27results about How to "Reduce computational efficiency" patented technology

The invention belongs to the field of time sequence anomaly detection, and discloses a time sequence anomaly detection method and system based on frequency enhanced convolution Transform, and the method comprises the steps: carrying out the sequence-level preprocessing of an input sequence, including normalization and block generation; encoding the input sequence by adopting a multi-head self-attention mechanism; extracting interrelationships in the sequence by a full convolution module having a plurality of stacked 1D convolution layers of different kernel sizes; s2 and S3 are repeated, and multi-layer coding is carried out on the sequence; converting the encoded embedding into a frequency signal by using a Fourier transform method; the KL divergence and the absolute error are respectively used for calculating the consistency loss of the time domain and the frequency domain, calculating the point-by-point anomaly score, and identifying whether the point is abnormal or not. Wide experiments on five common data sets show that the method is superior to an existing method in the aspect of abnormal recognition.

The invention discloses a mechanical structure reliability analysis method and system based on an active learning agent model, and belongs to the technical field of mechanical structure reliability analysis, and the method comprises the steps: analyzing the working condition and load condition of a mechanical structure to be subjected to reliability analysis, and determining a performance function of the mechanical structure in combination with the safety working requirements of the structure; based on the principle of equal probability conversion, the input variables are converted into a standard normal space, and Monte Carlo reliability analysis samples are generated; in a standard normal space, using a center cross method to generate a 4n initial fitting sample, calculating a function value of the sample, obtaining an initial response matrix, and fitting an initial proxy model; and establishing a distance constraint learning function based on the existing agent model and the fitting sample, and iteratively updating the agent model, the fitting sample, the response value matrix and the failure probability in combination with a prior reliable circular ring sample reduction method until a reliability analysis result with enough precision is obtained, and ending the reliability analysis system.

The invention discloses a power flow calculation method and system for a power system, and aims to relax key variables such as part of generator output and node voltage from equality constraints to inequality constraints in order to solve the problem that part of generator output and node voltage are difficult to give due to large-range change of an operation mode in a novel power system; after the inequality constraint is introduced, the power flow model is changed into a novel power system constraint power flow model from an original nonlinear equation set solving problem; converting an inequality in the constraint power flow model into an equation by adopting a method of constructing an auxiliary function, and then converting the constraint power flow model into a bounded constraint least square problem; aiming at the problem that a traditional optimization algorithm is difficult to converge, a trust region algorithm is adopted for solving, and the adjustment amount of variables such as generator output and node voltage and a final power flow solution are obtained. The method can effectively solve the problem that the power flow has no solution due to the fact that the initial power flow value is difficult to give, and theoretical support is provided for planning and operation of a power system.

The invention discloses a double-optimization efficient learning training method for on-orbit interaction of double spacecrafts, which aims at a task entering a specified target area, fully considers time-space characteristics of the task, establishes relative orbit dynamics of a tracking star and a target star and a mathematical model of the target area, designs constraint conditions, and establishes win-lose conditions of the tracking star and the target star. In order to improve the training efficiency, a twice optimized efficient learning training method is designed, firstly, a tracking star and a target star respectively adopt a decision-making method based on zero-control miss distance to carry out pursuit interaction, track data in the interaction process of the two parties are collected and analyzed, and a neural network is adopted to fit the action of the tracking star for guiding subsequent training; according to the method, the defect that convergence is difficult due to the fact that training starts from zero can be overcome, the neural network obtained through training can output the optimal thrust of the tracking star, and the tracking star can enter a designated area at the designated moment.

The invention discloses a distorted image correction method based on a fast multi-scale residual network. Relates to the field of image geometric distortion correction, in particular to the technical field of distortion image correction based on a fast multi-scale residual network. Comprising the following steps: S1, constructing a data set, and generating a paired data set of a distorted image and a standard image and a deformation displacement field file of a corresponding number of the distorted image by using a geometric distortion model; s2, a distorted image correction model based on a fast multi-scale residual network is constructed, the model is divided into a backbone network and a tributary network, the backbone network is used for recovering image features, and the tributary network is used for outputting image classification features; s3, training the distorted image correction model based on the fast multi-scale residual network by using the pairwise data set of the distorted image and the standard image and the deformation displacement field file; and S4, processing the to-be-corrected image by using the trained distortion image correction model based on the fast multi-scale residual network to obtain the corrected image and the corresponding classification thereof.

The invention belongs to the technical field of time-frequency analysis, and particularly relates to a rolling bearing fault method and system based on Riesz atlas sparse decomposition, which utilizes a new time-frequency analysis method-Riesz four-parameter spectrum time-frequency analysis method to obtain four-parameter information of amplitude, frequency, phase and direction of a vibration signal in a time-frequency domain. The time-frequency aggregation and the anti-noise performance of an analysis result are improved; in order to screen out an optimal parameter spectrum and expand the symbol dynamics entropy to a two-dimensional scale, a new entropy calculation method, namely cosine symbol dynamics entropy, is provided; and reconstructing components of the parameter spectrum obtained by entropy screening, and constructing a sparse filter parameter optimization component amplitude, so that a decomposition result has physical significance. The bearing vibration signal under the variable speed working condition and the bearing vibration signal under the constant speed are analyzed, the RSSD method is provided on the basis, and feature extraction and diagnosis of rolling bearing faults under the constant rotating speed working condition and the variable rotating speed working condition are achieved.

The application discloses a hyperspectral anomaly detection method based on background clustering constraint and potential feature separation, and relates to the technical field of hyperspectral remote sensing detection applications. First, band selection and partition generation of a hyperspectral original image are carried out to generate fixed-size image blocks. Then, a basic image reconstruction framework is constructed based on a lightweight spectral-spatial feature extraction encoder and a convolution decoder. Then, a pixel-level deep clustering network is introduced to complete latent feature clustering modeling, calibrate the background clustering label of the image block, and obtain the intra-class RX detection score in the feature space. Then, the intra-class RX score and the reconstructed image are reversely mapped to the original image space to construct a global RX response map and a reconstructed full image. Finally, a weight matrix is generated by using the reconstruction error between the original image and the reconstructed full image, the global RX response map is modulated, and the final anomaly detection result is output. The application fuses the background clustering constraint and the potential feature separation mechanism, effectively improves the detection accuracy of small anomaly targets, and significantly suppresses false alarm interference.

The invention discloses a reasoning calculation method and related equipment, and relates to the technical field of artificial intelligence, and the reasoning calculation method comprises the steps of obtaining document data to be subjected to reasoning calculation, segmenting the document data to obtain multiple segments of text data, reasoning and calculating the multiple segments of text data based on a preset large language model to obtain multiple segments of target text data, the preset large language model is a trained current large language model, determining relevance among the multiple segments of target text data based on a preset paragraph relation determination algorithm, and splicing the multiple segments of target text data based on the relevance to obtain document data after reasoning calculation. According to the method, the document data to be subjected to reasoning calculation are segmented, reasoning calculation is performed on each segment of text data, and then each segment of text data after reasoning calculation is spliced to obtain the document data after reasoning calculation, so that the reasoning calculation efficiency is improved.

On the basis of a statistical calculation method of harmonic output variables of a three-point estimation method, harmonic voltage Z of the output variables is respectively expanded at expected values of a fan, a photovoltaic system and a load as input random variables Xi in combination with a formula # imgabs0 #, and position coefficients xii, j and weights wi, j corresponding to each estimation point xi, j are obtained. According to the method, a group of estimation points x'i and j are additionally added on the basis of three-point estimation to construct multiple sampling points, so that accurate solution of random variable statistical characteristics is realized, the calculation accuracy is ensured, introduction of high-order moment can be avoided, and three-point sampling has higher practical value.

The invention provides a method and system for calculating bushing electric field distribution based on a two-dimensional axial symmetry model, and belongs to the technical field of power equipment simulation, and the method comprises the steps: 1, carrying out the dimension reduction processing of an actual transformer bushing three-dimensional structure according to the actual geometric structure symmetry of a transformer bushing, and obtaining an actual transformer bushing electric field distribution value; extracting a transformer bushing two-dimensional axisymmetric model capable of reflecting the actual structure of the bushing; 2, establishing a temperature field simulation model based on the two-dimensional axisymmetric model of the transformer bushing extracted in the step 1, and calculating the two-dimensional temperature field distribution of the transformer bushing; 3, establishing an electric field simulation model based on the two-dimensional axisymmetric model of the transformer bushing extracted in the step 1, coupling the temperature distribution of the transformer bushing obtained in the step 2 into the electric field simulation model, and calculating the two-dimensional electric field distribution of the transformer bushing; and 4, performing circumferential scanning on the calculation result of the two-dimensional electric field distribution of the transformer bushing, restoring the three-dimensional electric field distribution of the transformer bushing, and obtaining the three-dimensional electric field distribution of the transformer bushing.

The invention relates to the technical field of medical information systems, in particular to a breast dynamic enhancement MRI intelligent analysis system and method, and the system comprises a data collection module which is used for obtaining breast dynamic enhancement magnetic resonance imaging (DCE)-MRI data; the image preprocessing module is used for carrying out standardization processing on the DCE-MRI data; the segmentation module is used for segmenting the preprocessed image data into a format suitable for model input; the model reasoning module is used for performing deep learning analysis and focus diagnosis on the segmented image; the report generation module is used for generating a diagnosis report according to the model reasoning result; and the data storage module is used for storing data of each stage and a final diagnosis result, so that the analysis capability of the mammary gland DCE-MRI is comprehensively improved. The accuracy and the efficiency of diagnosis are remarkably improved, particularly, the performance is excellent in the aspect of tiny focus detection, and the clinical credibility is improved by enhancing the interpretability.

The present invention discloses a method for triggering and starting real-time orbit determination of a low-orbit satellite, which belongs to the field of satellite positioning and timing. The method is used for ground data processing, detects the update status of real-time low-orbit satellite-borne GNSS observations, detects and calculates the real-time integrity and continuity of low-orbit satellite-borne GNSS observations and GNSS products, performs cyclic compliance judgment among different GNSS systems, orbit determination arc lengths, and GNSS products, and triggers and starts real-time orbit determination when the observation and product quality meet the standards and the orbit determination arc segment observation is updated. The method can ensure the accuracy of real-time orbit determination, avoid repeated calculation when the observation is not updated, and avoid invalid / low-quality orbit determination or frequent error reporting when problems occur in the input observation and product quality, thereby saving calculation efficiency and avoiding tracing repeated problems during operation and maintenance.

The present invention discloses a water quality detection method and system based on artificial intelligence, and the method includes data collection, data preprocessing, water quality pre-classification, water quality trend analysis, pollution source tracing prediction and water quality detection. The present invention relates to the field of water quality detection technology, and specifically refers to a water quality detection method and system based on artificial intelligence. The present scheme adopts an artificial intelligence water quality detection method of water quality pre-classification, trend analysis and pollution source tracing; a deep neural network method combining genetic algorithm and random forest model is used for water quality pre-classification; a deep neural network method combining genetic algorithm and random forest model is used for water quality pre-classification and water quality trend analysis; a water quality pre-classification task is used to first pre-classify the data, exclude unpolluted water sources, and then combine the causal-inspired graph neural network, and through the causal-inspired operator and the improved graph neural network, the calculation speed and calculation effect of pollution source tracing are improved.

The present invention relates to the field of aerospace computational fluid dynamics technology, and discloses an efficient wide-speed domain format construction method based on algebraic form, including: generating a simulation discrete grid for the aerospace aircraft configuration to be calculated; decomposing the control equation flux passing through the discrete grid unit into convective flux and viscous flux; discretizing the convective flux using the HLLE++ format, and converting it into a combination of the left and right unit flux means and the dissipative term; decomposing the dissipative term into a combination of multiple groups of vectors, and decomposing each group of vectors into a product combination of HLLE++ format characteristic root terms, density terms, and velocity terms; integrating the convective flux into algebraic operations; iteratively solving the control equation to obtain the flow field information of each discrete grid unit. The present invention can solve the problems of low calculation efficiency and poor scalability of the existing HLLE++ construction, and has great application prospects in wide-speed domain multi-body separation, aircraft-missile separation, and numerical simulation of variant aircraft.

This invention is a method for inverting azimuth difference seismic data in inclined fractured rocks. Previous AVAZ inversion methods for fracture parameters were mostly based on the HTI medium assumption, with insufficient consideration for fracture dip angle. The fixed form of the inversion constraint terms made it difficult to adapt to changes in parameter statistical characteristics, and the regularization parameters were all manually adjusted, affecting inversion accuracy and efficiency. This invention establishes an approximate formula for the reflection coefficient of the TTI medium, characterized by the P-wave and S-wave velocities, density, and fracture elastic parameters of the background medium. It utilizes pre-stack azimuth difference data to perform AVAZ inversion of fracture parameters. Dynamic sparsity constraints are introduced, dynamically adjusting the sparsity of the constraints based on data characteristics, and a covariance matrix is ​​introduced to consider the statistical regularity between parameters. Combining iterative reweighted least squares and adaptive regularization parameter acquisition methods, the dynamic constraint inverse problem is transformed into a weighted... L A 2-norm objective function is used to achieve a stable solution. Data testing shows that this invention can effectively improve the inversion accuracy of crack elastic parameters.

The invention relates to the technical field of epilepsy prediction, in particular to an epilepsy prediction system based on an adjustable emission suppression spiking neural network, which specifically comprises a data preprocessing module, a spiking neural network module, a neural network optimization module, an emission mode judgment module and an accelerator module, a data set capable of being provided for neural network training and testing is obtained through the data preprocessing module, and then software optimization and hardware optimization are carried out on a pulse neural network through the pulse neural network module, the neural network optimization module and the emission mode judgment module. And finally, realizing the epilepsy prediction system based on the spiking neural network capable of adjusting suppression emission through an accelerator module. The epilepsy prediction system solves the problems that in the prior art, the calculation speed is low and the requirements of wearable equipment cannot be met due to the fact that the calculation amount of the spiking neural network is huge and the power consumption is large.

The technical scheme of the invention discloses a system for constructing a high-precision user behavior portrait through an improved federal learning algorithm, and the system is characterized in that the system comprises a multi-source privacy protection data obtaining module; a federated learning modeling module based on dynamic weighting and contribution proving; a multi-dimensional user behavior portrait module; a personalized vehicle network interaction strategy generation module; a dynamic execution and fair excitation module; and a feedback and model self-optimization module. According to the method, deep analysis and portrait construction can be carried out on historical data of user charging and discharging behavior habits, a high-precision and high-coverage user behavior portrait model is generated through an improved federated machine learning algorithm, the real-time income of users is improved, the user viscosity is enhanced, and the power grid stability and the renewable energy consumption rate are further improved.

The invention discloses a microgrid privacy protection method and system based on a novel homomorphic encryption algorithm, and relates to the technical field of microgrid control. The method comprises the steps of designing a micro-grid distributed cooperative control method based on a distributed control theory, and realizing frequency recovery of each distributed power supply in a micro-grid; defining a privacy protection connotation and a privacy protection range; according to the defined privacy protection connotation and privacy protection range, a microgrid privacy protection method based on a novel homomorphic encryption algorithm is designed, an initial value and a real-time value of each distributed power supply in the microgrid are protected from being leaked to node neighbors, and the distributed cooperative control target of the microgrid is achieved; and verifying the microgrid privacy protection method based on the novel homomorphic encryption algorithm by using a simulation experiment. According to the invention, the credible perception capability and privacy security of distributed cooperative operation of the micro-grid can be improved.

The application relates to the technical field of data storage and edge computing, and discloses a software-defined computable storage method and system, which comprises a front-end computing platform and a rear-end solid-state storage device connected through an NVMe protocol communication connection; the front-end computing platform is externally presented as a standard NVMe storage device, adopts a heterogeneous system on chip, and the heterogeneous system on chip integrates multiple heterogeneous processors; the front-end computing platform is sequentially provided with a PCIe endpoint function layer, an NVMe controller layer and a hardware abstraction layer, a kernel-mode user-mode bridging layer, a user-mode I / O engine layer, a lightweight user-mode FTL layer, a heterogeneous computing power scheduling layer, a scene-based computing command interface layer, a stream data service implementation layer and a communication expansion layer. The application can solve the technical problems of existing computable storage architectures, such as multiple data movements and function solidification.

This invention discloses a method for processing matrix multiplication weight data in model inference, adapted to large-scale matrix multiplication in BFP format for large models in the Transformer architecture. Addressing the pain points of existing architectures regarding BFP exponent and mantissa splitting, bandwidth, and resource consumption, this method employs (64,64) weight blocks, dual address generator 1:4 scheduling, waterline flow control, and double buffering techniques to achieve full-bandwidth read / write between DDR, BRAM, and computational units. Through multi-core parallelism and multi-round multiplication and accumulation, performance is improved by more than 3 times compared to FP16, reducing memory usage and design complexity while ensuring inference accuracy, providing an efficient hardware acceleration solution for LLM inference in resource-constrained environments.

This invention discloses a multi-robot path planning method and system based on hierarchical control. The method acquires model information and basic parameters of each robot in the system, and constructs a realistic map of the working environment using the SLAM algorithm. The grids of the constructed realistic map are merged, transforming a fine-grained grid map into a coarse-grained one. Considering the overall movement direction and target position of the robots, a global path input for the navigation system is obtained. This global path input is published to each robot, and robots can subscribe to other robots' paths to capture their global path information. Each robot perceives local environmental information in a local map and obtains information about obstacles around other robots. Based on the global path results from the MAPF algorithm, a local path planning method is used to generate local paths, enabling avoidance between robots. This provides a reliable solution for efficient collaboration in multi-robot systems.

The invention provides a mechanism deep learning dual-drive flow-slip disaster numerical simulation system, and relates to the technical field of geological disaster numerical simulation. The system integrates a physical mechanism model and a deep learning method. Based on a high-resolution DEM (Digital Elevation Model), by introducing a rock-soil type self-adaptive substrate entrainment mechanism, utilizing a shallow water wave equation to accurately calculate the terrain elevation, the flow direction, the flow velocity and the accumulation thickness of the first two time steps; and then taking the obtained multivariable field as four-channel input, and driving a CNN-GRU coupling network to perform rolling prediction. According to the method, the final accumulation form, the influence range and the dynamic evolution process can be quickly obtained only through a small amount of initial mechanism calculation, the simulation efficiency is remarkably improved on the premise of ensuring physical rationality, and the defects that a traditional pure mechanism model is long in calculation time consumption and a pure data driving model is physically distorted are overcome; the method is suitable for rapid risk assessment and emergency decision support of flow slip disasters such as landslide and debris flow.

The application provides a global recursive reconstruction method of a space robot recursive Newton-Euler dynamics algorithm, and relates to the technical field of space robot dynamics modeling. The method obtains the global closed matrix form of the mechanical arm movement screw and its differential by forward recursive reconstruction of the recursive Newton-Euler dynamics algorithm; the secondary diagonal matrix of the recursive operator is constructed to simplify the expression of the differential of the global closed matrix form of the mechanical arm movement screw; based on the global closed matrix form of the movement screw and its differential, the global closed matrix form of the required torque of each joint and the required force screw of the base is obtained by backward recursive reconstruction; based on the similarity of the backward recursive reconstruction results at the mathematical structure level, the global closed matrix form dynamics modeling of the space robot is completed. The method constructs an explicit matrix mapping form of the floating base space robot dynamics model, and realizes the direct mapping between the system state quantity and the input quantity.

The invention belongs to the technical field of multi-source power prediction, and discloses a multi-source power prediction comparative analysis method based on artificial intelligence, which realizes accurate prediction and comparative analysis of photovoltaic power generation power by fusing multiple data sources and an artificial intelligence technology. The technical scheme has the advantages of comprehensive data, high prediction precision, strong model generalization ability and the like, and can be widely applied to the fields of photovoltaic power stations, power grid dispatching centers, energy management companies and the like. And multi-source data fusion and intelligent analysis: carrying out fusion and intelligent analysis on multiple data sources to realize comprehensive prediction and comparative analysis on the photovoltaic power generation power. And multiple artificial intelligence algorithms are fused: the multiple artificial intelligence algorithms are adopted to construct a prediction model, an optimal prediction model is selected through comparative analysis, and prediction precision and generalization ability are improved. Model fusion and result optimization: carrying out fusion and optimization processing on prediction results of a plurality of prediction models, and further improving the accuracy and reliability of the prediction results.

The invention discloses an ultra-large point FFT (Fast Fourier Transform) fast processing method, which relates to the field of digital signal fast processing and comprises the following steps of: firstly, carrying out zero padding operation on original sampling signal data until the total length of a sequence meets integral multiples of M1 points; the method comprises the following steps of: performing zero padding operation on an input super-large point sequence, segmenting the data after the zero padding operation, segmenting the input super-large point sequence into L subsequences with the length of M1 points, performing FFT (Fast Fourier Transform) calculation with the point number of M1 points on the subsequences, and performing iterative calculation by adopting a high-radix FFT algorithm architecture; and finally, a specific twiddle factor is multiplied by the FFT calculation result of the sub-sequence to realize phase correction of the FFT result, the sub-FFT results after phase correction are combined and spliced according to a specific weighting mode, the component of each frequency point is ensured to be correctly adjusted, and the FFT result of the original data sequence is obtained. According to the method, the algorithm complexity can be reduced, and meanwhile, the calculation efficiency of the super-large point FFT is improved.

The application discloses a mountain low-altitude wind field reconstruction system based on sparse observation data and a graph neural network, and relates to the technical field of meteorological prediction, artificial intelligence and low-altitude economic guarantee cross technology, and comprises a data preprocessing module, a multi-scale graph neural modeling module, a physical constraint generation reconstruction module, a terrain self-adaptive migration module and a closed-loop cooperative scheduling module which work in sequence. The data preprocessing module is used for sampling enhancement and feature fusion of sparse observation data and terrain data. The mountain low-altitude wind field reconstruction system based on sparse observation data and the graph neural network solves the problem of insufficient feature extraction of sparse observation data, realizes accurate deduction from discrete observation points to continuous three-dimensional wind field, reduces the prediction error of wind speed, wind direction and turbulence intensity, and significantly enhances the capturing ability of local wind field characteristics such as canyon pipe effect and mountain vortex.

This invention introduces a deep learning method for EDR estimation based on aircraft response characteristics. By combining staged calculation and neural network learning, this method provides an accurate and reliable EDR estimation approach. Unlike traditional EDR estimation methods, the method described in this invention features clearer stage division and dynamic adjustment capabilities. The method includes the following steps: systematically integrating flight data collected from Quick Access Recorders (QARs) of all flights nationwide, constructing time windows, and performing intelligent hierarchical sampling; reading flight data from CSV files and dividing flight stages using a state machine; calculating takeoff and landing stages and cruise stages separately, using raw QAR data to calculate high-level features; finally, training the calculated high-level features using a ConvLSTM-ELM neural learning network model to obtain the optimal parameters of the model. After neural network training and learning, this method can accurately estimate the EDR value of the entire flight route, improving the accuracy and real-time performance of EDR calculation using recorded QAR data in the aviation field.