17results about How to "Avoid forecast errors" patented technology

The invention discloses a photovoltaic power generation power prediction method and system based on similar daily clustering and FEDform, and the method comprises the steps: obtaining photovoltaic power generation power historical data of a photovoltaic power station, carrying out the preprocessing of the photovoltaic power generation power historical data, and replacing a missing value with a mean value of the data of a same time node; clustering the replaced photovoltaic power generation power historical data set by using a KFCM, and evaluating a clustering effect in combination with a clustering evaluation index; performing correlation analysis on historical data sets after similar daily clustering of the KFCM clustering algorithm through an SRCC method, and determining meteorological characteristic factors with relatively high correlation with photovoltaic power generation power as input variables of an FEDformer prediction model; decomposing the correlation data set by using VMD to obtain a plurality of groups of subsequences so as to further extract features of different time scales; and predicting each sub-sequence by adopting an FEDformer prediction model, and accumulating prediction results of the sub-sequences to obtain a final photovoltaic power generation power prediction result. The stability of the photovoltaic power generation power and the accuracy of the prediction effect can be remarkably improved.

This invention proposes a method for predicting the health status of lithium batteries based on multidimensional features and neural network constant differential equations. The method includes the following steps: S1, preprocessing the capacity data and charging stage operation data collected during lithium battery operation, and constructing features from historical health status data; S2, constructing multidimensional feature inputs for health status prediction based on the charging stage operation data; S3, inputting the multidimensional features into a gated recurrent unit network to fuse and encode the historical health status sequence and constant current charging stage features to obtain a potential feature representation characterizing the battery degradation state; S4, comparing the predicted health status value output by the neural network constant differential equation model with the corresponding actual health status value, calculating the prediction error, and evaluating the prediction accuracy. This application achieves high-precision prediction of lithium battery health status by integrating a multidimensional feature screening mechanism and a continuous-time state evolution modeling method.

The invention relates to a tread pattern depth estimation method based on a physical information fusion network, and belongs to the technical field of intelligent traffic systems and vehicle active safety. The method comprises the following steps: firstly, acquiring three-axis acceleration data under different working conditions through a tire built-in sensor; zero phase shift filtering, phase alignment and resampling preprocessing are carried out on the signals to form standard waveform data; then constructing a spatial-temporal feature extraction network, extracting time sequence features through a convolutional layer and a circulating layer, and fusing normalized load and speed working condition information; a physical constraint module based on a tire rigidity mechanism is introduced, the pattern depth and the vertical deformation amount are predicted by using learnable parameters, and a theoretical load is reversely deduced to establish a mechanical equilibrium constraint; and finally, network parameters and physical parameters are synchronously optimized by adopting a mixed loss function, and wear state grades and confidence coefficients are output through a probability statistical method. According to the method, the estimation precision and the physical interpretability of the model under the complex variable load working condition are effectively improved.

The application discloses a method for instruction branch prefetching in an AIGPU processor, which comprises the following steps: 1) defining a branch prefetching instruction in a GPU instruction set, the branch prefetching instruction is used to check whether the instruction at label exists in the cache, if the instruction at label does not exist in the cache, one or more instruction data at label are fetched from the lower storage to the cache; 2) according to the PC absolute value or relative value coded by the branch prefetching instruction, the data at the program branch instruction address is prefetched. The application provides a mechanism for branch prefetching through an instruction, which can reduce the performance loss during branch jumping and improve the system performance. The application does not use a complex branch prediction circuit, and the prediction delay and prediction error are avoided.

The invention provides a cascade hydropower station reservoir water level prediction and early warning method and device, and the method comprises the steps: calculating the starting and load distribution conditions of each unit in an upstream hydropower station at each moment according to an upstream hydropower station load plan curve; calculating the total ex-warehouse flow of the upstream hydropower station based on the calculated load distribution condition and the gate opening state; performing time delay on the total ex-warehouse flow of the upstream hydropower station by using the flow transfer delay factor to serve as the total in-warehouse flow of the downstream hydropower station; according to the load plan curve of the downstream hydropower station, calculating the total ex-warehouse flow of the downstream hydropower station; the reservoir capacity change condition of the downstream hydropower station is calculated through the algebraic sum of the total reservoir inflow and the total reservoir outflow of the downstream hydropower station, and the reservoir outflow water level change is calculated based on the reservoir capacity change; and drawing a reservoir water level change curve according to reservoir water level change, and comparing the reservoir water level change curve with set water level early warning parameters to realize water level early warning. Early warning can be provided for water level out-of-limit of the downstream hydropower station.

The present invention relates to the technical field of thermal power plants, and in particular to a method and system for predicting the load of a thermal power plant. The method comprises the following steps: obtaining real-time operation data of a thermal power plant, including historical load data, unit operation parameter data, environmental parameter data, and power grid dispatching data; performing data missing processing based on a time series interpolation method on the real-time operation data, and detecting and correcting abnormal values ​​to obtain operation preprocessing data; performing multi-scale time feature extraction on the operation preprocessing data to obtain time feature data, wherein the multi-scale time feature includes hourly features, daily features, and weekly features; and constructing a multi-level load prediction model based on the time feature data. The present invention comprehensively covers the load features at different time levels such as hours, days, and weeks through multi-scale time feature extraction, providing richer input information for prediction.

The invention discloses a short-time airport departure passenger volume prediction method based on flight and security check integrated information, and belongs to the technical field of civil aviation transportation and intelligent transportation. Comprising the following steps: acquiring a flight information table and a passenger security check time table, and screening the flight information table and the passenger security check time table to obtain processed data; historical passenger advanced arrival time is collected, and fitting is carried out on the historical passenger advanced arrival time through a logarithmic normal distribution curve to obtain fitting parameters; predicting the advanced arrival time of the passenger based on the fitting parameters and the historical processing data; performing parameter adjustment on the fitting parameter to obtain an adjusted fitting parameter; obtaining a plurality of similar days of the to-be-predicted day based on the weather type and given features, and calculating an average value of adjustment fitting parameters of the similar days; a first parameter matrix is constructed based on the adjustment fitting parameters of each hour segment, and a second matrix is constructed based on the processing data; and generating a random number through the first parameter matrix and the second matrix, and obtaining a passenger arrival prediction amount counted by an hour set within one day based on the random number.

The application discloses a nozzle ablation prediction method based on control mechanism and diffusion contribution degree, and belongs to the technical field of thermal protection of solid rocket engines. The method obtains nozzle structure parameters, thermal protection material parameters and gas inflow parameters, calculates the Mach number, pressure and temperature of any section of the nozzle based on one-dimensional isentropic flow relationship, respectively calculates the ablation rates under chemical reaction control and diffusion control, calculates Damkohler number by taking the ratio of the two, and determines the ablation control mechanism. Further, the diffusion contribution degree constant is introduced to continuously correct the ablation rate in the transition stage, and finally the predicted ablation rate is output. The method has high calculation efficiency and can improve the prediction accuracy of the nozzle ablation.

This application provides a computer simulation-based method and system for simulating thermal desorption, mass transfer, and heat transfer, relating to the field of computer simulation technology. This application obtains a constructed geometric model of a contaminated soil pile and acquires multiple sets of pore pressure gradients at different depths within the contaminated soil pile at different times, along with corresponding gas Darcy velocities. Support vector regression is used to perform regression analysis on these multiple sets of pore pressure gradients and gas Darcy velocities to calculate the permeability tensor. The Darcy resistance term in the momentum conservation equation is corrected based on the permeability tensor of each grid cell, generating a gas flow equation for each grid cell. The gas flow equations of all grid cells are then combined to obtain the gas velocity field. The velocity vector is used as a convection parameter and substituted into the pre-set heat transport equation and pollutant transport equation to obtain the simulation results of thermal desorption, mass transfer, and heat transfer, achieving accurate simulation of the dynamic permeability changes caused by the gas slippage effect under high vacuum extraction.

The present disclosure relates to a model training, information processing method, device, medium and electronic equipment. The method comprises: obtaining training data, including first state information of reference carrying capacity in a first period, first reward information and second state information in a second period; predicting first order response information in the first period and second reward information in the second period through a target model according to the first state information and the first reward information; predicting second order response information in the second period through a model according to the second state information and the second reward information; parameter updating of the model is performed with the target confidence parameter and the product of the first joint probability distribution as the target; if the training termination condition is not met, return to the step of obtaining the training data; otherwise, obtain a reward prediction model. In this way, a reward prediction model with good generalization ability in counterfactual data can be reconstructed in a dataset with strong certainty and selection bias, so that the downstream solves the correct decision action.

The invention provides a charging behavior prediction model construction and prediction method and system based on a large model, and the method comprises the steps: carrying out the time sequence arrangement of a plurality of groups of historical charging data, selecting the historical charging data of a corresponding group number according to the window width of an incremental window method and a time sequence, and constructing a plurality of samples, and obtaining a sample set; the window width is gradually increased as time goes on; based on the sample set, training a large language model by adopting a low-rank adaptive supervised fine tuning method to obtain a charging behavior prediction model, and performing prediction by adopting the charging behavior prediction model to obtain charging data of next charging of the to-be-predicted user; according to the method and system, a sample set is constructed through multiple groups of historical charging behavior data and an incremental window method, multi-source information is fused, and the application value and prediction accuracy of a prediction model are improved; and meanwhile, historical charging behavior data of the user is deeply understood by utilizing the generation capability of the large language model to carry out comprehensive prediction, richer and more accurate prediction results are provided, and the interpretability of the prediction results is improved.

Methods, systems, and apparatus for calibrating abstention strategies to mitigate prediction errors in neural networks, including computer programs encoded on a computer storage medium. In one aspect, a system includes: receiving an input cue; processing the input cue using a neural network to generate a plurality of candidate outputs in response to the input cue; determining a similarity score characterizing the similarity between each of the candidate outputs and each of the other candidate outputs; determining whether the similarity score satisfies an abstention threshold; and, in response to determining that the similarity score satisfies a criterion based on satisfying the abstention threshold, providing one or more of the candidate outputs as a generated response to the input cue.

The invention discloses a low-carbon demand response strategy application method and device, and the method comprises the steps: obtaining the power historical data of renewable energy sources in a power system, obtaining moment information according to the power historical data, and constructing a corresponding fuzzy set; the method comprises the following steps: acquiring information data of a distributed generator, renewable energy sources, loads and carbon transactions in a power system, and constructing to obtain a system operation cost minimization problem considering uncertainty; obtaining a constraint condition according to the fuzzy set, and converting a system operation cost minimization problem considering uncertainty into a deterministic system operation cost minimization problem; and solving the deterministic system operation cost minimization problem to obtain a low-carbon demand response strategy, and implementing the low-carbon demand response strategy by the power system to realize low-carbon control and operation of the power system. The technical problems that in the prior art, prediction errors are large, practical practicability is not achieved, and accuracy is low are solved.

The invention relates to the technical field of refrigerator systems, and discloses a refrigerator power prediction method and device based on a multi-branch network, equipment and a medium. Firstly, first module operation parameters and second module operation parameters of the refrigerator system are obtained and input into a multi-branch network; the multi-branch network comprises a first network branch, a second network branch, an adaptive weight layer and a feature fusion layer. Performing feature extraction on the first module operation parameter based on the first network branch to obtain first feature data; and performing feature extraction on the second module operation parameter based on the second network branch to obtain second feature data. And performing adaptive weight adjustment on the first feature data and the second feature data based on the adaptive weight layer, and determining a first weighted vector corresponding to the first feature data and a second weighted vector corresponding to the second feature data. And finally, performing fusion processing and feature transformation processing on the first weighted vector and the second weighted vector based on a feature fusion layer to obtain a cold machine power prediction result.

The invention discloses a ship-based electromagnetic directional valve service life prediction method and device, a medium and a product, and relates to the field of electromagnetic directional valve service life prediction.The method comprises the steps that monitoring data of performance parameters in different failure modes are obtained; according to the monitoring data, constructing a performance degradation model of each performance parameter in different failure modes based on a Wiener process; according to the performance degradation model, adopting a Coupla function to construct a multi-performance reliability model; determining a life prediction model of the electromagnetic reversing valve based on the multi-performance reliability model; and predicting the service life of the electromagnetic reversing valve by using the service life prediction model of the electromagnetic reversing valve. According to the method, the service life of the marine electromagnetic reversing valve can be predicted more accurately.

The invention discloses a travel mode determination method and device, equipment, a storage medium and a product, and relates to the technical field of geographic information. The method comprises the following steps: acquiring a plurality of position coordinates corresponding to an action track of a target object in a historical time range, and acquiring road attribute data corresponding to a target road in accordance with a position matching relationship with the action track; acquiring a plurality of pieces of first track attribute data based on the position relationship among the plurality of position coordinates; obtaining a plurality of pieces of second track attribute data based on a track interaction relationship between the plurality of position coordinates and the road attribute data; and performing classification prediction on the action track according to the plurality of first track attribute data and the plurality of second track attribute data to obtain a travel mode prediction result of the target object. Namely, the travel mode of the target object is classified and predicted by combining the relationship between the real-time position coordinate corresponding to the action track of the target object and the road, so that the prediction accuracy of the travel mode is improved.

The invention provides a life prediction method and system for a closed multi-cell steel structure, and relates to the technical field of structural finite element analysis, and the method comprises the steps: taking the closed multi-cell steel structure as a prototype, determining a scale reduction proportion, and building a scale reduction structure of the closed multi-cell steel structure; performing a laboratory accelerated environment test and a mechanical test on the scale structure in an equivalent service environment of the closed multi-cell steel structure, obtaining mechanical response test data of the scale structure, and determining test targets of the scale structure at different moments; establishing a scaling structure simulation model by taking the scaled plate material data as input, and obtaining a transfer coefficient; the method comprises the following steps of: establishing a full-scale structure simulation model of a closed multi-cell steel structure by taking original plate material data as input; and the full-scale structure simulation model is used for outputting the crack propagation size and the remaining life of the target welding structure at different moments under the full-scale structure. According to the method, the accuracy of life prediction of the closed multi-cell steel structure is effectively improved.