42 results about "PROJECTIONS PREDICTIONS" patented technology

The invention discloses a wind speed prediction method and system based on a hybrid convolutional network and a parallel prediction model, and relates to the technical field of weather forecast, and the method comprises the steps: firstly carrying out the cluster screening through a clustering method, and then selecting a certain turbine as a target data set for prediction. During prediction, a GCN model is used to carry out spatial feature learning on historical wind speed data, then a TCN model is used to carry out time feature learning on the historical wind speed data, and then time sequence format data constructed by fusing spatial and temporal features are input into a Transform-LSTM parallel structure prediction model for prediction. According to the wind speed prediction method and system based on the hybrid convolutional network and the parallel prediction model, which adopt the structure and the steps, the prediction result is highly consistent with the observation value in numerical value, and relatively high accuracy is also shown in the aspect of trend prediction.

The invention discloses a product forging data intelligent management system and method based on 5G cloud computing, and relates to the field of intelligent manufacturing. According to the system, multi-source data such as temperature, stress, load and images are collected through a process data module and weighted labeling is carried out; the multi-model reasoning module selects support vector regression, a random forest and a convolutional neural network for parallel prediction according to data features; the prediction fusion module generates a unified prediction result by adopting a nonlinear function based on confidence score; the cloud-edge collaborative scheduling module determines cloud or edge deployment in combination with task complexity, edge computing power and a network state; the parameter optimization module adopts an EPQ-Opt algorithm to optimize process parameters based on energy consumption prediction and residual score; and the security guarantee module adjusts the strategy through consistency detection and robustness evaluation and guarantees data security. The method significantly improves the prediction precision and response speed, reduces the energy consumption, enhances the system safety, and is suitable for the field of high-end forging and intelligent manufacturing.

The invention provides an electric power material demand prediction method, system and device and a medium, and belongs to the technical field of electric power material regulation, and the method comprises the steps: collecting historical electric power material demand data and influence factor data, and carrying out the preprocessing of cleaning, transformation and feature extraction; building a deep learning model based on a TensorFlow deep learning framework; performing training, model parameter adjustment and performance evaluation on the deep learning model by using the preprocessed historical data to obtain a final prediction model; and collecting real-time electric power material demand data and influence factor data, pre-processing the data, and inputting the data into the final prediction model for electric power material demand prediction. According to the method, the deep learning model is constructed through the TensorFlow deep learning framework, prediction of the electric power material demand data is realized in combination with the processed historical electric power material demand data, and the prediction precision is high.

The invention discloses a deep large-mining-height working face surrounding rock stress dynamic prediction method. The method comprises the following steps: S1, data acquisition and selection; s2, decomposing a stress signal; s3, trend term stress prediction; s4, periodic term stress prediction; and S5, predicting result fusion. The prediction system comprises the following modules: a data acquisition module, a data preprocessing module, a stress signal decomposition module, a trend term stress prediction module, a periodic term stress prediction module and a prediction result fusion module. Through the advanced CEEMDAN-Kmeans algorithm and multi-algorithm coupling model, the high-precision dynamic prediction of the surrounding rock stress is realized, the signal processing efficiency and accuracy and the prediction precision are improved, the generalization ability of the model to a complex stress change mode is also enhanced, and the prediction precision of the surrounding rock stress is improved. And powerful technical support is provided for coal mine safety production and roadway surrounding rock stress management.

Methods, systems, and techniques for training an implicit neural representation (INR) network to perform time series data forecasting. Lookback and horizon time series of data are obtained, with the lookback time series of data spanning a lookback time window and the horizon time series of data spanning a horizon time window following the lookback time window. A lookback basis and a horizon basis are determined by processing the lookback time series of data using the INR network. Weight and bias parameters are determined using a regression based on the lookback basis and time series. Predicted horizon values are forecast from the horizon basis values and the weight and bias parameters. The INR network is trained to reduce forecast error between the horizon time series of data and the predicted horizon values, with the training involving penalizing linear redundancies between pairs of bases selected from the lookback and horizon bases.

A power grid short-term load prediction method comprises the following steps: determining a prediction target period; and predicting the power grid short-term load in the prediction target period by using a pre-trained prediction model, wherein the prediction model is: The present application provides a power grid short-term load prediction method, system, computer device and storage medium, comprehensively considers the influence of long-term trend, seasonal factors, special events such as holidays and weather changes on the power grid load, establishes a load prediction model to accurately predict the future load of the power grid.

According to the in-province power flow calculation and report generation method and platform based on the digital intelligent AI, an integrated solution of data input, model calculation and report output is formed, standardization and processizing of provincial level power flow planning work are achieved, and the planning efficiency and the planning precision are improved; the method comprises the steps of 1, predicting load electric quantity, comparing and selecting data, and forming a high-medium-low scheme; historical load data, historical electric quantity data and historical economic data are uploaded, the load electric quantity is predicted by adopting 10 methods, and 10 groups of load electric quantities are predicted and generated; calculating an average value of the 10 groups of data, taking data similar to the average value as a middle scheme, taking a group slightly higher than the middle scheme as a high scheme, and taking a group slightly lower than the middle scheme as a low scheme; step 2, power balance and power flow calculation; step 3, report generation; and calling the DeepSeek-R1-0528 model to complete the writing of the report.

This invention discloses a time series forecasting method, apparatus, program product, storage medium, and its applications, relating to the field of time series analysis, to address the problems of high computational complexity and poor reliability of prediction results in time series forecasting tasks. This invention trains an inference model using time series data. This inference model extracts dependencies between variables based on the autocorrelation matrix of the input original time series; integrates these dependencies into the original time series to obtain key time-series features; learns long-term dependencies between variables from these key time-series features; and maps the time series for future time steps from these long-term dependencies. This invention achieves accurate time series forecasting with high reliability at a computationally low level.

The application discloses a kind of day-ahead wind power power ramp event prediction methods, comprising the following steps: S1.day-ahead wind power prediction: using extreme value driving model, based on historical wind power and meteorological characteristics, produce the wind power prediction of Q time points of next day;S2.predicting confidence interval construction: using wind power oriented conformal inference method, for each future time point, construct confidence interval C;S3.ramp event detection based on confidence interval: the prediction result of next day wind power ramp event is obtained by confidence perception detection algorithm.The application improves the prediction accuracy and reliability of wind power ramp event with significant operation risk by fusing multi-scale time series feature analysis, customized loss function for extreme event and adaptive confidence interval construction technology with statistical guarantee.

The present invention provides a resource adjustment method, device, server, and storage medium, relating to the field of cloud computing technology. The method comprises: predicting a first load for a prediction time period based on target user workloads for multiple first historical time periods, and predicting a second load for a prediction time period based on target user workloads for multiple second historical time periods; predicting a load for the prediction time period based on the first load and the second load; classifying the load for the prediction time period to obtain the total amount of resources for the prediction time period, and determining a target user resource adjustment value based on the total amount of resources for the prediction time period. An embodiment of the present invention provides a method for predicting load based on historical workloads on different dates and historical workloads on the same date but different time periods, and then determining a target user resource adjustment value based on the load, thereby improving not only prediction accuracy but also work efficiency.

This invention discloses an ozone forecasting method based on multi-model fusion, which consists of the following steps: data preprocessing, feature engineering, model training, model evaluation, model prediction, and model correction. This process ultimately yields reliable ozone prediction results. This method is easy to operate, data acquisition is readily available, and it does not require the collection of large amounts of precursor pollutant emission data. It can predict most ozone pollution conditions using only meteorological data, significantly improving prediction accuracy and compensating for the large biases in predictions based on a single model.

The invention discloses an intra-day electricity price probabilistic prediction method fusing time sequence depth representation and a gradient boosting tree. The method comprises the following steps: constructing a market state space and generating a multi-scale time sequence; feature depth engineering is carried out based on time-varying heterogeneity and a microstructure; performing time sequence depth representation and probabilistic prediction based on a hybrid model; and generating prediction probability density and deducing a multi-step path. The invention provides a brand new intra-day electricity price probabilistic prediction method. The method aims to deeply mine an internal dynamic rule of a time sequence through a hybrid neural network model, organically fuse the internal dynamic rule with heterogeneous features representing market states, and finally realize normal form transformation from traditional point prediction to probabilistic prediction with higher information value in combination with a quantile regression thought.

The application discloses a product forging data intelligent management system and method based on 5G cloud computing, and relates to the field of intelligent manufacturing.The system collects temperature, stress, load and image and other multi-source data through a process data module and marks them with weights; a multi-model reasoning module selects support vector regression, random forest and convolutional neural network in parallel prediction according to data characteristics; a prediction fusion module generates unified prediction results by using a nonlinear function based on confidence score; a cloud-edge collaborative scheduling module determines cloud or edge deployment in combination with task complexity, edge computing capability and network state; a parameter optimization module optimizes process parameters by using an EPQ-Opt algorithm based on energy consumption prediction and residual score; and a security guarantee module adjusts strategies and guarantees data security through consistency detection and robustness evaluation.The application significantly improves prediction accuracy and response speed, reduces energy consumption and enhances system security, and is suitable for high-end forging and intelligent manufacturing fields.

Methods and systems for managing inference models are disclosed. To manage inference models, a plurality of predictions that each indicate whether a state will occur may be obtained, the plurality of predictions being generated by respective inference models of at least one inference model. The plurality of predictions may be analyzed to obtain a statistical characterization regarding agreement in the plurality of predictions. A determination may be made regarding whether the statistical characterization meets criteria. In a first instance of the determination in which the statistical characterization meets the criteria, an action set may be obtained, the action set being based on an occurrence of the state predicted by the plurality of predictions to occur and usable to update an operating state of the data processing system to hedge against a risk of an undesired outcome from the occurrence of the state.

The invention relates to the technical field of digital economy, and provides a digital economy integration and optimization method and system based on an information chain, and the method comprises the following steps: data collection and integration: building a data integration platform, collecting market data, customer data and supply chain data, and integrating the data into a centralized data warehouse through ETL (extraction, conversion and loading); data analysis and mining: analyzing the integrated data based on a Transform model, and mining the market trend and demand; and real-time monitoring and prediction: predicting future market dynamics through an autoregression model by using an information chain and historical data, and supporting strategic decisions. Through ETL and standardization processing, the problem of multi-source data isomerism is solved, through combination of a Transform model and a self-attention mechanism, the market trend analysis accuracy is improved by 30%, the method is significantly superior to a traditional statistical method, through combination of an autoregression model and an information chain, real-time market monitoring and prediction are achieved, and the prediction error rate is reduced to 5% or below.

This invention relates to the field of enterprise management technology, specifically to an intelligent prediction method and system for enterprise management indicators, comprising: a data processing module, a prediction model module, and a prediction analysis module; the data processing module processes structured and unstructured data; the prediction model module constructs a prediction model to predict business activities and financial statements; and the prediction analysis module performs sensitivity assessment on the prediction results. This system, through processing and analyzing structured and unstructured data, and by combining macro and micro perspectives, achieves the prediction of enterprise management indicators, thereby improving the universality of the prediction.

Embodiments of the present disclosure relate to performance monitoring on prediction model In an aspect, a terminal device receives, from a network device, an indication of a first input type, or an indication of a second input type or an indication associated with a switch between the first input type and the second input type for a prediction model. The terminal device takes one of the following as an input of the prediction model for a next prediction: prediction results of the prediction model, wherein the indication of the first input type is received or wherein the indication associated with the switch is received and a previous input of the prediction model is measurements; or measurements of the feature, wherein the indication of the second input type is received or wherein the indication associated with the switch is received and a previous input of the prediction model is prediction results.

The application discloses a Markov attack path prediction method based on CVSS, and specifically comprises the following steps: step 1, scanning network host vulnerability information to generate a configuration file of.nessus; step 2, generating an attack graph: importing the configuration file generated in the previous step into Mulval, associating information between various host vulnerabilities through Mulval, and generating an attack graph; step 3, constructing a state transition graph: obtaining a simplified state transition graph according to the attack graph generated in step 2; step 4, initializing a Markov probability transition matrix: obtaining a probability transition matrix according to the state transition graph; and step 5, predicting an attack path probability. The method adopts a mode of measuring attack benefits to accurately predict a path to a single vulnerability level, realizes multi-step and multi-time prediction, simplifies the prediction method, and solves the problems of path redundancy, rationality and effectiveness of prior probability setting in the prediction path of the Bayesian model.

The application discloses a two-three-dimensional map adaptive projection matching method based on a hidden Markov chain, constructs a hidden Markov projection prediction model based on user preferences and projection characteristics, takes a map projection category as a hidden state, takes a user browsing position or a visual angle as an observation state, fuses user preferences and projection standard parameters to form a probability of each hidden state occurrence at each moment, updates an observation probability at each moment, and forms a current optimal projection matching combination through continuous iteration. The application integrates quantitative projection characteristics, combines user preferences, and influences a two-three-dimensional GIS visualization mode in a brand-new concept, selects a map projection suitable for different users and different scenes from an intelligent perspective, effectively overcomes browsing obstacles caused by a lack of projection field knowledge of part of users, and enhances a user's visualization experience.

The invention discloses a power plant coal consumption prediction method, device and system and a storage medium, which are used for improving the prediction precision of power plant coal consumption prediction. The method comprises the following steps: acquiring various preset data related to the coal consumption of the power plant; constructing an input feature vector for predicting the coal consumption of the power plant according to various preset data related to the coal consumption of the power plant; respectively inputting the input feature vector into a plurality of pre-constructed models, wherein the models comprise at least two of a first model for capturing a time sequence dependence rule, a second model for processing short-term mutation features and a third model for mining cross-power-plant knowledge migration association; and obtaining the attention weight of each model, fusing the output values of the plurality of models based on the attention weight, and taking the fusion result as the predicted value of the coal consumption of the power plant. By adopting the method, the prediction precision of power plant coal consumption prediction is improved by constructing a prediction system of multiple models.

The invention relates to the field of power system automation, and provides an industry power load prediction method based on ensemble learning and big data driving, and the method comprises the steps: S1, collecting multi-source data; s2, data preprocessing and feature engineering; s3, optimal feature selection and feature combination; s4, performing multi-model training and prediction; s5, predicting result fusion; and S6, recording a final prediction result. According to the method, a feature candidate set capable of comprehensively describing load driving factors is constructed by time sequence features, meteorological features and date social features, discrete weather types are quantified into continuous meteorological influence indexes, and dynamic weight time sequence features based on time attenuation coefficients are constructed; algorithms such as XGBoost and random forest are fused, and complex nonlinear relations and interaction effects in data can be automatically and efficiently learned and captured, so that the prediction precision is remarkably improved.

The application relates to the technical field of water conservancy engineering safety monitoring, in particular to a diversion channel side slope displacement dynamic interval prediction and abnormality identification method based on DeepAR, which comprises the following steps: input variable selection; correlation calculation; DeepAR model construction; model training and prediction; prediction effect evaluation; displacement prediction abnormality identification; the method has the beneficial effects that the displacement probability distribution at different time points is obtained, the mean value and the variance of the displacement prediction are dynamically calculated, the prediction interval changing with time under different confidence degrees is calculated through the probability distribution, the interval prediction model with the bandwidth changing with time is constructed, the prediction precision is improved, and the side slope displacement state is more comprehensively obtained.

The invention belongs to the technical field of data mining, and discloses a standard necessary patent prediction method based on transfer learning and a related device. The method comprises the following steps: acquiring target domain patent data and target domain patent data to be predicted; obtaining a pre-trained source domain standard necessary patent prediction model; carrying out transfer learning on the pre-trained source domain standard necessary patent prediction model based on target domain patent data to obtain a target domain standard necessary patent prediction model; and processing the target domain to-be-predicted patent data by using the target domain standard necessary patent prediction model to obtain a prediction result whether the target domain to-be-predicted patent can become a standard necessary patent or not. According to the method, a method of combining feature-based migration and model-based migration is adopted, data distribution differences are utilized, migration learning is used for improving the performance of standard necessary patent prediction, and the prediction accuracy of data of different countries is improved.

The embodiment of the invention provides a longitudinal water drive use degree prediction method and system, and belongs to the technical field of oil reservoir development. The method comprises the following steps: collecting physical experiment data and numerical simulation data corresponding to a target reservoir to form corresponding prediction basic data; constructing a corresponding using degree prediction model based on the prediction basic data; wherein the utilization degree prediction model comprises a plurality of evaluation indexes and prediction indexes constructed by attributes corresponding to prediction basic data; in the water drive process, real-time production data are collected, and real-time use degree prediction is conducted based on the real-time production data and the use degree prediction model; and carrying out development scheme optimization based on a real-time utilization degree prediction result, and carrying out data optimization on the scheme in real time. According to the scheme of the invention, the prediction precision of the use degree is improved, and the control capability on the complex dynamic change of the reservoir is enhanced.

The invention discloses a pre-orthogonal self-service projection prediction model construction method, and relates to the technical field of projection prediction, and the method comprises the following steps: data preprocessing; performing feature splitting and dimension determination; feature selection and maximum selection principle; an orthogonalization process; model training and forest construction; firstly, original data are preprocessed, a random feature matrix X and a target vector Y are obtained, and data preprocessing comprises data cleaning, denoising and missing value filling; according to the method, a plurality of basic models are integrated, an averaging processing means is adopted, the accuracy of a prediction result is enhanced, a self-adaptive maximum selection mechanism is applied, the complex relevance between variables is grasped, the feature selection process is optimized by implementing a self-adaptive sparse constraint strategy, the most influential feature is screened out, and the accuracy of the prediction result is improved. The prediction efficiency of the model is improved, the adaptive characteristic of the model is enhanced, and it is ensured that the model can show excellent generalization performance when facing new data.

The invention belongs to the technical field of corrosion protection and prediction of ocean engineering structures, and particularly relates to a method for predicting the cathode protection potential of an FPSO stand pipe supporting structure. According to the prediction method, the advantages of the seasonal autoregression integral moving average model and the long short-term memory neural network are combined, collaborative modeling and high-precision prediction of linear and nonlinear characteristics in the potential data are achieved, the prediction precision is high, and the prediction result robustness is high. The method for predicting the cathode protection potential of the FPSO riser support structure comprises the following steps: collecting historical potential time sequence data of the FPSO riser support structure under the condition of external cathode protection potential, and preprocessing the historical potential time sequence data; constructing and training a seasonal autoregressive integral moving average model; constructing and training a long-short-term memory neural network model; and performing combined prediction on the target time period to obtain a prediction result of the target time period of the cathode protection potential of the FPSO riser support structure.

The invention relates to a converter valve submodule monitoring method based on status words and a computer system, and belongs to the technical field of power system fault prediction. According to the invention, the fault state of the sub-module after the current time period is predicted according to the electrical quantity time sequence data and the status word sequence of the sub-module in the current time period, the prediction result is output in the form of the status word, and the sub-module is monitored according to the predicted status word. The electrical quantity time sequence data and the status word sequence of the sub-module are selected for prediction, fault related information of the sub-module is effectively reflected, the potential relation between each fault state and the abnormal state of the sub-module is captured through prediction of the fault state of the sub-module, accurate prediction and monitoring of the sub-module are achieved, and the fault diagnosis accuracy of the sub-module is improved. The fault prediction and monitoring capability of the flexible direct current converter valve sub-module is effectively improved, and the problem that potential abnormity cannot be found and processed in time due to the fact that real-time online analysis cannot be carried out on the sub-module in the prior art is solved.

The invention discloses a spaceflight BDR module life prediction method based on Arrhenius and Wiener models. The spaceflight BDR module life prediction method comprises the following steps of S1, determining life characteristic parameters of a BDR module; s2, designing a stepping accelerated degradation test scheme; s3, preprocessing the test data in the step S2; s4, establishing a mixed life prediction model; s5, importing the preprocessed test data into the mixed life prediction model for model parameter identification; and S6, based on the identified mixed life prediction model, extrapolating to obtain the actual life of the BDR module. According to the method, the actual service life of the BDR module under the typical working condition of 25 DEG C is predicted, the prediction error is lower than 9%, the development requirements of high reliability and long service life of spaceflight electronic products are met, the test effect is high, and sample consumption is low.

The invention relates to an energy consumption prediction method of an improved gray model based on Caputo fractional derivative and fractional adaptive reverse accumulation, and belongs to the field of energy consumption prediction. According to the method, a Caputo fractional derivative and a fractional adaptive reverse accumulation operator are introduced, so that a prediction model has a dynamic memory function, and weights of new and old information in data can be adaptively adjusted; secondly, a nonlinear correction term and an optimized background value are added into the model, so that the fitting performance of nonlinear data is enhanced; and then, obtaining an analytical solution of the model by utilizing Laplace transformation, and performing parameter optimization by applying a particle swarm optimization algorithm to ensure the optimal performance of the model. And finally, applying the model to prediction of the average daily energy consumption in China. The prediction result not only provides practical value for the application of the new model in the field of energy consumption prediction, but also provides reliable theoretical basis and data support for relevant decision making.

This invention belongs to the field of oil and gas exploration technology, and relates to a method and system for quantitative seismic prediction of free oil porosity. In the prediction process, high-resolution seismic elastic parameter data volumes obtained through pre-stack statistical inversion are used, and a set of machine learning prediction feature values ​​for free oil porosity is constructed based on rock physical analysis, improving the prediction capability of free oil porosity in thin sweet spots. Finally, using the KRR free oil porosity seismic prediction model, the free oil porosity information in seismic elastic parameters and sensitive seismic attributes is deeply mined to achieve quantitative prediction of free oil porosity, with a prediction accuracy of 90%, which is more than 20% higher than the prediction accuracy of conventional methods.