15 results about "Temperature forecasting" patented technology

A method, computer program product, and computing system for forecasting a temperature of a storage object of a storage system using a machine learning model. The storage object may be divided into a plurality of storage sub-objects. A temperature may be determined for each storage sub-object using a simple moving average. A portion of the temperature of the storage object may be projected onto the temperature of each of the plurality of storage sub-objects based upon, at least in part, the temperature determined for each storage sub-object and the temperature determined for each storage object.

The application discloses a kind of urban solid waste incineration process furnace temperature robust prediction method, comprising the following steps: S1, according to the initial furnace temperature model of preset training set is established;S2, assume that the prior distribution of noise in training data follows skew t distribution, the output weight and the set of hyperparameters of model are iteratively optimized by maximum likelihood estimation and expected conditional maximum algorithm, establish furnace temperature prediction model;S3, furnace temperature in incineration process is predicted by furnace temperature prediction model.The process data of urban solid waste incineration process is obtained in real time, and the furnace temperature prediction model based on robust random configuration network is established, the prior distribution of asymmetric abnormal value in incineration process operation data is simulated by skew t distribution with heavy tail characteristics, and the output weight of furnace temperature prediction model is solved by maximum likelihood estimation method, the robustness of furnace temperature prediction model to abnormal data is improved, and the real-time accurate prediction of urban solid waste incineration process furnace temperature is realized.

The application relates to the technical field of marine environment prediction, and discloses a two-branch two-stage sea surface temperature prediction method based on multi-element input. The method acquires and pre-processes multi-element data such as sea surface temperature, 2-meter temperature and atmospheric top incident solar radiation; a two-branch collaborative optimization deep learning model is constructed, and the model is trained; data of continuous days before the time to be predicted is input into the model to generate a future sea surface temperature prediction result. Among them, a short-term prediction branch extracts space-time features through ConvGRU and multi-scale convolution to predict a short-term result, and a medium and long-term prediction branch models long-range dependence through adaptive weighting and a Transformer encoder to predict a medium and long-term result; a future multi-day prediction is generated through self-recurrence rolling. Through two-branch collaboration, the application suppresses error accumulation, significantly improves the precision and stability of medium and long-term sea surface temperature prediction, and can provide efficient and accurate technical support for marine resource development.

The invention relates to the technical field of air temperature forecasting, and discloses an air temperature forecasting model construction method based on machine learning, which comprises the following steps of: collecting live data, namely, high-low temperature and rainfall per 3h of 78 national meteorological stations in Hubei province, and EC high-resolution mode analysis and forecasting data; preprocessing the data, cleaning the original data, and generating a sample set; utilizing a machine learning method to establish a 3h-by-3h air temperature forecasting model of the sub-stations; inputting the training set data in the three groups into an air temperature forecasting model, and extracting the features of the training set data; outputting a result, and performing applicability evaluation on the air temperature forecasting model; optimizing the air temperature forecasting model, inputting the test set or new data into the air temperature forecasting model, and calculating an average absolute error; and deploying the trained model on an intelligent grid service platform to carry out model business. In conclusion, the temperature forecasting capability is improved, and the automatic, objective and intelligent forecasting level is improved.

The invention discloses a sintering air bellow temperature forecasting method and system based on a local feature Transform network, and belongs to the technical field of intelligent monitoring in the metallurgical process. The method comprises the steps that waste gas temperature, trolley speed and material layer thickness data of a target air bellow and an adjacent air bellow are collected and preprocessed; performing sliding window slicing on the historical data to construct a sample set; the method comprises the following steps of: constructing a local feature Transform network which is independently designed by adopting a channel, performing Patch division on each variable sequence to extract a time sequence local feature, and capturing an internal dependency relationship of variables by utilizing a self-attention mechanism; and training and optimizing network parameters, and finally realizing accurate prediction of the exhaust gas temperature of the target bellows in a future period of time. The method effectively solves the problems that an existing method depends on a mechanism model, parameters are difficult to obtain, the generalization ability is poor, and a local time sequence mode is insufficient to capture, and the forecasting precision and the working condition adaptability are improved.

This invention relates to a method for correcting temperature forecasts using a large meteorological model based on short-term real-time information calibration. The method includes: S1, data collection; S2, data preprocessing and sample set creation; S3, temperature correction forecast model construction; S4, sample set partitioning and model training and testing; and S5, outputting the temperature forecast result after short-term real-time calibration. This invention, by fully utilizing the prior information of the large meteorological model forecast, introduces residual information between short-term real-time data and the forecast as a constraint, revealing the spatiotemporal correlation structure of the modeling error and its evolution with forecast lead time. Furthermore, it enables the correction process to adaptively adjust the calibration strategy according to the error state, thereby improving the accuracy, stability, and consistency of temperature forecasts and enhancing the operational application level of large meteorological model temperature forecast calibration technology.

The invention relates to the technical field of marine environment forecasting, and discloses a double-branch two-stage sea surface temperature forecasting method based on multi-element input. The method comprises the following steps of: acquiring multi-element data such as sea surface temperature, 2-meter temperature and atmospheric top incident solar radiation and preprocessing the multi-element data; constructing a double-branch collaborative optimization deep learning model, and training the model; and inputting data of continuous days before a to-be-forecasted moment into the model, and generating a future sea surface temperature forecasting result. Wherein the short-term forecasting branch extracts spatial-temporal characteristics through ConvGRU and multi-scale convolution to forecast a short-term result, and the medium and long-term forecasting branch carries out modeling long-range dependence through adaptive weighting and a Transform encoder to forecast a medium and long-term result; and a future multi-day forecast is generated through autoregression rolling. According to the method, error accumulation is inhibited through double-branch cooperation, the precision and stability of medium-and-long-term forecasting of the sea surface temperature are remarkably improved, and efficient and accurate technical support can be provided for ocean resource development.

The invention discloses an hour-by-hour air temperature objective correction method based on a high-resolution numerical mode, and the method comprises the steps: collecting monitoring station data of a preset region, and carrying out the preprocessing of the monitoring station data; performing temperature daily change rule and mode deviation characteristic analysis according to the monitoring station data to obtain temperature daily change characteristics, constructing a multi-mode integration scheme based on dynamic weight, and averagely fusing the multi-mode integration scheme by adopting a Bayesian model to obtain an integration forecast; performing product detection evaluation on the integrated forecast according to the temperature daily change characteristics to obtain temperature evaluation, constructing an optimal similar set correction localization parameter according to the temperature evaluation and mode physical quantity correlation analysis, and establishing an optimal similar set correction method; sliding error regression correction is adopted for predicting and recorrecting the hour-by-hour temperature in the adjacent time period of the optimal similar set correction method, hour-by-hour temperature objective correction data are obtained, and a correction result is output.

The invention provides a combined temperature forecast correction method and system, and relates to the technical field of weather forecast. According to the method, three kinds of errors are systematically corrected, and the climate mode temperature forecast deviation is corrected. The method comprises the following steps: firstly, considering an error source of temperature forecast, and respectively disassembling observation temperature data and original forecast temperature data in a training period into three independent components, namely a mean term, a trend term and a residual term; and using conditional Gaussian correction to optimize the residual term error, and keeping the rank correlation structure of the original ensemble forecast. And according to requirements, performing mean value correction, trend correction and residual error correction on the original forecast temperature data, combining a mean value correction result, a trend correction result and a residual error correction result of the original forecast temperature data, and outputting a combined temperature forecast correction result. The method is used for temperature forecast correction and has the advantages of being good in correction effect, flexible to use, efficient in calculation and the like.

This invention relates to the field of ocean temperature forecasting, specifically a three-dimensional sea surface temperature (SST) numerical forecast correction method based on a physically constrained spatiotemporal graph network. It aims to address the problems of shallow algorithm models, limited spatiotemporal dimensions, and poor adaptability in existing SST numerical forecast correction methods. The method first utilizes Kriging interpolation to spatially reconstruct and spatiotemporally align multi-source SST data. Second, it constructs a fully coupled spatiotemporal-depth model, combining graph convolutional networks, spatiotemporal attention mechanisms, and LSTM to extract multidimensional features and temporal patterns, and uses a deep embedding module to characterize seawater structure. During model training, the three-dimensional heat diffusion equation and vertical temperature gradient smoothing constraints are explicitly embedded into the loss function, constructing an optimization objective driven by both data and physics. Finally, the optimal model is used to predict residuals and generate the final correction result. This method can correct systematic biases in numerical forecast products and improve the accuracy of SST forecasts in complex sea areas.

The invention provides a grain pile space temperature field anomaly dynamic prediction method based on a graph neural network, and relates to the technical field of grain pile disaster prediction.The method comprises the steps that a temperature prediction model is built in the graph neural network through historical temperature data, and a predicted temperature sequence is obtained; obtaining temperature forecast, obtaining a temperature influence coefficient by combining the change rate of the temperature forecast and the change rate of the predicted temperature sequence, forming a corrected predicted temperature sequence, obtaining historical pest and disease damage data and a disease temperature sequence, screening a new site and a re-site according to the corrected predicted temperature sequence, obtaining a re-occurrence coefficient, and obtaining the disease damage data of the pest and disease damage data of the pest and disease damage data of the pest and disease damage data of the pest and disease damage. And respectively adjusting the corrected predicted temperature sequences to obtain evaluation sequences, and analyzing the risk of plant diseases and insect pests. Dynamic prediction of the grain pile temperature is achieved by building the temperature prediction model, and diseases and pests are found in advance in combination with the grain pile temperature and the disease and pest history.

The invention discloses a remote sensing end-to-end ocean three-dimensional temperature forecasting method based on artificial intelligence. The method comprises the following steps: acquiring multi-source remote sensing data and ocean reanalysis data, preprocessing the acquired multi-source remote sensing data and reanalysis data, constructing a space-time sequence forecasting model, training the space-time sequence forecasting model to be qualified, inputting the preprocessed multi-source remote sensing data into the space-time sequence forecasting model which is trained to be qualified, and forecasting the ocean reanalysis data according to the preprocessed space-time sequence forecasting model. And obtaining a forecast result, and carrying out visual display on the forecast result. According to the method, a remote sensing end-to-end forecasting mode is used, a generative space-time model architecture and a sliding window attention mechanism are provided, a space-time problem is disassembled into a space problem combined with a time dimension, and a global attention mechanism is simplified into a window attention mechanism by performing window segmentation in space, so that the calculation overhead is reduced, and the calculation efficiency is improved. And high-resolution ocean three-dimensional environment forecasting can be realized without inputting a three-dimensional numerical mode background field.

A method, computer program product, and computing system for forecasting a temperature of a storage object of a storage system using a first machine learning model and a plurality of input / output (IO) features. The storage object may be divided into a plurality of storage sub-objects. A temperature may be determined for each storage sub-object with a subset of the plurality of IO features using a second machine learning model. A portion of the temperature of the storage object may be projected onto the temperature of each of the plurality of storage sub-objects based upon, at least in part, the temperature determined for each storage sub-object and the temperature determined for each storage object.

The invention provides a strip steel temperature forecasting method and system, electronic equipment and a storage medium, and relates to the technical field of metallurgy control, and the method comprises the steps that the actual temperature and rolling related data of strip steel at the key position in the current period are obtained; determining the heat exchange coefficient of the strip steel in the current period according to the rolling related data through the heat exchange coefficient model of the current period; through a strip steel temperature field calculation model, according to the rolling related data, combined with the heat exchange coefficient in the current period, the forecast temperature of the strip steel at the key position is determined; according to the forecast temperature and the actual temperature corresponding to the key position, through an optimization algorithm, key mechanism parameters in the heat exchange coefficient sub-model are inverted, and updated parameters of the key mechanism parameters are obtained; and the heat exchange coefficient model is updated according to the updating parameters, and the heat exchange coefficient model of the next period is obtained. And through a closed-loop dynamic temperature forecasting process, the forecasting precision of the strip steel temperature under different working conditions is improved.

The application belongs to the field of numerical prediction, and discloses a deep neural network mean sea surface temperature prediction method, wherein the sea surface temperature in reanalysis grid data information is selected as a prediction true value of a to-be-detected prediction area; data matching is performed to obtain a variable element data set matched in time and space levels; a sea surface temperature prediction training set is constructed; a multi-layer network structure of a mean sea surface temperature prediction model fusing spatial partial derivative value solving is built, and the idea of a Runge-Kutta method in a numerical mode is combined to complete multi-step prediction of the sea surface temperature. The application models the time and space characteristics of variables, overcomes the defects of discrete errors of a traditional numerical prediction method, poor interpretability of traditional deep learning, and strong data dependence, and combines existing prior knowledge in numerical prediction and certain training data to obtain more accurate element prediction results.