52 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 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 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.

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.

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 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.

The invention discloses a multi-interface heterogeneous Internet of Things access device, and relates to the technical field of Internet of Things, the access device comprises a transmission specification module for carrying out standardization and non-standardization integration on a common protocol of the device to form a unified device transmission specification, and the multi-interface heterogeneous Internet of Things access device is used for carrying out multi-interface heterogeneous Internet of Things access through the access device. The multi-interface heterogeneous Internet of Things access equipment has remarkable advantages, supports various communication protocols and interfaces, can seamlessly access Internet of Things equipment of different manufacturers and types, expands the application range, reduces the replacement cost, improves the expansibility, and meanwhile, improves the access efficiency by virtue of a high-concurrency processing and real-time data storage module of an advanced distributed architecture and a high-efficiency algorithm. According to the system, concurrent data requests of massive devices can be dealt with, timely processing and storage of the data are ensured, the real-time performance of the system is guaranteed, and the high-degree-of-freedom object model setting module endows the system with high flexibility and can accurately adapt to various device characteristics and complex service scenes.

The invention provides an axial plunger pump fault diagnosis method based on a space-time DQN model. The axial plunger pump fault diagnosis method comprises the following steps that a pressure signal sequence of key measuring points of an axial plunger pump is collected through a pressure sensor; performing time-frequency domain conversion on the one-dimensional pressure signal by using continuous wavelet transform to obtain a multi-scale time-frequency characteristic matrix and finish standardization processing; obtaining a time sequence representation vector and a space representation vector; and splicing and fusing the two types of representations in feature dimensions to form state representations, inputting the state representations into a Q network of a DQN model to output action values of various fault types, adaptively adjusting a risk penalty weight and a discount factor to construct a Bellman-based target equation, updating network parameters through Huber loss, and outputting a diagnosis result. According to the method, the time-frequency coupling characteristic of the pressure signal of the plunger pump and the dynamic uncertainty of the operation environment are considered, the time-space correlation information can be effectively captured, the diagnosis precision is high, the stability is high, the algorithm operation is efficient, and the method has good engineering practical value.

This invention relates to an optimization method for port selection and time slot scheduling of a joint fluid antenna based on a wireless powered communication network (WPCN), belonging to the field of wireless communication technology. It solves the problems of poor communication quality and low throughput of traditional WPCNs, leading to poor network self-sustainability. First, to optimize port selection and time scheduling in the WET and WIT phases, an optimization problem to maximize the total system throughput is constructed. Then, closed-form solutions for the optimal time allocation in the WET and WIT phases are derived, and the optimal positions of the port selection parameters in the WIT phase are also derived. Finally, the optimal port index in the WET phase is derived, and an efficient algorithm based on the alternating optimization (AO) method is proposed to obtain the optimal port activation state iteratively.

The invention relates to the technical field of aerospace robot docking, in particular to a non-cooperative target 6D pose estimation method based on multi-spectrum feature interaction, which comprises the following steps: acquiring and preprocessing image data, and establishing a training data set; according to the training data set, respectively obtaining low-frequency features and high-frequency features, interactively constructing a 6D pose estimation model, and designing a loss function to train the 6D pose estimation model; and performing pose prediction through the trained 6D pose estimation model, and outputting a prediction result to realize pose estimation of the non-cooperative target. The 6D pose estimation model comprehensively processes high-frequency features and low-frequency features of spacecraft image data so as to realize aggregation of long-range and long-distance context features; and the 6D pose estimation model has the characteristics of lightweight deployment, efficient algorithm and the like, can improve the efficiency and precision of non-cooperative spacecraft target pose estimation, and can be applied to 6D relative pose estimation for close-range spacecrafts and assist autonomous docking of spacecrafts.

The invention provides a heart conductivity inversion optimization algorithm of a supervised full-connection neural network, and belongs to the field of medical electrical impedance imaging algorithms. The method comprises the following steps: constructing a human thoracic cavity heart section initial image and carrying out finite element subdivision on a to-be-detected region; establishing a forward modeling objective function and an inversion objective function; conductivity distribution and corresponding potential difference value data models are generated in batches through the forward model, and a training set is constructed; a full-connection neural network of an encoder-decoder structure is constructed, the input is a potential difference value vector, the output is a conductivity variable quantity, and feature transmission is optimized through bottleneck layer compression and residual connection; introducing a forward modeling consistency regularization item into the loss function; a dynamic learning rate strategy and a gradient cutting technology are adopted. The method does not need to depend on clinical data acquisition equipment, high-precision conductivity inversion is achieved through a pure algorithm, the nonlinear mapping relation between the electrical impedance imaging input quantity and the electrical impedance imaging output quantity is represented, and efficient algorithm support is provided for non-invasive diagnosis of heart diseases.

The present invention provides a method for selecting efficient algorithms for personalized customized production lines, relating to the field of smart factory technology. The method integrates various scheduling algorithms and designs a unique algorithm selection mechanism. It uses a constraint-based algorithm selector, then a hyperparameter optimizer to perform optimal parameter configuration, and finally sends it to a solver to solve the scheduling strategy. The present invention solves the deficiency that the flexible production line scheduling system cannot autonomously match algorithms. For production operation problems, it can significantly reduce the overall system energy consumption, improve manufacturing production efficiency, shorten the maximum completion time, and significantly reduce the waste of materials and time. In addition, since the products produced using the optimal algorithm are of high quality, the production process is smoother, and economic benefits are effectively improved.

The invention discloses an intelligent customer service telephone traffic work order intelligent extraction method, and the method comprises the steps: carrying out the real-time voice transcription of the call recording of a user and an agent, and automatically extracting key information through a large model; according to the key information, a predefined work order template is automatically matched, corresponding fields are filled, and a seat is assisted in completing work order input. In combination with the capability of an AI large model, an efficient algorithm model is applied, and call content is analyzed and extracted through addition of a specific business scene knowledge base and matching of a work order template, so that the function of automatic work order filling is realized.

The application discloses a multi-unmanned aerial vehicle path planning method based on agent model optimization, acquires a multi-unmanned aerial vehicle planning task; a path planning model optimization target function is established, the target function is a total length of all unmanned aerial vehicle paths; Monte Carlo sampling is carried out based on the target function, a group of decision vector values are randomly generated, and a target function value corresponding to each decision vector is calculated as a sample data point; the sample data point is fitted by using a Gaussian process to generate an agent model; the agent model meeting the requirement is used as an auxiliary target; the target function and the target function of the auxiliary target are iteratively evolved by using a genetic algorithm; and the unmanned aerial vehicle path planning is output. The application establishes a path planning model, and solves the model by using an efficient algorithm to acquire an effective path planning scheme.

This invention relates to an initial registration method for overall fuel tank point clouds based on structural feature descriptors. It includes an efficient algorithm for extracting fuel tank contour lines and fastener vertices, and designs a validity judgment strategy to select feature combinations that contribute significantly to subsequent descriptor construction. A novel structural feature descriptor is designed, based on which accurate registration between point clouds is achieved. A distance constraint condition replaces the iterative steps in the registration process, effectively improving algorithm efficiency. This invention addresses the problems of poor registration accuracy and low reliability of point cloud data in locally highly similar scenes, thereby improving the accuracy of digital 3D reconstruction of overall fuel tanks for large aircraft and providing high-quality 3D data for subsequent inspection and measurement tasks.