97 results about "Swarm intelligence" patented technology

The present application relates to the technical field of agricultural remote sensing and machine learning, and particularly relates to a leaf area index estimation method based on improved XGBoost. The method comprises the following steps: acquiring unmanned aerial vehicle multi-spectral images and sample leaf area index measured values, and constructing a vegetation index map sample data set after preprocessing; performing feature extraction and fusion on the vegetation index map by using a deep learning network; constructing an improved beaver optimization algorithm, generating an initial population by using a two-stage initialization strategy, updating the position of the architect subpopulation by using an elite directional felling strategy, recombining individuals and the global optimal solution by using a vertical and horizontal cross strategy; optimizing the XGBoost hyperparameters by using the improved beaver optimization algorithm, and establishing a leaf area index estimation model. The leaf area index estimation method based on improved XGBoost combines deep learning feature extraction, improved swarm intelligence optimization algorithm and integrated learning regression modeling, and is helpful to improve the prediction accuracy and stability of the leaf area index estimation model.

This invention discloses a brain-inspired bio-inspired asynchronous event-driven sparse computation method for massive video swarm intelligence, belonging to the field of brain-inspired computing technology. Addressing the problems of resource overload, low computational efficiency, and insufficient system adaptability in city-level video swarm intelligence sensing, it constructs an edge-cloud collaborative asynchronous event-driven architecture: the edge triggers effective events based on a bio-inspired mechanism to generate and transmit sparse video data; the edge uses an SNN-ANN dual-stream architecture to asynchronously extract semantic features; the intermediate layer only triggers spatiotemporal fusion and trajectory stitching for cross-domain events; and the cloud completes global situation aggregation and dynamically adjusts the trigger thresholds of each layer according to system resource load. This invention enables sparse computation with no-event sleep and event-awakening capabilities, significantly reducing data transmission and computational overhead, improving system energy efficiency and stability, and can be widely applied to massive video swarm intelligence sensing scenarios such as smart transportation, security monitoring, and city brains.

The present application relates to the technical field of astronomical satellite mission planning, in particular to a method and system for solving short-term mission planning of astronomical satellite. The method comprises: step 1) constructing a short-term mission planning mathematical model of the astronomical satellite to be planned, and abstracting the mission planning problem as a maximized optimization problem; step 2) solving by using a hybrid search strategy artificial bee colony algorithm, searching for excellent solutions by the employed bees based on an "elite solution guided search" strategy, and searching by the follower bees based on a "neighborhood optimal solution update" strategy, so as to accelerate the solution and improve the solution accuracy. Compared with the basic artificial algorithm, the method has the advantages of fast convergence speed, high solution accuracy and strong optimization ability, and has fewer control parameters than other swarm intelligence algorithms; in the short-term mission planning problem of the astronomical satellite, the method can obtain higher task completion degree and greater observation benefit.

This invention discloses a GNSS integer ambiguity fixing method integrating intelligent optimization algorithms and VIB strategies, belonging to the field of satellite navigation and positioning technology. This method combines the advantages of VIB strategies and swarm intelligence fusion optimization algorithms. By directionally grouping the ambiguity floating-point solution covariance structure, the ambiguities are guided into groups. The PSOAF and AWDE intelligent optimization algorithms are used to perform parallel searches on the grouped ambiguities, improving search efficiency and positioning accuracy. Simultaneously, the probability assessment and fixing judgment of the integer solutions of each sub-block ambiguity and the overall ambiguity ensure the reliability of the ambiguity solutions, making it suitable for complex and dynamic GNSS positioning scenarios.

The application discloses a kind of wideband signal-oriented distributed movable antenna layout optimization method, comprising: based on swarm intelligence algorithm, antenna layout scheme is iteratively optimized until reaching iteration stop condition, the best fitness of population corresponding antenna layout scheme is regarded as the optimal scheme of antenna layout output;Wherein, the fitness of population is determined according to the wideband cumulative Cramer-Rao bound of its corresponding antenna layout scheme.The present application can directly construct the bottom mapping relationship between continuous position variable and wideband signal direction finding error lower limit by introducing wideband Cramer-Rao bound as fitness function.Because the index itself represents the theoretical minimum direction finding error of antenna layout, it can accurately quantify the spatial spectrum coupling effect of full frequency band;As fitness function, it can make the optimization directly towards the most essential optimization goal, ensure that the output physical array theoretically approximates the wideband direction finding physical limit under this degree of freedom.

The application discloses a kind of millimeter wave sign detection methods based on swarm intelligence and improved wavelet threshold value, wherein the method includes: obtaining the original vital sign signal collected by millimeter wave radar;Construct the multi-objective fitness function of fusion sample entropy, pearson correlation coefficient and kurtosis;The multi-objective fitness function is optimized using the improved Harris eagle optimization algorithm, and the optimal parameter combination of CEEMDAN decomposition algorithm is adaptively solved;Based on the optimal parameter combination, the original vital sign signal is decomposed by CEEMDAN, and a plurality of intrinsic mode function components are obtained.The application constructs the cascade processing framework of "parameter optimization-signal separation-noise suppression", solves the problem that CEEMDAN parameter depends on artificial experience, respiratory and heartbeat signal band aliasing and the problem of insufficient performance of traditional wavelet threshold denoising.

This invention relates to a swarm intelligence-driven AI-based social companionship and matching method, comprising: collecting multimodal data of patients in social interactions; analyzing the data using a swarm intelligence algorithm that integrates multi-view manual annotations to extract key feature vectors; constructing and continuously updating a dynamic social function profile of the patient based on this profile; calculating the matching degree between the patient and other users or social activities using a neural network matching model based on this profile, and generating a personalized recommendation list; and finally performing the matching to facilitate the patient's participation in online social activities or the establishment of a one-on-one companionship relationship. This invention achieves accurate assessment and dynamic tracking of the social status of AD patients, and effectively improves the personalization and effectiveness of social intervention through intelligent matching, forming a continuously optimized closed-loop support system.

This invention relates to the field of UAV navigation and discloses a UAV swarm path planning method based on swarm intelligence collaboration. The method includes acquiring relative state and target orientation data between the UAV and its neighbors, calculating local collision time parameters characterizing collision risk, constraining the obstacle avoidance gain upper limit using the flight control cutoff frequency, generating a yaw correction when the local collision time parameter is less than a threshold, and superimposing the correction with the base yaw rate to obtain the total control quantity, which is then output to the flight control module to drive the UAV. This invention limits the command spectral density by the cutoff frequency, ensuring the total control quantity is within the system's linear response bandwidth, effectively suppressing trajectory oscillations induced by command delays, and utilizing the displacement generated by roll deviation to break the symmetrical force topology, eliminating deadlock, and enhancing the path convergence stability of the swarm in confined spaces.

The application belongs to the technical field of swarm intelligence control, and proposes an agent cluster pursuit and evasion game method based on hierarchical reinforcement learning. The method maps discrete instructions and continuous actions to target assignment and path planning respectively in view of the problem of mixed decision space in the cluster pursuit and evasion scene, and proposes a novel hierarchical reinforcement learning framework. In view of the uncertainty problem caused by the enemy strategy, moving obstacles and insufficient training, a robustness-enhanced adaptive method is proposed. In addition, the method embeds a probability integration network between the instruction network and the action network for quantifying uncertainty, and adjusts the interaction frequency of the two-layer network based on uncertainty. In view of the instability problem of the traditional training method, a fusion training method is proposed. The method independently pre-trains the instruction network and the action network, and cross-trains the two networks to promote the adaptive interaction mechanism.

This invention provides a method and system for direction-of-arrival (DOA) estimation of minimum redundancy linear arrays based on the quantum giant trevally mechanism, belonging to the field of array signal processing. To address the problem of drastic performance degradation of minimum redundancy linear arrays under harsh conditions of impulse noise, this invention proposes using the mean square error of DOA estimation and the probability of successful estimation as core optimization indicators. This method effectively improves the performance degradation problem of arrays under impulse noise by constructing a mapping relationship between the positions of minimum redundancy linear array elements and DOA estimation performance, significantly enhancing the accuracy and robustness of the direction-finding system. The quantum swarm intelligence optimization method designed in this invention provides a promising solution path for the optimization problem through a global search strategy and fitness function design. This invention not only overcomes the applicability and performance bottlenecks of traditional methods under impulse noise environments but also has significant theoretical and practical application value for promoting the engineering application of array technology in high-precision direction-finding.

This invention discloses a method and system for analyzing large user power loads based on swarm intelligence, comprising: Step 1: collecting power consumption operation data and constructing an analysis window; Step 2: calculating time-shifted phase, demand inertia, and response potential energy to form a ternary load state vector; Step 3: constructing a directed swarm influence diagram based on the ternary load state vector; Step 4: calculating edge strength, incoming edge strength, and load deviation characteristics, and classifying user types; Step 5: performing peak warning propagation calculations to generate peak propagation chains; Step 6: performing iterative calculations based on a propagation potential energy-driven mechanism to obtain the optimal intervention scheme vector; Step 7: generating load analysis results and adjustment schemes. This invention achieves accurate analysis and optimized control of large user loads.

The application discloses a kind of based on group intelligence optimization's ciphertext domain image visible watermark embedding method and system, belong to the field of encrypted storage technology.The method includes obtaining original plaintext image, using preset encryption algorithm to the original plaintext image is encrypted, generate ciphertext image, to ciphertext image is remaining entropy space modeling, and according to copyright information generates visible watermark image;Watermark embedding parameter set to be optimized is constructed, watermark embedding parameter set is encoded as individual position vector in group intelligence algorithm, executes the multi-objective optimization search based on group intelligence, carries out optimal parameter selection set ciphertext domain watermark embedding based on search result, obtains the ciphertext image with visible watermark, with visible watermark ciphertext image is safely distributed and service processing handle.The application directly embeds visible watermark in encrypted image, and automatically weighs security, visual saliency and function reservation by group intelligence optimization, realizes the unification of security and intuitive copyright declaration.

This application relates to the field of swarm intelligence optimization technology, specifically to a method for optimizing drone inspection routes for photovoltaic (PV) modules. The method includes: collecting spatial location data of each PV site in a PV power plant, the PV lines between any two connected PV sites, and the nodes along the PV lines; obtaining the terrain influence coefficient between any two connected PV sites; obtaining the terrain influence correction value between any two connected PV sites; obtaining the ascending and descending segments along the PV lines between any two connected PV sites in each direction; obtaining the unidirectional consumption degree and unilateral weights; constructing a weighted and directed graph of the PV power plant based on the unilateral weights; and optimizing the drone's patrol route for PV modules. This application improves the accuracy of drone-based PV module line inspection route planning.

The application provides a kind of electric vehicle cluster charging and discharging collaborative control method and system based on swarm intelligence, and relates to the technical field of intelligent power distribution network operation control.The method first collects real-time status of electric vehicles in the region and transformer load data, and constructs a multi-objective optimization model considering power distribution network load variance and user battery aging cost.It implements double-layer asynchronous cascade control: by analyzing historical interaction logs to extract time response and power execution characteristics, response fingerprint indicators representing instruction execution reliability are generated;Accordingly, the cluster is dynamically divided into base load adjustment subgroups and rapid compensation subgroups.The system uses particle swarm optimization to solve the base load subgroup to generate a benchmark strategy, and establishes a physical model to predict the power lag residual during its execution;Further, the rapid compensation subgroup is optimized to generate a compensation strategy to suppress the residual.The application realizes the collaborative optimization of peak load shifting and user economic benefits of power distribution network.

This application relates to the field of material structure health monitoring technology, and in particular to a method, device, equipment, storage medium, and computer program product for damage identification of composite laminates. The method involves acquiring structural description information of the laminate to be tested, constructing an analysis model of the laminate, and determining a parameter space; solving for multiple natural frequencies for different combinations of damage parameters within the parameter space, and establishing a vibration feature sample library that pairs natural frequency features with damage parameters; employing a hybrid intelligent modeling strategy based on the sample library, utilizing swarm intelligence to optimize neural network parameters, and training candidate identification models with multiple natural frequencies as input and damage parameters as output; selecting a target identification model based on preset engineering requirements constraints, collecting vibration signals, and extracting multiple natural frequencies consistent with the sample library to form the vibration features to be tested; after random noise processing and frequency offset correction of the vibration features to be tested, inputting them into the target identification model, and outputting the damage parameter identification results.

This application discloses a two-stage optimization method and apparatus for end-to-end swarm intelligence sensing systems. The method includes: first, establishing time-slot models, computational models, communication models, and energy consumption models that represent the complete task execution process between sensing devices, UAVs, and execution devices in the swarm intelligence sensing system. Based on these mathematical models, the association factors between the UAV and ground equipment, communication resource allocation, computational resource allocation, and the UAV's flight trajectory are collaboratively optimized. First, the global search capability of a genetic algorithm is used to provide a high-quality initial exploration region. Second, a deep deterministic policy gradient is used to further train and explore this region to obtain the optimal solution that reduces system communication latency and saves energy consumption, thereby ensuring the high efficiency and low energy consumption of the "sensing-communication-computation-execution" task closed loop and minimizing overall energy consumption.

A method for determining the association and continuity combination of top-side-rock structural surfaces based on unsupervised learning is proposed. This method involves investigating the structural surfaces of the roof and side-rock masses in underground engineering projects to obtain geometric and statistical information. A unified encoding is performed to construct a joint feature set of roof-side-rock structural surfaces. An unsupervised density-based clustering algorithm is used for initial cluster analysis of the joint feature set. A swarm intelligence-based Lüperfox optimization algorithm is introduced to optimize key parameters of the DBSCAN clustering algorithm. A Latin hypercube sampling method is used to improve the population initialization process of the Lüperfox optimization algorithm, resulting in better DBSCAN hyperparameters and optimized structural surface clustering results. The method determines the structural surface system affiliation of structural surfaces in different locations, quantitatively calculates the spatial continuity and combination relationship of structural surfaces, and outputs the spatial association determination results and continuity levels of the roof-side-rock structural surfaces. This method enables intelligent identification and quantitative analysis of the spatial relationship between roof and side-rock rock structural surfaces.

This invention belongs to the field of intelligent computing and offshore wind power monitoring technology, specifically involving a collaborative monitoring method for corrosion prevention in offshore wind farms that integrates swarm intelligence. The method includes: acquiring real-time salt spray deposition rate and real-time relative humidity; generating local initial screening; obtaining an environmental stress index; obtaining initial pheromones; calculating a comprehensive pheromone for assessing the swarm's collaborative filtration status; calculating the collaborative focusing degree for assessing high-risk targets across the network and guiding inspection resources; obtaining depth probing measurements characterizing substantial damage to the metal substrate; calculating a degradation risk score for extrapolating the probability of potential structural brittle fracture; and generating corrosion prevention scheduling instructions to guide monitoring status. This invention solves the technical problems in existing technologies, such as the lack of collaborative linkage among offshore wind farm nodes, the difficulty in extracting initial corrosion characteristics due to environmental noise, and the inability of inspection resources to dynamically focus on truly high-risk areas.

This invention relates to the field of early warning technology, and discloses a cable stress intelligent sensing and early warning method and device, comprising: a force acquisition module to acquire standardized multi-point force array data; a reference separation module to extract thermal effect baseline and contact deviation data and divide complete cycle periods; a deformation reconstruction module to generate potential deformation and bending deformation based on a swarm intelligence algorithm; an offset extraction module to acquire the offset of the eccentric hysteresis center; a stress assessment module to fuse the above parameters to amplify the average force value to obtain the equivalent stress index; a dynamic threshold module to generate a safety threshold based on historical data and calculate the over-limit ratio; and finally, an early warning module to output an alarm status. This invention can accurately locate hidden bending peaks induced by micro-rotation angles, achieving early warning.

This invention discloses a method, apparatus, and electronic equipment for calculating the direct carbon emission factor of generator sets, belonging to the field of power system carbon accounting technology. The method includes: acquiring the real-time power generation of the generator set and inputting it into a pre-constructed carbon emission factor prediction model to obtain the corresponding real-time carbon emission factor; wherein, historical actual carbon emission factors are calculated through historical power generation and fuel consumption, an initial model including trend and disturbance terms is constructed, and with the goal of minimizing the sum of squared errors, a swarm intelligence optimization algorithm is used to optimize within the parameter constraints to determine the optimal model parameters, thereby forming the carbon emission factor prediction model. By implementing this invention, the problems of existing generator set direct carbon emission factor calculation models being unable to simultaneously consider the macro-evolution trend of carbon emissions and local nonlinear fluctuations, and the complex model parameter solution being prone to getting trapped in local optima, leading to inaccurate carbon emission factor calculations, can be solved.

The application discloses a kind of underground cavern group complex construction ventilation environment space-time prediction method based on deep learning, including data acquisition, data cleaning, data noise reduction and normalization processing: construct and include sequence perception global Token generation module, graph structure learning module, graph aggregation module, time coding module and trend perception attention module's space-time prediction model: normalized data is divided into training set, verification set and test set, constructs joint loss function, utilizes optimization algorithm to train the space-time prediction model, and adopts swarm intelligence optimization algorithm to automatically optimize hyperparameter;Real-time monitoring data is input after pre-processing into trained space-time prediction model, and the wind speed, dust concentration prediction value of future time step is output, and the operating frequency of fan of ventilation system is dynamically adjusted according to prediction value.

This invention discloses a multi-scale spatiotemporal semantic object state representation method based on brain-inspired biomimetic mapping, belonging to the field of brain-inspired computing technology. Addressing the problems of cross-level semantic abstraction fragmentation, low efficiency of topological association, and semantic redundancy accumulation in city-level video swarm intelligence perception, this invention constructs a hierarchical mapping architecture from edge to middle layer to cloud, sequentially performing progressive abstraction representations from pixel level to individual level, group level, and city level. A multi-dimensional weighted sensor network topology model is constructed, generating a full-cycle continuous spatiotemporal state vector through cross-sensor association matching and trajectory stitching, and completing global optimization and deduplication of cross-camera samples. Simultaneous parallel encoding of metadata and feature streams is performed for swarm intelligence semantic compactness, globally deduplicating and differentially encoding duplicate features and redundant samples. This invention achieves efficient multi-scale spatiotemporal semantic expression through edge-cloud collaboration, significantly reducing transmission and storage overhead and improving the accuracy of cross-regional long-term trajectory stitching.

The application discloses a running control method and system of a direct drive motor, relates to the technical field of control of the direct drive motor, and realizes the real-time collection of three-phase voltage fluctuation data, extracts a harmonic spectrum in combination with frequency domain analysis, and preliminarily estimates a conduction delay and a dead zone compensation time; when low-order harmonic exceeds a standard, the dead zone compensation is increased to form preliminary optimization parameters; subsequently, neutral point deviation, common-mode voltage and three-phase asymmetry are evaluated through waveform simulation; finally, a swarm intelligence optimization algorithm is adopted to iteratively adjust a potential balance correction coefficient, the conduction delay, the dead zone compensation and a phase-to-phase timing offset angle, target timing parameters are obtained, and three-phase switching control instructions are generated and applied to a control system. In the high-power direct drive motor control, the application realizes the timing design of optimized switching action, effectively reduces harmonic interference, avoids system risks caused by potential imbalance, and improves equipment operation stability and reliability.

This invention belongs to the field of AI swarm intelligence training technology, and discloses a central neural network host and system for professionally training super agent clusters. The core is a rack-mounted central neural network host, which includes a heterogeneous computing array, a central neural network chip, an algorithm-encrypted globally shared storage unit, low-latency high-speed interconnect interfaces, a hardware-level risk control and computing power allocation unit, and a stable power supply and heat dissipation module. Each module is independently powered and supports hot-swapping. As the cluster core, this host achieves millisecond-level scheduling, microsecond-level communication, and hardware-level security management of the super agent cluster, significantly improving the training efficiency and computing power utilization of the agent cluster, ensuring the security and stability of the training process, and providing a domestically produced hardware foundation for the unified training and collaborative evolution of super agent clusters, adapting to the needs of large-scale AI applications in multiple scenarios.

This invention provides a task planning method for unmanned system swarm intelligence based on virtual-real migration and feedback evolution. It constructs a local environmental perception and sharing distribution mechanism for unmanned system swarm task scenarios, extracting local perception features; builds an airborne task planning model based on unified state information and globally shared features, forming a lightweight task planning model suitable for airborne platform deployment; constructs a distributed collaborative decision-making and conflict resolution mechanism, a virtual-real feature offset analysis mechanism, and a closed-loop result hierarchical comprehensive evaluation mechanism to obtain the evaluation results required for model optimization; and constructs a collaborative evolution update mechanism for the large model based on the evaluation results to adaptively update the airborne task planning model, realizing the continuous evolution of unmanned system swarm intelligence task planning capabilities in dynamic environments. This invention can improve the collaboration, robustness, and environmental adaptability of unmanned system swarm task planning under conditions of limited communication, limited computing power, and dynamic environmental changes.

The application discloses a large model autonomous learning method for unmanned system swarm intelligence strategy generation, comprising the following steps: S1, a relationship model between agents is constructed, and a coordination model is constructed according to a cooperation relationship and an efficiency relationship when a task is executed; S2, a path planning model of the agents when the task is executed is established based on the coordination model; S3, a resource consumption model is constructed by counting resource consumption of the agents when the task is executed based on the coordination model; S4, a task completion model is constructed by counting a task completion condition of the agents when the task is executed based on the coordination model; S5, the path planning model, the resource consumption model and the task completion model are combined to construct an optimization model, and the model is solved through a multi-objective particle swarm optimization algorithm; and S6, training and evaluation are carried out based on the optimization model. The application can significantly improve path planning flexibility and adaptability of an unmanned cluster in a complex environment.

An adaptive hierarchical multidimensional data insight analysis method based on swarm intelligence, belonging to the field of artificial intelligence technology, utilizes recursive decomposition and synchronous data exploration mechanisms to construct a valid topic tree and automatically prune invalid branches. For leaf nodes, the swarm intelligence agent performs autonomous multi-round searches and multimodal heterogeneous data fusion, recording end-to-end evidence. The verification system verifies credibility through code replay and visual backtracking, quantifies the originality of node analysis using density clustering and truth constraint mechanisms, and scores based on relevance and depth. Finally, an interactive insight topology is constructed, supporting on-demand drill-down rendering from macro-level overview to micro-level evidence. This invention effectively solves the problems of ambiguous entry points and homogenized viewpoints in big data analysis. By lowering the threshold for data analysis through swarm intelligence, it leverages multi-angle analysis by the swarm to reveal non-explicit hidden correlations and high-value sparse insights, achieving full-process intelligentization from automatic planning to in-depth mining.

The application provides a kind of group intelligence evaluation method, device, equipment and medium based on large language model multi-agent system, relating to artificial intelligence technical field.The method comprises: obtaining scene task data;The scene task data is input into large language model multi-agent system for processing, and the scene task execution result is obtained;Wherein, the large language model multi-agent system is a multi-agent system evaluated by group intelligence.The embodiment of the application realizes that the large language model multi-agent system has reliable, verified group intelligence basis when coping with actual scene task, and can significantly improve the accuracy of scene task execution result.