27 results about "Temperature forecasting" patented technology

The invention relates to a temperature forecast correction method based on a PSD-Net and a PSD-Net, and belongs to the technical field of weather forecast, and the method comprises the steps: obtaining a dynamic meteorological variable based on the PSD-Net, and loading topographic data and a report starting time observation truth value at the same time; preprocessing the dynamic meteorological variable, the topographic data and the report starting time observation truth value; inputting the preprocessed data into a temperature forecast correction model to obtain temperature correction field data; wherein the temperature forecast correction model is obtained by training a PSD-Net model based on a training data set, and the training data set comprises historical dynamic meteorological variables, topographic data and a report starting time observation true value. Compared with the traditional numerical mode and the original output of the archaeological model, the temperature forecast MAE corrected by the method is reduced by more than 37.6%, the accuracy rate within 2 DEG C is improved by 14%-19%, and the precision advantage is more prominent especially in complex terrain areas and extreme weather events.

The invention provides a finish rolling inlet temperature forecast control method and device, electronic equipment and a storage medium, and relates to the technical field of steel rolling, and the method comprises the following steps: firstly, constructing a temperature forecast control model based on historical data in the hot rolling cooling process of different plates, and then according to the temperature data collected at the real temperature and the output result of the temperature forecast control model, calculating the temperature forecast control value; dynamically adjusting parameters of the temperature forecast control model; based on the deviation between the temperature distribution predicted by the temperature forecast control model and the target temperature distribution, parameters of a cooling system are adjusted so as to control the cooling temperature of a finish rolling inlet; through the method, the technical problem that the cooling temperature control precision is low in the hot rolling production process is solved, and the technical effects of improving the temperature stability of a finish rolling inlet, and improving the cooling efficiency and the product quality stability are achieved.

The invention relates to the technical field of temperature forecasting and machine learning, and provides a sea surface temperature forecasting statistical correction method based on machine learning, and the method comprises the following steps: obtaining sea surface temperature forecasting data of a target area and sea surface temperature observation data of the target area; constructing a statistical correction model; a neural network used for calculating model parameters of a statistical correction model is constructed, features reflecting the position of a target area and the sea surface temperature of the target area are input into the neural network, and the neural network outputs the model parameters of the statistical correction model; the sea surface temperature forecast data, the sea surface temperature observation data and the model parameters are input into the statistical correction model, and the statistical correction model calculates a sea surface temperature forecast statistical correction result based on the model parameters, the sea surface temperature forecast data and the sea surface temperature observation data; by adopting the method, the sea surface temperature forecasting error can be reduced, and the forecasting precision is improved.

The application provides a finish rolling inlet temperature prediction control method and device, electronic equipment and storage medium, relates to the rolling technology field, and the method first constructs a temperature prediction control model based on historical data in the hot rolling cooling process of different plates. Then, according to the temperature data collected at the real temperature time and the output result of the temperature prediction control model, the parameters of the temperature prediction control model are dynamically adjusted. Based on the deviation between the temperature distribution predicted by the temperature prediction control model and the target temperature distribution, the parameters of the cooling system are adjusted to control the cooling temperature at the finish rolling inlet. The above method solves the technical problem of low cooling temperature control precision in the hot rolling production process, and achieves the technical effects of improving the finish rolling inlet temperature stability, improving the cooling efficiency and product quality stability.

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.

The application discloses a continuous annealing water mist cooling process section temperature prediction method, comprising the following steps: obtaining process parameters and field feedback data of a water mist cooling section equipment; calculating the relationship between specific heat capacity, density and strip steel temperature; calculating the strip steel temperature after heat dissipation from the end point of the slow cooling section to the start point of the water mist cooling section; calculating the relationship between the heat exchange coefficient of the strip steel and the strip steel temperature in the water mist cooling process; calculating the cooling amount of the strip steel; calculating the heat exchange correction coefficient; calculating the actual heat exchange coefficient; calculating the temperature of the strip steel after passing through the water mist cooling section; and calculating the final temperature after heat dissipation from the end point of the water mist cooling section to the outlet of the unit. The application combines the water mist cooling equipment and utilizes the related knowledge of heat dissipation principle to predict the temperature change in the water mist cooling process, which is beneficial to effectively setting the cooling capacity of the water mist cooling equipment.

This invention relates to the field of temperature forecasting technology, and more particularly to a method and system for analyzing the temperature sensitivity of load impact based on regional characteristic analysis. The method includes the following steps: acquiring historical power load data, temperature data, geographic information data, and energy usage ratio data corresponding to a target area, and performing time-series synchronous preprocessing and quantification of regional characteristic indicators to obtain corresponding power regional characteristic indicators within the same sub-region; performing regional classification impact assessment and load sensitivity calculation on the corresponding geographic sub-regions within the target area to obtain the temperature sensitivity coefficients of power load in different categories of regions; and performing power resource allocation management on the corresponding geographic sub-regions within the target area to generate power resource allocation management strategies for different temperature-sensitive areas, thereby executing corresponding power resource optimization allocation management work. This invention enables more accurate load forecasting and optimized power resource allocation.

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 relates to a forecasting method, device and equipment based on temperature actual condition and prediction data and a medium. The forecasting method based on the temperature actual condition and prediction data comprises the following steps: acquiring temperature prediction data and temperature actual condition data of a target area; determining a temperature prediction deviation based on the temperature prediction data and the temperature live data; if the temperature prediction deviation meets a deviation correction condition, correcting the temperature prediction data through a pre-trained temperature prediction deviation model to obtain a corrected temperature prediction result; and performing snowfall forecasting based on the corrected temperature forecasting result to obtain a corresponding snowfall forecasting result. According to the embodiment of the invention, the accuracy of temperature prediction in an extreme disaster process can be improved, and the prediction capability of a sudden snow disaster in an extreme cooling process is improved.

The invention discloses a direct fire heating section strip steel temperature forecasting method. The method comprises the steps of constructing transverse division of strip steel under a single pair of furnace rollers, collecting process parameters of a field production direct fire heating section, calculating the forced convective heat transfer capacity of a direct fire burner, calculating the radiation heat transfer of flue gas to the strip steel, calculating the radiation heat transfer of a furnace wall to the strip steel, and calculating the temperature of a direct fire heating outlet. According to the method, infinitesimal calculation is carried out on the single pair of furnace rollers in the direct fire heating section, the outlet temperature of the strip steel in the direct fire heating stage is obtained, and the temperature condition of the strip steel can be effectively forecasted. By applying the method, the temperature of the strip steel can be effectively and accurately forecasted, the temperature condition of the strip steel can be forecasted in advance before production, the temperature fluctuation of the strip steel is prevented from being too large, and the performance fluctuation of the strip steel is reduced; and the repair condition caused by strip steel temperature fluctuation is reduced, and the production efficiency is improved.

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.

The invention discloses a vehicle charging control method and device, equipment and a storage medium, and the method comprises the steps: detecting whether a vehicle starts an intelligent travel function for reserving the future vehicle use time or not after a charging instruction is received; if yes, weather forecast data, including temperature forecast data, between the current time and the car reservation time is obtained; calculating a weighted temperature value according to the temperature forecast data, and obtaining a temperature deviation value in combination with the real-time battery cell temperature; and if the deviation value exceeds the preset range, the thermal management assembly is started preferentially in the electric charge trough period in the future time period, and charging is executed after the battery temperature is preprocessed to the optimal slow charging interval. According to the method, prospective judgment is carried out by introducing the vehicle reservation time and the weather forecast, and high-energy-consumption temperature regulation and control are transferred to a low-price electricity period to be executed, so that the total charging cost is effectively reduced, and the efficiency is improved. The method can be widely applied to the technical field of vehicles.

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 discloses a sea surface temperature forecasting method and system based on deep learning and a storage medium, and relates to the technical field of sea forecasting. The method comprises the following steps: performing disturbance processing on an initial field by adopting a growth model propagation method to obtain a disturbance initial field; constructing a sea surface temperature forecasting model based on deep learning, using an improved SwinTransform network as a backbone network, and training the backbone network to obtain a trained sea surface temperature forecasting model; performing 24-hour scale forecasting on set members through the trained sea surface temperature forecasting model by using the disturbance initial field to generate a forecasting set; in a forecast assimilation cycle process, a background error covariance matrix is calculated by using a background error covariance matrix calculation model based on deep learning to perform data updating; and inputting the updated analysis set as an initial field of the next assimilation period into the sea surface temperature forecasting model. The sea surface temperature assimilation capability and the sea surface temperature forecasting effect are improved.

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 invention relates to the technical field of weather forecast correction, in particular to a PM2.5 concentration-based logarithmic value mode temperature forecast correction method, which comprises the following steps of: S1, collecting hourly hourly temperature data and daily highest and lowest temperature data in the past three years, and simultaneously acquiring PM2.5 concentration data in a corresponding time period; s2, deviation analysis is carried out; and S3, selecting 155g / m as a PM2.5 concentration threshold value, and dividing the data sample into a high-concentration sample (Chigh) and a low-concentration sample (Craw). And S4, determining which regression model is used to carry out temperature forecast correction by predicting the PM2.5 concentration of the current day. According to the method, on the basis of the statistical relation between the PM2.5 concentration and the temperature forecast deviation, the forecast deviation under different pollution concentration conditions is coped with through a double regression model strategy, effective correction of traditional numerical mode forecast is achieved, and the accuracy and reliability of temperature forecast are 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.

The invention relates to the technical field of forecast error analysis, in particular to a temperature forecast error evaluation method under an extreme weather condition, which comprises the following steps: identifying core influence factors of extreme weather temperature forecast; quantifying the dimension of each core influence factor and the corresponding quantitative index, and calculating the influence weight of each core influence factor on the forecast error; constructing a global error evaluation model and optimizing and solving to obtain a global error evaluation result; based on the global error evaluation result, constructing a deviation attribution model and optimizing and solving to obtain a deviation attribution scheme; and based on a global error evaluation result and a deviation attribution scheme, carrying out error feedback on extreme weather temperature forecast. The method can provide more accurate, scientific and efficient temperature forecast under complex extreme weather conditions.