79 results about "Iterative search" patented technology

The invention discloses a free-form surface three-axis ball-end cutter equal approximation error finish machining tool path generation method which comprises the following steps: firstly, importing a free-form surface model to be machined, and setting data such as the radius, the line spacing, the approximation error maximum allowable value and the precision of a ball-end cutter; secondly, a group of section planes are planned according to the row spacing to intersect with the curved surface, the intersecting line serves as a cutter contact curve, and an equal-bow-height-error cutter contact iterative search method for driving cutter contact adjustment through the geometric distance is provided for the cutter contact curve on the section planes; the maximum distance between a cutter cutting envelope surface and a cutter contact track line is used as an approximation error, and an adaptive discrete method is adopted to carry out approximation error calculation; and finally, the cutter location points of the equal-bow-height-error cutter contact points serve as initial values, an equal-error cutter location point calculation method of step length self-adaptive adjustment iteration is provided, approximation errors between the cutter location points are all within an allowable range, and therefore the free-form surface three-axis ball-end cutter equal approximation error finish machining cutter path is obtained.

This invention relates to the field of robot motion planning technology, and proposes a method and system for obstacle avoidance path planning for a multi-degree-of-freedom robotic arm. The method includes: constructing a resultant force guiding field composed of an attractive potential field and a repulsive potential field; iteratively searching from the starting point to the target point along the gradient direction of the resultant force guiding field to generate a pre-path point sequence; mapping the generated pre-path point sequence to the joint space through inverse kinematics to obtain a candidate configuration sequence; sequentially detecting whether the local path segments between adjacent configurations in the candidate configuration sequence satisfy collision constraints, and determining that adjacent configurations are gaps to be repaired if they do not satisfy the constraints; establishing a bidirectional random expansion tree and adjusting the expansion step size in real time according to the potential energy intensity of the repulsive potential field in the current region; repairing the gaps to be repaired through the interconnection of the bidirectional random expansion tree, and splicing the repaired path segments with the path segments that satisfy the collision constraints to generate the final obstacle avoidance motion path.

The application discloses a micro-nano grating and photocathode collaborative design method. The method breaks the traditional isolated design, and considers the micro-nano grating and the photocathode as an organic whole, and takes the spectral response or integral quantum efficiency of the system as a whole as a target function. Specifically, the method comprises the following steps: establishing a system structure model and clearly defining an optimization target and process constraints; establishing a complex refractive index-wavelength correlation model of the photocathode to accurately obtain a complex refractive index distribution; determining a set of parameters to be optimized and setting initial values; calculating the system electric field distribution under the current parameters based on an electromagnetic simulation model; combining the electric field distribution and the photoelectric emission mechanism to calculate the spectral response of the system in the target waveband; and using a parameter optimization algorithm to iteratively search the parameter space, and outputting an optimal parameter combination. The application fully considers the electromagnetic and photoelectric coupling between the two and the actual process constraints, has the advantages of high design accuracy, strong pertinence, good implementability and the like, and can significantly improve the detection sensitivity of a weak light detection device.

This invention provides a method and system for elastic scheduling of cloud-edge resources in intelligent converged terminals for low-latency scenarios, relating to the field of resource scheduling technology. The method includes: acquiring and decomposing the end-to-end latency constraints of a target low-latency service request, and setting N initial candidate execution paths; mapping the N initial candidate execution paths to path state vectors and performing multi-dimensional evaluation analysis; performing path iterative search of the N initial candidate execution paths based on the comprehensive evaluation vector; configuring an elastic scheduling strategy using the path iterative search results; and performing intelligent scheduling management of the target low-latency service request. This invention solves the technical problems of existing cloud-edge-device scheduling methods that rely on static rules or single-node load, leading to unstable latency and low resource scheduling efficiency for low-latency services. It achieves the technical effect of improving the latency stability and resource scheduling efficiency of low-latency service requests through multi-dimensional constraint decomposition and path iterative optimization to realize cloud-edge-device collaborative scheduling.

This invention discloses a multi-step load forecasting method for integrated energy systems based on Bayesian optimization and anti-overfitting, comprising the following steps: acquiring and preprocessing historical time-series data of the integrated energy system; constructing an initial feature set, using a random forest model to calculate the importance of each feature in the initial feature set, and selecting a core feature subset from the initial feature set according to a preset cumulative importance threshold; defining the hyperparameter search space of the hybrid model; using a Bayesian optimization framework, aiming to minimize the comprehensive loss on the validation set, and determining an optimal hyperparameter combination through iterative search; configuring and constructing the hybrid model according to the optimal hyperparameter combination; independently training the hybrid model for electricity load, cooling load, and heating load respectively, inputting the current time-series features into the prediction model, and outputting multi-step predicted values ​​of each type of load within a specified future time period. This effectively improves the overall accuracy and generalization ability of multi-step load forecasting for the integrated energy system over the next 24 hours.

This invention relates to the field of flexible DC transmission technology for offshore wind power, and discloses a method and system for collaborative optimization of control parameters of converter stations and wind turbine converters in offshore wind power flexible DC systems. The method includes: constructing an electromagnetic transient simulation model comprising a sending-end converter station, a receiving-end converter station, a DC transmission line, and a wind farm; introducing multiple disturbance conditions and combining variations in control parameters, recording dynamic response process data; establishing a collaborative optimization criterion composed of multiple performance indicators directly mapped from the dynamic response process data; and employing a multi-objective evolutionary optimization mechanism with control parameters as the variables to be optimized and performance indicators as the optimization guide for iterative search. This invention achieves global collaborative configuration of control parameters for converter stations and wind turbine converters, solving the problem of traditional step-by-step tuning methods neglecting dynamic interaction effects, and significantly improving the overall operational robustness of offshore wind power flexible DC systems under multiple disturbance conditions.

The application provides a robot joint space trajectory planning obstacle avoidance point optimization method and system based on operation space dynamics, and belongs to the technical field of industrial robot motion planning and optimization. The method comprises the following steps: constructing a dynamics model of a mechanical arm and initializing a task environment to obtain a joint space dynamics equation, a starting point, a target point and obstacle information; deducing and constructing a Cartesian operation space dynamics evaluation model based on the dynamics model of the mechanical arm; iteratively searching for an intermediate obstacle avoidance point in an obstacle avoidance space based on a particle swarm optimization algorithm and taking the starting point, the target point and the obstacle information as constraints; using the Cartesian operation space dynamics evaluation model, combining joint space displacement, and calculating the comprehensive generation value of a collision-free path from the starting point to the target point via each candidate point; and outputting the candidate point with the minimum comprehensive generation value to generate a final PTP motion trajectory of the mechanical arm. The application integrates dynamics evaluation, optimizes the obstacle avoidance point, and improves the efficiency of the PTP trajectory.

The application provides an unmanned ship path planning method based on information entropy field guidance, and relates to the technical field of unmanned ship navigation. The method first acquires a target region image, labels obstacles, and calibrates the starting point and the ending point of the unmanned ship path; then designs an information entropy value function and gives each position in the target region an initial information entropy value to form an initial information entropy field; iteratively searches the unmanned ship path by using an intelligent sampling strategy combined with an RRT algorithm, and completes initial unmanned ship path planning; optimizes the initial unmanned ship path in four steps to obtain an optimized path, combines a hybrid memory module to accumulate historical path experience, then updates the information entropy value by local enhancement and global attenuation, and outputs the historical optimal unmanned ship path after repeated iteration. The application can comprehensively improve the efficiency, accuracy and practicality of the static obstacle path planning of the unmanned ship in a complex environment.

The application provides a multi-satellite multi-stage observation task planning method and system based on genetic iteration search. A set of to-be-observed tasks and a set of observation time windows of satellites are acquired, and a set of cost coefficients is constructed. The set of cost coefficients includes a plurality of cost coefficient combinations, and each cost coefficient combination includes cost coefficients of all to-be-observed tasks. Based on the set of to-be-observed tasks and the set of observation time windows, an initial to-be-observed task planning scheme corresponding to each cost coefficient combination in the set of cost coefficients is acquired, and a scheme profit of the initial to-be-observed task planning scheme is calculated. The set of cost coefficients is updated based on the scheme profit, and a to-be-observed task planning scheme is acquired based on the updated set of cost coefficients. The effect and reliability of the planning scheme are improved.

The application provides a competition program generation method based on blackboard-driven search and agent cooperation, and belongs to the technical field of software engineering and intelligent code generation. The method comprises the following steps: S1, obtaining a competition topic and completing problem modeling, initializing a shared blackboard and a search tree root node, and writing in constraint and boundary points; S2, generating multiple competition strategies and scoring to form strategy priori, and writing back to the blackboard for guiding subsequent search; S3, taking a candidate code + blackboard context as a state, taking generation / evaluation / repair as an action, and using the iterative search of the Monte Carlo tree search to score back; S4, dynamically cooperating to execute generation, testing and repair according to blackboard information, continuously writing back evidence and outputting the optimal candidate result. The method can realize multi-agent cooperation and knowledge reuse under global search constraints, thereby improving the correctness and stability of the competition program generation.

A multi-objective optimization method for heating section parameters of an electromagnetic induction ethylene cracking furnace belongs to the field of ethylene cracking furnace optimization technology. It includes: determining key structural and electrical parameters of the heating section as optimization variables and setting their value ranges to construct a multi-dimensional design variable space; generating an initial sample set and initializing the particle swarm optimization using Latin hypercube sampling; establishing an electromagnetic field-heat conduction coupled simulation model to calculate the Joule heat distribution and furnace tube temperature field under different parameter combinations; constructing a multi-objective evaluation function based on temperature uniformity, electromagnetic heat transfer efficiency, and coil loss; using a multi-objective particle swarm optimization algorithm combined with non-dominated sorting and external archive mechanisms for iterative search to form a Pareto optimal solution set; and selecting the final heating section design parameter scheme according to engineering requirements. This invention can achieve multi-parameter collaborative optimization, significantly improving heating uniformity and energy utilization efficiency.

This invention belongs to the field of secure communication technology, specifically relating to a method and system for detecting encrypted malicious traffic based on prior knowledge constraints. The method maps encrypted malicious traffic samples to a grayscale load image, prior header features, and temporal statistical sequence features. Global spatial features of the grayscale image are extracted, and the header features are mapped to header units and injected into image units to obtain image branches; temporal branches are obtained through causal dilated temporal convolution. The features of the two branches are weighted and fused according to preset weights, and the difficulty of the samples is jointly measured by combining classification interval, prediction uncertainty, and historical stability to filter difficult samples. Iterative search is used to optimize the fusion weights, and low-rank directional correction is used to adjust the fusion weights for easily confused categories. Relying on prior feature constraints, adaptive adjustment of difficult samples and accurate correction of easily confused categories are achieved.

The application relates to the technical field of artificial intelligence, and discloses a deep-buried multi-structural-face underground powerhouse side wall pre-supporting intelligent design method and system, which aims to solve the problems of supporting lag and poor precision of an existing method, and mainly comprises the following steps: setting the value range of structural face parameters and pre-supporting direction parameters, adopting discrete element numerical simulation to construct a data set under different working conditions; constructing a multi-structural-face surrounding rock deformation prediction model for predicting the maximum deformation of the side wall; taking the prediction model as a fitness function of a particle swarm optimization algorithm to build an optimization framework; obtaining actual structural face parameters of a region to be supported, and iteratively searching the particle swarm optimization algorithm to make the fitness function output the optimal pre-supporting direction parameter with the minimum value; and before the underground powerhouse side wall is excavated, the next layer of rock mass which has not been excavated is obliquely pre-supported according to the optimal parameter. The application realizes the advance of the pre-supporting time and improves the supporting precision, and is suitable for underground powerhouses in complex geological regions.

The application discloses a sum and difference beam optimization method of a cover array antenna, and comprises the following steps: creating an array antenna model and a cover array antenna model; performing quadrilateral mesh division on the models respectively; based on the corresponding quadrilateral mesh division of the models, performing simulation calculation by using a high-order moment method, and extracting corresponding active unit directional diagrams; applying excitation to the antenna units in the models, combining the active unit directional diagrams, calculating the sum and difference beams of the models under different scanning angles, and comparing corresponding performance indexes; and using an improved hybrid differential evolution algorithm to optimize the sum and difference beams of the cover array antenna model which does not meet the index requirements; wherein the improved hybrid differential evolution algorithm performs global and local iterative searches, and adaptively calculates a mutation factor and a crossover factor in the global and local iterative search processes. The application realizes the optimization design of the sum and difference beams of the cover array antenna, and is more in line with engineering application requirements.

The application relates to a blasting effect evaluation method based on a GNSS high-precision space-time reference, comprising the following steps: acquiring blasting seismic wave signals of multiple blasting sources in blasting operation through multiple measuring points with GNSS high-precision space-time reference arranged in a target rock mass region; extracting P-wave arrival time based on the blasting seismic wave signals of the multiple blasting sources, acquiring multiple groups of blasting event P-wave arrival time data groups corresponding to the same blasting source; determining the expected spatial position of all target blasting sources through blasting source parameter iterative search based on residual evaluation; identifying blind shots and determining the positioning blasting source through the expected spatial position; constructing a rock mass PPV space comprehensive distribution field based on a PPV value set of each positioning blasting source, and determining a rock mass damage region and degree caused by the blasting operation in combination with a wave velocity drop quantitative value; and obtaining a blasting effect evaluation result based on the blind shot identification result and the rock mass damage region and degree caused by the blasting operation. The application can realize accurate and rapid blasting effect evaluation.

The application discloses a kind of even circle array one-dimensional spatial spectrum direction finding signal processing device, including data processing and covariance matrix module, MUSIC algorithm processing module, Capon algorithm processing module, processing result fusion module and DML algorithm processing module;The function of data processing and covariance matrix module is received signal pre-processing, and covariance matrix is obtained by calculation;MUSIC algorithm processing module is calculated using input covariance matrix to obtain the MUSIC spatial spectrum of receiving array;Capon algorithm processing module is calculated from covariance matrix to obtain the Capon spatial spectrum of receiving array;Processing result fusion module analyzes and judges the calculation result of MUSIC spatial spectrum and Capon spatial spectrum, whether MUSIC spatial spectrum needs iterative search, obtains the direction finding result of incoherent signal, and judges whether it contains coherent signal;DML algorithm processing module processes a pair of coherent signal DOA calculation, and outputs spatial signal direction finding result.This device can accurately calculate the DOA of incoherent signal;And on the basis of incoherent signal direction finding, a pair of coherent signal direction finding is completed.

The invention discloses an NOMA-assisted mobile edge computing energy efficiency optimization method based on PSO-DQN, is used for solving the technical problems that the influence of a transmission sequence is not considered, the optimization algorithm collaboration is insufficient, the multi-objective optimization balance is poor and an interference processing mechanism is incomplete in the prior art, and belongs to the technical field of mobile edge computing. The method comprises the following steps: step 1, optimizing a user-server transmission sequence; the transmission interference between the user equipment is regarded as a fixed value, and an optimal transmission sequence set of the user equipment to the edge server is determined through PSO and DQN iterative search; step 2, optimizing a transmission sequence and an unloading proportion between the user equipment; and step 2, based on the optimal transmission sequence set obtained in the step 1, carrying out joint iteration on PSO and DQN, further optimizing a transmission sequence and an unloading proportion between the user equipment, and determining an optimal resource allocation strategy.

This invention discloses a single-image robot visual image detail enhancement algorithm inspired by exponential-trigonometric functions, comprising the following steps: Step 1, obtaining initial residual features from the original image; Step 2, designing a loss function to describe pixel value loss and evaluate whether the residual image patch matching reaches the optimal level; Step 3, initializing image candidate patches, setting search boundaries and the initial position of each image candidate patch, and comparing each image candidate patch with the designed loss function to obtain the initial optimal image patch and the initial optimal fitness; Step 4, using an optimization algorithm to iteratively search the original image using the initial residual features and perform residual updates to obtain the final optimal image patch; Step 5, superimposing the optimal image patch onto the original image to obtain the final detail-enhanced image. This invention can significantly improve the texture clarity and edge discernibility of robot-acquired images, directly improving the accuracy and stability of downstream visual tasks.

This invention discloses a method for registering IOS and CBCT images based on particle swarm optimization and single-tooth optimization, belonging to the field of image data processing. The method includes the following steps: Preprocessing and segmentation steps are used to obtain the semantic segmentation results of teeth from IOS and CBCT images, as well as point cloud data; a particle swarm optimization algorithm is introduced to iteratively search and optimize the six-degree-of-freedom rigid transformation parameters between the IOS and CBCT image data, thereby completing the initial global registration at the dental arch scale; using the globally registered result as a basis, the registration object is divided into multiple local units based on a single tooth, and local iterative alignment is performed on each unit to eliminate minor misalignments on individual teeth and optimize the overall registration effect. This invention, based on handling cross-modal differences and achieving global registration, further ensures registration accuracy at the single-tooth level through a local optimization mechanism, providing reliable automated registration support for clinical scenarios such as orthodontics and implantology.

The application discloses a flight model allocation method, device and equipment, the method comprises the following steps: collecting flight information, model information, airport information and economic data of a target airline; extracting a first flight set within a first preset time range from the flight information; setting a same model change penalty threshold for each flight in the first flight set; establishing a target function of the model change penalty threshold; constructing a model allocation model with multiple optimization targets; iteratively searching the target function, and obtaining a candidate model allocation scheme and a candidate model change number corresponding to the output of the model allocation model according to each candidate model change penalty threshold; and outputting a target model change penalty threshold and a target flight model allocation scheme within the first preset time range after iterative solution. The embodiment of the application can automatically adjust the model change penalty threshold, optimize the flight model allocation scheme, and improve the efficiency of flight model allocation.

A GIS field-electrical fusion real-time condition awareness and early warning system and method, comprising an embedded synchronized signal acquisition and measurement unit (100) and an industrial personal computer (200), wherein a simulator (201), a partial discharge source locator (202), and an early warning device (203) are deployed on the industrial personal computer (200); when the embedded unit (100) detects, according to a strongly correlated feature, that an electromagnetic field signal within a GIS comprises a partial discharge signal, the embedded unit (100) obtains a full time-domain waveform plot comprising a time-domain waveform plot and a frequency-domain waveform plot of the partial discharge signal; the simulator (201) performs coarse positioning on a partial discharge source on the basis of the full time-domain waveform plot of the GIS partial discharge, and performs simulation-enhanced computation by using a coarse positioning result as an initial injection point, so as to obtain simulation-enhanced data for the partial discharge source; the partial discharge source locator (202) performs iterative searching on a measured discharge intensity calculated according to the full time-domain waveform plot and a simulation-enhanced result, so as to obtain an actual discharge location of the partial discharge source; and the early warning device (203) performs early warning on the basis of a full waveform in a time domain and early warning information comprising the actual discharge location of the partial discharge source.

The application discloses a three-dimensional engine rendering control method based on adaptive deep learning. By collecting scene geometric complexity, texture complexity, processor utilization, video memory occupation and historical rendering performance data, a rendering state feature vector is constructed, and an initial rendering parameter is generated by inputting the prediction model; on this basis, an exploration search mechanism is introduced to perform multidimensional trial on the parameter, and candidate parameters are screened in combination with the trial rendering result; further based on a directional search strategy, the parameter optimization direction is determined and iterative search is performed to obtain refined rendering parameters; the optimized parameters are applied to the three-dimensional engine to complete rendering processing, and performance and image quality data are synchronously acquired; meanwhile, a rendering cycle data feedback mechanism is constructed to realize dynamic updating of the parameters and the state. The method fuses the prediction and search strategies, realizes collaborative control of rendering efficiency and image quality, and has adaptive adjustment and cyclic optimization capabilities.

The application discloses a software repair method based on a large model and an iterative tree search, which fuses a Monte Carlo tree search, screens the most potential patches from a patch tree according to UCT values, then generates new candidate patches based on the selected patches in combination with thought chain reasoning and self-reflection, then executes test cases to verify patch correctness, and if the test passes, marks the patch as reasonable, and if the test fails, adds the patch to the patch tree, in order to evaluate patch quality, when test cases are sufficient, scores by Test-as-Judge according to test pass rate, and when test coverage is limited, scores by LLM-as-Judge in combination with semantics and context, and finally updates the patch tree by reverse propagation from the selected patch to the root. After the complete iterative search process, all reasonable patches can be obtained. The application solves the local optimal trap and search redundancy problem existing in the existing automatic program repair method based on a large model, and further realizes efficient and low-cost repair of program bugs.

This invention proposes a globally constrained heuristic method and system for optimizing the routing of transmission lines in complex mountainous areas, belonging to the field of power engineering planning and design and disaster prevention and mitigation technology. The method includes: acquiring and processing geospatial elevation data of the target area to output wind speed cloud maps influenced by terrain; calculating terrain flow field data based on the wind speed cloud maps influenced by terrain, and constructing a discretized terrain model containing three-dimensional coordinates and environmental cost values; setting transmission line selection constraints, including target straight-line distance, distance tolerance, target direction angle, angle tolerance, and minimum distance between path points; defining the path cost function as the integral of the path segment length and environmental feature values; using a minimum heap structure for iterative search based on the discretized terrain model to calculate multiple discrete path point sequences with the minimum cumulative cost while avoiding constraints on already selected path nodes; and evaluating the selected optimal paths to obtain the transmission line selection results.

The present application relates to a double-ended DC power transmission fault location method, system, storage medium and computer, the method first uses the energy structure characteristics of current signal to construct high sensitivity starting criterion, accurately records the fault time. Secondly, based on the voltage and current data before and after the fault time, the first modal counter-traveling voltage wave is extracted, and the method of Laguerre orthogonal matrix fitting combined with Hilbert transform is used for accurate denoising, and the noise interference is effectively filtered out. Then, the Bergeron time domain equivalent model of the double-ended DC power transmission system containing frequency variable loss is constructed, the denoised counter-traveling voltage wave is taken as the excitation, and the time domain fault voltage signal is solved. Finally, based on the fault voltage signal, the weighted energy density spatial distribution function is constructed, and the two-stage iterative search strategy is adopted to accurately locate the fault point. The present application has strong anti-interference ability, high location accuracy, and is not affected by the transition resistance.

This invention relates to the field of tunnel drilling and blasting technology, and particularly to a method, medium, and equipment for optimizing borehole placement based on face point cloud constraints. The method includes: scanning the tunnel face using a 3D lidar to obtain unmeshed face point cloud data in a local coordinate system; converting the face point cloud model to the absolute coordinate system of tunnel construction using a coordinate registration algorithm to obtain a 3D face point cloud model in absolute coordinates; constructing a reverse spatial linear equation for the borehole based on the coplanar constraint of the borehole bottom according to tunnel blasting design methods; and calculating the true borehole coordinates and actual borehole depth using a combination of spatial iterative search and local microplane fitting based on the 3D face point cloud model and the 3D borehole spatial trajectory equation. This invention can calculate the true borehole coordinates and actual borehole depth adaptable to uneven rock surfaces, solving the problems of uneven blasting foundations and severe over- and under-excavation.

The application relates to a large model-based code search method, which comprises the following steps: obtaining a target code library to be searched; performing reasoning analysis on code segments in the code library through a code understanding intelligent agent, taking extracted semantic information as IOF data; converting the IOF data into a feature vector, storing the feature vector into an initialized vector database, and constructing a mapping index of an IOF field to an original code segment; analyzing the semantics of a user query through a query understanding intelligent agent and generating initial search metadata; performing preliminary search in the vector database based on the search metadata to obtain a candidate list; constructing an iterative search loop containing an evaluation intelligent agent, the evaluation intelligent agent judging the matching degree of the current candidate list and the query, if a termination condition is not reached, re-generating search metadata and performing incremental search; when the termination condition is met, performing semantic reordering on the accumulated candidate IOF data through a reordering intelligent agent, and finally outputting recommended code segment results.

The present application relates to a kind of electric power facility failure prediction and emergency repair scheduling method, comprising the following steps: collecting various data in dispatching area, obtain multi-source time series data, with the multi-source time series data of each type of electric power facility as characteristic variable, with the failure probability of corresponding electric power facility as target variable, train random forest model, predict the failure probability of each electric power facility at current time, and based on the risk level of the preset failure probability interval division, carry out dispatching optimization to high-risk facility. The matching framework of repair team capability and fault point demand is constructed, and the repair team capability and fault point demand are quantitatively matched under the same dimension. A repair team scheduling optimization model is constructed, a variety of driving strategies are embedded in the scheduling optimization model, iterative search is carried out using NSGA-II algorithm, a Pareto optimal solution set is obtained and partial order comparison and sorting are carried out, and a single optimal repair scheduling decision scheme is selected using fuzzy comprehensive evaluation method.