306 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 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 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 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 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 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 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 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 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 an intelligent rainfall forecasting method and system based on real-time assimilation driving of sky-air-ground multi-mode sensing data, and relates to the field of machine learning, and the method comprises the steps: carrying out the coordinate alignment of an obtained standardized multi-source meteorological data set, distributing a weight according to the time-space credibility of a data source, and carrying out the calculation of the time-space credibility of the data source; generating an enhanced radar image feature set implying multi-modal information, and inputting the enhanced radar image feature set into the double-branch-UNet-GAN collaborative optimization model for training to obtain an optimal model adaptive to multi-modal data; based on severe convective weather characteristics and business requirements, precision correction and lightweight processing are performed on a forecast result after test set adversarial optimization through a regional attention mechanism, visual display is realized through an APP and a webpage terminal, positioning query and early warning push functions are synchronously provided, and a closed loop from data to service is completed. According to the method, full-chain innovation is formed from data fusion, model performance, aging precision, resource adaptation to service landing, and the scientificity and application value of intelligent rainfall forecasting are remarkably improved.

The invention discloses a soil organic matter deep learning inversion method added with an error consideration mechanism. The method comprises the following steps: acquiring data, and constructing a feature data set; carrying out sampling point layout by utilizing conditional Latin hypercube sampling; detecting the soil sample; calculating a Pearson's correlation coefficient of spectral information of the satellite remote sensing image and organic matters, and selecting spectral features as input features based on correlation; performing model optimization by using a deep learning algorithm to obtain an optimal model; searching a most reasonable value in a true value error range by using a genetic algorithm, and storing a corresponding deep learning model at the moment; and performing soil organic matter inversion in a research area by using the model, and drawing a fertility distribution diagram by using drawing software. According to the invention, soil organic matter inversion is realized by using a machine learning algorithm, the sampling frequency is greatly reduced, the inversion precision of the model is improved, and thus the drawing of a soil organic matter distribution diagram in a large farm scale and a county scale is realized.

The invention discloses an autoclave temperature offline simulation and online prediction method based on Hybrid KAN feature fusion. The autoclave temperature offline simulation and online prediction method comprises the steps that historical temperature time sequence data and static process parameter data of different batches are collected; performing feature screening and preprocessing, and constructing a time sequence data input sequence and a static process parameter input sequence; designing a Hybrid KAN neural network model, taking the time sequence data input sequence and the static process parameter input sequence as input, and outputting a predicted value of the temperature of the autoclave at the next moment through feature extraction and fusion; taking minimization of a loss function as a target, training the model, and obtaining an optimal model by using a structured pruning strategy; and deploying an optimal model, and realizing off-line simulation and on-line prediction of the temperature of the autoclave through rolling time window iteration multi-step prediction. The method is high in accuracy, wide in universality, small in model parameter scale, high in reasoning efficiency and suitable for autoclave temperature prediction in complex scenes.

According to the large language model reasoning optimization method and device, the storage medium and the computer equipment provided by the invention, the multi-dimensional monitoring data is acquired, and then the multi-dimensional monitoring data is input into the pre-trained environment decision network to obtain the optimal model configuration. The current resource state is evaluated according to the multi-dimensional monitoring data, and the optimal execution path is determined according to the resource state and the optimal model configuration. And finally, adjusting the target model based on the optimal model configuration, and performing model reasoning according to the optimal execution path in the reasoning process of the target model. In the process, the resource state is evaluated and the optimal model configuration is determined by collecting the multi-dimensional detection data, and then the optimal execution path is dynamically determined, so that the model structure and the calculation strategy can be dynamically adjusted according to the state during actual operation, and the response delay is effectively reduced and the resource utilization efficiency is improved while the reasoning precision is guaranteed.

The invention provides a laser powder bed melting method for preparing a high-toughness TC4 titanium alloy based on machine learning. The method comprises the steps that performance data of the TC4 titanium alloy prepared through different SLM process parameters are collected; constructing a hybrid expert (MoE) machine learning prediction model framework; classifying the TC4 data by adopting a K-means clustering algorithm, and taking a clustering center as an initial weight of an input layer and a first layer of the gating network; presetting a TC4 performance prediction model through the gating network and the plurality of expert networks after clustering information initialization; performing small-range iteration through large-step network search in combination with a Bayesian optimization method so as to determine an optimal model structure and complete model training; the trained performance prediction model and a genetic algorithm are used for carrying out backstepping to obtain SLM printing parameters of the high-toughness TC4 alloy; and SLM forming is carried out, and the high-toughness TC4 titanium alloy is prepared. According to the method, a calculation framework which is high in precision and suitable for exploring a high-unknown characteristic space is constructed, and far-reaching influences on titanium alloy additive manufacturing and process optimization of other alloy systems are achieved.

The invention discloses a U-Net-based multi-mode wind energy resource monthly scale prediction correction method and system, belongs to the technical field of wind energy resource evaluation and climate numerical value prediction crossing, and is used for correcting monthly scale wind speed output by a climate mode. According to the method, a climate state wind speed field is constructed by utilizing ERA5 reanalysis, and a monthly-scale 10m wind speed anomaly is calculated to serve as a correction reference; monthly-scale historical return data of a plurality of dynamic climate modes are obtained, 10m wind speed and multilayer meteorological elements are extracted, unified interpolation and standardization are carried out, and a sample set is formed; a U-Net correction model with a coding and decoding structure is constructed based on a sample set, feature combination and hyper-parameters are optimized through cross validation, and nonlinear mapping from a multi-mode forecast field to an ERA5 distance flat field is learned. And correcting future monthly scale forecast by using the optimal model, generating a wind speed product of which space structure and amplitude distribution are closer to observation, and providing high-credibility wind energy climate information for wind power planning, power generation planning and power grid dispatching.

The invention discloses a Taylor flow two-phase volume fraction prediction method based on CFD and machine learning, and belongs to the field of hydrodynamics. The method aims at solving the problems that traditional CFD is low in efficiency and weak in generalization, and pure machine learning lacks explanatory and physical consistency. According to the method, a mixed CFD-ML framework integrating an interFoam solver of OpenFOAM and machine learning is constructed. The method comprises the steps that firstly, a multi-working-condition calculation example is established based on OpenFOAM, and a training data set containing velocity fields Ux and Uy and a liquid phase volume fraction field alpha. Water is generated through interFoam; training a fourier neural operator (FNO)-based model by using a training solver to obtain an optimal model; and finally, loading the model by using a prediction loop solver, and quickly predicting the volume fraction field of the next time step in CFD time marching. The method improves the prediction efficiency and precision, guarantees the physical consistency, is suitable for the fields of ocean engineering, oil and gas transmission and the like, and can be expanded to a multiphase flow scene.

The embodiment of the invention relates to an OPC model optimization method, electronic equipment and a storage medium. The method comprises the following steps: comparing a current first loss function value of each model with a loss function value of a preset number of historical optimal models in subsequent iterations after a preset number of iterations; determining a current second loss function value of a model of which the loss function value is expected to be lower than a loss function value of a historical optimal model in each model according to a measurement point selected based on a predetermined rule; wherein the loss function value is related to a first loss function value indicating the difference between the simulation value of the critical dimension and the target value and a second loss function value indicating the difference between the simulation values of the critical dimension for different sampling points; and determining an updated model based on comparison between a current loss function value, determined by the current first loss function value and the current second loss function value, of each model in each iteration and a loss function value of a historical optimal model. According to the technical scheme, the modeling efficiency of the OPC model can be remarkably improved.

A Seq2Seq multi-step 4D flight path prediction method based on gating error correction comprises the following steps: data preparation: selecting data of a plurality of real flight paths of the same flight; data preprocessing, including data normalization and data set division; a TCN-GRU-GECM model is constructed, and the TCN-GRU Carrying out the training of the TCN-GRU-GECM model; inputting a test set data sample as an input sequence into the stored optimal model to obtain a predicted value of the tth time step; and S6, traversing all the input sequences, circularly executing the previous process, and finally realizing a multi-step 4D prediction task for the whole track. Error accumulation is effectively inhibited, an error window is maintained through a gating error correction module, an error trend is analyzed based on a mean value and a standard deviation of historical errors, a correction value is dynamically generated by utilizing a gating mechanism and is fed back to a decoder, and the problem of error propagation amplification in autoregression prediction is remarkably relieved.

The invention discloses a data mining technology-based construction method and application of an elderly diabetic hypoglycemia risk prediction model, and belongs to the technical field of medicines and computers. The method comprises the following steps: selecting elderly diabetic patients meeting standards, collecting demographic, disease and lifestyle factor data, dividing a training set and a verification set, comparing the performance of five data mining models, screening an optimal model, confirming the effectiveness of the model through external verification, and visualizing the result. The model can output a quantitative risk probability, is suitable for multi-scene real-time evaluation, can accurately identify high-risk groups, guides hierarchical intervention, reduces the incidence rate of hypoglycemia, and improves the management efficiency and safety of elderly diabetic patients.

The invention discloses a deep learning-based smart building adaptive comprehensive management and control method and system, relates to the technical field of smart buildings, and comprises the steps of effectively reducing time sequence dimensions and removing redundant trend information through neural clustering and a DCT frequency domain compression mechanism; the prediction stability and generalization ability of the model under a long time span are enhanced, global optimization is performed on LSTM model parameters through an adaptive genetic algorithm and an APSO algorithm, and optimal model search which jumps out of local minimum and is faster in convergence is realized, so that the generalization ability and prediction precision of the model for user behavior changes are enhanced, and the prediction accuracy of the user behavior changes is improved. The performance and the self-adaptive optimization capability of the user behavior prediction model are remarkably improved, and through an MAML rapid parameter updating mechanism, strategy migration is realized, so that the control model is adapted in real time under abnormal conditions, the response speed is improved, and the control model has the continuous optimization capability in a dynamic scene.

The invention discloses a bearing anti-noise fault diagnosis method based on a multi-cascade cross-dimension dynamic interaction Transform. The method comprises the following steps: acquiring original vibration signals of a bearing at different positions by using a sensor; carrying out data preprocessing, and dividing the collected data into a training set, a verification set and a test set; performing feature extraction and conversion, converting a data type into a quaternion, and constructing an anti-noise bearing fault diagnosis model consisting of a multi-cascade cross-dimensional interactive ScConv module and a dynamic quaternion dual-channel Transform module; training based on the training set and the verification set, and adjusting parameter configuration and a model structure until an optimal model is obtained; and performing model effect verification through the test set to obtain a fault classification result, and evaluating the fault diagnosis performance. The method provided by the invention solves the problems that the recognition rate of a fault bearing is low in a strong noise environment, and a traditional method is poor in universality and low in diagnosis precision.

The invention discloses a time sequence reconstruction and machine learning coupled chlorophyll monitoring data breakpoint restoration method, and belongs to the technical field of water quality monitoring. The invention discloses a chlorophyll monitoring data breakpoint restoration method based on coupling of time sequence reconstruction and machine learning, and the method comprises the following steps: S1, collecting water quality monitoring data, and cleaning the monitoring data to obtain preprocessed data; s2, performing time sequence reconstruction on the preprocessed data to obtain a weekly average 1 data set; s3, respectively constructing a radial basis function neural network model and a back propagation neural network model by taking the chlorophyll concentration as a response variable and the conventional water quality parameter as a predictive variable; s4, performing performance evaluation on each model by taking a root mean square error, an average absolute percentage error, goodness of fit and relative error distribution statistics as evaluation indexes, and screening out an optimal model; and S5, applying the conventional water quality parameters in the breakpoint interval of the chlorophyll monitoring data in the water body to the optimal model, and outputting the restored chlorophyll concentration value to complete the dynamic restoration of the breakpoint.

The invention provides a deep learning trajectory prediction method introducing a vehicle kinematics constraint, and aims to solve the problem that trajectory prediction lacks physical consistency. The invention relates to the field of automatic driving. The system comprises a deep learning prediction module, a physical model prediction module and a model optimization training module. The deep learning prediction module receives vehicle and map information, extracts features and interacts with each other by using a gating cycle unit GRU and a graph convolution sub-graph network, and outputs a first prediction trajectory. And the physical model prediction module uses a PID controller to calculate a control quantity according to the reference position state, and drives a kinematic model to generate a second prediction trajectory conforming to kinematic constraints through closed-loop deduction. And the model optimization training module constructs joint loss and back propagation optimization network parameters based on a prediction error and a physical consistency error between the two trajectories, and finally loads an optimal model output trajectory.

A method of training a machine learning model to predict seafloor ripple geometry that includes receiving one or more input values, each input value based on an observation associated with ocean wave and seafloor conditions, and preprocessing the one or more input values. The method includes generating a training data set based on the preprocessed data set, splitting the training data set into a plurality of folds, and training via stacked generalization the machine learning model by performing a cross validation of each fold of training data based on at least one deterministic equilibrium ripple predictor model and on at least one machine learning algorithm. The method may include generating via the trained machine learning model, a set of one or more seafloor ripple geometry predictions, and performing Bayesian regression on the set of one or more seafloor ripple predictions to generate a probabilistic distribution of predicted seafloor ripple geometry.

The invention relates to the technical field of grassland ecological monitoring, and discloses a grassland biomass estimation method based on multi-modal phenotype fusion and moisture content correction. The method comprises the following steps: setting a 0.5 m * 0.5 m quadrat in a grassland research area, synchronously acquiring a multi-spectral image of an unmanned aerial vehicle, multi-view structural data of a ZED 2i depth camera and ground actual measurement data, extracting structural features such as a multi-view vegetation projection volume index and 10 vegetation indexes after preprocessing, and constructing an XGBoost moisture content inversion model; and constructing a biomass initial model by using a pure structure, a pure spectrum and fusion characteristics, introducing a moisture content correction formula to correct deviation, and screening an optimal model through Monte Carlo cross validation. According to the method, multi-source data are effectively fused, moisture interference is stripped, the grassland biomass estimation precision is improved, and reliable technical support is provided for grassland ecological monitoring, carbon cycle evaluation and resource management.

The invention discloses a domain adaptation width learning industrial penicillin concentration prediction method based on parameter migration, and the method is based on BLS, guarantees the calculation precision, and improves the calculation efficiency of a model. According to the method, learnable parameter conversion mapping is designed, the output parameters of the source domain and the target domain are projected into the same parameter space, and the data distribution difference under different domains is reduced to the maximum extent. A distribution alignment regular term of a source domain and a target domain is designed based on MMD, and the migration efficiency of data between the domains is improved. An output parameter regular term and a migration parameter regular term are constructed in an objective function, and overfitting and knowledge negative migration of the model are avoided. A model parameter optimization algorithm is designed, alternative optimization is carried out on output parameters and migration parameters, and optimal model parameters are calculated in a self-adaptive mode. The method is applied to soft measurement modeling of the industrial penicillin fermentation process with the multi-working-condition characteristic, and high-precision prediction of the penicillin concentration in the industrial penicillin fermentation process can be achieved.