6results about How to "Avoid forecast errors" patented technology

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.

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 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.

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.