412 results about "Optimality model" patented technology

The invention discloses an equipment temperature adjusting method fusing a long short-term memory network, and particularly relates to the technical field of temperature control, which comprises the following steps: determining the deployment position of a sensor through thermal simulation, collecting multi-source heterogeneous data, dynamically adjusting the sampling frequency in combination with the temperature and the load current change rate, and adjusting the temperature of the sensor; after data preprocessing, an attention mechanism enhanced LSTM prediction model is constructed, a time sequence sample data set is divided according to equipment thermal response characteristics, training is carried out, and an optimal model is obtained through early stop mechanism optimization; predictive feedback double-closed-loop regulation and control is achieved based on the optimal model, outer loop PI control is combined with an integral separation mechanism to generate a basic control quantity, an inner loop outputs a correction quantity through fuzzification, reasoning and defuzzification, an actuator is driven after superposition, and safety linkage is triggered synchronously; constructing an incremental data buffer pool to screen effective samples, and adaptively updating model parameters by adopting a layered fine tuning strategy; the temperature regulation and control precision and the long-term self-adaptive capability are obviously improved, and the over-temperature risk of equipment is reduced.

The invention discloses a waterworks double-coagulant accurate prediction method based on automatic machine learning, and the method comprises the steps: firstly obtaining the water quality data of a waterworks, the agent dosage data of two coagulants, and other basic data, and carrying out the preprocessing of the data; an automatic machine learning method is adopted, and a tap water double-coagulant dosage prediction model under the production condition is built; the model is optimized according to an actual effluent target value, and accurate prediction of the dosage of the two coagulants is realized by using the optimal model. According to the invention, accurate calculation and intelligent regulation and control of the dosage of the coagulant in the waterworks are realized, and the predictive capability of the double coagulant is particularly emphasized, so that the innovation point ensures that the effluent quality reaches the drinking water standard, meanwhile, the dependence on manpower is remarkably reduced, the operation cost and the medicament cost of the waterworks are saved, and the economic benefit is increased. And double improvement of economic benefits and environmental benefits is realized.

The invention discloses a power prediction method and system considering net load power and meteorological factors, and the method comprises the steps: obtaining historical net load data and corresponding meteorological data in a preset time period, and carrying out the preprocessing, and obtaining net load time sequence data and meteorological time sequence data; based on the net load time sequence data, carrying out stability test and differential processing to obtain stable net load time sequence data; establishing an optimal SARIMA model based on the stationary net load time sequence data; extracting trend features and seasonal features based on the optimal SARIMA model; forming a training set based on the meteorological time sequence data, the trend features and the seasonal features; constructing a power prediction model, and training based on the training set and the loss function to obtain a trained power prediction model; and obtaining future meteorological time series data, historical trend characteristics and historical seasonal characteristics of the target time period, and inputting the data, the historical trend characteristics and the historical seasonal characteristics into the trained power prediction model to obtain a net load power prediction value. And the accuracy and the reliability of power prediction are improved.

The invention belongs to the technical field of gas storages, and particularly relates to an experimental method and device for evaluating fault stability under injection-production alternating stress of a gas storage. The method comprises the following steps: acquiring reservoir information of a to-be-detected gas storage; making a three-dimensional model according to the reservoir information, and configuring model parameters according to formation water and natural gas initially injected into the three-dimensional model; an injection-production pipe is inserted into the three-dimensional model, the multi-cycle gas injection-production process is simulated, and fault changes in the three-dimensional model are monitored; and optimizing model parameters of the three-dimensional model according to the fault change condition, and determining optimal model parameters. A fault with any dip angle can be simulated, the experimental model comprises a whole geologic body simulating a gas storage, surrounding rocks including a cover layer and a bottom supporting layer and wrapping the periphery of a reservoir body, the reservoir is disconnected by the fault, the contact relation of the two reservoirs can be designed according to the actual condition of the stratum, and an injection-production well is designed in the model. The injection-production well simulates high-speed injection-production of the gas storage.

The invention discloses an insulator defect detection method based on improved YOLOv11n. The insulator defect detection method specifically comprises the following steps of: detecting defects of an insulator; the method comprises the following steps of: 1, acquiring an insulator defect image data set, dividing the data set into a training set, a verification set and a test set, and preprocessing; 2, in the YOLOv11n network, an SCConv module is adopted to replace a C3k2 module, an SPPCSPC module is adopted to replace an SPPF module, an SBA module is adopted to replace an Upsample module, and a new LXMstrip Pool module is adopted, so that an improved YOLOv11n model is obtained; 3, training the improved detection model by adopting the training set and the verification set, and storing the optimal trained model; and 4, carrying out precision test on the optimal model by adopting the test set, and obtaining a final insulator defect detection model when the precision requirement is met. Compared with the prior art, the insulator defect detection method based on the improved YOLOv11n disclosed by the invention has the advantages that the detection precision of the insulator defect can be effectively improved, and the problems of missing detection and false detection of the defect during actual detection are avoided.

The present disclosure provides a system and a method for adaptively identifying an optimal model to select a route to a location, the method comprising: A method for adaptively identifying an optimal model to select a route to a location, comprising: providing one or more first models based on a routing characteristic associated with the location; retrieving one or more first parameters associated with the routing characteristic to determine an effectiveness of each of the one or more first models in minimizing a route expense parameter; and selecting the optimal model from the one or more first models based on the effectiveness.

The invention belongs to the technical field of computer application, and relates to an operation inspection equipment fault detection method and system based on an improved deep learning model, and the method comprises the steps: obtaining original data, employing EEMD to decompose the original data for feature enhancement, obtaining a decomposition signal, carrying out the noise reduction of the decomposition signal, and obtaining a feature signal after noise reduction; according to the feature signals after noise reduction, a deep learning model is constructed based on Resnet and a dynamic Transform encoder, and the prediction probability of each fault category is output; a ZOA optimization algorithm is used to optimize hyper-parameters of a deep learning model, an optimization model is obtained, the performance of the optimization model is evaluated, an optimal model is obtained, and the prediction probability of each fault category is output, so that false report and missing report of faults can be effectively reduced in a fault detection task, potential safety hazards caused by the fact that the faults are not found in time are reduced, and the fault detection efficiency is improved. Therefore, the stability and reliability of the power system are improved.

The invention discloses a grouting parameter intelligent feedback method based on rock mass groutability evaluation, which comprises the following steps: collecting geological condition data, rock mass quality data, field test data and grouting process data, and constructing a rock mass groutability grading data set; an SMOTE algorithm is adopted to process data imbalance, input indexes are screened through Pearson correlation analysis, and data are normalized through deviation standardization; an XGBoost classification model is constructed, hyper-parameters are optimized through grid search, the model is trained through K-fold cross validation, and the rock mass groutability grade is evaluated; constructing an XGBoost regression model by taking a rock mass groutability grade, grouting construction data and monitoring data as input, and predicting the maximum value and the minimum value of grouting pressure and slurry density by using an optimal model; and generating a grouting parameter interval according to the predicted maximum value and minimum value, and dynamically feeding back to the grouting equipment to regulate and control parameters. According to the method, scientificity and accuracy of rock mass groutability evaluation and grouting parameter regulation and control can be effectively improved.

The invention discloses a distributed phase modifier locating and sizing method considering frequency stability improvement, and belongs to the field of power system stability and control. Comprising the following steps: performing quantitative evaluation on the inertia supporting capacity of a power grid by node inertia, analyzing the influence of access of the phase modifier on the frequency of the power grid, and performing a distributed phase modifier locating and sizing configuration strategy considering the frequency stability constraint. According to the method, aiming at the frequency stability problem of a new energy sending end power grid caused by a large disturbance fault of the system, the frequency supporting capacity of the system is improved to the maximum extent by solving the optimal model with the minimum configuration capacity as an optimization target.

The invention discloses a flood season dam project stability prediction method based on multi-model joint decision making. The method comprises the following steps of obtaining parameters of a dam to be predicted and setting a judgment index, establishing a numerical model according to the parameters of the dam to be predicted, assigning values to the parameters of the numerical model according to the judgment index, and solving a safety coefficient of the numerical model of the dam. Three single machine learning models are established, an improved grey wolf algorithm is introduced for optimization, and an optimal model is obtained through judgment indexes and corresponding safety coefficient training models; performing decision-level fusion on the optimal model through a D-S evidence theory to construct a prediction model; and solving the safety coefficient of the to-be-predicted dam through the prediction model, and comparing the safety coefficient with the allowable safety coefficient of the to-be-predicted dam to complete dam stability prediction. According to the method, the multiple single machine learning models are optimized and fused to construct the prediction model, the advantages of different models can be effectively fused, and the precision and reliability of dam stability prediction are greatly improved.

The invention discloses a data classification method and system based on a deep multi-path attention adaptive graph convolutional network, and relates to the technical field of medical image processing. Rs-fMRI data is acquired and preprocessed to obtain a BOLD sequence, a function connection feature vector is constructed and input into a DMAGCN model, and finally an optimal model is acquired through five-fold cross validation for classification. The data quality is guaranteed through data preprocessing, and a foundation is laid for accurate analysis. Functional connection feature vectors effectively represent data, after a model is input, a Transform backbone network and an MLP branch network can extract multi-source domain features, non-imaging data are utilized in combination with a graph network, the model can learn rich features, and generalization and adaptability are enhanced. According to the method, the classification accuracy is improved, the performance is excellent when uncertain data classification such as autism spectrum disorder is processed, related disease research is promoted, and an efficient and reliable method is provided for medical data classification.

The invention discloses a deep learning and numerical mode seamless fusion-based short temporary rainfall forecasting method. The method comprises the steps of constructing a short temporary rainfall initial forecasting model based on a Vison Transform network, and constructing a deep learning and numerical mode seamless fusion-based short temporary rainfall correction forecasting model based on an improved U-Net network; and collecting various meteorological data in real time, preprocessing the data, inputting the preprocessed data into the trained short-temporary rainfall forecast optimal model to obtain 0-6h short-temporary rainfall forecast, fusing the short-temporary rainfall forecast with 2-6h short-temporary rainfall forecast in a real-time regional numerical mode, inputting the trained short-temporary rainfall optimal correction forecast model, and obtaining 0-6h seamless fused short-temporary rainfall forecast. The method solves the problems that in the prior art, deep learning extrapolation and numerical mode short and temporary rainfall fusion forecasting is discontinuous in time, inconsistent in spatial position and low in forecasting accuracy.

The invention discloses an IGBT residual life prediction method based on variational Bayes and a mixed Wiener process, and belongs to the technical field of IGBT residual life prediction, and the method comprises the following steps: S1, giving out the definition of the mixed Wiener process, and building a degradation model to describe the degradation track of an IGBT; s2, performing off-line parameter estimation based on a variational Bayesian algorithm by using a prior sample; s3, selecting an optimal model in the degradation models according to an automatic correlation determination method; s4, selecting a prior sample which is most similar to the test sample at the current moment; s5, updating the mean value and variance of the weight vector of the test sample on line; and S6, solving a probability density function of the residual life of the mixed Wiener process in the sense of the first arrival time, and estimating the residual life value of the IGBT at each moment. According to the IGBT residual life prediction method based on the variational Bayes and the mixed Wiener process, the degradation mode can be automatically determined, the fitting precision of an IGBT degradation track is improved, the requirement for specialty is reduced, and the universality of the model is improved.

The embodiment of the invention provides an urban green land community ecosystem regulation service optimization factor identification method and device based on a fusion algorithm and electronic equipment, and belongs to the technical field of ecological data processing, and the method comprises the steps: collecting a plant community, an elevation model and meteorological monitoring data to form a basic data set; uniformly quantifying the data and evaluating the ecological service in combination with the measurement and calculation model to form a standardized data set; inputting the features into a plurality of machine learning models, and screening out a key feature set through operations such as guided aggregation and the like; constructing an IOFESRM-LMEM model, outputting an optimal model through a series of operations, and analyzing key factors; and finally, outputting an optimization result, a key factor and an evaluation result by using a multi-dimensional index evaluation model. According to the invention, data support is provided for improving the ecological function of the urban green land, formulating ecological planning and optimizing urban management.

The invention provides a coast erosion susceptibility interpretable evaluation method based on a random forest, and the method comprises the steps: selecting disaster-pregnancy factors, and obtaining disaster-pregnancy factor data; coastline data are extracted, coast erosion areas are divided based on coastline changes, and coast erosion area distribution conditions are obtained; preprocessing the disaster-gestation factor data and the coastline data to construct a coast erosion data set, and dividing the coast erosion data set into a training set and a test set according to a proportion; constructing a coast erosion susceptibility evaluation model based on a random forest algorithm; carrying out comprehensive evaluation and comparison on the models to screen out an optimal model; based on the optimal random forest model obtained through screening, the contribution of each factor in coast erosion is analyzed and quantified through feature importance, the factors contributing to coast erosion are identified and obtained, and partial dependence and SHAP are used for carrying out interpretable analysis on the model so as to explain the influence of different disaster-gestation factors on model prediction.

The invention discloses a construction method of a microplastic toxicity prediction model based on transcriptomics and a QSAR (Quantitative Synthetic Aperture Radar) model, which comprises the following steps: measuring actual observation values of cell survival rates of different microplastic samples after contamination and changes of genes in the cells, and screening out the genes as specific genes; selecting a physicochemical descriptor and then determining a gene expression descriptor of the specific gene; establishing a training set and a test set; a plurality of machine learning algorithms are utilized to construct QSAR models respectively, and an optimal QSAR model is selected according to a performance evaluation result; and carrying out performance verification on the optimal QSAR model, and screening out a microplastic toxicity prediction range suitable for the optimal QSAR model. The construction method of the microplastic toxicity prediction model can realize reliable prediction of toxicity, and can effectively support safety evaluation and biotoxicity mechanism research of microplastics.

The invention discloses a clinical data monitoring method based on model training, and the method comprises the following steps: 1, carrying out data collection, namely collecting clinical data, analyzing a data source in the collection process, and selecting the data source; 2, performing data preprocessing to obtain preprocessed data; step 3, selecting a modeling method, performing modeling by using the preprocessed data, and performing modeling related data acquisition in the modeling process to obtain a plurality of pieces of modeling related data; 4, processing the multiple pieces of modeling related data to obtain multiple pieces of modeling evaluation information, and carrying out preferential selection on the multiple pieces of modeling evaluation information to obtain an optimal model; and 5, putting the optimal model into use, and carrying out clinical data monitoring. According to the invention, clinical data can be monitored more intelligently and comprehensively.

The invention relates to the technical field of underwater positioning, in particular to an AUV (Autonomous Underwater Vehicle) three-dimensional pose joint estimation method and system based on multi-modal layering, and the method comprises the steps: distributing a historical observation sequence to corresponding independent convolutional neural network branches according to modals, carrying out the local time sequence feature extraction through each branch, and carrying out the local time sequence feature extraction; outputting local time sequence characteristics of each mode; performing hierarchical feature fusion based on local time sequence features of each mode, inputting global fusion features into a double-branch regression head, respectively decoding through a position regression branch and an attitude regression branch, and outputting a three-dimensional position increment and an attitude increment; and constructing a loss function by using the three-dimensional position increment and the attitude increment, training to obtain an optimal model, and deploying the optimal model to an AUV platform, thereby breaking through the limitation that the traditional method only focuses on a two-dimensional plane or separately estimates the attitude, completely covering the full-space positioning demand of the AUV three-dimensional maneuvering task, and improving the integrity and consistency of the attitude estimation.

The invention relates to a fish and shrimp growth trend prediction method and device based on a growth model. The method comprises the following steps: determining target fish and shrimp types, culture conditions and day age range data; obtaining weight data of the target fish and shrimp species in each day from the day age range data under the determined culture condition; preprocessing the weight data to obtain preprocessed weight data; determining a nonlinear model with good fitting efficiency in fishes and shrimps; based on the preprocessed weight data, performing modeling through a nonlinear model to obtain a first model, a second model and a third model; obtaining key information based on the first model, the second model and the third model; determining an optimal model in the first model, the second model and the third model based on the key information; and performing growth trend prediction on the target fish and shrimp species under the current culture condition by using the optimal model. The method can assist in determining the growth and development state of the animal, and brings great convenience to related workers.

The invention discloses a COPD-FE risk prediction method based on disease and symptom combination, and is applied to the technical field of chronic obstructive pulmonary disease risk prediction. Comprising the following steps: acquiring chronic obstructive pulmonary frequent acute exacerbation influence factor data of a patient; the influence factors are screened through LASSO regression and an improved Boruta algorithm respectively; the LASSO independent influence factors and the Boruta independent influence factors are combined in different modes, a Logistic regression model and an XGBoost model are trained, and a plurality of COPD-FE risk prediction models are obtained; and evaluating the performance of all the COPD-FE risk prediction models, and selecting the COPD-FE risk prediction model meeting the requirement to predict the COPD-FE risk. According to the method, clinical data of patients are collected, a risk prediction model is constructed in combination with a feature selection method and machine learning, and an optimal model is screened out through comprehensive evaluation.

The invention provides a corn disease and insect pest detection method based on MTA-YOLOv11. The problem that an existing detection method is insufficient in small target recognition and edge feature perception in a complex environment is solved. According to the method, on the basis of YOLOv11n, an MERDEM module, a TK-Focus Block module and an MLKD module are introduced and used for enhancing a detail edge, focusing a key area and fusing multi-scale global semantics respectively, and therefore the model can more accurately detect pest and disease damage targets under the complex background; the method comprises the following steps: constructing a Corn-d corn disease and insect pest image data set, dividing the Corn-d corn disease and insect pest image data set into a training set and a verification set in proportion, evaluating a training process of an MTA-YOLOv11 model through the verification set and storing an optimal model weight, and reasoning a corn field image to be detected according to an optimal model corresponding to the optimal model weight, and outputting a detection result containing the disease and pest category, the positioning frame and the visual label. The corn disease and pest detection precision is improved, and the method is light in weight and high in adaptability to complex scenes.

The invention provides an SVG controller modeling analysis method based on field experiment data, and relates to the technical field of electric power grids. According to the method, the high-low penetration fault test is carried out on the SVG, the field experiment data is obtained, the calculation data of the transient model of the SVG under different model parameters are combined, the least square method is adopted to carry out parameter identification, and the optimal model parameters of the transient model of the SVG controller are obtained. The process avoids modeling of complex topology in the SVG and laboratory communication protocol debugging, is suitable for testing of SVGs of various models, and is high in field test result accuracy, simple in wiring and extremely low in risk. A field test result can truly reflect transient response characteristics of station-level current and reactive power, and a modeling path based on the field test is opened. The SVG control characteristic extraction efficiency is improved, the model precision and modeling efficiency of the complex topology SVG are improved, and therefore the analysis efficiency of the SVG analysis process is improved.

The invention discloses an alloy specific strength optimization method combining uncertainty and heuristic algorithms. The alloy specific strength optimization method comprises the steps that a high-entropy alloy component and a strength data set of the high-entropy alloy component at a high temperature are constructed; calculating physicochemical properties based on components, and selecting and screening key feature subsets by adopting correlation analysis and forward sequence selection; comparing the prediction performance and uncertainty of each machine learning model, and determining an optimal model; selecting a target system, performing performance prediction on a candidate system by using an optimal model, estimating uncertainty in combination with a folding knife method, and constructing an upper confidence boundary as an evaluation index; the upper confidence boundary serves as a fitness function of a heuristic algorithm, and optimized alloy components and fitness values are output; the performance of the optimized components is verified through experiments, if the requirements are not met, the result is fed back, and optimization continues until the components with the performance meeting the requirements are obtained. According to the alloy specific strength optimization method combining uncertainty and heuristic algorithms, the problems of high cost and long period caused by dependence on a trial and error method in the prior art are solved.

The invention discloses a flooding wetland carbon flux upscaling method and system fusing a hydrodynamic model and integrated machine learning. The invention relates to the technical field of water conservancy and ecological environment monitoring management, and discloses a method for carrying out multi-scale segmentation on an underlying surface of a flooding wetland by collecting flooding wetland vortex covariance measurement, a digital elevation model, hydro meteorology and remote sensing image data to obtain a carbon flux upscaling calculation unit; a flooding wetland hydrodynamic model is established, and related hydrological situation index factors influencing the flooding wetland NEE are calculated; constructing a plurality of machine learning models, and optimizing the prediction weight of each model to obtain an optimal model integration prediction scheme; nEE spatial upscaling is carried out, multi-model prediction difference is utilized to quantitatively characterize prediction uncertainty, and a NEE space-time distribution diagram and an uncertainty diagram are obtained; according to the method, the wetland NEE upscaling high-precision prediction is realized, and a new technical method and reliable data support are provided for flooding wetland carbon flux research and ecological management.

The invention provides an AI-based oil well yield prediction system and method, and relates to the technical field of artificial intelligence, and the system comprises a production data collection module which collects real-time data of oil well production and processes the real-time data to obtain processed data; the historical data collection module collects historical data of oil well production; a feature extraction module performs feature processing on the historical data to obtain feature data; and the prediction module constructs a recurrent neural network model, optimizes the recurrent neural network model by using an artificial mouse optimization algorithm to obtain an optimal model, and inputs the processed real-time data and the historical data into the optimal model to obtain a predicted yield. According to the method, the recurrent neural network model is constructed, the recurrent neural network model is optimized by using the artificial travel mouse optimization algorithm, the processing data and the feature data are input into the optimal model, the predicted yield is obtained, and the accuracy and efficiency of oil well yield prediction are improved.

The invention discloses a method for monitoring the coverage and thickness of a biological crust in a mining area based on UAV multispectral data, and the method comprises the steps: carrying a multispectral sensor through an unmanned plane, and collecting the multispectral image data of the biological crust in an experiment area; synchronously sampling and measuring actual measurement parameters of the biological crust on the ground; the multispectral image data are imported into cartographic software to be preprocessed, and various vegetation indexes are calculated; matching the vegetation indexes with actually measured parameters to form a data set, drawing a correlation heat map, and screening out the vegetation indexes of which the correlation meets conditions as input features of a machine learning model; multiple machine learning models are constructed and trained, and the machine learning model with the highest prediction precision is output as an optimal model; and evaluating the optimal model, and generating a distribution diagram of the biological crust coverage and thickness. According to the method, the unmanned aerial vehicle multispectral remote sensing technology and the advanced machine learning algorithm are fused, the monitoring efficiency and the data accuracy are improved, and a scientific basis is provided for ecological restoration of a mining area.

The invention provides a muscle fatty degeneration risk assessment method based on machine learning, and relates to the technical field of disease risk assessment. The method comprises the following steps: acquiring a data sample of an HD patient; carrying out feature screening on related features in the data sample according to a Boruta algorithm and Lasso regression based on interaction importance among the features, and generating an important feature set; based on the important feature set, constructing and training a plurality of machine learning prediction models by using the corresponding data samples, and determining an optimal model; inputting data of an actual HD patient into the optimal model to generate a prediction result; performing global explanation and local explanation on the prediction result based on the SHAP value; and generating a risk assessment result according to the global explanation and the local explanation of the prediction result. By adopting the method, the features can be accurately screened, and the prediction result of the model can be explained by accurately utilizing the SHAP value.

The invention relates to the technical field of machine learning, and discloses a concrete filled steel tube member lateral impact deflection prediction method based on machine learning, comprising: generating a lateral impact sample set; respectively training a support vector machine model, a random forest model and an extreme gradient lifting model based on the lateral impact sample set, and screening an optimal model; inputting the characteristic parameters of each lateral impact sample into the optimal model, and performing performance analysis on the optimal model by adopting an interpretable method to obtain optimal characteristic parameters; constructing a relational expression between the maximum deflection and the optimal characteristic parameters, selecting a basic quantity, and after converting the relational expression into a dimensionless relational expression based on a theorem, performing fitting by adopting a symbolic regression method of genetic coding to generate a fitted maximum deflection prediction formula of the component under lateral impact so as to obtain the optimal maximum deflection; according to the method, the maximum deflection prediction precision of the component is improved.

The invention discloses an early-stage enteromorpha biomass monitoring method which comprises the following steps: collecting an early-stage enteromorpha frond sample, and obtaining actually measured reflectivity hyperspectral data under different biomass levels through a water tank control experiment; in combination with a spectral response function of a high-resolution satellite sensor, acquiring the equivalent reflectivity of enteromorpha at different biomass levels; calculating a plurality of spectral indexes based on the equivalent reflectivity; establishing an empirical inversion model between various spectral indexes and actually measured biomass, and screening out an optimal inversion model through precision comparison; applying the optimal model to a high-resolution satellite image to generate an early enteromorpha biomass remote sensing monitoring product; according to the invention, refined and quantitative monitoring of early enteromorpha is realized, and effective technical support is provided for scientific early warning and prevention and control of green tide disasters.

The invention discloses a grape downy mildew resistance whole genome selective breeding method based on machine learning, which comprises the following steps: randomly dividing 132 samples into a training set and a test set according to a ratio of 4: 1, and respectively extracting first 1-100 thousand variation sites as gradient training data sets according to a whole genome association analysis result; and on the basis of 10 classic regression models and the dimensionality-reduced variation data set, machine learning training and evaluation are carried out on 105 training set samples, finally, the variation data set with the highest prediction accuracy and an optimal model are screened out, and phenotype prediction is carried out on 27 test set samples by using the optimal model. The invention relates to the technical field of plant breeding, and the grape downy mildew resistance whole-genome selective breeding method based on machine learning has remarkable advantages in resistance prediction and screening, breeding efficiency improvement and multi-character comprehensive improvement, breaks through the limitation of a traditional breeding method, and is suitable for large-scale popularization and application. An innovative solution is provided for green and sustainable development of the grape industry.