24 results about "Weighted distance" patented technology

The application relates to the technical field of big model computing power scheduling, in particular to a computing power cooperative intelligent scheduling method and system based on a big model application, which comprises the following steps: obtaining a global computing power task request containing multiple big model inference tasks, extracting multi-dimensional features according to task constraint conditions and forming a task demand vector. An improved greedy algorithm is adopted to match the task demand vector and a state vector of a dynamic heterogeneous computing power resource pool, a preliminary scheduling instruction set is generated through weighted distance, a multi-step forward-looking evaluation model with computing power resource balance and task communication overhead as joint targets is constructed, the running state of tasks and resources in multiple time slices is simulated, the scheduling instruction is corrected, and finally the instruction is issued to a hardware computing unit to complete task execution. The method can improve the matching accuracy of tasks and computing power resources, optimize the balance of resource allocation, and reduce the data communication overhead between tasks.

This invention discloses a method for optimizing the design of complex equipment based on a hybrid adaptive sampling surrogate model. This method divides the design space into several Voronoi polygons controlled by sample points. Three indices—leave-one-out error, local nonlinearity, and polygon region size—are used to evaluate the importance of each sample point region. An entropy-weighted distance method is used to select the most suitable sensitive region for adding points. A learning function based on error estimation is then combined to determine new sampling points. This iterative update constructs a high-precision surrogate model, establishing a mapping relationship between design parameters and optimization objectives, thereby solving the design optimization problem. This invention innovatively proposes a multi-index adaptive weight allocation method to select sensitive sample regions and proposes a novel learning function to determine the location of added points. This method can construct a high-precision surrogate model using fewer sample points and can be used for the optimization design of complex equipment, including but not limited to tunnel boring machines.

The application relates to the technical field of power distribution network protection, and provides a waveform self-similarity fault type identification method and system based on a Tanimoto coefficient. The method comprises the following steps: acquiring multi-channel time sequence waveform data, pre-processing the waveform data and performing multi-scale division, and generating a multi-scale waveform feature primitive set containing time domain, frequency domain and time-frequency domain feature vectors; based on the multi-scale waveform feature primitive set, a generalized Tanimoto coefficient between different physical channels and different analysis scales is calculated, and a cross-scale and cross-channel self-similarity tensor is constructed; the self-similarity tensor is subjected to tensor decomposition, a time intensity vector of an atomic self-similarity mode corresponding to a fault mode is extracted, and is fused into a decoupled self-similarity feature vector; the decoupled self-similarity feature vector and a pre-stored standard fault feature template are subjected to weighted distance calculation and hierarchical comparison, and a fault type identification conclusion is output according to a comparison result. The method is helpful to improve the accuracy of fault type identification under complex working conditions.

The application relates to the technical field of agricultural automation control, in particular to a seedling tray falling speed self-adaptive adjusting method based on a laser radar, which comprises the following steps: obtaining point cloud data obtained by scanning a seedling tray bottom surface by the laser radar; wherein the point cloud data comprises three-dimensional coordinates, distance values and echo intensities of a plurality of measuring points; performing confidence degree screening on the measuring points based on the point cloud data to obtain an effective measuring point set; according to the echo intensities of the measuring points in the effective measuring point set, calibrating single-point confidence degree weights of the measuring points, and performing confidence degree weighting on the distance values of the measuring points to obtain confidence degree weighted distance values of the measuring points. The application can automatically distinguish three regions of a convex edge, a concave groove and a flat bottom surface through partition identification of the seedling tray bottom surface, and can perform self-checking and error correction on the partition result, so that the partition result is closer to the actual structure of the bottom surface, lays a foundation for subsequent differential processing of the regions, and improves the accuracy of speed adjustment.

The application discloses an automatic viewpoint planning method and device for motor end cover screw hole group inner wall detection. In view of the problem of missing depth values in the center area of the screw hole, multi-ray back projection and CAD surface intersection are adopted to realize stable three-dimensional hole positioning. Based on the geometric parameters of the screw hole, a combination of front view points and inclined view points is automatically generated, and the combination is converted into an executable joint angle configuration through inverse kinematics solving and collision detection. The multi-screw hole viewpoint access problem is modeled as a clustering traveling salesman problem, and a genetic algorithm combined with dynamic programming is used for hierarchical path optimization, taking the joint space weighted distance as the cost, so that the overall detection efficiency of the mechanical arm is improved.

The present application relates to the technical field of automobile parts detection, in particular to a kind of automobile air conditioner compressor valve group air tightness detection method, comprising: acquisition is detected valve group multiple detection cycle in original air tightness detection data set collected by intelligent sensing system, data set includes pressure decay sequence, leakage acoustic wave sequence and mounting seat vibration sequence.Pressure decay sequence extracts pressure leakage feature vector, and acoustic fingerprint feature vector is obtained by analyzing leakage acoustic wave sequence.Improved nearest neighbor classification algorithm with feature dimension weighted distance measurement is used to determine sample similarity, two types of feature vectors are classified jointly, and leakage mode classification result is output.Air tightness detection conclusion is generated in combination with classification result and vibration sequence.The method can accurately determine the leakage condition of the valve group and locate the specific position of the leaking valve piece, improve the detection dimension and fault positioning accuracy, and adapt to the fine air tightness detection application of the valve group.

The application provides a complex environment ship lock foundation pit intelligent measurement method and device, relates to the image processing and engineering measurement technical field, and the registration weight is determined according to the laser reflection intensity of each point in the target point cloud set, the weighted distance is constructed by introducing the weight when establishing the point pair corresponding relation, and the registration process is preferentially dependent on the high-quality point with obvious structural features;Based on the weighted corresponding relationship, the optimal space transformation parameter is solved and the displacement field is calculated, further, the displacement meter monitoring data is used as an external reference, the displacement field is calibrated by calculating the deviation and constructing the system deviation field, the cumulative error in the registration process is eliminated, the technical problems that the low reflection intensity area interference registration accuracy under the complex environment and the lack of external reference lead to the systematic drift of the displacement field are effectively solved, and the accuracy and reliability of the deformation area identification are improved.

This specification provides a method and system for evaluating the seismic performance of long-span buildings. The method includes: acquiring multidimensional performance response data of the long-span building under seismic motion to form a sample set; determining the initial number of cluster centers based on a preset number K of seismic performance levels; calculating the sensitivity coefficient of each response parameter to overall damage; identifying extreme response samples in the sample set and selecting the point with the largest weighted Euclidean distance from the origin as the first initial cluster center; calculating the local density of unselected candidate sample points and calculating the minimum weighted distance between the sample point and all selected centers; multiplying the local density by the minimum weighted distance to obtain an evaluation index; selecting the sample point with the largest evaluation index as the next center; and using the determined K centers as initial centroids to perform weighted cluster analysis on the performance sample set to obtain a classification of K seismic performance levels.

The application discloses a watershed space-time rainfall generation method and system based on rainfall weighted flow distance, comprising the following steps: calculating the distance from each rainfall station to the drainage outlet in a watershed, and performing normalization processing; constructing a rainfall weighted distance constraint in any time period; converting the constraint relationship into a nonlinear least square optimization problem; solving the optimization problem by using a sequential quadratic programming algorithm; repeating the optimization process for all time periods to obtain a watershed rainfall proportion matrix, wherein the watershed rainfall proportion matrix is used for representing the proportional distribution relationship of a rainfall process at different rainfall stations and in different time periods. The application can flexibly generate various rainfall distribution scenarios under the condition of meeting specific rainfall space-time index constraint conditions, so as to quantitatively analyze the influence of rainfall center movement on urban flood process.

This invention discloses a multispectral screen pixel defect detection method and system, comprising the following steps: S1, acquiring screen images using a multispectral sensor and preprocessing them; S2, extracting pixel spectral features and reducing dimensionality; S3, determining the defect type using K-means clustering; S4, grouping defective pixels by type and location using weighted distance-based region topology clustering to construct the spatial topology of the defect region; S5, accurately constructing the defect region boundary using improved Delaunay triangulation to eliminate discontinuities between pixels; S6, comparing and analyzing the smoothed boundary with the original image to output a defect location and type detection report. This invention achieves high-precision, low-missibility, continuous, smooth screen pixel defect detection and structured output through multispectral acquisition, spectral feature analysis, clustering determination, and improved Delaunay boundary reconstruction.

This invention discloses a fast simulation method and system for stochastic wind fields based on a two-layer parallel architecture. The method is based on the Shinozuka harmonic synthesis framework and employs a spatial + frequency two-layer parallel architecture. In the spatial dimension, nested loops are eliminated through a tensor broadcast mechanism, and a single parallel computation yields the coherent weighted distance matrix for all spatial point pairs. In the frequency dimension, single-frequency amplitude calculation is encapsulated as a pure function, and multi-frequency tasks are batch-parallelized through vectorized mapping operators, with an adaptive memory management mechanism dynamically adjusting the batch size. The system includes modules for parameter input, parallel computation, memory management, and time-domain generation, supporting CPU / GPU heterogeneous acceleration. This invention significantly improves the efficiency of stochastic wind field simulation while maintaining complete physical accuracy, and is suitable for wind-resistant design of structures such as long-span bridges, super high-rise buildings, and offshore wind turbines.

This invention belongs to the field of radar signal processing technology and relates to a method for identifying radar active interference in small samples. The method includes constructing a simulated radar active interference sample set and performing short-time Fourier transform processing, dividing it into a support set and a query set according to the small sample learning method; embedding multi-scale asymmetric features of the sample input into a network to extract multi-scale and directional features; correcting the category prototype center through an improved prototype network and prototype correction method; generating a distance scaling coefficient using a distance sensing module; completing interference category discrimination and updating model parameters through weighted distance measurement; and using the trained model to classify and identify test samples. This invention solves the problems of inaccurate category prototype representation and poor adaptability of distance measurement in small sample radar active interference identification through the collaborative design of prototype correction and distance sensing guidance.

The application provides a vehicle state feature extraction method based on frequency domain decoupling and staggered space-time interaction, which comprises the following steps: obtaining a historical dynamic state sequence of a target vehicle and surrounding traffic participants, introducing an anisotropic weighted distance measurement to screen interactive neighbors with high lateral conflict risk, and completing feature tensor construction and data standardization in a local coordinate system; constructing a feature extraction network comprising a hierarchical multi-scale space-time encoder, performing frequency domain filtering by using a multi-granularity one-dimensional convolution kernel, decoupling high-frequency sensor noise and low-frequency motion trend, and dynamically calibrating features in combination with a channel attention mechanism; constructing a staggered space-time interaction module, performing multiple cycle iterations of independent time sequence state evolution and predictive spatial context aggregation, and extracting a dynamic social game logic between vehicles; and outputting a high-dimensional global space-time interaction feature tensor, which provides reliable data support for accurate perception and safe decision-making of high-level autonomous vehicles in congestion and high-dynamic interaction scenarios.

The application relates to the technical field of fault prediction, and discloses a solid-state transformer fault prediction method and system based on multi-source data. The method comprises the following steps: constructing an initial feature distribution model based on historical operation records; obtaining a deviating feature vector according to the weighted distance between real-time data flow and the initial model; calculating an abnormal score according to the deviating feature vector, aggregating outliers to form an abnormal event sequence; extracting features to construct a fault signal vector, matching a benchmark fluctuation vector to obtain an abnormal confirmation list; carrying out correlation analysis on historical fault data to obtain a confidence degree sequence; carrying out cluster analysis on a head abnormal event set to screen a risk subset; and simulating resource allocation to optimize a configuration scheme. The method can realize high-precision prediction of solid-state transformer faults and resource allocation optimization.

The application discloses a kind of mine ventilation optimization method and system based on edge computing architecture, and optimization method includes the following steps: gas concentration information, air velocity information and temperature information perceived to the environmental perception unit are corrected and normalized processing;Characteristic vector is extracted to normalized data, the weighted Manhattan distance of characteristic vector and window center is calculated, and according to the weighted distance matching of characteristic vector and preset working condition characteristic matrix, in combination with historical window frequency statistics and time consistency determination, output working condition label;Build digital twin ventilation network model, to design energy consumption minimization, air volume distribution uniformity maximization, equipment life equalization as optimization goal, according to the output working condition label, build total target optimization function;Solve total target optimization function, obtain optimal control instruction, and issue to underground fan and air door, and dynamically adjust control instruction according to gas concentration information, air velocity information and temperature information obtained by environmental perception unit in real time.

The application provides a kind of surface deformation monitoring method and related device based on multi-source geodetic data, it is related to surveying and mapping engineering technical field, the method is by obtaining satellite observation data, three-dimensional point cloud data and topographic deformation data, then the topographic feature parameters of monitoring point are extracted from three-dimensional point cloud data, and the topographic weighted distance corresponding to monitoring point and slope gradient constraint parameter are determined, and the three-dimensional deformation field of target area is constructed, further, satellite observation data and topographic deformation data are input into three-dimensional deformation field using Kalman filtering algorithm, the observation covariance matrix of monitoring point and deformation state estimation result are obtained, and surface deformation monitoring model is generated according to deformation state estimation result and observation covariance matrix, finally sent to terminal equipment for visual presentation. In this way, the accuracy and effectiveness of surface deformation monitoring result under complex terrain conditions are effectively improved.

The application discloses an emergency material warehouse layout method and system based on historical disasters and regional characteristics, and belongs to the technical field of emergency management and spatial decision; the method comprises the following steps: normalizing parameters in a demand point set, and calculating comprehensive weights; using kernel density estimation to calculate a demand point spatial distribution density set, and selecting a candidate warehouse set; taking minimizing weighted distance, minimizing construction cost and maximizing coverage weight as targets, a multi-objective optimization model is constructed; the fitness of a current candidate material warehouse scheme is calculated; s schemes are selected from the candidate material warehouse scheme group, and an individual with the optimal fitness is selected until the scale reaches M; two parent schemes are randomly selected, and a distribution factor is calculated; the parent schemes are mutated to obtain child schemes; parent and child scheme groups are combined, the first M optimal individuals are reserved to obtain a new scheme group; if the number of iterations does not reach the maximum number of iterations and the fitness does not converge, iteration is continued; and decision support is provided for scientific storage and rapid deployment of emergency materials.

The present application belongs to the technical field of industrial energy digital management, and particularly relates to a kind of industrial equipment low carbonization reconstruction efficiency intelligent evaluation method and system, its method includes: collecting the multi-source heterogeneous operation data before and after industrial equipment reconstruction;Dynamic response hysteresis index representing system dynamic instability and hysteresis degree is constructed, and the search radius of density-based clustering algorithm is adaptively adjusted using dynamic response hysteresis index;Carbon sensitive weighted distance cost function is constructed, and the optimal warping path between the measured sequence after reconstruction and the ideal benchmark sequence is found using dynamic time warping algorithm based on cost function;A low-carbon reconstruction efficiency comprehensive scoring model is constructed, and the low-carbon reconstruction efficiency comprehensive score is calculated to evaluate the low-carbon reconstruction efficiency of industrial equipment. The present application can eliminate thermal inertia misjudgment and focus on core emission reduction conditions to achieve scientific and comprehensive performance evaluation.

The application discloses a rattan weaving skill data auxiliary management method and system based on image analysis, relates to the rattan weaving image processing technical field, and constructs an initial weaving topology graph through acquisition of a rattan weaving original image; high-confidence and interference topology first-level subgraphs are divided through pixel quality evaluation; the length of an adjacent boundary and the similarity of a topology structure are calculated with the high-confidence topology subgraphs as references, and a structure priori vector is coded; the vector dispersion is selected to perform weighted fusion or is divided into interference topology second-level subgraphs according to a weighted distance to determine a generated priori; the topology subgraphs are repaired through a conditional generation model, and a complete weaving topology graph is fused and output; and the precision can be optimized and improved through time sequence, symmetry and boundary consistency. The application can accurately repair the topology structure of an interference area, and significantly improves the integrity and reliability of the rattan weaving topology graph.

This invention belongs to the field of building structure testing technology, and relates to an intelligent analysis and testing method for the seismic performance of curtain wall structures based on vibration monitoring. The method includes: collecting and preprocessing multi-source synchronous excitation and response data to obtain dynamic acceleration sequences and standard wind pressure sequences; extracting structural dynamic features from the dynamic acceleration sequences to obtain high-frequency and low-frequency vibration energy; processing the standard wind pressure sequences to obtain average wind pressure and wind pressure abrupt change range; constructing a physical response index that integrates nonlinear hysteresis effects and using this index to reconstruct the multi-dimensional spatial feature data through clustering distance to obtain a physical state weighted distance; performing adaptive benchmark calibration based on the physical state weighted distance and outputting seismic performance degradation assessment results. This invention solves the problem of false alarms in strong winds and missed alarms in light winds that easily occur in anomaly detection algorithms under complex wind pressure and meteorological conditions.

The present application relates to the technical field of data processing, and more particularly to an environment data collection method and system for a vehicle-mounted refrigerator. The method comprises the steps of: collecting vibration acceleration data and extracting a multi-dimensional feature vector; for each feature vector, calculating its local dispersion and global difference; based on the local dispersion and global difference, determining the global abnormal contribution degree of each feature vector and calculating a linear reinforcement factor; based on the global abnormal contribution degree of each feature vector, calculating the modified weighted distance between the vibration acceleration data and its neighborhood data; based on the modified weighted distance, obtaining the modified LOF score of the vibration acceleration data, and based on the modified LOF score and the linear reinforcement factor, calculating the modified local outlier factor, and then determining the abnormal condition of the vibration acceleration data and whether the data collection system needs to collect data again. The method enhances the recognition sensitivity of early mechanical failures of the vehicle-mounted refrigerator.

This invention discloses a method for identifying and batch processing defects in multi-page printed materials, relating to the technical field of printing quality inspection. The method first establishes a three-level coordinate system to achieve structured alignment of the entire page. Secondly, it collects multi-dimensional features to establish a statistical sample library. It then constructs a normal process drift model to dynamically compensate for the target features of each page size. The entropy weight method quantifies the weights of 12-dimensional features, including printing sequence correlation deviations. Combined with weighted distance, adjacent distance difference, and IQR constraint verification mechanisms, it achieves defect grouping and anomaly removal. Finally, a three-component Gaussian mixture model is introduced to complete the final determination of the source relationship, followed by batch labeling. This invention transforms the detection complexity from O(N) step-by-step judgment to batch processing based on position indexing, significantly improving quality control efficiency and providing accurate traceability. Through multi-dimensional feature cascade analysis and probabilistic model judgment, it effectively distinguishes between regular process fluctuations and real defect differences, eliminating environmental drift misjudgments.

The present application relates to the technical field of computer vision, in particular to a soil nematode automatic identification system and method based on microscopic image features, the system comprising: an image acquisition module, a structure representation module, a feature decoupling module, a attention weighting module, and an identification decision module.In the present application, the spatial offset vector is constructed by analyzing the target organ data and calculating the geometric barycenter and the gray centroid, the structural deflection of the nematode organ relative to the main body axis is accurately quantified, the initial features are orthogonally projected and separated by using the genus / species level phenotype prototype vector, the common feature interference is eliminated and the specific residual vector reflecting the difference between the groups is retained, the high response diagnosis area is defined by combining the gradient return mechanism, the attention weight of the feature dimension is adaptively assigned according to the activation amplitude, and the sensitive capture of the micro deformation is realized through the anisotropic weighted distance calculation, so as to avoid the subjective error of artificial observation and improve the accuracy of genus / species identification of the close related groups.

This invention discloses a comprehensive log collection and maintenance method and system, relating to the field of intelligent operation and maintenance technology. The method includes: collecting multi-source log data and performing standardization processing to generate standardized log data; calculating information gain to generate attribute weights based on the standardized log data; calculating multi-class attribute distances using K-Prototype clustering to generate a final weighted distance to obtain a clustering dataset; optimizing the GNN model using the PGNN framework combined with a graph attention mechanism to output an optimized clustering dataset; generating anomaly candidate clusters based on the optimized clustering dataset; extracting anomaly characteristics of the anomaly candidate clusters; and classifying the anomaly characteristics of the anomaly candidate clusters using a K-NN classifier to obtain the data point classification results. This invention improves the accuracy and response speed of anomaly log identification, achieving more efficient log management.