28results about How to "Strong engineering practical value" patented technology

The invention relates to the technical field of knowledge graph completion, in particular to a large model knowledge graph completion method and system based on causal guidance. The method comprises the following steps: acquiring a target knowledge graph and an input triple to be complemented, performing structured analysis on an input triple relationship, extracting key topological characteristics, constructing a structured mediation variable, mapping the structured mediation variable into a structure guide prefix, injecting the structure guide prefix into large model input, and constructing a double-path inference model to generate an inference prediction result; and meanwhile, a gradient sensing dynamic loss balance mechanism is introduced, the loss weight is adaptively adjusted according to reasoning feedback, and finally a more accurate and stable knowledge graph completion result is output. According to the method, the controllability, interpretability and training stability of the reasoning process can be enhanced while the knowledge graph completion precision is improved.

The present application belongs to the technical field of material corrosion data processing and industrial equipment state monitoring, and provides a kind of multi-source feature extraction and structured expression method of air conditioner heat exchanger corrosion data, specifically comprising the following steps: obtaining multi-source corrosion original data;Data preprocessing;Corrosion morphology feature extraction;Electrochemical feature extraction;Environmental influence feature extraction;Feature normalization processing;Structured feature vector construction;Form a structured feature vector with fixed dimension, unified expression. Each component in the feature vector corresponds to a corrosion-related parameter with clear physical meaning, completely describing the corrosion state, corrosion kinetics characteristics and service environment conditions of the heat exchanger under specific space-time conditions. Advantage: significantly improve the usability of data, provide an ideal data interface for multi-modal data fusion analysis and large model technology application, significantly improve the objectivity and reliability of the analysis results, have strong engineering practical value.

The invention discloses a method and a system for simulating correlation of signals between sonar array elements changing along with space. The method comprises the following steps: (1) generating uncorrelated Gaussian white noise; (2) converting uncorrelated Gaussian white noise into Gaussian white noise with spatiality through a spatial correlation generation algorithm; and (3) converting the Gaussian white noise with the spatiality into sonar array element signals with the spatiality through AR (Augmented Reality) filtering. Aiming at certain spatial correlation between marine environment noise caused by limited spacing between array elements of a sonar array, dynamic decomposition is carried out on frequency bands in an effective bandwidth, and then Gaussian white noise with spatial correlation characteristics is synthesized; and the related Gaussian white noise excites the marine environment noise AR model to obtain a signal time sequence between sonar array elements with spatial correlation. According to the method, the sparse characteristic of correlation is fully utilized, the number of filters is reduced, the sparse matrix is adopted to accelerate the calculation process, and the calculation efficiency of the sonar simulation system is effectively improved.

This invention relates to the field of audio circuit hardware technology, and in particular to a low-latency ARC circuit configuration method and system based on I2S audio switching. External video data is received through an ARC circuit compatibility interface and input to a video conversion chip for data separation, achieving synchronous separation of I2S audio signals and MIPI video signals. The separated I2S audio signals are then simulated and sent to the host SOC and external I / O terminals respectively by a first-stage audio switching chip. Through link delay analysis and instantaneous delay judgment, the audio path is dynamically configured to achieve switching control between the internal processing path and the direct path. A second-stage audio switching chip realizes multi-channel audio multiplexing and direct transmission simulation, achieving a low-latency, highly compatible ARC audio output scheme while ensuring audio and video timing alignment. This invention can significantly reduce the direct transmission latency of ARC audio while ensuring audio and video synchronization and system compatibility, and improves the flexibility and reliability of audio path configuration.

The invention is suitable for the technical field of satellite communication, and provides an AI-based satellite-ground integrated unmanned aerial vehicle communication channel management method and system, and the method comprises the steps: obtaining the real-time temperature of a radio frequency front-end module of a current unmanned aerial vehicle satellite communication terminal under the condition of determining that a reference temperature node exists, and when the real-time temperature exceeds the reference temperature node, cooling measures of the unmanned aerial vehicle are controlled based on the temperature node, so that the temperature of the radio frequency front-end module is adjusted to be below the reference temperature node in a future time period. According to the method, existing communication links and cooling hardware structures are not changed, the communication stability and reliability after low-orbit satellite link switching can be improved only through control strategy optimization, the risks of short-time link falling and performance degradation are reduced, finer and more intelligent satellite-ground integrated unmanned aerial vehicle communication channel management is achieved, and the method has remarkable engineering practical value.

The present application belongs to the field of blast furnace system health management and prediction, and specifically discloses a blast furnace degradation model calibration and residual life prediction method under a noise environment. The method is based on a fractional Brownian motion with historical dependence, constructs an initial degradation model of the blast furnace system, estimates the model parameters by the maximum likelihood estimation method, and determines the optimal model structure of the blast furnace system temperature change by the Akaike information criterion. In addition, the present application also designs a model calibration trigger mechanism; when the mechanism is not triggered, the Bayesian fusion particle filter is used to estimate the potential degradation state of the system and update the model parameters; when the mechanism is triggered, a prediction error model is constructed and the degradation model structure is calibrated to adapt to complex working conditions. Finally, the probability distribution function of the residual life of the blast furnace system is derived, and the residual life prediction of the blast furnace system is carried out according to the calibrated degradation model.

The application provides a kind of robust laser SLAM repositioning and mapping method for embodied intelligent robot in the technical field of robot autonomous navigation, comprising: receiving original laser radar point cloud and IMU data, pre-processing point cloud to extract feature points;IMU pre-integration provides initial pose constraint;Loop closure detection is through the two-stage cascade of ScanContext global search and LinK3D local matching, obtains repositioning constraint;Front-end odometry matches feature points with local voxel map, combines IMU optimization to output pose estimation, filters key frame to generate laser odometry factor;With repositioning constraint as initial value, use improved ICP to accurately register to obtain repositioning factor;Finally, construct factor graph, jointly optimize IMU, laser odometry and repositioning factor, solve global consistent pose sequence and map.The application has the advantages that: it greatly improves the system robustness, repositioning accuracy and global map consistency of quadruped robot in severe motion and large-scale scene, while meeting the real-time constraint of embedded platform.

This invention relates to the field of machine tool condition monitoring and health assessment technology, specifically to a feature analysis method and system for ranking machine tool health based on acoustic emission technology. The method involves: cleaning the raw acoustic emission signals collected by multi-channel acoustic emission sensors along the X, Y, and Z axes of the machine tool, removing invalid data, and generating mean and fluctuation sequences respectively; extracting four core feature indicators based on the preprocessed mean and fluctuation sequences; dynamically allocating sensor weights to integrate the indicators according to the test focus object, and after minimization and normalization, calculating and ranking the health score based on weights trained by machine learning. This invention enables accurate quantitative assessment and batch ranking of machine tool health status, supporting intelligent operation and maintenance throughout the entire lifecycle of the machine tool.

The application discloses a trajectory optimization method and system based on differentiable safety constraints in automatic driving, and relates to the technical field of automatic driving motion planning and control; constraint conditions involved in trajectory optimization in the automatic driving process are constructed, an end-to-end neural network architecture is designed based on the constructed constraint conditions, the designed neural network architecture is trained in a dual optimization mode, open-loop simulation tests are carried out based on public data sets, and closed-loop road tests are carried out based on a real vehicle computing platform; the application adopts the trajectory optimization method and system based on differentiable safety constraints in automatic driving to improve the problems of insufficient safety of trajectory planning and difficulty in constraint execution of an existing end-to-end model in a complex scene, and effectively improves the compliance and comfort of the automatic driving system in actual application.

The present application provides a kind of ghost imaging monitoring method and system based on environmental coupling simulation and image enhancement, the method comprises: setting initial light source, the initial light source is handled with splitter matrix model to obtain probe light path light source and reference light path light source, based on the probe light path light source and reference light path light source, respectively construct probe light path and reference light path;In probe light path, lens, object to be measured and bucket detector are set in sequence, and surface detector is set in reference light path, high gauss blur is introduced in probe light path to simulate heavy fog environment, and random phase screen based on Perlin noise is introduced to simulate turbulent environment.The present application builds ghost imaging system through Python, uses Gaussian simulation to simulate heavy fog environment and turbulent environment, and combines the concept of histogram equalization in digital image processing, the imaging quality of ghost imaging is optimized by non-linear mapping gray scale chart, and the imaging quality of ghost imaging system under long-distance condition can be improved.

The invention discloses a spacecraft pose estimation and uncertainty modeling method based on an intrinsic space, and belongs to the technical field of spacecraft pose estimation. The method comprises the following steps: directly constructing a hierarchical Bayesian probability model on a rotating manifold SO (3) and a translation space, respectively using Feisnow distribution and Gaussian distribution, and introducing conjugate prior to realize principle decomposition and quantification of accidental uncertainty and cognitive uncertainty. Through an end-to-end multi-task neural network, pose probability model parameters, key points and segmentation information are jointly learned, and an iterative optimization module is adopted to improve the estimation precision. In the training stage, joint optimization is carried out through edge negative logarithm likelihood and evidence regularization; in the reasoning stage, probability distribution of pose prediction is obtained by analyzing marginalization, and two types of uncertainty are distinguished. According to the method, the pose estimation precision is improved, meanwhile, the uncertainty of good calibration can be output, and a reliable basis is provided for on-orbit autonomous safe operation of a spacecraft.

This invention discloses a method, system, and application for classifying the adjustable potential of photovoltaic (PV) power distribution areas, relating to the fields of smart distribution areas and power big data analysis technology. The invention first acquires source-load characteristic data of users in the distribution area, and then performs net load calculation and preprocessing on this data; the net load represents the power fed back to or drawn from the distribution area by the user. The preprocessed source-load characteristic data is then classified to obtain user categories and corresponding electricity consumption behavior characteristic curves. Based on the electricity consumption behavior characteristic curves, the adjustable load power ratio of each user type is calculated, constructing a PV adjustable potential classification standard. This invention can fully exploit the temporal and local characteristics of source-load data, significantly improving classification accuracy and providing a scientific basis for developing differentiated PV consumption and control strategies for distribution areas.

The invention relates to an insulation state evaluation method and system based on space charge characteristics, and the method comprises the steps: obtaining an original image of space charge density distribution, extracting a curve contour, and recognizing a curve type; based on the curve contour and the curve category, extracting a local average change rate and a peak value feature of the curve; and on the basis of the local average change rate and the peak value characteristics, in combination with the constructed sample database, performing insulation state evaluation in a weighted form to obtain an insulation state evaluation result. According to the invention, by introducing an image recognition technology, key characteristic quantities in a space charge distribution diagram can be extracted for insulating material samples in different aging states, and objective analysis and quantitative evaluation of space charge information are realized.

This invention provides a method and system for identifying interference sources in the auxiliary machinery loads of underwater platforms. Starting from small-sample electromagnetic signals monitored by the electromagnetic environment, it identifies electromagnetic interference signals in the underwater platform's power grid and autonomously analyzes the loads causing the interference, thus achieving effective analysis and identification of electromagnetic interference sources. Based on the characteristics of the auxiliary machinery loads in the underwater platform's power grid, this invention uses an equivalent physical model to simulate the causes of electromagnetic environment deterioration. Simultaneously, it establishes an intelligent electromagnetic interference signal identification model based on a BP neural network algorithm, achieving accurate identification of electromagnetic interference sources caused by changes in the underwater platform's power grid load, demonstrating strong engineering practical value. This invention reduces the efficiency of electromagnetic interference troubleshooting from "monthly" to "weekly" or "daily," significantly improving the efficiency of interference troubleshooting for underwater platform auxiliary machinery loads and reducing maintenance costs.

This invention provides a finite element method for solving generalized axisymmetric plane problems using stress as the fundamental variable, relating to the field of engineering analysis. The method includes: S1. Selecting basis functions that satisfy the equilibrium equations; S2. Applying the complementary energy principle to establish the element equations for each element; S3. Assembling all element equations to form the overall stiffness equation; S4. Applying forced boundary conditions to the stiffness equation; S5. Solving the stiffness equation; S6. Obtaining all stress components at any point within the element through basis function interpolation; S7. Repeating S1 to S6 to obtain the element stress distribution under each basic load condition; S8. Obtaining the stress state under any composite load based on the principle of linear superposition; S9. Evaluating the strength of the stressed body according to material failure criteria. This invention does not require users to possess professional modeling skills; through simple parameter input, the stress solution of complex axisymmetric problems can be obtained quickly and accurately, and strength evaluation and performance characterization can be performed accordingly.

The invention provides a finite element method for solving a generalized axisymmetric plane problem by taking stress as a basic variable, and relates to the field of engineering analysis, and the finite element method comprises the following steps: S1, selecting a primary function meeting an equilibrium equation; s2, establishing a unit equation of each unit by applying a complementary energy principle; s3, assembling all unit equations to form an overall rigidity equation; s4, applying a forced boundary condition to the stiffness equation; s5, solving a stiffness equation; s6, obtaining all stress components of any point in the unit through primary function interpolation; s7, repeating the steps S1 to S6, and solving to obtain unit stress distribution under each basic load working condition; s8, based on a linear superposition principle, obtaining a stress state under any composite load; and S9, performing strength evaluation on the stress body according to a material failure criterion. According to the method, a user does not need to have professional modeling skills, the stress solution of the complex axial symmetry problem can be quickly and accurately obtained through simple parameter input, and strength evaluation and performance characterization are carried out according to the stress solution.

This invention discloses an intelligent personal radiation dose acquisition and monitoring system, specifically relating to the field of nuclear radiation dose monitoring. It addresses the problems of existing dose monitoring systems, such as coarse radiation signal analysis, delayed exposure risk identification, and difficulty in prospective assessment under complex radiation fields and dynamic body positioning conditions. The system performs refined waveform analysis on the raw pulse signals acquired by the personal detection unit, dynamically corrects scattering characteristics and energy deposition based on real-time personal positioning data, constructs an intermediate energy deposition spectrum reflecting the interaction between radiation and human tissue, and predicts the exposure situation within future monitoring time windows based on the evolution of spectral characteristics. This enables intelligent assessment and early warning of personal radiation exposure risks, improves the real-time performance and reliability of nuclear radiation protection, is suitable for nuclear emergency response and high-risk operational scenarios, and supports continuous monitoring and rapid deployment.

The invention relates to a display equipment electromagnetic leakage signal detection method, which belongs to the technical field of electromagnetic detection, and specifically comprises the following steps: firstly, acquiring a space electromagnetic signal through broadband receiving equipment, and preprocessing to obtain a baseband complex signal; by improving a multiple autocorrelation algorithm, initial detection of leakage signals and extraction of core parameters such as a pixel clock and line-field synchronization can be completed without prior parameters; then constructing a confidence discrimination matrix based on pixel amplitude and phase time sequence characteristics, and accurately distinguishing effective leakage signals from various interferences; and then weak signal enhancement is realized through self-adaptive threshold feature preferential selection and confidence coefficient weighted multi-frame coherent accumulation, and finally detection result output is completed, so that the problems that weak leakage signals are submerged by noise and the detection probability is low in a long-distance and high-interference scene can be effectively solved.

The application discloses a kind of fast variable load control methods of molten salt heat storage coupling combined heat and power system, the method first establishes the simplified dynamic model of combined heat and power unit and electric heater, then based on target variable load rate and combined heat and power unit dynamic model, calculates the feedforward compensation power of electric heater, and according to the deviation of system total output power and unit target power, feedback adjustment power is calculated by proportional-integral-derivative control algorithm, and feedforward compensation power and feedback adjustment power are synthesized as the final power instruction of electric heater.In addition, in the process of load tracking, control parameters and target variable load rate are adaptively adjusted according to the system operating state.The application can significantly improve the fast variable load capability of the system, realize accurate, fast and stable load tracking, and meet the demand of power grid for fast peak shaving and frequency modulation.

The application discloses a ground subsidence evolution mechanism analysis method based on GeoShapley and belongs to the field of geological disasters. The method is based on synthetic aperture radar interferometric measurement image data, adopts time-series InSAR technology to obtain regional long-time-series ground surface deformation information, comprehensively integrates geographical space driving factors such as layered compressible layers and layered underground water levels and position coordinate data, constructs a spatially matched regional ground subsidence evolution attribution analysis data set, and integrates an optimally selected subsidence simulation model; position characteristics are taken as single joint characteristic factors and are integrated into a GeoShapley framework, inherent position effects, non-spatial factor position invariant effects and position-non-spatial factor spatial interaction effects of ground subsidence are quantified, and different regional subsidence evolution mechanisms are explored from three dimensions of factor driving, spatial interaction coupling and spatial aggregation. The method can accurately disassemble subsidence multidimensional effects, adapt to subsidence dynamic evolution characteristics, and can provide certain scientific basis for regional ground subsidence partition management and precise prevention and control.

The application relates to artificial intelligence and knowledge engineering, and proposes a method and system for bidirectional semantic mapping between data-information-knowledge-wisdom-intention (DIKWP) multi-layers. By constructing a semantic tensor field and using category theory to define cross-layer functor mapping, combined with the "intention vectorization-knowledge graph embedding" algorithm, the high-level intention is projected to the low-level data / knowledge. And the reverse semantic path search is designed to back up the candidate intention from the observed data. The system sets up a semantic closed loop consistency detection and correction mechanism to ensure the equivalence of layer conversion and the reliability of reasoning. An executable interface is provided to output semantic sub-graph, explanation chain and score, which is suitable for explainable AI, controllable large model and cognitive robot scenes, and improves the relevance, safety and robustness.

The application discloses a kind of based on context multi-arm tiger machine's self-adapting text classification model selection method and system, to solve the problem of inaccurate model selection caused by different classification models in online text classification system Different adaptability difference of different text samples.The application maps multiple text classification models as different machine arms in multi-arm tiger machine, and extracts context features from the text samples to be classified, to depict the statistical distribution characteristics, sparsity features, position distribution features and sentiment features of text.Through dimension division on context features, construct low-dimensional and structured context representation, and evaluate the expected performance of each classification model based on context multi-arm tiger machine mechanism, adaptively select the classification model suitable for the current text sample.Experiments show that the application can effectively reduce the cumulative error rate and average decision regret in the text classification process, improve the overall performance of online text classification system, and has good engineering application value.

This invention discloses a comprehensive evaluation method and system for the health status of a storage battery. The method includes: screening lagging batteries under discharge conditions and retaining healthy batteries as the first healthy battery; screening lagging batteries under float charging conditions and retaining healthy batteries as the second healthy battery; based on the data of the first healthy battery, using a deep learning method, training an LSTM neural network optimized by particle swarm optimization using a set of known time-series data of battery core capacity discharge, and after the network training is completed, directly inputting short-time discharge capacity data to predict the corresponding SOH, which is used as the first SOH; based on the data of the second healthy battery, calculating the second SOH using the battery voltage monitored in real time under float charging conditions; and weightedly fusing the first SOH and the second SOH to obtain the battery's SOH. The advantage of this invention is that it achieves accurate estimation of the battery's SOH.

The application discloses a BIM-based prefabricated building node stress monitoring and design feedback system, relates to the technical field of building engineering structure monitoring, and comprises the following steps: constructing a building information modeling model, extracting component geometric information, connection modes and load paths associated with the node, and forming an initial parameter set of node mechanical properties; combining real-time stress monitoring data of the node, performing Fourier transform and wavelet decomposition, and extracting frequency domain characteristic parameters; constructing a finite element correction model, simulating stress response paths under multiple load combinations; comparing predicted and measured stress peaks, identifying abnormal nodes, and performing parameter optimization according to node construction information, automatically adjusting component size, steel reinforcement anchoring length or concrete grade, generating an optimized parameter set, and writing back to the building information modeling model to form a closed-loop correction; the application can realize continuous monitoring, abnormal diagnosis and intelligent optimization of the stress state of the node, and improve the safety and intelligent level of prefabricated building structure design.

An electroencephalogram signal feature hierarchical optimization method for fatigue detection of a special equipment operator is characterized by comprising the steps that original electroencephalogram signals of the special equipment operator under different fatigue levels are collected; performing multi-step preprocessing on the original electroencephalogram signals to obtain a high-purity electroencephalogram signal sample set; dividing the high-purity electroencephalogram signal sample set according to frequency bands, extracting multi-dimensional and multi-type features, performing standardized normalization processing on the features, and constructing a multi-dimensional feature set; performing accurate optimization on the multi-dimensional feature set through a four-stage hierarchical collaborative optimization mechanism to obtain an optimal core feature subset; wherein the four-stage hierarchical collaborative optimization mechanism comprises intra-class pre-screening, cross-type collinearity elimination, physiological weighted enhanced screening and attention-oriented recursive feature elimination optimization; and inputting the optimal core feature subset into a detection model for detection, and outputting a fatigue state detection result.

The invention discloses an overall flood classification method and system based on flood composition and encountering conditions, and the method comprises the steps: S1, collecting and sorting the overall flood data of a research section, including the flood process of a research section session and the inflow process of an upstream main inflow section at a corresponding time; s2, calculating the flood volume ratio of inflow water of upstream main inflow water sections of different overall floods to downstream floods in different time periods; s3, calculating the average proportion of incoming water of the upstream main incoming water section of each overall flood to the flood volume of the downstream flood in different time periods; s4, primarily classifying the floods according to the average proportion of inflow of upstream main inflow sections of different overall floods to the flood volume of downstream floods in different time periods; s5, flood encounter evaluation indexes are defined, secondary classification is conducted on the overall flood according to the evaluation indexes, and refined classification of the overall flood is achieved; according to the method, the overall flood is classified, the upstream and downstream overall flood can be quantitatively and finely classified, and a basic support is provided for researches such as overall design flood and similar flood recognition.

The invention relates to the technical field of geophysical exploration signal processing, and discloses a GPR echo signal denoising method based on improved WTD and VMD. Comprising the following steps: adaptively optimizing a decomposition modal number and a penalty factor of the VMD by utilizing an HHO algorithm; performing 2D-VMD decomposition on the original GPR data by using the optimal parameter to obtain a plurality of IMFs; dividing the IMF into a signal IMF and a noise IMF through a correlation coefficient; a wavelet threshold parameter is optimized and improved by using a PSO algorithm, and the noise IMF is processed; and after reconstruction, direct waves are removed by adopting an averaging method. Through a dual parameter optimization mechanism, an improved threshold function with continuity and no deviation and a differential threshold processing strategy, adaptive high-precision denoising of a GPR signal is realized, the signal-to-noise ratio is effectively improved, a weak target signal is reserved, direct wave interference is remarkably suppressed, and the method has the advantages of high robustness and high robustness. The method has the advantages of high parameter adaptive capacity, high denoising precision, high engineering practicability and the like.