19results about How to "Avoid computational complexity" patented technology

The invention discloses an electric power system state estimation method based on graph contrast learning. The method comprises the following steps: constructing graph sequence data of electric power system state estimation; constructing an electric power system state estimation model based on graph contrast learning, and putting the graph sequence data into the electric power system state estimation model based on graph contrast learning; inputting the node feature sequence and the masked edge features into a hybrid encoder of a dynamic edge convolutional neural network combining a self-attention mechanism and a residual block and a graph convolutional neural network with a dynamic propagation strategy of a gating mechanism to comprehensively process the features of nodes and edges; comparing an updating mechanism and a sampling symmetry training strategy of model parameters of the learning framework through a graph; and calculating a node voltage phase angle by using the branch phase angle difference, and outputting a state estimation result. According to the method, the internal structure and mode of the power system data can be effectively learned by combining graph contrast learning and a deep neural network technology, and the capability of identifying and filtering abnormal data is improved.

The invention discloses an aerial view target detection method and system, a storage medium and equipment, and belongs to the field of BEV visual detection map reconstruction.The method comprises the steps that S1, images from different camera visual angles are input, and features of the different camera visual angles are extracted through a backbone network; s2, redesigning a time encoder through deformation and splicing by using long-period time information, and processing the characteristics of different camera visual angles through the designed time encoder; s3, based on a processing result of the step S2, further utilizing dynamic deformable attention to extract spatial features of the image; s4, processing the features obtained in the step S3 by using a feedforward network, and generating a final BEV feature map; and S5, performing target detection by using the final BEV feature map. According to the method, dynamic deformable attention is fused in aerial view angle detection, so that image query is more comprehensive, the calculation overhead is low, meanwhile, time sequence coding is improved, long-time historical information can be better integrated, and the robustness and accuracy of detection are improved.

The invention relates to a probe selection method and device for dynamic channel reconstruction, equipment, a medium and a product, and is applied to the technical field of wireless communication. The method comprises the following steps: acquiring standard channel parameters of a plurality of road points in a dynamic channel, the number of snapshots and a probe set of each road point; and according to the standard channel parameters of every two adjacent road points and the number of the snapshots, calculating the channel parameter variation of each snapshot at the moment. And calculating a to-be-selected probe set of each snapshot according to the channel parameter variable quantity and the probe sets of every two adjacent road points. And based on a probe selection model, screening the to-be-selected probe set of each snapshot to obtain an optimal probe combination of each snapshot. The change of the probe position of the dynamic channel is reflected through the channel parameter variable quantity corresponding to each snapshot, and the probe selection of the snapshots is associated with the probe of the adjacent road point. And the problem of complicated calculation caused by selecting the probe corresponding to the snapshot from all the probes is avoided. Therefore, the complexity of dynamic channel reconstruction is reduced.

The invention discloses an intelligent question and answer method and device, equipment and a medium. The target answer is generated in a mode of generating the token through iteration, and calculation complexity and resource consumption caused by one-time generation are avoided. When it is determined that only one first fragment matched with the reference token exists in the reference document, the second fragment after the first fragment is obtained, so that the retrieval question and answer model can be further combined with the second fragment, namely combined with the following text information of the first fragment to generate the prediction fragment, the relevance between the prediction fragment and the inquiry text is improved, and the prediction efficiency is improved. Effective fragments subsequently determined on the basis of the prediction fragments have higher traceability. Under the condition that only one first fragment exists in the reference document, the retrieval question and answer model can generate the prediction fragment based on the inquiry text, the question and answer instruction, the reference document, the reference token and the second fragment, multiple tokens are generated through one-time iteration, and the generation efficiency of the target answer is improved.

The invention discloses a calculation method of stock equity ratio of a customer and a related device, and relates to the technical field of financial enterprise analysis, and the method comprises the steps: determining a target node from a preset stock equity relation directed ring graph; converting the equity relation directed acyclic graph to obtain an equity relation directed acyclic graph of the target node; determining a fan-in node of the target node in the equity relation directed acyclic graph, and constructing a termination subgraph based on the fan-in node of the target node; determining a fan-in node of the termination sub-graph based on the equity relation directed acyclic graph, and determining a target fan-in node of the termination sub-graph from the fan-in node of the termination sub-graph; and calculating the equity ratio of the customer corresponding to each target fan-in node, and further determining the equity ratio of the target customer corresponding to the target node. According to the scheme, the equity relationship directly related to the target customer is accurately positioned by utilizing the concept of the termination sub-graph and the target fan-in node, so that the equity ratio of the target customer is efficiently and accurately calculated.

The invention discloses a transmission line decoupling simulation acceleration method and system, and the method comprises the steps: carrying out the decoupling of transmission lines between internal combustion engines and between the internal combustion engines and energy storage through the natural decoupling characteristics of the transmission lines, and obtaining a transmission line decoupling characteristic equation; constructing a transmission line decoupling circuit model through the transmission line decoupling characteristic equation; and based on a transmission line decoupling circuit model, independent simulation solution is carried out through voltage and current information interaction. According to the method, the calculation complexity of reconstruction and inversion calculation of a high-order matrix is avoided, the calculation amount during system calculation is reduced, and the electromagnetic transient simulation speed is increased.

The invention belongs to the technical field of frequency modulation continuous wave radars, and particularly relates to a frequency modulation continuous wave radar interference elimination method based on adaptive dictionary matching. The method comprises the following steps: establishing a mathematical model of radar sending signals, receiving signals and interference signals; selecting different time delays and frequency modulation slopes according to the mathematical model of the interference signals to construct a dictionary with enough precision; roughly and uniformly extracting dictionary data and receiving signals to calculate correlation; according to the correlation, finer dictionary data and received signals are uniformly extracted near parameters larger than a given threshold value, and the correlation is calculated; determining interference parameters according to the correlation after the expected precision is reached; calculating interference signals according to the determined parameters and eliminating the interference signals from the received signals; according to the method, the problems of calculation complexity and precision reduction caused by a traditional interference suppression method can be avoided, the interference recognition and elimination efficiency is improved, the method is suitable for scenes where interference signals are varied frequently and environment complexity is increased, and the robustness and detection performance of a system are enhanced.

The invention relates to a mother-type ship database-based ship noise forecasting method, which comprises the following steps of: collecting mother-type ship noise actual measurement data, performing arrangement by taking each place as a dimension, and establishing a mother-type ship database; carrying out statistical processing on the data, and calculating statistical indexes of noise measured values of all rooms of all mother type ships; the measured values of the same place of each mother ship are regarded as different results repeatedly measured for the same experiment, and a normal distribution model is established; adding the average value of the noise measured values at all positions and the standard deviation of a certain multiple of the normal distribution model as the noise basic value of the new ship; comparing the difference between a noise source and a propagation path between the predicted ship and the mother ship, establishing a function relationship between a single difference and a noise level by using an empirical formula or an actual measurement result similar to new ship equipment arrangement, and superposing all change influence results to obtain a total influence result of the noise at the place; and obtaining a predicted value of the noise of the new ship based on a superposition result of the noise basic value and the total influence result.

The present invention provides a network risk analysis method and system based on a multi-level game model, which relates to the technical field of network risk analysis, including constructing a multi-level dynamic game model, based on the constructed multi-level dynamic game model, using a multi-level game equilibrium solution algorithm, decomposing the multi-level game problem into a number of sub-game problems corresponding to different network levels, using a reverse induction method to solve each sub-game problem respectively, and obtaining a multi-level game equilibrium solution through iterative optimization until preset conditions are met; inputting the obtained multi-level game equilibrium solution into a pre-trained multi-level risk assessment model, outputting a risk assessment value, and triggering a strategy adjustment mechanism when the risk assessment value exceeds a preset risk warning threshold, updating the defense strategy by recalculating the multi-level game equilibrium solution, and finally obtaining the optimal defense strategy combination under risk minimization.

The present invention relates to providing a method for optimizing fuel consumption during the cruising phase of an aircraft, wherein the flight parameters and meteorological data of the aircraft are collected in real time through airborne sensors, and the flight parameters and meteorological data include flight altitude, flight speed, outside temperature, wind speed, wind direction and aircraft weight; the collected flight data are transmitted to a ground server at intervals through an air-to-ground data transmission system; the ground server performs data cleaning, data normalization and feature selection on the flight data; a deep learning neural network model is trained based on historical flight data to predict the fuel flow and ground speed under current flight conditions; the unit distance fuel cost is calculated through a mathematical model; an optimization algorithm is used to find the optimal cruising speed with the lowest fuel consumption; and the optimal cruising speed is fed back to the aircraft through the air-to-ground data transmission system to adjust the flight state. The present invention can dynamically adjust the cruising speed according to real-time flight data, significantly improve fuel economy, and has strong adaptability and is easy to operate.

The invention relates to the technical field of flaw detection, in particular to an online flaw detection method and system for flaw detection by combining an image analysis and processing technology. Comprising the following steps: S1, obtaining detection image data, preprocessing the detection image data, carrying out grid division on the preprocessed image, and extracting features; s2, performing odd-even division on the gridded image, and calculating an angle according to a division result; and S3, constructing a prediction model and performing real-time prediction analysis. According to the method, the image data are collected at equal intervals and preprocessed, so that the calculation complexity is reduced, and the processing efficiency is improved; performing odd-even grid division, calculating an included angle, and refining defect types and severity; an LSTM model is constructed for real-time prediction, and the prediction precision and reliability are improved in combination with historical data; and finally, a closed-loop system is formed, real-time online monitoring is realized, the defect type and severity are accurately judged, the continuity and reliability of detection are ensured, and powerful technical support is provided for defect damage detection.

The application belongs to the technical field of magnetic thrust bearing vibration reduction and isolation, and provides a reluctance composite permanent magnetic thrust bearing based on a Halbach array and a non-equal-length annular magnetic group magnetic force calculation method. The stator adopts an annular magnetic group and damping ring alternately arranged configuration, the magnetic force generated by the interaction between the stator and the rotor annular magnetic group is used for non-contact bearing, and the damping ring cuts the magnetic induction lines to generate a damping effect when the annular rotor magnetic group generates axial movement, thereby inhibiting the vibration under the impact load and improving the vibration reduction effect; meanwhile, the Halbach array is used to effectively improve the unit volume bearing capacity and damping effect. In addition, the magnetic dipole moment method and the Monte Carlo method are used for non-equal-length complex magnetic body axial force calculation, the four-fold integral calculation problem is avoided, the calculation is simple, accurate, practical and has high engineering application value.

The invention discloses a three-dimensional low-complexity probabilistic shaping coding method for a PDM optical communication system, and the method comprises the steps: carrying out the 3D-QPSK constellation mapping of a high-power signal, and obtaining a processed high-power signal. And after weight-driven bit inversion processing is carried out on the low-power signal, 3D-8QAM constellation mapping is carried out, and a processed low-power signal is obtained. And carrying out PDM superposition on the processed high-power signal and the processed low-power signal to obtain a 3D-32QAM signal after probability shaping. The PDM and WDBR-PS technologies are applied to the three-dimensional constellation, the WDBR technology only needs to be operated in the bit dimension, and the hardware burden of a PDM system sensitive to resource allocation cannot be increased. Meanwhile, by expanding a two-dimensional constellation to a three-dimensional constellation, not only is the PAPR of the OFDM signal effectively reduced, but also the problem that the bit error rate is suddenly increased due to the fact that the distance between constellation points is too small in high-order modulation is avoided.

The invention provides a vehicle positioning method and device, a storage medium and an electronic device, and the method comprises the steps: generating an aerial view of a target vehicle; semantic segmentation is carried out on the aerial view to obtain an aerial view semantic segmentation map, and the aerial view semantic segmentation map comprises category information of each pixel in the aerial view; performing distance transformation on category information of each pixel in the aerial view semantic segmentation map to obtain a distance transformation result; mapping the distance transformation result to category information to obtain a smooth semantic segmentation result of the aerial view semantic segmentation map; registering the aerial view semantic segmentation maps according to a smooth semantic segmentation result, and constructing a similarity function between two adjacent frames of aerial view semantic segmentation maps; according to the similarity function, pose estimation is carried out on the target vehicle in the aerial view semantic segmentation map to obtain a positioning result, and through the vehicle positioning method and device, the technical problem that the calculation complexity is high during vehicle positioning in the prior art is solved.

This invention discloses a method for navigating large cargo transport in complex curved road environments using a two-vehicle cooperative system. The method includes: constructing a double-layer grid map to represent the hierarchical spatial constraints of the transport vehicles and cargo; using the A* algorithm to perform articulation point path search and generate an initial trajectory that satisfies topological constraints; detecting collision regions using an algorithm combining directed bounding boxes and the separating axis theorem; and performing distributed trajectory optimization in the collision regions based on the alternating direction multiplier method and model predictive control algorithm. The two-vehicle cooperative transport group is decomposed into a transport vehicle subsystem and a cargo subsystem, achieving trajectory optimization while satisfying dynamic constraints, articulation geometric constraints, and obstacle avoidance constraints. This invention solves the problem of navigating two-vehicle cooperative transport groups on curves.

The invention belongs to the field of electric power, and discloses a method and a device for constructing an electromagnetic equivalent model of a wind power plant. Selecting a target electromagnetic transient model from the pi-type lumped parameter line model and the distribution parameter line model for each section of current collection line; selecting a grouping strategy of the wind turbine generator according to a target frequency band concerned by electromagnetic transient analysis; for a scene needing to execute dynamic grouping, a K-means clustering algorithm based on an improved bird flock algorithm is adopted to perform grouping on the wind turbine generator set so as to determine an optimal clustering center; and on the basis of the target electromagnetic transient model and the grouping result of the wind turbine generator sets, performing parameter equivalence calculation on the generator sets in the same cluster by adopting a capacity weighting algorithm so as to complete construction of the electromagnetic equivalence model of the wind power plant.

The invention discloses a noise estimation method and device for an orthogonal frequency division multiplexing communication system, and the method comprises the following steps: S1, calculating respective initial noise estimation matrixes on subcarriers based on a received training sequence; s2, on the basis of the initial noise estimation matrix, a measurement parameter vector used for representing noise characteristics of each subcarrier is obtained through calculation, and the dimension of the measurement parameter vector is equal to the number of the subcarriers; s3, dynamically and adaptively dividing all the subcarriers into one or more continuous frequency segments according to the measurement parameter vector, and determining the dividing boundary by the change characteristic of the measurement parameter vector in the frequency domain; and S4, for each frequency segment obtained by division, based on the initial noise estimation matrix corresponding to the subcarriers contained in the segment, calculating a noise covariance matrix of the segment, so that colored noise can be more effectively converted into white noise, the detection error of the signal is remarkably reduced, and the receiving performance and demodulation reliability of the whole communication system are improved.

This invention discloses a fast and high-precision cell identification and segmentation method, which includes performing affine and magnification transformations on cell images and corresponding masks, calculating the center mask, constructing a multi-coder-autoencoder model, training the network model, using the network model for cell identification and segmentation, and using the watershed algorithm to segment the cell image to obtain individual cell images and masks. This invention overcomes the shortcomings of traditional semantic segmentation-based algorithms in handling cell adhesion, while also incorporating the advantages of instance segmentation algorithms for cell segmentation. At the same time, it avoids the space and computational complexity brought about by using instance segmentation algorithms, and has the beneficial effects of simple model, high compatibility, fast speed and strong scalability.

The invention relates to the technical field of building design, and discloses a low-carbon building design decision method for hot-summer and warm-winter areas based on GAN and GA. By setting a generator in a GAN model to hierarchically generate building external design parameters and internal design parameters, introducing a reinforcement learning algorithm, and setting an adaptive discriminator, the genetic algorithm GA is combined with a particle swarm optimization PSO. The method can achieve a balance between energy efficiency and building material costs while meeting low-carbon emission requirements, and fully realize the intelligence and dynamic response capabilities of building design.