the steel smelting cost serves as an output variable, and a smelting cost mathematical model is constructed; s4, the smelting cost mathematical model is utilized, a genetic algorithm is constructed, and automatic optimization of the chemical components of all the elements is achieved with the purpose of smelting cost minimization. According to the method provided by the invention, the chemical components are optimized based on the existing rolling data, additional smelting is not needed, the optimization cost is relatively low, the quantity of samples capable of being processed is large, the result is more accurate and reliable, and the optimization time is greatly shortened.

This invention discloses a method, model, and application for predicting the available cadmium content in soil, relating to the field of soil nutrient prediction technology. The method includes the following steps: (1) collecting multiple farmland soil samples and measuring key nutrient indicators; (2) recording, statistically analyzing, and plotting the measured data; (3) performing correlation analysis on all statistical data to determine indicators significantly correlated with available cadmium; (4) establishing a prediction model for available cadmium in soil using multiple linear regression analysis; and calculating the available cadmium content in the soil based on the prediction model. The prediction model and method provided by this invention are simple, have few variable parameters, and high prediction accuracy, effectively predicting the available cadmium content in soil and providing a reference for the scientific management of cadmium-polluted farmland.

The application is suitable for the technical field of NOx concentration prediction, and provides an intelligent ammonia injection denitration prediction system based on a time sequence neural network model, which comprises the following steps: S1, data acquisition; S2, data processing, the importance of the data is preliminarily calculated through simple multiple linear regression analysis; the application solves the problems that the current denitration ammonia injection system adopts fixed ammonia distribution, cannot adapt to the variability of denitration inlet flue gas NOx under the condition of unit flexibility peak shaving, and has problems such as excessive ammonia injection and insufficient ammonia injection amount, under the condition of meeting the unit outlet emission, excessive ammonia injection will cause the increase of consumables and the problems such as the blockage of the boiler air preheater, and too little ammonia injection amount cannot meet the NOx emission standard, the accuracy of improving the inlet NOx concentration is achieved, the average error of the predicted value and the reference value of the inlet NOx concentration is reduced, and the power plant is effectively helped to control the ammonia injection amount in real time according to the prediction result, so as to realize intelligent quantitative ammonia injection.

The invention discloses a sugarcane variety lodging resistance identification method which comprises the following steps: collecting stem base diameter data, stem middle diameter data, stem height data, stem hardness data, root system development degree data and leaf size and weight data; and establishing a lodging resistance evaluation model based on multiple linear regression analysis according to the stem base diameter data, the stem middle diameter data, the stem height data, the stem hardness data, the root system development degree data and the leaf size and weight data. According to the method, a plurality of key indexes influencing the lodging-resistant capability of the sugarcane plants are comprehensively considered, the key indexes comprise the morphological index, the mechanical index, the root system index and the like, and compared with a traditional identification method with a single index or few indexes, the lodging-resistant characteristics of the sugarcane plants can be more comprehensively reflected. By constructing the lodging-resistant capability evaluation model, the lodging-resistant capability evaluation result can be quickly obtained only by substituting the measured data into the model, so that the identification efficiency is greatly improved.

This application provides a method, apparatus, and device for obtaining bound water saturation. The method includes: acquiring reservoir parameters of a rock sample to be tested, and calculating the bound water saturation of the rock sample based on the reservoir parameters and a bound water saturation formula. The bound water saturation formula is pre-established based on the bound water saturation of multiple first rock samples and reservoir parameters, through multiple linear regression analysis. The bound water saturation of the multiple first rock samples is calculated based on the cumulative permeability contribution rate corresponding to the category to which the first rock sample belongs under porosity and pore structure index. Different cumulative permeability contribution rates are used to calculate the bound water saturation of different categories of rock samples, thereby ensuring the accuracy of the bound water saturation of the multiple first rock samples and the established bound water saturation formula. Therefore, the accurate bound water saturation of the rock sample to be tested can be obtained based on this formula.

The invention discloses a preparation method of a radix astragali extracting solution with high antioxidant activity and the extracting solution, and aims to solve the problems of low extraction rate of active substances and inaccurate detection of antioxidant activity in the prior art. According to the method, five factors including ethanol content, extracting solution multiple and the like are taken as key variables, U10 * (108) uniform test design is adopted, the DPPH free radical scavenging rate is accurately determined by combining an electron paramagnetic resonance technology, and the contents of astragaloside, general flavone and polysaccharide are synchronously detected. A quantitative model is established through multivariate linear regression analysis, and the optimal process parameters are determined: the ethanol content is 80%, the extracting solution multiple is 4, the temperature is 85 DEG C, the time is 1.5 h, and the extraction time is 1 time. The DPPH free radical scavenging rate of the extracting solution prepared through the technology is larger than or equal to 92.75%, polysaccharide is larger than or equal to 12520 mg / L, total flavone is larger than or equal to 323.77 mg / L, astragaloside is larger than or equal to 257 mg / L, synergistic efficient extraction of multiple components is achieved, and the extracting solution is suitable for industrial production.

The invention provides a construction method of a precise medication model for mycophenolic acid drugs, a prediction device and electronic equipment. Belongs to the cross technical field of precision medicine and pharmacology. The construction method of the precise medication model for the mycophenolic acid drugs comprises the following steps: S1, acquiring clinical data of a patient; s2, collecting blood samples at different time points after the patient takes the medicine, and detecting the blood concentration of the mycophenolic acid medicine; s3, the non-atrioventricular model is used as a basic model, multiple linear regression analysis is carried out, a precise medication model for the mycophenolic acid drugs is established, and a mathematical model of the precise medication model for the mycophenolic acid drugs is shown as a formula (1). By the adoption of the accurate medication model for the mycophenolic acid drugs, the blood sampling frequency for monitoring the blood concentration of the mycophenolic acid drugs can be reduced, the workload of medical workers is reduced, the pain of patients is relieved, and the compliance of the patients is improved.

The invention relates to the technical field of metallogenic research of wollastonite ore, in particular to a method and a system for constructing a metallogenic mode of wollastonite ore based on space-time constraint. The method comprises the following steps: acquiring multi-source basic data in a target area by taking a contact zone of an invading body and carbonate rock and a peripheral buffer range as the target area; extracting an initial geographic feature data set from the multi-source basic data; the method comprises the following steps: performing time sequence stability analysis on observation characteristics of a mineral marginal zone corresponding to wollastonite contact excursion mineralization, and determining a target time scale and a spatial data block in combination with spatial continuity constraints of wollastonite contact excursion mineralization; based on the target time scale and the spatial data block, screening a space-time coupling feature data set; and performing multiple linear regression analysis on the time-space coupling characteristic data set, screening target characteristic parameters related to the wollastonite mineralization process, and constructing a wollastonite mineralization mode based on the target characteristic parameters. According to the method, the geological credibility of the metallogenic characteristics can be improved.

The invention provides a method and a device for evaluating the performance consistency of a fuel cell, relates to the technical field of fuel cells, and solves the technical problem that the prior art is difficult to meet the requirement of the industry for comprehensively and accurately evaluating the performance of the fuel cell. The method comprises the following steps: acquiring measurement parameters of each fuel cell in an operation process through a sensor; the measurement parameters comprise battery performance measurement parameters and working condition environment parameters; analyzing the measurement parameters by adopting multiple linear regression analysis, and establishing a quantitative relation model corresponding to each fuel cell; the quantitative relation model is used for representing the incidence relation between the battery performance measurement parameters and the working condition environment parameters; and for each fuel cell, carrying out performance consistency evaluation on the cell performance prediction parameters obtained by calculation under the working condition environment parameters of the same working condition based on the corresponding quantitative relation model to obtain a performance consistency evaluation result. The method is used in the fuel cell evaluation process.

The present application is suitable for the field of mineral exploration, and provides a lithium geochemical anomaly identification method and system for a lithology complex area, which comprises the following steps: obtaining geochemical data of the area, and preprocessing the geochemical data of the area; determining PLSR independent variable indexes according to the preprocessed geochemical data; constructing a PLSR regression model according to the PLSR independent variable indexes; determining lithium geochemical background values of each sample point in the area according to the PLSR regression model; and identifying lithium geochemical anomalies in the area according to the predicted upper limit of the lithium geochemical background values. The present application uses PLSR to construct a regression model between lithium and lithology indicating elements, and then can determine the lithium geochemical background values of each sample point, effectively solves the multicollinearity problem in lithium multiple linear regression analysis, improves the calculation accuracy of the lithium geochemical background values of each sample point in the lithology complex area, and lays a solid foundation for lithium geochemical anomaly identification.

The invention discloses a color matching perceptual prediction method based on CNCSCOLOR, and the method specifically comprises the following steps: designing a product through employing colors in CNCSCOLOR, and converting the design colors of the product into a Sudoku color matching graph; designing m reference Sudoku color matching schemes, and selecting 18 perceptual adjective pairs; scoring each perceptual adjective pair of each reference Sudoku color matching scheme by adopting questionnaire scoring, and performing statistical analysis on the perceptual adjective pair by adopting basic mean value analysis to obtain a perceptual evaluation mean value; defining a color attribute value of the Sudoku color matching scheme based on CNCSCOLOR; performing multiple linear regression analysis according to the data of the perceptual evaluation mean value and the color attribute value to obtain a series regression equation of 18 perceptual adjective pairs; and S3, calculating the numerical value of each color attribute according to the Sudoku color matching scheme obtained in the S1, substituting the numerical value of each color attribute into the corresponding perceptual adjective pair regression equation, and predicting the corresponding perceptual degree of the product color design. According to the invention, the problem of inconsistent color matching perceptual results in the prior art is solved.

The invention provides a high-ground-temperature tunnel influence factor determination method and system, and belongs to the technical field of tunnel construction management, and the method comprises the steps: S1, obtaining a maximum lining temperature value and a plurality of influence parameters; s2, establishing a multiple linear regression analysis model based on the maximum value of the lining temperature and a plurality of influence parameters; s3, calculating a standardization coefficient Beta value of the multiple linear regression analysis model by utilizing statistical analysis software; and S4, determining influence factors of the high-ground-temperature tunnel according to the standardization coefficient Beta value. According to the method, the multiple linear regression model is applied to temperature field prediction of the tunnel lining structure, influence factors with remarkable influences can be identified, on one hand, the prediction accuracy of the high-ground-temperature tunnel is improved, on the other hand, valuable reference can be provided for manual intervention cooling, and the method is suitable for popularization and application. And construction of the high-ground-temperature tunnel and selection of cooling measures are facilitated.

The invention provides a fitting function boundary-based three-dimensional crustal stress field inversion method, which belongs to the technical field of geotechnical engineering, and comprises the following steps: establishing a three-dimensional finite element model, and extracting lateral boundary coordinates for polynomial fitting to obtain a boundary elevation fitting function; calculating a lateral pressure value of each boundary point according to the fitting function; six independent working condition loads are applied to the model, and finite element calculation is carried out to obtain stress components of all measuring points; performing multiple linear regression analysis on the stress component by taking the actually measured stress as a target value to obtain a working condition coefficient; and performing weighted stacking on each working condition stress field to obtain an initial ground stress field after inversion. According to the method, by precisely fitting the lateral boundary terrain, the problem that boundary conditions are not accurately applied in a traditional method is solved, and the precision and reliability of ground stress inversion under the complex terrain condition are remarkably improved.

The application relates to a sidewalk tree screening method based on a forest ecological index, a regional environment model is established by using a DEM technology, tree body data of different types of sidewalk trees are measured and recorded, a plurality of tree body data sub-models are established, and simulation calculation is sequentially performed on the tree body data sub-models, a simulation result is analyzed by using a stepwise multiple linear regression, a regional environment model and a sidewalk tree type model are fused, a simulation model is established, the regional environment model is trained by using the tree body data sub-models, simulation model characteristics are obtained, a heat balance coefficient of the simulation model and a tree species growth characteristic value are calculated, a trend curve is estimated, the simulation model trend curve is compared with a reference target model trend curve, and high-quality plants suitable for the target region are determined. When the simulation model is constructed, the heat balance coefficient in the target region range and the growth characteristic value trend of the plants in the target region are considered, so that more stable and longer forest ecological effects can be achieved in the target region.

The present invention discloses a sensitivity analysis method and system for factors affecting the redistribution of moisture in the vadose zone of a subsidence area, and relates to the technical field of water resource protection and utilization in ecologically fragile mining areas in Northwest China. The method comprises the steps of: conducting a soil-water characteristic curve test under a disturbance stress path in a coal mining subsidence subsidence area; obtaining a VG soil-water characteristic curve model suitable for the coal mining subsidence subsidence area; determining the redistribution of moisture in the vadose zone of the subsidence area under various working conditions characterized by saturation; performing a sensitivity analysis on the main influencing factors affecting the redistribution of moisture in the vadose zone of the subsidence area under coal mining subsidence disturbance based on the range analysis method and the multivariate linear regression analysis method, and ranking the sensitivity of the main influencing factors. The present invention can calculate the accurate law of moisture redistribution in the vadose zone of a coal mining subsidence subsidence area, and rationally analyze the sensitivity of factors affecting moisture redistribution in the vadose zone, thus providing an important theoretical basis for achieving rapid repair of coal mining subsidence subsidence areas.

The invention discloses a cauliflower flower ball color accurate quantification and grading method, and belongs to the technical field of agricultural informatization and agricultural product quality detection. The method comprises the following steps: selecting a cauliflower sample; carrying out image acquisition on the cauliflower flower balls by using handheld multispectral imaging equipment; selecting a to-be-detected area on the surface of the ball-flower through an ROI extraction technology, and calculating a spectral reflectivity mean value; processing the spectral data by using principal component analysis and multiple linear regression analysis, establishing a membership function and calculating a quantitative model formula; carrying out multi-modal fusion on the multispectral image and the spectral data by adopting a convolutional neural network, and carrying out color classification and grading prediction; and training and verifying the convolutional neural network model. According to the method, through combination of multispectral imaging, machine learning and deep learning technologies, a set of broccoli ball-flower color analysis process is established: firstly, high-dimensional spectral data is obtained through multispectral imaging, then, colors are accurately quantified through a machine learning algorithm, and finally, color grading is realized through a deep learning model.