69 results about "Efficient algorithm" patented technology

The invention provides a power distribution network fault intelligent positioning and self-healing recombination method and system. The method comprises the steps that S1, operation data of a power distribution network are acquired and preprocessed; s2, modeling the power distribution network topology into a weighted undirected graph, and constructing transient characteristics including node characteristics and edge characteristics; s3, on the basis of the transient characteristics and the power distribution network topology, the fault type is judged in real time by adopting a graph convolutional network, and a fault section is determined in combination with a traveling wave distance measurement and impedance method; s4, when entering an isolation fault state, automatically generating a power supply reconstruction scheme meeting current, voltage and switch constraints, and selecting an optimal scheme through multi-objective optimization; and S5, issuing a switching instruction according to the optimal scheme to complete topology reconstruction, and updating a fault identification and recombination strategy according to an actual execution result to improve positioning precision and recovery efficiency. According to the invention, a novel fault processing scheme integrating multi-source measurement, an efficient algorithm and online learning can be adopted, so that the power failure time is shortened, the power failure range is reduced, and the toughness of the power distribution network is improved.

The invention discloses a high-voltage SVG real-time harmonic detection and compensation system based on edge calculation, and belongs to the technical field of power equipment. The method comprises the steps of S1, enhancing environment perception and self-adaptive capability, S2, constructing a distributed cooperative control system, S3, improving robustness and self-healing capability of the system, S4, enhancing robustness and anti-interference capability of an algorithm, S5, managing intelligent edge computing resources, and S6, improving interoperability and standardization of equipment. The step S1 of enhancing the environment perception and self-adaptive capability comprises power grid topology intelligent identification, load characteristic online learning and multi-harmonic source cooperative suppression. Through localization processing and an efficient algorithm of the edge calculation unit, the harmonic detection delay is shortened, the compensation response time is shortened, compared with a traditional method, the harmonic compensation method has obvious improvement, harmonic changes in a power grid can be responded more quickly, the harmonic compensation precision is improved, and harmonic pollution in the power grid can be eliminated more accurately.

The invention provides a multi-modal computer vision data fusion method, and relates to the field of computer vision data fusion. The method comprises the following steps: 1, firstly, carrying out data alignment, obtaining a new image representation through pixel-level fusion, and then carrying out sensor fusion to integrate data into a uniform format for subsequent analysis; 2, feature fusion is carried out, firstly, feature splicing is carried out to serve as input of a model, then an attention mechanism is used to pay attention to more important modal information, and finally joint embedding is carried out to compare and analyze data; and step 3, finally, decision fusion is carried out, classification results are weighted through a voting mechanism, and then weighted averaging is carried out on data to obtain a final result. By processing heterogeneity, missing data and noise among different modals, data fusion is performed among different modals in advance, the fusion effect is optimized through a more efficient algorithm by secondary data processing, and the fusion efficiency is improved.

The invention discloses a computational analysis method applied to high-power power electronic networking equipment, and relates to the technical field of power systems. According to the method, broadband power grid impedance, equipment state and device working condition data are acquired through a sensing layer, and accurate input is provided through layered compression and priority transmission; the cooperative calculation layer introduces a power grid impedance correction coupling interference matrix, establishes an electrothermal coupling loss mapping relation, and realizes coupling interference quantification, loss real-time calculation and full life cycle prediction; the linkage optimization layer constructs a multi-objective optimization function, an optimal control parameter is solved through an efficient algorithm, and a segmented execution strategy is adopted to adapt to different working conditions; the closed-loop feedback layer collects operation feedback data, dynamically updates the model and optimizes the weight, and links fault black-start support and optimal power supply recovery path planning. According to the invention, multi-target collaborative optimization of system stability, operation efficiency, equipment service life and power supply reliability is realized, and technical support is provided for large-scale safe and efficient operation of high-power networking equipment.

The present invention discloses a wireless rapid positioning method based on polarization code, which relates to the field of wireless communication technology, including: inputting a wireless signal into a polarization code encoder, generating a polarization coding sequence, constructing a channel measurement matrix, analyzing channel state information, extracting the delay characteristics and power loss characteristics of the path to generate a candidate path set, evaluating the path credibility, and screening out the optimal path set; for the generated optimal path set, extracting the characteristics of each path from the sparse characteristics of the signal, and generating a positioning characteristic vector for each path; constructing a target positioning model, fusing the path characteristics, combining a simulated annealing optimization algorithm for global search, and outputting the precise position coordinates of the target. The channel measurement matrix is ​​optimized through polarization coding characteristics, and global optimization is achieved by integrating multi-dimensional path characteristics, which not only improves positioning accuracy and robustness, and enhances adaptability in complex scenarios, but also significantly reduces computational complexity through lightweight design and efficient algorithms, and achieves efficient real-time positioning.

The utility model provides an edge intelligent controller artificial intelligence expansion module comprising an acquisition module connected with a main control module, the acquisition module comprising one or more combinations of an Ethernet interface, a USB interface and an input interface; the main control module is connected with a right extension module; the right expansion module is in communication connection with the edge intelligent controller, and the right expansion module comprises a power input and a right expansion interface. The edge intelligent controller artificial intelligence expansion module can provide an additional calculation unit and support parallel processing capability, so that the data processing speed is accelerated. In the artificial intelligence extension module of the edge intelligent controller, a more efficient algorithm can be adopted or an existing algorithm can be optimized, so that the demand of computing resources is reduced, and the computing efficiency is improved. The device can also be used in cooperation with an edge intelligent controller, and reliable integration is achieved.

The invention discloses a multi-physics field coupling numerical method for simulating wave-ocean current-earthquake-seabed interaction, and relates to the technical field of ocean engineering numerical simulation, and the method comprises the following steps: model construction, load application, coupling solution, and result analysis and application. According to the method, revolutionary simulation of collaborative response of a seabed and a structure in a complex marine environment and multi-physics field high-precision bidirectional coupling of random waves, steady-state ocean currents and seismic excitation are realized by constructing a total-factor coupled high-precision numerical model, the problems of incomplete coupling dimensions and excessive model simplification of a traditional method are solved, and the method has the advantages of being high in practicability and high in reliability. According to the wave-induced seabed liquefaction simulation method, the simulation result and the actual working condition coincidence degree are remarkably improved, the frequency domain transfer function method is introduced to analyze the seabed pore pressure response, the cognitive depth and the prediction precision of the wave-induced seabed liquefaction mechanism are remarkably improved, and in addition, through efficient algorithms such as GPU parallel calculation, self-adaptive grids and frequency domain-time domain mixed solution, the wave-induced seabed liquefaction simulation method has the advantages that the wave-induced seabed liquefaction simulation precision is improved. And the calculation efficiency is greatly improved while the precision is ensured.

The invention discloses a rigid pavement texture carving parameter intelligent optimization design method and system, and relates to the field of pavement texture design, and the method comprises the steps: collecting three types of core data to construct a multi-dimensional pavement working condition database, carrying out the data processing and working condition risk quantification, carrying out the hierarchical training through a CatBoost algorithm, solidifying a texture performance mapping model, extracting a performance weight, and carrying out the calculation of the performance weight. And then defining parameter engineering constraints, generating a Pareto optimal frontier through an NSGA-III algorithm, screening an optimal scheme in combination with an engineering preference weight, and finally outputting a standardized design scheme and a quantitative association report. According to the method, a multi-dimensional association database is constructed by collecting three types of core data, quantitative modeling is carried out, refined design of rigid pavement texture parameters is achieved, multi-performance collaborative optimization is achieved by focusing on anti-sliding, noise reduction and drainage core requirements, the limitation of single target optimization is broken, design efficiency and global optimization capacity are improved by relying on an efficient algorithm, and the method is suitable for large-scale popularization and application. Industry specifications are met, and project landing feasibility is ensured.

The invention belongs to the technical field of crucible material proportion optimization, and particularly relates to a quartz crucible material proportion optimization method based on a genetic algorithm. Crucible performance data under different proportions are collected and sorted, data quality is ensured by means of data cleaning and standardization, the data are divided into a training set and a test set for subsequent model training and evaluation, a mathematical relationship between the proportion and crucible performance is established by adopting a regression model, and the performance of the crucible is evaluated. The prediction precision of the model is ensured through training and testing, so that an accurate fitness function is provided for a genetic algorithm; the genetic algorithm is introduced, so that the method can efficiently search an optimal ratio in a global range, and is prevented from falling into a local optimal solution; according to the method, the effectiveness of the optimal ratio is ensured, the research and development period is greatly shortened, the cost is reduced, and the global optimal ratio is quickly determined through systematic data processing, accurate model construction and efficient algorithm application.

The invention belongs to the technical field of image processing and recognition, and particularly relates to an aerospace image recognition method for image focusing detection based on a Gaussian model, which comprises the following steps of: acquiring an aerospace image; the collected images are preprocessed; extracting feature information of a target from the preprocessed image by using a deep learning technology, and performing feature extraction on the image by using a convolutional neural network (CNN); a target is detected according to the extracted feature information, and a target detection algorithm based on deep learning is used; and post-processing the result output by the target detection module. According to the invention, the feature expression in the image is automatically learned by using the deep learning technology, and the target can be accurately identified. And through an optimization algorithm and a parallel computing technology, the accuracy of target detection is improved. An efficient algorithm and a hardware acceleration technology are adopted, a large amount of image data can be rapidly processed, and the data processing time is shortened. And meanwhile, the parallel computing technology is adopted to realize computing acceleration, so that the real-time performance is improved.

The invention provides a line fault position prediction method, and belongs to the technical field of fault detection, and the method comprises the steps: carrying out the modeling of a transmission line, and carrying out the preprocessing of a feature signal; analyzing the frequency domain of the discrete signal in combination with discrete Fourier transform and fast Fourier transform; and constructing a dynamic shaping fusion model, and predicting a line fault position by using the dynamic shaping fusion model. According to the method, a dynamic shaping model is introduced, the feature extraction capability of CNN, the time sequence processing advantage of LSTM and the complex mode learning capability of ANN are combined, and an efficient algorithm framework suitable for transmission line multi-fault positioning is provided. On the basis of deep learning, the problems that an existing fault positioning method is inaccurate in fault positioning, low in actual use reliability, weak in fault signal detectability and weak in characterization capacity are solved, and accurate fault positioning of the energy transmission line is more effectively achieved.

The invention provides a system and method for generating explanation cues, and the system comprises an environment state observation and feature extraction module which is used for carrying out the collection and feature extraction of the information of an original observable environment, and obtaining a basic data set; the intelligent agent observable environment state feature extraction module is used for generating a playing combination according to the basic data set and analyzing the current situation to obtain an environment state feature set; and the text generation prompt module is used for integrating the multi-source information and generating explanation prompt words. According to the technical scheme, through an automatic generation mechanism, high-quality explanation cues are quickly generated by utilizing an efficient algorithm and powerful computing resources; manual intervention is reduced, and the production efficiency is greatly improved.

The invention relates to the field of thick film measurement, and discloses an implementation measurement method of a thick film sample pre-fitting algorithm, comprising the following steps: step 1, establishing a model for a specific sample; step 2, inputting a film thickness value di, calculating ellipsometric angles psi and delta in a central wavelength range, and converting data into signals with 1 / lambda ([mu] m-1) as coordinates; 3, solving an average period Di at the central wavelength, and inputting different film thickness values di for multiple times to obtain a corresponding relation between the average period T and the thickness d; and 4, analyzing measurement data, and finding a thickness approximate value. According to the method, the pre-fitting time is compressed to be within 0.5 s, on one hand, when the relation between the film thickness and the distance between the adjacent extreme points of the signal is established and measurement data is analyzed, the extreme points are searched and data statistics is carried out by adopting an efficient algorithm, and the calculation time is shortened;

The invention discloses an implementation method of a sub-connection active STAR-RIS assisted secure communication system. A base station, a sub-connection active STAR-RIS, a legal user and an eavesdropping user are included. According to the invention, M units of STAR-RIS are grouped into L sub-arrays, and an amplifier is shared to reduce power consumption and cost; with maximization of system secrecy energy efficiency as a target, base station beam forming, STAR-RIS reflection / transmission coefficients and amplifier amplification coefficients are jointly optimized; and solving the non-convex optimization problem by adopting an efficient algorithm based on block coordinate descent. According to the invention, the hardware overhead and the system power consumption are effectively reduced through the sub-connection structure, meanwhile, the secure transmission efficiency of the system is remarkably improved through joint optimization, multiplicative fading is overcome, and an efficient and reliable solution can be provided for 6G secure communication.

The present disclosure relates to a media content recommendation method, device, electronic equipment and storage medium. The media content recommendation method comprises: obtaining a content value score of first media content and obtaining related data of the first media content; determining first recommendation data according to the content value score of the first media content and the related data of the first media content; determining second recommendation data according to the first recommendation data and a received control instruction, the second recommendation data comprising a push priority of second media content, the control instruction being used to adjust a push priority of the first media content, the second media content being different from the first media content and comprising a plurality of media content; and determining and pushing target media content according to the push priority of the second media content and a preset priority threshold. Through the present disclosure, new hot content recommendation can be performed through manual intervention while ensuring efficient algorithm execution of content recommendation and meeting user individualization requirements.

The invention provides a high-efficiency algorithm for extracting effective readings of an instrument. The high-efficiency algorithm comprises the following steps: S1, defining three pointers; s2, judging whether the reading accords with an increasing trend or not; s3, carrying out reasonable amplification judgment; s4, extracting all effective readings to obtain total energy consumption data; according to the high-efficiency algorithm for extracting the effective readings of the instrument, the precision and reliability of data acquisition are improved through a plurality of measures such as meticulous effective reading screening, amplification judgment, table return processing and exception processing; through a time interval division and energy consumption calculation method and algorithm, energy consumption in each time period can be accurately calculated, and energy consumption data of a plurality of time intervals can be provided according to actual conditions; the method is very useful for energy monitoring and analysis, especially for application scenarios requiring accurate tracking of energy consumption changes.

Systems and methods related to normalization of runtime data for algorithm training in a zero-trust computing environment are provided. The data set is first projected into a feature space using at least one transform model, and used to extract identified features of a dataset, yielding a pre-processed dataset before subsequent runtime algorithm consumption. Systems and methods are also presented for algorithm certification in a zero-trust computing environment, and report generation in a zero-trust computing environment. In yet another embodiment, systems and methods for processing data using a foundational model for data curation are provided. These systems and methods enable more efficient algorithm deployment and operation.

The present invention relates to the field of digital information transmission technology, and specifically provides a network security protection encryption method and device. The method includes: obtaining the data to be tested and encryption algorithms, marking them as each target algorithm, collecting the test data of each target algorithm, and obtaining the performance evaluation index and security evaluation index of each target algorithm through processing; obtaining the basic characteristic data of the data to be encrypted, and obtaining the data demand performance parameter and data demand security parameter of the data to be encrypted through processing; comprehensively analyzing to obtain the comprehensive energy efficiency evaluation index of each target algorithm, and screening the encryption algorithms. By providing a network security protection encryption method and device, the present invention comprehensively analyzes to obtain the comprehensive energy efficiency evaluation index of each target algorithm, which helps to select a more efficient algorithm in terms of resource utilization, thereby reducing the waste of system resources, improving the overall efficiency and response speed, and also reducing the risk of system failures caused by algorithm defects or deficiencies.

The present invention discloses a text content extraction and recognition method based on vertical merging of line text boxes. By using a finger to point at the question to be viewed under the device camera and uploading it to the server in the form of a picture, all the text related to this question can be selected with a rectangular box through a simple algorithm, achieving vertical merging of one line, and presenting the text in the rectangular box. According to the position information, semantic information, and finger coordinate information of the text box, the present invention uses a simple and efficient algorithm to realize the merging of multiple relevant text boxes, and outputs the content in the merged text box. This algorithm is simple and efficient, solving the problem of insufficient server resources. At the same time, the present invention uses object detection and hand detection recognition to find the coordinates of the finger key points. After using the existing model and subsequent training, the accuracy is improved and the speed becomes faster, which can better cooperate with the text box merging algorithm.

A method for performing scaling operations in a neural network, the method comprising: selecting a dynamic range; selecting a set of prime moduli such that a product of moduli in the set of prime moduli is greater than or equal to the dynamic range; selecting a power of 2 scaling factor m; selecting a k factor such that 2 k is a smallest positive integer satisfying, wherein is a number of moduli in the moduli set; precomputing and storing parameters in memory; and computing a scaled version of a Residue Number System (RNS) number by removing m least significant bits using the parameters and the k factor without binary reconstruction of the RNS number.

The invention relates to an energy storage vehicle number minimization determination method and system in a distributed energy network, and the method comprises the steps: firstly constructing an energy storage vehicle power supply model, defining the network node position, user use, power supply demands and other conditions, and then constructing an energy storage vehicle number minimization model with the cost minimization as the target under the constraint condition of meeting the power demand, discretizing vehicle deployment positions, introducing a binary variable to optimize a minimum energy storage vehicle number model, finally constructing a multi-energy storage vehicle network topological graph, solving the model by adopting a greedy strategy, and outputting the minimum energy storage vehicle number and deployment positions; according to the invention, by optimizing the deployment positions of the energy storage vehicles and the scheduling of user power, constructing an integer linear programming model, and providing a low-complexity and high-efficiency algorithm based on a graph theory and a greedy algorithm for solving, the calculation complexity during path planning is reduced, the optimal deployment of the distributed energy network is ensured to be realized with the minimum number of energy storage vehicles, and the optimal deployment efficiency of the distributed energy network is improved. And the utilization efficiency of resources is obviously improved.

This application relates to an unsupervised multimodal data fusion method for medical diagnosis. The method preprocesses each modality of data in all samples to obtain first image features, first text features, and first physiological features. These first image features, first text features, and first physiological features from each training sample are then input into a variational autoencoder (VAE) and a generative adversarial network (GAN) to train the VAE and GAN respectively. Finally, any multimodal data to be fused is sequentially passed through the trained VAE and GAN to output the second features of the corresponding modality. The second features of each modality are then fused to obtain the final fused feature. This method, in an unsupervised environment, designs an efficient algorithm capable of simultaneously processing and fusing different medical modalities, providing richer semantic knowledge representations for complex tasks.

The invention discloses a VCX protocol-based private network data stream encryption and decryption method and system, and the method comprises the steps: S1, carrying out the real-time collection operation of data through a data collection end, and sequentially carrying out the encryption operation of the collected data through a VCX encryption network bridge for multiple times; s2, transmitting the data encrypted for multiple times to a data storage end through a wireless local area network; and S3, the VCX decryption network bridge sequentially carries out multiple times of decryption and reduction on the multiple times of encrypted data received by the data storage end, and the data storage end carries out storage operation on the reduced data. According to the method, the direct insertion type VCX encryption network bridge and the direct insertion type VCX decryption network bridge are adopted, the VCX encryption network bridge and the VCX decryption network bridge are subjected to three-layer encryption and decryption processing, the data safety is greatly improved, symmetric cryptography algorithms are adopted as encryption algorithms and decryption algorithms, it is guaranteed that the algorithms are simple and efficient, large-data-volume encryption and decryption operation can be conveniently carried out, and the encryption and decryption efficiency is improved. The problem of unsafe data transmission in the existing private network is effectively solved.

The invention relates to the technical field of aero-engine simulation analysis, and particularly provides an aero-engine multi-stage wheel disc structure-oriented numerical analysis efficient algorithm, which comprises the steps of S1, establishing a cyclic coordinate system, and obtaining a sector model stiffness matrix and an external force vector; s2, eliminating the internal degree of freedom of the wheel disc; s3, solving the degree of freedom of the inter-disc structure after the internal degree of freedom of the wheel disc is eliminated; s4, solving the internal degrees of freedom of all the wheel discs through back substitution; and S5, obtaining a strain field and a stress field, and judging a potential failure point according to the strain field and the stress field. The numerical simulation precision and efficiency of the multi-stage wheel disc structure can be improved.

The invention discloses a computer automatic identification method for an architectural CAD drawing. The method comprises the following steps: carrying out primitive line segment processing; constructing a quadtree and carrying out connected clustering; segmenting by adopting a well algorithm; performing gridding processing on a profile map in the CAD drawing; the discrete wall body units are aggregated into an overall outer contour; and carrying out smoothing processing on the overall outer contour. According to the method, large-scale CAD drawing data can be rapidly processed by using efficient algorithms such as the quadtree and the check set, and the building entity component can be identified. According to the method, the tolerance is adjusted, so that the method can adapt to different drawing complexities. According to the method, the manual modeling time is shortened, the error rate is reduced, and the building efficiency of the building BIM model is improved.

The invention discloses an electric vehicle charging and discharging intelligent optimization decision-making method and system based on learning mechanism guidance. Relates to the technical field of electric vehicle and power distribution network collaborative optimization scheduling. The method comprises the following steps: step 1, acquiring daily load data of an electric vehicle, distributed wind power and photovoltaic output respectively; 2, simulating a classic scene through a K-means clustering method based on the daily load data in the step 1 to obtain simulation data; 3, constructing a multi-target optimization model according to a time-of-use electricity price system and electric vehicle charging and discharging constraints; and 4, inputting the simulation data into a multi-objective optimization model, solving by adopting a double-Q learning algorithm and a multi-objective particle swarm algorithm, and determining an optimal scheduling strategy based on a TOPSIS decision method. According to the method, an EV charging and discharging cooperative scheduling mechanism of multi-interest subject demands can be considered, and accurate optimization of a multi-target Pareto optimal solution under complex constraints is realized through an efficient algorithm.

The invention relates to an overall fuel tank point cloud initial registration method based on structural feature descriptors, which comprises an effective fuel tank contour line and fastener vertex extraction algorithm, and designs an effectiveness judgment strategy to screen feature combinations which contribute to subsequent descriptor construction; a brand new structural feature descriptor is designed, and accurate registration between point clouds is realized based on the descriptor; and a distance constraint condition is adopted to replace an iteration step in a registration process, so that the algorithm efficiency is effectively improved. According to the method, the problems of poor point cloud data registration precision and low reliability in a local highly similar scene are solved, so that the digital three-dimensional reconstruction precision of the whole fuel tank of the large aircraft is improved, and high-quality three-dimensional data are provided for subsequent detection and measurement tasks.

The invention relates to the technical field of language processing, in particular to a multi-scene Tibetan character recognition and error correction method based on a Tibetan language large model, Tibetan syllable vectors are generated through the Tibetan language large model, an error correction model is constructed based on the vectors, and efficient and accurate recognition of Tibetan characters is achieved. By constructing an error correction model, the recognition result is subjected to deep error correction by utilizing the strong semantic understanding capability of a large language model. The method not only improves the recognition accuracy, but also enhances the robustness and stability of the system, so that a reliable recognition result can be obtained in multiple scenes. And an efficient algorithm and a model structure are adopted, so that the processing efficiency can be remarkably improved while the recognition accuracy is ensured. The method is of great significance to rapid processing and analysis of large-scale Tibetan texts, and is helpful to promote rapid development of Tibetan information processing technology, thereby solving the problem of low accuracy of an existing Tibetan character recognition error correction method.

The invention discloses a Lyapunov-based sampling rate control and transfer calculation resource allocation joint optimization method. The method comprises the following steps of S1, collecting an edge server set; s2, calculating the calculation task load of the edge server in the time slot; s3, calculating energy consumption generated during a sensing data calculation task; s4, obtaining a three-dimensional joint optimization formula oriented to the agricultural sensor sampling rate, the edge server preprocessing mode, the edge-cloud communication and the computing resources; s5, defining a function and optimizing the function; based on the scene characteristic and resource coupling relation of the agricultural Internet of Things, three core problems of dynamic regulation and control of the sampling rate of a sensing layer, collaborative allocation of resources of a transfer layer and precise adaptation of full-link service are focused, an integrated resource optimization framework and an efficient algorithm are constructed, and collaborative improvement of data acquisition precision, resource utilization efficiency and service response speed is realized.

The invention relates to a safe short packet transmission method in multi-label backscatter communication, namely a safe short packet transmission method based on maximizing the minimum secrecy rate in all Internet of Things nodes in a short packet BackCom network. The method is realized by jointly optimizing the transmission power of a special energy source, the packet length of a short packet and the power reflection coefficient (PRC) of a backscattering label, a closed expression of the optimal PRC and the transmission power is derived, and an original problem is allowed to be decomposed into two manageable sub-problems. In order to effectively solve the sub-problems, an effective algorithm for solving the non-convex optimization problem by using continuous convex approximation SCA is provided, a theoretical basis is laid for designing a safe and energy-saving BackCom system, and particularly, the algorithm is customized for Internet of Things applications with strict delay and reliability requirements. The framework is easily adapted to other wireless communication scenarios with similar constraints.