15988 results about "Statistical physics" patented technology

The invention relates to the technical field of online calibration, in particular to a multi-parameter fusion intelligent electric energy meter online calibration method and system, and the method comprises the following steps: collecting voltage waveforms, current harmonics and active power data, dividing windows, calculating a covariance matrix, and generating a feature set; a power factor curvature extreme value and a temperature inflection point offset are analyzed to generate an interference identifier, current density distribution and a voltage distortion spectrum are jointly analyzed to extract a harmonic energy ratio to generate a feature vector, and phase compensation is performed on a pulse sequence to generate a calibration instruction set. According to the method, the covariance matrix is constructed by synchronously collecting voltage and current power parameters, the abnormal mark section is generated by combining the temperature change and the covariance difference value, the environment disturbance and the real deviation are effectively distinguished, and the temperature hysteresis effect is identified through the power factor curvature extreme value and the temperature inflection point offset. And combining current density and voltage distortion spectrum analysis to extract a fundamental wave and harmonic wave energy ratio, establishing a composite calibration reference, and dynamically adjusting a pulse duty ratio to realize harmonic wave energy compensation.

The local intrinsic dimensionality (LID) for a diffusion model with respect to a particular data sample is determined by using the diffusion model's diffusion process to apply noise to a data sample and evaluate how the estimated log probability of the data sample changes at different levels of noise. Particularly, the differential of change in noise to change in log probability can be used to determine the local intrinsic dimensionality. This may be determined by evaluating the log probability at several noise levels and determining a slope of the difference. In additional examples, the differential is evaluated directly at a selected noise level. The selected noise level can be optimized by calculating the estimated LID for various data samples at a variety of noise levels and selecting the LID that corresponds to a “knee” where the estimated LID sharply changes.

The invention discloses an automatic control method and system for secondary granulation of a high-voltage zinc oxide resistor disc, relates to the technical field of intelligent manufacturing of power equipment, and solves the problems of out-of-control particle morphology caused by dynamic coupling parameter identification lag and control instability caused by multi-physical field parameter coupling in an existing method. According to the invention, a dynamic physical property parameter matrix is generated in real time based on multi-band dielectric relaxation spectrum analysis and terahertz wave tomography; predicting a fluidized phase change threshold value and an energy gathering area through multi-physics field coupling modeling; a time sequence attention deep reinforcement learning algorithm is adopted to generate a multi-field cooperative adjustment instruction; positioning a parameter conflict source and triggering decoupling compensation by combining a high-frequency vibration and acoustic emission combined monitoring module; performing closed-loop correction on the control network weight based on the laser spectrum data and a partial least squares regression model; the real-time performance of fluidization parameter identification, the stability of multi-field coupling control and the recovery efficiency of abnormal working conditions are remarkably improved, and meanwhile the batch consistency of the electrical performance of the resistor discs is guaranteed.

The invention belongs to the technical field of industrial measurement, and discloses a pump machine metal shell size detection method based on image analysis, which comprises the following steps: synchronously acquiring image data of a pump machine metal shell in a visible light wave band and a near-infrared wave band; the contrast ratio of image data is optimized through a dynamic exposure control technology, and a high-dynamic-range multispectral image is obtained; three-dimensional geometric information of the pump machine metal shell is obtained, registration fusion is carried out on the three-dimensional geometric information and the high-dynamic-range multispectral image, a dense three-dimensional point cloud model with multispectral textures is constructed, and a multi-frequency heterodyne algorithm is adopted to process a high-reflection area in the dense three-dimensional point cloud model; the method comprises the following steps: collecting a multi-angle reflection image of a pump machine metal shell by rotating a linear polarizer, calculating a Stokes vector to extract a diffuse reflection component, carrying out diffuse reflection component constraint and brightness suppression on a high-reflection area based on a CIE-Lab color space, and outputting a dense three-dimensional point cloud model after texture enhancement; and the size detection precision of the pump machine metal shell is improved.

The invention discloses an asphalt pavement fatigue damage model calibration method based on AI and digital twinning, and relates to the technical field of damage detection. Compared with the prior art, the problems that traditional asphalt pavement design depends on empirical formulas and static parameters, material aging, environmental coupling and load uncertainty are difficult to dynamically reflect, and cross-scale correlation between microscopic interface behaviors and macroscopic structure performance is lacked are solved; the method comprises the following steps: collecting and preprocessing multi-source heterogeneous data in real time through a multi-modal data fusion and dynamic sensing system, simulating and accurately quantifying asphalt-aggregate interface binding energy and adhesion work in combination with molecular dynamics, and constructing a cross-scale damage evolution model; a physical information neural network is used for embedding an improved Paris formula, actually measured data and a physical rule are deeply fused, and the locality hypothesis of a traditional model is effectively corrected.

The invention relates to the technical field of crustal stress field data processing, in particular to a crustal stress field three-dimensional dynamic inversion method based on a multi-scale adaptive algorithm. The method comprises the following steps: acquiring a geological data set of a target area; constructing a crustal stress field three-dimensional initial model based on the geological data set, and performing geologic body space division and mesh generation to obtain crustal stress field three-dimensional mesh model data; performing multi-scale region division on the crustal stress field three-dimensional grid model data, and establishing a multi-scale weighting function to obtain multi-scale partition mapping information; and constructing a cross-scale boundary adaptive transmission mechanism, and establishing a stress tensor continuity constraint model at a multi-scale partition boundary to obtain cross-scale stress boundary coupling data. Through a multi-scale adaptive algorithm and dynamic closed-loop optimization, high-precision, dynamic and continuous inversion of a crustal stress field in a complex geologic structure is realized.

The invention provides a mesoscale convection parameter optimization method and system based on a genetic algorithm, and relates to the technical field of weather forecast, and the method comprises the steps: modeling a rainfall evolution state through a Sheng differential equation, inferring and recognizing power system parameters in combination with variation, and extracting features through a space-time heterogeneous graph neural network and a diffusion probability model; the parameter threshold is corrected by adopting the physically guided neural network, and the optimization objective function is constructed through the deep neural network to realize parameter optimization, so that the accuracy of rainfall forecasting can be improved, the forecasting error can be reduced, and the method has relatively strong adaptability and generalization ability.

The invention relates to the technical field of temperature control, and discloses a temperature error compensation method and system for a multi-heating-section coffee maker, and the method comprises the steps: synchronously collecting the real-time temperature value of each heating section, and calculating a temperature error index; constructing a thermal coupling interference model based on the physical distance between adjacent sections and the heat conduction characteristic of the medium; generating a dynamic decoupling compensation parameter according to the model and the error index (including constructing a symmetric interference matrix, calculating a coupling interference component, applying negative feedback and identifying a main interference component); a decoupling parameter is converted into a power adjustment instruction through a multivariable control algorithm (superposition of basic compensation and decoupling compensation, amplitude limiting and phase compensation); and heating output is updated according to the power instruction, and iterative execution is performed based on the error index change trend until the temperatures of all sections reach steady-state balance. The method can effectively model and compensate thermal coupling interference between sections, improves the efficiency of temperature error compensation, and achieves the quick and stable cooperative temperature control of multiple sections.

The present application relates to the technical field of batteries, and discloses a thermal runaway risk prediction method and apparatus, a device, and a storage medium. The method comprises: processing, by at least two neural network layers in a target prediction model, thermal runaway risk parameters layer by layer, wherein the target prediction model is obtained by pre-training on the basis of state vectors of a plurality of time steps, so that the memory capability of the model for past state sequences can be enhanced, and thus the model can better learn the dynamic characteristics of an energy storage battery system, and captures a complex temporal association relationship among multiple variables, thereby improving the accuracy of thermal runaway risk prediction and reducing the safety risk of the energy storage battery system.

The invention relates to the technical field of fluid pipeline topological optimization, in particular to a fluid pipeline topological optimization design method based on a parameter simulation model. The method comprises the following steps of performing parametric modeling on a fluid pipeline to obtain a pipeline topology geometric parameter set; according to topological feature identification of the pipeline topology geometric parameter set, obtaining pipeline topology description data; constructing a multi-physics field equation set according to the pipeline topology description data to obtain a pipeline coupling field basic equation set; carrying out characteristic decomposition on the pipeline coupling field basic equation set to obtain a pipeline decoupling equation set; performing iterative solution on the pipeline decoupling equation set to obtain a pipeline multi-physics field coupling solution; performing sensitivity coefficient evaluation according to the pipeline multi-physics field coupling solution to obtain pipeline physics field sensitivity; and performing time domain integral response analysis on the pipeline physical field sensitivity to obtain the contribution degree of the pipeline physical field. According to the method, the deviation between the topological design and the practical application of the fluid pipeline can be obviously reduced.

The invention discloses a power flow generating capacity prediction method based on STL decomposition and multi-model fusion, which adopts an STL decomposition method to perform trend term, season term and residual term decomposition on historical generating capacity data, optimizes the decomposition process through a Bisquare weighting function and an internal loop iteration mechanism, and enhances the processing capacity for abnormal values and high-frequency fluctuations. The method comprises the following steps: extracting multi-scale frequency domain features by using a TimeNet model in combination with fast Fourier transform (FFT), predicting a trend term and a seasonal term, and performing accurate modeling on a residual term by using an Itransform model in combination with a self-attention mechanism and gating residual connection. Meteorological factors related to the tidal current generating capacity are screened, prediction is carried out in combination with historical operation data, and high-precision prediction of the tidal current generating capacity is achieved. The method has high adaptability and robustness, can effectively deal with multi-source influence and high-frequency fluctuation in tidal current power generation data, and provides an accurate and stable prediction result.

The invention relates to the technical field of gas pipeline safety assessment, in particular to a gas pipeline safety assessment early warning system and method based on data analysis. The method comprises the following steps: collecting gas pressure data of a gas pipeline at multiple points at the same time, carrying out time-space synchronization processing to obtain aligned gas pressure data so as to construct a continuous gas pressure field of the pipeline, based on the gas pressure field, identifying the pressure distribution difference of the pipeline, estimating the transient flow velocity of the gas, continuously recording the transient flow velocity of the gas, and deducing the change of the flow velocity. Judging the deformation condition of the inner wall of the pipeline in combination with air pressure field data, positioning a deformation area, reconstructing a pipeline frame, analyzing deformation response, identifying a deformation type, identifying a corrosion evolution trend, performing safety evaluation, judging the gas circulation degree and performing physical safety evaluation. According to the invention, dynamic monitoring of the gas pipeline is realized, a data-driven safety management mode is promoted, the early warning capability of potential risks is improved, and a more intelligent safety assessment and early warning mechanism is formed.

The invention relates to the technical field of environment perception, and discloses an optimization method and device for a multi-climate self-adaptive environment perception cooling fan system, and the method comprises the steps: collecting multi-point temperature, humidity and air pressure data, and carrying out the filtering processing, and obtaining an environment state vector; executing mathematical modeling of the multi-degree-of-freedom cooling system according to the environment state vector to obtain a linearized state space model; performing temperature gradient estimation and humidity compensation based on the linearized state space model to obtain an adaptive control law; inputting the adaptive control law into a model-free adaptive prediction controller to obtain a rolling optimization control sequence; weight self-adaptive adjustment and heat dissipation efficiency hierarchical prediction control are carried out on the rolling optimization control sequence based on climate conditions, fan rotating speed control and wind direction adjustment execution signals are generated, the problem that a traditional heat dissipation system is not sensitive to space temperature distribution and humidity changes is solved, and the heat dissipation control precision under different humidity conditions is improved.

The invention relates to the technical field of rock mechanics, and discloses a rock three-dimensional reconstruction method and system based on multi-source information fusion, and the method comprises the steps: obtaining and preprocessing data, carrying out the spatial feature learning of a fusion feature vector through a 3D-CNN network, and constructing a three-dimensional voxel model of rock microscopic damage; converting the fused image data into a point cloud model of the underground cavern surrounding rock structure by adopting a three-dimensional reconstruction algorithm based on point cloud, and constructing a digital twin framework of the underground cavern surrounding rock structure based on an implicit surface reconstruction algorithm; feature parameters output by the three-dimensional voxel model and the digital twinning framework are used as input, and the optimal supporting opportunity and supporting parameters are output through an LSTM-CNN fusion model; in the underground engineering construction process, surrounding rock deformation data are collected in real time, and a supporting scheme is adjusted in real time through a depth deterministic strategy gradient algorithm; according to the method, the scientificity and timeliness of support design under complex geological conditions can be improved.

The invention is an advanced deep learning system that combines a latent transformer core with a latent dynamics analyzer. This system processes input data into latent space vectors, which are then analyzed in parallel for both prediction and dynamic modeling. The latent transformer generates short-term predictions, while the latent dynamics analyzer derives equations of motion describing the underlying system dynamics. By integrating spectral analysis and change detection, the system can identify significant shifts in behavior, particularly useful for complex systems like financial markets. The invention enables more accurate predictions, interpretable insights, and early detection of regime changes. Its end-to-end training approach ensures all components work harmoniously, balancing predictive accuracy with physical plausibility and interpretability.

The invention relates to a proton exchange membrane fuel cell (PEMFC) high current density performance prediction method, system, equipment and medium. The method comprises the following steps: establishing a multi-physical field coupling model which comprehensively considers complex processes such as electrochemical reaction, proton conduction, gas diffusion and heat transfer, and describing the change of each physical quantity by adopting a partial differential equation based on a basic physical law; performing grid division and numerical discretization on the proton exchange membrane fuel cell model; selecting model parameters, and verifying the model through experimental data of different working conditions; inputting actual working condition parameters into a model to predict performance, and analyzing a simulation result; using a convolutional neural network, a recurrent neural network and an auto-encoder to extract features from different types of data and fuse the features to form a comprehensive feature vector; a deep neural network prediction model is constructed, and a cross entropy loss function and an Adam optimizer are adopted for training; dropout, L1 and L2 regularization, k-fold cross validation and transfer learning are utilized to optimize the model, and the generalization ability is improved; the system, the equipment and the medium realize high current density performance prediction of the proton exchange membrane fuel cell (PEMFC) based on the method; the prediction precision is improved, the experiment cost is reduced, the internal mechanism can be deeply understood, and powerful support is provided for design optimization, operation management and fault diagnosis of the fuel cell.

The invention discloses an efficient cross-season energy storage energy pile, and relates to the technical field of new energy and energy conservation. The problems that in an existing energy storage system, the thermal load prediction error is large, underground thermal diffusion attenuation is caused, the heat exchange capacity is lowered, and the geological adaptability is insufficient are solved. According to the scheme, an LA mixed time sequence prediction model is adopted to optimize load prediction, a distributed optical fiber temperature measurement array and a finite element inversion algorithm are combined to accurately reconstruct a stratum temperature field, and the geological type is identified based on a support vector machine classifier to realize self-adaptive regulation and control of heat exchange parameters; meanwhile, the heat pump power, the circulating pump frequency and the heat charging and discharging rate of the phase change material are optimized through a depth deterministic strategy gradient algorithm and a gradient heat release strategy; the heat exchange efficiency, the long-term stability and the complex environment adaptability of the cross-season energy storage system are remarkably improved, and the energy-saving effect of a building energy supply system is improved.

The invention discloses a sparse finite angle CBCT reconstruction method and system based on residual diffusion and a storage medium, and the method comprises the steps: carrying out the CBCT sparse finite angle scanning of a to-be-detected target, and obtaining sparse projection data; fDK reconstruction is carried out on the sparse projection data to obtain an initial CBCT image; generating a first optimized CBCT image from the initial CBCT image through an image pre-training network; through the first optimized CBCT image and the sparse projection data, using the trained residual diffusion model to determine a residual image of the to-be-detected target; summing the first optimized CBCT image of the to-be-detected target and the residual image of the to-be-detected target to obtain a second optimized CBCT image of the to-be-detected target, and the second optimized CBCT image is a final CBCT reconstruction image. According to the method, the problems of stripe artifacts and low-contrast tissue annihilation under limited angle scanning are solved, the large-view CBCT reconstruction resolution is improved, and the radiation dose is reduced.

The invention provides a multi-level geothermal well collaborative scheduling method and system based on multi-time scale prediction, and relates to the technical field of data processing. The method comprises the following steps: constructing a well group output model based on operation parameters of a shallow geothermal well group and a deep geothermal well group; constructing a multi-scale load prediction model based on the historical load data and the historical meteorological data; determining a load prediction result of the target time period by using the multi-scale load prediction model, wherein the load prediction result comprises a day-ahead load, a day-mid load and a real-time load; and performing joint calculation by using the well group output model, the load prediction result and the multi-objective optimization function to obtain optimal scheduling parameters of the shallow geothermal well group and the deep geothermal well group in the current scheduling period. According to the technical scheme, the output ratio of the shallow geothermal well and the deep geothermal well can be dynamically coordinated according to the predicted load requirements of different time scales, and efficient utilization of multi-level geothermal resources is achieved.

The present invention is a rainfall prediction method, system, device and medium based on machine learning, which relates to the field of meteorological prediction technology. It uses atmospheric precipitable water volume (PWV) data, rainfall data and related meteorological parameters to input into a trained rainfall prediction network, and realizes accurate prediction of rainfall through an improved Transformer model. The model includes an encoder, a decoder and a final output layer, wherein feature extraction is performed inside the encoder through a multi-head probabilistic sparse self-attention module and a distillation module, and the encoder output containing feature information is used as the input of the decoder. The decoder passes through the decoder mask multi-head probabilistic sparse self-attention layer, and performs a multi-head self-attention operation with the intermediate result output by the encoder, and finally adjusts the data output dimension through a fully connected layer to generate a prediction result.

The invention discloses a method and system for intelligently constructing a two-dimensional hydrodynamic model based on a large language model, and relates to the technical field of artificial intelligence and hydraulic numerical simulation, and the system comprises an intelligent region block division module which is used for analyzing geographic information data through the large language model LLM, recognizing topographic features and engineering facilities, and dividing region blocks; the self-adaptive grid generation module is used for setting different grid types and dynamically setting grid density according to different partitions; the terrain interpolation optimization module is used for selecting an interpolation algorithm to calculate a grid unit terrain and solve an optimal grid terrain based on a water level-reservoir capacity relationship verification result, and checking and marking an elevation abnormal mutation grid unit; and the two-dimensional hydrodynamic model construction module is used for outputting the grid and the time sequence data to a configuration file according to the format requirement of the target two-dimensional hydrodynamic model, and constructing the two-dimensional hydrodynamic model. According to the method, the problems of dependence on artificial experience, long time consumption of grid division and tedious adjustment are effectively solved, and integrated intelligent modeling is realized.

The invention discloses a point cloud registration method, system and device and a medium, and relates to the technical field of three-dimensional reconstruction of scenes, and the method comprises the steps: obtaining a source point cloud and a target point cloud; semantic segmentation is carried out according to spatial structure characteristics of the point clouds, and plane points and non-plane points of the source point clouds and the target point clouds are obtained respectively; two-way distance search constraints are applied to planar points and non-planar points in the source point cloud and the target point cloud respectively, and a corresponding relation of two-way matching constraints is established; point-to-surface registration and point-to-point registration based on the maximum correlation entropy criterion are carried out on the plane points and the non-plane points after bidirectional constraint, and rotation matrixes and translation vectors of the plane points and the non-plane points are respectively obtained through multiple iterations; weighting the rotation matrix and the translation vector according to an adaptive weight, and applying the weighted rotation matrix and translation vector to the source point cloud to obtain the source point cloud after pose transformation; according to the method, the nearest neighbor corresponding relation from the source point cloud to the target point cloud and from the target point cloud to the source point cloud is considered, and the matching accuracy of the corresponding points is improved.

The invention belongs to the technical field of automatic detection, and discloses an online laser detection and grading regulation and control system for particle size distribution of crushed raw ore. The invention aims to solve the problems of halo effect interference caused by adhesion of fine dust in a complex industrial environment and insufficient detection precision of a traditional method. The system obtains dynamic scattering light field data through the laser scanning module, identifies a halo effect region and generates a compensation coefficient by using the light field preprocessing module, and realizes accurate reconstruction of particle boundaries in combination with the edge reconstruction module. The particle size distribution analysis module extracts multi-dimensional geometric features based on the accurate boundary data, and generates a real-time particle size distribution curve. The grading strategy generation module formulates a regulation and control strategy according to deviation characteristics of the curve and a preset standard, and the dynamic regulation and control module adjusts parameters of crushing equipment in real time and optimizes particle size distribution. The method effectively overcomes the halo effect interference, improves the detection precision and the system stability, breaks through the single limitation of a traditional method, and provides comprehensive data support for a downstream process.

The invention discloses a macroscopic progressive damage intelligent evaluation method driven by multi-scale microscopic damage observation, and the method comprises the steps: selecting a plurality of representative materials to carry out a microscopic mechanical test, and observing the damage evolution process under different loading conditions through MicroCT to obtain a microscopic mechanical test result; simulating a crack state based on a micro-mechanical model to reproduce a micro-mechanical test result, and performing material parameter correction of simulation calculation by taking test data as a constraint to obtain a micro-numerical modeling calculation result; and determining a representative volume element (RVE) scale based on a microscopic numerical modeling calculation result, and describing a macroscopic damage behavior by utilizing a continuous damage mechanical model so as to obtain evolution relation data of a macroscopic damage variable, stress and strain. According to the method, the damage behaviors of metal and composite material structures under complex working conditions can be accurately predicted, and the safety and reliability of aircraft structures can be improved.

The invention discloses an airspace engine 3D printing deformation compensation method. The method comprises the following steps that S1, a three-dimensional CAD model is constructed, and a printing layer set is generated; s2, obtaining residual stress tensor fields of the current printing layer and the historical printing layer; s3, constructing a stress shadow mapping tensor; s4, inputting the stress shadow mapping tensor and the current printing layer parameter into the reverse stress propagation neural network model, and outputting a deformation prediction vector field; s5, performing geometric compensation processing on the geometric area of the printing layer according to the deformation prediction vector field; s6, generating a printing code according to the compensated geometric model; and S7, carrying out error comparison on the actual deformation vector field and the overall prediction deformation vector field, if the error is greater than a preset tolerance threshold value, feeding back error information to the step S5, and repeatedly executing the steps S5 to S7 until the error vector field does not exceed the tolerance threshold value. According to the method, residual stress modeling and the reverse stress propagation neural network are fused, and 3D printing deformation compensation of the airspace engine is achieved.

A real-time quantitative characterization method, equipment and a medium for rock mass evolution are disclosed. The method includes: the multiphase field detection and monitoring data is fused; a deep learning model driven by physical principles is established based on the physical principles of fluid density; the deep learning model is trained using real-time fused data as input and corresponding evolution distribution images as output; a trained deep learning model is used to obtain an evolution distribution image based on multi-phase field detection and monitoring data of different time periods and types; a mathematical model is used to quantitatively characterize of physical and mechanical parameters in the whole process of progressive failure of the dynamic evolution of the rock mass based on the macroscopic mechanical parameters and evolution distribution images synchronized with multiphase field detection and monitoring data.

The invention discloses a sliding bearing friction wear prediction method based on fluid mechanics, and relates to the technical field of mechanical state monitoring, and the method comprises the steps: collecting single-point temperature, local pressure, vibration time domain signals and a bearing pedestal inclination angle through a sensor, and generating sensor data; performing field reconstruction based on a fluid mechanics conservation equation on the sensor data to obtain multi-field data; performing spatial alignment on the multi-field data, inputting the multi-field data into a long short-term memory (LSTM) network, and generating wear state characteristics; training a sparse correlation vector machine regression model RVM by using the historical wear data, establishing a nonlinear mapping relationship between the wear state characteristics and the wear depth, taking the wear state characteristics as the input of the vector machine regression model RVM, and outputting the predicted wear depth; sensor data and the predicted wear depth are fused in real time through Kalman filtering, and when prediction deviation exceeds a covariance threshold value, vector machine regression model RVM parameters are updated.

The invention belongs to the technical field of turbulent flow field prediction and deep learning, and discloses an incompressible turbulent flow field prediction method based on a potential diffusion model. The method comprises the following steps: acquiring original turbulence data; processing the turbulence data; constructing a turbulence prediction model; model training; and evaluating the model and the like. The model of the technical scheme of the invention specifically comprises the following steps: designing a multi-scale Fourier auto-encoder for extracting multi-scale space and frequency domain features in a turbulence field and obtaining a global structure and a local scale structure of turbulence; a novel accelerated sampling method is proposed and introduced in the diffusion process, namely a diffusion probability model solver greatly shortens the reasoning time in a potential space and keeps high fidelity in long-time-sequence prediction; a physical constraint loss item based on a partial differential equation is introduced, and a Navier-Stokes equation (N-S) is explicitly introduced into a training process, so that the physical consistency of results is effectively improved, and errors are remarkably reduced.

The invention provides a thermal wave imaging detection method based on nonlinear frequency modulation microwave excitation induction, and the method comprises the steps: constructing a composite excitation module of Gaussian beam and dynamic phase compensation, decomposing high-frequency / low-frequency sub-pulses for alternate emission, synchronously collecting infrared non-uniform sampling and microwave polarization diversity data, and carrying out the detection of the thermal wave imaging. And through feature fusion of a time domain CNN and a frequency domain graph neural network, propagation parameters are iteratively corrected in combination with a thermal diffusion equation model, and defect and deep structure detection is realized. According to the method, the composite excitation structure is combined with high-frequency / low-frequency sub-pulse alternate emission, the micro-defect detection resolution and the deep structure penetrating capacity are remarkably improved, the feature robustness is enhanced through multi-modal data acquisition and cross-modal neural network fusion, detection depth self-adaptive optimization is achieved through a depth compensation model and Kalman filtering, and the detection precision is improved. The parameter precision is improved with the assistance of a terahertz spectrum coupling matrix and Landweber iterative inversion, and finally an advanced detection system integrating efficient excitation, multi-dimensional perception and intelligent analysis is formed.

The invention relates to the technical field of laser spectrum detection, in particular to an LIBS (Laser-induced Breakdown Spectroscopy) spectrum noise reduction method, system and equipment based on adaptive threshold wavelet transform and a storage medium. Acquiring an original spectral signal of the laser-induced breakdown spectroscopy; performing five-layer multi-layer wavelet decomposition on the original spectral signal by adopting a db4 wavelet basis function to obtain a high-frequency coefficient and a low-frequency coefficient of each layer; calculating a noise intensity standard deviation based on the detail coefficient of the highest decomposition layer; dynamically determining the optimal value of the regulation factor through a double-layer optimization strategy combining a grid search method and a golden section iterative optimization method; constructing an adaptive threshold value based on the noise intensity standard deviation and the adjustment factor; carrying out threshold value processing on the high-frequency coefficient by adopting a self-adaptive threshold value; and performing wavelet reconstruction on the processed high-frequency coefficient and low-frequency coefficient, and outputting a denoised spectral signal. While the LIBS spectral signal-to-noise ratio is remarkably improved, the spectral feature form is completely reserved, and reliable technical support is provided for laser-induced breakdown spectroscopy detection in a complex industrial environment.