24results about How to "Reliable predictions" patented technology

The invention discloses a photovoltaic power prediction method based on improved empirical mode decomposition and an optimized long short-term memory network, and the method comprises the steps: firstly carrying out the preprocessing of abnormal value elimination, missing value filling, normalization and the like of photovoltaic power and related meteorological data, and improving the data quality; then, an improved empirical mode decomposition (EE-ANEMD) algorithm is adopted to decompose the preprocessed power sequence into a multi-scale intrinsic mode function component and a residual term, and high-frequency noise, intermediate-frequency fluctuation and a low-frequency trend are effectively separated; global optimization is carried out on the hidden layer unit number, the initial learning rate and the maximum number of training times of the LSTM network through an improved sparrow search algorithm (ISSA), finally, the optimized LSTM is utilized to carry out training prediction on each component, and results are fused and subjected to reverse normalization to obtain a final value. Experiments show that the test set RMSE of the method is reduced compared with that of a single LSTM, the mid-term prediction precision is remarkably improved, and reliable technical support is provided for power system dispatching, new energy consumption planning and photovoltaic power station operation and maintenance.

The invention provides a rock mass structural surface strength prediction method driven by a ground vibration load, and relates to the technical field of rock mass mechanics. The method comprises the following steps: acquiring and integrating geometric and mechanical parameters, seismic oscillation parameters and test and numerical simulation data of a structural plane to form a standardized database; cleaning and standardizing database data, constructing a dynamic attenuation factor, and screening and enhancing key features to obtain initial input features; constructing a physical experience reference model and a machine learning predictor, and training a hybrid prediction model by combining prediction results of the physical experience reference model and the machine learning predictor; verifying the model and quantizing the output uncertainty; inputting the basic data calling model to complete calculation and outputting a result. According to the method, the reliability and adaptability of rock mass structural surface strength prediction are improved, and support is provided for seismic design of geotechnical engineering.

The invention relates to the technical field of index prediction in the social economic field, and discloses a social economic index set prediction method, which comprises the following steps of collecting multi-source data related to social economy, the multi-source data comprises medical business data of a medical institution, medical insurance data of a medical insurance department and social economic environment data of an external data source; and cleaning and standardizing the collected multi-source data to remove noise, missing values and abnormal values in the data, and unifying the data format and dimension. Data are obtained through multiple channels, the data basis of social and economic index analysis is enriched, multi-aspect conditions are presented, macroscopic information is reflected, understanding of phenomena and trends is enhanced, the accuracy and scientificity of index prediction are improved, and more valuable data support is provided for decision making. The problems of limited data sources and insufficient data mastering in the previous social economic index research are solved.

The invention provides an intelligent control method for heat balance in the aluminum alloying process. The intelligent control method comprises the steps that S1, the target aluminum content of molten steel in an RH refining device, the total mass of the molten steel and the specific heat capacity of the molten steel are obtained; s2, according to the actual production state and the production steel type, the oxygen value of the molten steel before alloying and the refining entering temperature are collected according to the time sequence, and the aluminum yield is calculated; s3, based on the aluminum yield, heat balance operation judgment conditions are set, and if yes, calculation is conducted according to an empirical formula; if yes, executing the step S4; s4, calculating the heat effect of the aluminum dissolving process, the heat effect of the aluminum melting process and the heat effect of the aluminum-oxygen reaction; s5, calculating the total heat effect; s6, the temperature change value of the molten steel system in the alloying process is calculated; and S7, according to the difference value between the temperature change value of the molten steel system in the alloying process and the target refining final temperature, a compensation heating or cooling instruction is output, the actual final temperature is made to be consistent with the target value, the instruction is automatically executed to complete aluminum alloy affiliation, and the temperature-controlled molten steel with the aluminum content reaching the standard is obtained.

This invention discloses a seismic prediction method for gravity-induced geostress parameters in TTI media. The specific process includes: Step 1, establishing calculation models for the minimum and maximum horizontal stresses and DHSR of the TTI media; Step 2, performing discrete Fourier transform on partially stacked seismic data from different azimuths to obtain zero-order and second-order Fourier coefficient data volumes; Step 3, predicting TTI media model parameters: performing Bayesian Fourier coefficient inversion to predict P-wave and S-wave moduli, densities, fracture densities, and dip fracture parameters; and calculating fracture dip angles; Step 4, calculating TTI media geostress parameters: substituting the predicted TTI media model parameters into the calculation model established in Step 1 to calculate the minimum and maximum horizontal stresses and DHSR of the TTI media. This invention can provide stable and reliable prediction results for TTI media geostress parameters, which helps guide fracturing development operations in unconventional reservoirs.

The invention discloses a drainage basin ecological hydrological process simulation and prediction system based on a mechanism hydrological model and AI coupling, and relates to the technical field of drainage basin ecological hydrological simulation and prediction. Multi-source data integration and preprocessing are carried out through a data input layer, and a standardized data set is output and provided for a model coupling layer; the model coupling layer directly receives the standardized data set of the data input layer and outputs an optimized simulation result and a predicted value to the simulation and prediction layer; the simulation prediction layer receives a simulation result and a prediction value of the model coupling layer, performs multi-dimensional ecological hydrological element collaborative simulation and short-term-medium and long-term scene adaptive prediction, and outputs a simulation prediction result to the result output layer; and the result output layer receives the simulation prediction result of the simulation prediction layer and provides visual interaction and decision suggestion generation functions. The invention provides an innovative scheme of deep fusion of a mechanism model and an AI technology, and comprehensive requirements of physical rationality, data fitting precision, multi-element coverage and efficient response are covered.

This invention belongs to the field of medium- and long-term power generation in new energy, and discloses a medium- and long-term power forecasting method and related equipment based on ERA5 reanalysis data. This method uses multi-year ERA5 reanalysis data to perform climate model analysis on the area where the power plant is located, obtains the climatological average irradiance, and constructs an error correction model by combining it with historical measured data from the power plant. This allows for medium- and long-term power forecasting using historical data from the same period of the power plant's climatological output. By using multi-year ERA5 reanalysis data to perform climate model analysis on the area where the power plant is located, this method can accurately capture the climatological average irradiance of the area, effectively solving the forecasting problem caused by the lack of historical data for newly built or short-term operating photovoltaic power plants. Using this method is of crucial practical significance for power plants to reasonably declare medium- and long-term trading volumes in electricity transactions and reduce revenue losses caused by positive and negative volume deviations, significantly enhancing the competitiveness of power plants in the electricity market.

The application discloses a plateau meteorological data downscaling method based on cross-terrain knowledge transfer, and belongs to the technical field of data-driven meteorological modeling and calculation. The method comprises the following steps: obtaining low-resolution meteorological data and corresponding high-resolution meteorological data of a source domain, low-resolution meteorological data and corresponding high-resolution meteorological data of a target domain, and terrain data; training a basic downscaling network model based on the low-resolution meteorological data and the corresponding high-resolution meteorological data of the source domain; performing adaptive training on the model based on the low-resolution meteorological data and the terrain data of the target domain and in combination with a composite target function containing a terrain difference regularization term; fine-tuning the model based on the meteorological data of the target domain to obtain a final downscaling model, and realizing downscaling of the low-resolution meteorological data by using the model. The application can improve the model performance, generalization ability and physical consistency.

The present application relates to the technical field of mineral prediction, and discloses a mineral prediction method and system based on a multi-modal Transformer architecture. The method comprises collecting multi-modal data related to mineral prediction through multiple heterogeneous data sources; cleaning, aligning and standardizing the collected data to generate a multi-modal data set in a unified format; deeply encoding the data set using a multi-modal Transformer encoder to extract multi-modal feature representations; based on the feature representations, calculating the correlation weights between the features through the Transformer self-attention mechanism to construct a dynamic attention relationship graph; evaluating the importance of the features according to the correlation weights in the graph to filter key features to form a core feature set; and inputting the core feature set into a prediction model to generate a mineral prediction result. The method can mine the correlation information of multi-modal data, filter core features, and adapt to the demand for mineral prediction under complex geological conditions.

The application discloses a multi-scale calculation method and system for the magneto-caloric effect of a two-dimensional magnet, and the method combines density functional theory, atomic spin and thermodynamic knowledge related to the magneto-caloric effect, so that the step-by-step calculation of the two-dimensional magnet material is realized only according to the crystal structure of the two-dimensional magnet, and evaluation indexes of relevant magnetic properties and magneto-caloric properties are obtained after the step-by-step calculation at the electronic level, the atomic level and the macroscopic thermodynamic level, and finally, the prediction result is accurate and reliable.

The invention discloses a bin plate type thermal insulation material performance detection method and system, and relates to the technical field of material detection, and the method comprises the following steps: extracting performance characteristic data; predicting the protective performance change trend of the warehouse plate type thermal insulation material under different environmental conditions based on the performance characteristic data; establishing an analysis space used for protection performance change trend abnormity identification, sampling and correcting performance data in the analysis space, and analyzing a relation between the performance data and a target threshold value and a historical sequence; and through abnormal path identification and curve fitting, key factors influencing the protection performance of the warehouse plate type thermal insulation material are identified, and a production process and a maintenance strategy are adjusted based on the key factors. Through anomaly recognition and curve fitting, performance anomaly and key factors thereof can be found in time, and data support is provided for optimizing a production process and a maintenance strategy, so that the stability and reliability of the material are improved, and the long-term and efficient thermal insulation effect of the material is ensured.

This invention relates to a method for predicting the plastic cracking time of concrete, comprising: obtaining a concrete mix proportion; determining the cracking time of the concrete mix proportion based on the concrete mix proportion and a pre-established correspondence between the concrete mix proportion and cracking time; wherein the process of establishing the correspondence includes: preparing several concrete specimens and curing them according to the concrete mix proportion; for each concrete specimen, acquiring images of the concrete specimen at multiple monitoring times using DIC technology, obtaining strain data from the images, determining the strain half-width and height from the strain data, and then fitting a time-strain half-width and height relationship model; calculating the time corresponding to the strain half-width and height limit based on the time-strain half-width and height relationship model and a pre-determined strain half-width and height limit, adding the time corresponding to the strain half-width and height limit to the curing time of the concrete specimen to obtain the cracking time of the concrete specimen, thus establishing a correspondence between the concrete mix proportion and cracking time.

The invention relates to the field of precise milling and turning, in particular to a dynamic quality planning intelligent management method based on a mechanism model, which comprises the following steps: collecting multi-source heterogeneous data, and respectively constructing an implicit disturbance risk index for representing a system disturbance risk and a wear state parameter for representing a system wear state based on the data; calculating to obtain a system critical index in combination with the implicit disturbance risk index and the wear state parameter; presetting a critical state grade threshold value, and comparing the system critical index with the critical state grade threshold value to obtain a critical state evaluation result; generating a process correction factor based on the critical state evaluation result and the system critical index; according to the process correction factor, outputting a grading correction strategy for the processing process parameters; dynamic balance of production efficiency and quality safety is realized, and quality collapse is effectively inhibited.

This application relates to the field of battery state monitoring technology for electric vehicles, and particularly to a method, apparatus, and electronic device for multi-parameter prediction of electric bus batteries. The method includes: acquiring battery condition data of the electric bus; extracting multi-scale features from the battery condition data using an encoder employing a fusion-like attention mechanism; inputting the multi-scale features into a hidden state layer, which outputs online updated features; filtering battery feature data based on the online updated features; inputting the battery feature data into a decoder; and outputting prediction results for multiple battery parameters of the electric bus from the decoder. This solves the problems in related technologies, such as lengthy data processing for multi-parameter prediction of electric bus batteries, weak capture of long-term dependencies, poor computational efficiency, and low prediction accuracy.

The application provides a marine clay-geogrid interface cyclic shear stress prediction model construction method, and relates to the technical field of marine engineering. The method comprises the following steps: preparing and assembling a marine clay-geogrid interface shear test sample; after the sample is assembled, a multi-working-condition interface cyclic shear test is carried out to obtain effective original test data; based on the effective original test data, an interface cyclic shear test database is constructed; based on the interface cyclic shear test database, a deep learning prediction model is constructed and trained; the accuracy of the prediction model is verified, the optimal prediction model is screened out, and a marine clay-geogrid interface cyclic shear stress prediction formula is built based on the optimal prediction model. The application can obtain reliable test data under multiple working conditions, accurately depict the shear stress evolution law by constructing a CNN-BiLSTM model, build an engineering usable prediction formula, and provide reliable support for the design and safety evaluation of marine engineering reinforced structures.

This invention provides a method for predicting blasting vibration velocity on interbedded soft and hard rock slopes, comprising the following steps: conducting field blasting tests on interbedded soft and hard rock slopes to obtain blasting vibration velocity data; sampling rocks for the interbedded soft and hard rock slopes and obtaining the physical and mechanical parameters of the rocks in the field through indoor mechanical tests; establishing a finite element numerical model based on the physical and mechanical parameters; verifying the simulation results of the finite element numerical model using the blasting vibration velocity data; supplementing with different working conditions to establish numerical models under different working conditions and calculating the vibration velocity results; and combining the dimensional homogeneity theorem with formula fitting based on the vibration velocity results to obtain a mathematical prediction model for blasting vibration velocity considering blasting parameters and slope attitude. This invention has significant practical significance and engineering application value for solving problems related to the prevention of geological disasters in slope engineering.

The invention relates to the technical field of oil and gas exploitation, in particular to an oil and gas exploitation process intelligent linkage method which comprises the following steps: S1, data acquisition and monitoring: acquiring temperature, pressure and flow data in an oil refining process in real time through data acquisition equipment; s2, model optimization and prediction; s3, intelligent control and adjustment; according to the method, the production process is optimized through data analysis, the mining efficiency is improved, the model is utilized, the operation state of the oil refining process is known, adjustment is made according to needs, efficient decision making is achieved, all units in the oil refining process are automatically controlled, the operation process is more accurate and stable, and the oil refining efficiency is improved. Model prediction can be used to accurately analyze the correlation between data so as to accurately predict the future trend, and is not influenced by subjective consciousness and personal experience, the prediction result is relatively reliable, the human input and subjective interference in the prediction process are reduced, excessive bandwidth and computing power are not consumed, and the prediction efficiency is improved. And seamless connection and sharing of data can be realized.

The invention discloses a method for predicting the heat insulation performance of a multi-layer heat insulation material based on a random forest model, and aims to solve the problem that an accurate model among material structure parameters, working condition parameters and heat insulation performance is difficult to establish in a traditional method. The method comprises the following steps: firstly, obtaining structure parameters, working condition parameters and corresponding heat insulation performance data of a variable-density multi-layer heat insulation material sample to form a data set; aiming at the characteristics of the variable-density multi-layer heat-insulating material, constructing enhanced characteristics through characteristic engineering; and inputting the feature vector as input and the heat insulation performance as a prediction target into a random forest model for training, optimizing key parameters of the model in training, verifying the performance of the trained model by using an evaluation index, and predicting the heat insulation performance of the new material by using the model according to structural parameters and working condition parameters of the new material. According to the method, a structure, working condition and performance relation model can be efficiently and accurately established by utilizing the high-dimensional and nonlinear processing capability of the random forest, and a brand-new material design and performance evaluation tool is provided.

The application discloses a load aggregation body prediction method and system of an integrated framework, and the method comprises the following steps: applying a prediction result of a trained load aggregation body prediction model to perform scheduling; wherein the construction of the load aggregation body prediction model comprises the following steps: obtaining load aggregation body historical data; performing external influence factor analysis on the load aggregation body historical data, and screening important external influence factors; applying a K-shape algorithm to cluster the load aggregation body historical data, and dividing the load aggregation body historical data into a plurality of clusters; constructing a load aggregation body prediction model, including a CNN-LSTM-ATTENTION prediction model and a GBDT prediction model; performing load prediction on each cluster through the CNN-LSTM-ATTENTION prediction model by using the screened important external influence factors and the divided plurality of clusters; and applying the GBDT prediction model to perform integrated prediction on the load prediction results of the clusters, thereby obtaining a load aggregation body prediction result; and the application can improve the prediction accuracy of the load aggregation body prediction model.

The application discloses a grouting amount integrated agent prediction model based on stacking, which comprises an integrated agent model, the integrated agent model is provided with two layers, the first layer comprises three base learners which are trained and verified by using a five-fold cross-validation method, and the second layer comprises one meta learner; the three base learners are respectively an SVR neural network, a BPNN neural network and an RF model; the meta learner is an ANFIS neural network; and training data in a training set of the meta learner comprises prediction result data of the three base learners. The application further discloses a prediction method of the grouting amount integrated agent prediction model based on stacking. The application can increase model diversity, reduce overfitting and prediction uncertainty, and generate more accurate and more robust prediction results.

The invention provides a battery capacity retention rate prediction method and device, electronic equipment and a storage medium, and belongs to the technical field of lithium batteries, and the method comprises the steps: obtaining the target storage temperature and target storage time of a battery; calling a preset rate model to determine a corresponding capacity recovery attenuation rate of the battery at the target storage temperature; and determining the corresponding capacity retention rate of the battery after the target storage time based on the capacity recovery decay rate. According to the scheme, the prediction accuracy of the battery capacity retention rate can be effectively improved.

This invention discloses a method for analyzing the mobility of original formation water in gas reservoirs, comprising the following steps: S1, acquiring target well and target layer image data, and constructing a three-dimensional multi-pore structure model; S2, restoring the original formation conditions to the three-dimensional multi-pore structure model; S3, establishing a gas-water two-phase displacement mathematical model based on the lattice Boltzmann method, and coupling the two to obtain a coupled model; S4, determining the original state of the gas reservoir, setting evolutionary solution conditions, and performing evolutionary calculations on the coupled model based on the evolution equation to obtain a three-dimensional multi-pore structure model containing both gas and water phases; S5, performing multi-angle slice analysis, classifying and analyzing the mobility of the water phase, and obtaining the distribution of mobile water. This method does not require closed coring operations and avoids subsequent high-cost experiments such as nuclear magnetic resonance and core displacement, effectively reducing research costs, providing accurate and reliable prediction results, greatly shortening the testing and analysis cycle, and realizing the evaluation of formation water mobility under the original conditions of gas reservoirs.

The invention discloses a marine seat fatigue test system based on digital twinning and iterative learning control, and the system comprises a data collection and working condition simulation module which is used for obtaining marine environment, ship motion and seat mechanical response data, and generating a composite load spectrum simulating a real working condition; the marine seat digital twin model module constructs a virtual model corresponding to a physical seat, integrates structural dynamics, a material constitutive model and a damage accumulation model, and is used for mapping the real-time state of the physical seat; the iterative learning and intelligent optimization control module is used for receiving feedback of the digital twinborn model, correcting a test load spectrum on line, and allocating computing resources by using a dynamic priority scheduling model so as to accelerate the test; and the life prediction and evaluation module is used for probabilistically predicting the residual fatigue life of the seat. Through combination of the high-fidelity digital twinborn model and iterative learning control, precise simulation of complex and random ocean loads is realized, and a test environment is closer to a real working condition.

The invention relates to the technical field of lithium ion batteries, in particular to an energy storage lithium ion battery health state prediction method, which comprises the following steps that sparse test point data are acquired through a battery aging experiment, and each test point comprises a cycle number, internal resistance, an increment health state characteristic and a health state label; systematic slicing and resampling are carried out on a time axis by utilizing an aging mining method, training samples containing different circulation history paths are generated, and a mapping relation between circulation history and health state attenuation is learned by adopting a deep learning model, so that high-precision health state prediction is realized; the method has the beneficial effects that the problem of scarcity of battery aging data is solved, and the health state prediction precision is remarkably improved; the method has good generalization ability and has flexibility and expandability.