92 results about "Energy diagram" patented technology

The invention relates to the field of road compactness monitoring, in particular to a road compactness real-time regulation and control method and system based on digital twinning, and the method comprises the steps: collecting vibration acceleration, temperature and position data, and generating a time-space aligned multi-source fusion feature data set after processing; inputting a pre-trained LSTM model to construct a dynamically updated digital twinborn body, and outputting a three-dimensional compaction energy spectrum; dispersing the atlas and calculating parameters, and generating a compaction degree deviation matrix; a regulation and control instruction is generated and issued based on matrix optimization; and according to the measured data and the predicted value residual error, triggering re-optimization and calibrating the sensor. According to the method, the problems of non-uniform compaction quality and over-high energy consumption caused by poor adaptability, decision lag and error coupling of a traditional static model are solved.

The invention relates to an anisotropic elastic medium Rayleigh surface wave frequency dispersion curve inversion method, which comprises the steps of collecting near-earth surface wave exploration seismic data, obtaining a Rayleigh surface wave frequency dispersion energy diagram based on a phase shift method, and extracting a frequency dispersion curve from the frequency dispersion energy diagram based on a convolutional neural network artificial intelligence method; constructing a near-surface anisotropic elastic parameter initial model; calculating to obtain a theoretical Rayleigh surface wave dispersion curve by using a Rayleigh surface wave dispersion curve forward modeling method according to the current elastic parameter model; designing a loss function according to the observed Rayleigh surface wave dispersion curve and the theoretically calculated Rayleigh surface wave dispersion curve, and calculating and judging whether the loss function reaches a set threshold value or converges to a minimum value; if yes, outputting a current near-surface shear wave velocity model; if the conditions are not met, updating the shear wave velocity model by adopting a quasi-Newton method; and outputting the near-surface shear wave velocity model and the sensitive function of the Rayleigh surface wave frequency dispersion curve to the anisotropic elastic parameter after the loss function meets the condition.

The invention relates to the technical field of image enhancement, in particular to a medical image focus recognition method and system based on a neural network, and the method comprises the following steps: setting neighborhood windows of different sizes based on input medical image data, calculating the Shannon entropy value of each neighborhood window, calculating the local energy value, and forming a local energy diagram; and fusing the Shannon entropy value and the local energy map to obtain a fused information entropy energy map. According to the method, neighborhood windows of different sizes are set for medical image data, and the Shannon entropy value and the local energy value are calculated for each window, so that the information complexity and the local pixel active degree of the image in spatial distribution can be fully extracted, and the information entropy energy spectrum formed by fusing the information complexity and the local pixel active degree has higher region sensitivity; high-response areas are screened through the atlas, boundary coordinates of the high-response areas are recorded, and the positioning precision can be improved in high-intensity change areas.

The invention relates to the technical field of equipment health management and fault diagnosis, and particularly discloses a time-frequency enhanced current diagnosis method. According to the method, multi-phase current, temperature and rotating speed data are synchronously obtained, and a standardized sequence is generated through time alignment and noise suppression; self-adaptive spectrum analysis is carried out based on the working condition robust index, and a multi-scale energy diagram and frequency domain features are generated; fusion embedding is constructed through time domain feature extraction and time-frequency alignment mapping; and carrying out dynamic weight fusion and quality judgment in combination with the cross-modal consistency score, and finally generating a lightweight deployment model. According to the method, the anti-interference performance and interpretability of current diagnosis characteristics under multiple working conditions are effectively improved, accurate extraction and lightweight deployment of fault characteristics are realized, and the adaptability and reliability of a diagnosis system in a complex industrial environment are remarkably enhanced.

The invention relates to the technical field of seismic detection, in particular to a surface wave frequency dispersion curve automatic extraction method and system and a storage medium. According to the surface wave frequency dispersion curve automatic extraction method provided by the invention, data point partitioning is performed on a surface wave frequency dispersion energy diagram based on data point extraction and clustering, then a central point in each region is extracted as a pick-up point through a mean value taking mode, and a frequency dispersion curve is constructed based on the pick-up point. The method breaks the current cognition of screening the frequency scatter points based on the principle of maximum energy, comprehensively considers the speed, energy and frequency to cluster the frequency scatter points, achieves the recognition of an energy concentration region mode, then extracts the frequency scatter points based on the clustering result, can accurately capture local features, avoids manual operation errors, and greatly improves the extraction precision of the frequency scatter points. The consistency and stability of extraction rules of frequency dispersion points in different areas are guaranteed, the height generality of a frequency dispersion curve to a surface wave frequency dispersion energy diagram is guaranteed, and high-precision and high-efficiency extraction of the frequency dispersion curve is guaranteed.

The invention discloses a method and a device for positioning a steel rail telescopic regulator based on dynamic and static data fusion. The method comprises the following steps of: acquiring track geometric data, a railway track curve and machine account information of which the distance from the steel rail telescopic regulator is within a preset distance range; according to a railway track curve and ledger information, carrying out initial correction on the track geometric data; performing modal decomposition on the track geometric data after the initial correction by using an adaptive chirp signal modal decomposition algorithm; performing Wigner time-frequency analysis on the track geometric data after modal decomposition to generate a mileage frequency diagram; converting the mileage frequency diagram into a mileage energy diagram by utilizing a preset moving window edge spectrum analysis algorithm; according to the mileage energy diagram and the ledger information, the position of the steel rail telescopic adjuster is determined, the efficiency and accuracy of positioning the steel rail telescopic adjuster can be improved, the positioning time and labor cost are reduced, and then the stability and safety of high-speed railway driving performance are improved.

The invention discloses a wind turbine generator impeller anomaly detection method and system based on sound vibration signal identification. According to the method, firstly, impeller response is collected through a microphone / vibration sensor, and a Mel spectrogram is generated; then, a Teager-Kaiser energy operator and self-correlation analysis are utilized, and under the condition of not depending on a rotating speed signal, the rotating period of the impeller is recognized, and frequency spectrum segmentation is carried out; calculating a cross-period Mel frequency spectrum dynamic deviation, and normalizing the cross-period Mel frequency spectrum dynamic deviation through an amplitude correction coefficient related to the rotating speed; generating a periodic coherent energy diagram by adopting an improved structural similarity algorithm; performing filtering enhancement by using a harmonic resonance template, performing morphological deconstruction and parameterization on an abnormal region in the graph, and extracting geometric features; and finally, calculating a comprehensive abnormal score based on the multi-dimensional features and realizing automatic early warning. According to the method, the problems of variable working condition interference and rotating speed dependence are effectively solved, and accurate and stable detection of early abnormality of the impeller can be realized.

The invention relates to a multi-modal gait recognition method based on space-time semantic modeling and cross-modal cooperation, and the method comprises the steps: inputting a skeleton energy diagram, a contour energy diagram, a contour diagram and a skeleton diagram into four feature extraction branches with the same structure, and obtaining four modal features and two stage features of each modal; inputting the two stage features of each group of cross-modal combination into a double-stage feature interaction enhancement module to obtain a cross-modal fusion feature; all the modal features and the cross-modal fusion features are mapped and pooled and then input into a classification head, and a multi-modal gait recognition result is obtained. According to the method, key features under different view angles and walking conditions are effectively focused, the integrity of local channel information is reserved, modeling is performed on spatio-temporal information through multiple branches, high-level semantic features are extracted, spatio-temporal changes of gaits under different view angles and walking conditions are accurately captured, features of different modal data are fused, and the gait time-space information is obtained. And the gait recognition performance under multi-view and different walking conditions is improved.

The invention relates to an underground distributed optical fiber (DAS) anisotropic shale reservoir guided wave frequency dispersion curve inversion method and a medium, and the method comprises the steps: obtaining guided wave seismic data of a shale reservoir, calculating a guided wave frequency dispersion energy diagram according to the obtained guided wave seismic data, and extracting an observation guided wave frequency dispersion curve from the guided wave frequency dispersion energy diagram; establishing an initial anisotropic elastic parameter model of the shale reservoir; according to the initial or updated anisotropic elastic parameter model of the shale reservoir, performing forward modeling to obtain a theoretical guided wave frequency dispersion curve; constructing an objective function, and calculating and judging whether the objective function is converged or not according to a residual error between the theoretical guided wave frequency dispersion curve and the observation guided wave frequency dispersion curve; if the target function converges, outputting an anisotropic elastic parameter model of the current shale reservoir; if the target function is not converged, updating the anisotropic elastic parameter model by adopting a gradient algorithm until the target function is converged; and outputting the optimized anisotropic elastic parameter model of the shale reservoir.

The invention discloses an adaptive copper foil defect rapid detection method based on wavelet transformation. The method comprises the following steps: shooting a copper foil to obtain a copper foil grayscale image; constructing a three-layer pyramid by adopting wavelet transform, and extracting features to obtain respective normalized energy diagrams; difference operation is carried out on the normalized energy diagrams of the adjacent layers of pyramids to obtain difference diagrams, and then weight calculation is carried out to obtain respective weight diagrams; performing common processing on the normalized energy diagrams and the weight diagrams of all the layer pyramids to obtain a to-be-segmented image, and performing binarization processing on the to-be-segmented image to obtain a binarized image; and extracting a connected domain in the binarized image, and filtering the connected domain to obtain a copper foil defect area. According to the method, the problem that picture defect detection is affected by lighting during shooting is relieved, the method is simple, can be suitable for images of different specifications, facilitates engineering implementation, is high in processing speed and has high application value, and the accuracy rate in the aspect of copper foil defect detection reaches 89.6%.

The invention discloses a frequency dispersion curve automatic extraction method based on deep learning and a related device, and relates to the technical field of geophysics and underground structure exploration, and the method comprises the steps: obtaining station pair data; performing cross-correlation processing on the station pair data to obtain a plurality of pieces of cross-correlation data; performing data processing on each piece of cross-correlation data to obtain processed cross-correlation data; according to the processed cross-correlation data, a tau-p conversion technology is adopted to obtain a frequency dispersion energy diagram; performing image recognition on the frequency dispersion energy diagram based on a deep learning model to obtain a frequency dispersion curve; the frequency dispersion curve is used for displaying the change rule of the frequency dispersion characteristic along with the periodic change speed; the deep learning model adopts an encoder-decoder framework, and the depth learning model adopts an encoder-decoder framework; in the deep learning model, a pooling layer is replaced by convolution with the step length being two, and up-sampling is carried out by adopting transposed convolution. Based on the method provided by the invention, the frequency dispersion curve can be efficiently and accurately extracted.

The invention discloses a tooth profile grinding three-dimensional heat distribution reconstruction and structure evaluation method and system, and the method comprises the steps: building a three-dimensional tooth surface discrete grid through combining a grinding wheel motion track, a tooth surface geometric morphology and a grinding wheel macrostructure, and generating a contact unit set with a time label through track mapping and path continuity; grinding energy input and grinding wheel abrasive particle distribution difference are combined, a weighted energy diagram is constructed, a directed energy transfer path is formed under a grid adjacency relation, an energy flow mode is obtained through iterative diffusion, a time sequence convolution and offset extraction mechanism is introduced, a thermal migration disturbance condition reflecting local thermal diffusion abnormity is generated, the thermal migration disturbance condition is coupled with a three-dimensional grid, and a three-dimensional model is obtained. And driving an unsteady state heat conduction solver to obtain a tooth surface heat distribution field, extracting a tooth surface potential sensitive area set by using a structure evaluation operator, and realizing comprehensive evaluation of heat-force response and structure risks.

The invention relates to the technical field of biological radar signal processing, in particular to an FMCW radar-based heart beat interval estimation method, which comprises the following steps of: S1, converting a chest vibration echo phase time sequence obtained by irradiating a chest area of a monitored object by an FMCW radar into an acceleration time sequence by using a second-order time derivative; s2, dynamically mapping the center frequency and the wavelet order in a preset frequency analysis interval, constructing a self-adaptive wavelet dictionary, then executing multi-order wavelet time domain convolution operation on the acceleration time sequence by using the dictionary, and aggregating time-frequency energy distribution to generate a time-frequency energy diagram; and S3, performing a deconvolution operation reconstruction strategy based on an energy-guided multi-stage time-frequency feature screening technology and wavelet function conjugation, generating an approximate time domain signal of heart beat vibration, and completing heart beat information inversion. According to the method, the accuracy and robustness of IBI extraction can be effectively improved under the condition of low signal-to-noise ratio, so that stable monitoring of light and moderate HRV (heart rate variability) is supported.

The invention discloses a new energy and load prediction error cause mining method based on a knowledge graph, and relates to the related technical field of new energy management, and the method comprises the steps: building an energy-load prediction knowledge graph based on new energy and load data; new energy power generation data, load data and environment data are collected and updated to the energy-load prediction knowledge graph; executing mode recognition on the data nodes, and determining prediction error data nodes; identifying, analyzing and predicting error data nodes, and determining relevance; quantitatively evaluating a plurality of prediction error influence factors; carrying out weight distribution to obtain an error source distribution result; and adjusting and optimizing the new energy load prediction model. The technical problems of load prediction errors and inaccurate error cause determination caused by complex influence factors and imperfect prediction models in existing new energy load prediction are solved, and the technical effects of improving the accuracy of load prediction and enabling power grid energy distribution to be balanced are achieved.

The invention relates to the technical field of vehicle-mounted equipment, and discloses a high-vibration environment-oriented vehicle-mounted graphic server active anti-seismic system, which comprises the following steps of: firstly, acquiring a real-time vibration data flow of a vehicle-mounted graphic server, constructing an energy spectrum, and analyzing a resonance modal cluster to generate a damping regulation and control path; analyzing a dominant resonance mode, and identifying a critical oscillation node to calculate an inertia compensation coefficient; nonlinear filtering is carried out on the vibration spectrum based on the coefficient to obtain an anti-interference frequency band set, a servo driving instruction set is generated through topological mapping, a dynamic stiffness parameter is inquired, and a parameter distribution vector is marked; then, the vector is loaded to an active memory controller, an energy dissipation state is monitored, a gain threshold value combination is adaptively adjusted, and an anti-seismic robustness index is calculated; and finally, generating vibration characteristic lines, extracting steady-state, transient and chaotic components, and constructing a multi-cascade active anti-seismic mechanism. According to the method, the anti-seismic stability of vehicle-mounted graphic calculation can be guaranteed.

The invention discloses an amniotic epithelial stem cell screening method and device based on microscopic image feature extraction, relates to the technical field of microscopic image analysis and cell screening, and is used for solving the problem that group topology and internal activity in amniotic epithelial stem cell lossless screening are difficult to collaboratively quantify. The method comprises the following steps: firstly, performing enhancement processing on a phase difference microscopic image, and extracting a kernel centroid and a global gradient energy diagram; then, constructing a Voronoi jurisdiction, and coupling a cytoplasm texture entropy and a gray scale attenuation gradient to generate a cytoplasm compactness factor; meanwhile, calculating a cell gap topology consistency index based on mapping of the Voronoi boundary and the gradient map; and finally, weighting and correcting the compactness factor by using a topological index to obtain a dryness maintenance confidence coefficient, and outputting a target coordinate. Through dual verification of geometric topology and physical gradient, combined constraint screening of internal and external characteristics of cells is realized.

The invention discloses a clothes changing pedestrian re-identification method, device and equipment, a medium and a product, and relates to the technical field of target detection, and the method comprises the steps: decomposing the appearance characteristics of each pedestrian in target video data into body structure characteristics and clothes variable characteristics; on the basis of target video data, generating space-time dynamic characteristics of joint movement in a gait cycle by adopting a trained space-time diagram convolutional network, and generating multi-modal gait representation of each pedestrian in combination with a gait energy diagram; the gait energy diagram is generated according to target video data; inputting the body structure features, the clothes variable features and the multi-modal gait representation of each pedestrian into a trained scene perception gating network to obtain fusion features of each pedestrian; according to the fusion features of the pedestrians, whether the pedestrians are the same person or not is judged, cross-modal feature complementation can be achieved, and the accuracy of re-recognition of the clothes changing pedestrians is improved.

Embodiments of the present application provide a palmprint image generation method and apparatus, a device, a storage medium, and a program product. The method comprises: determining a plurality of control points on the basis of a predetermined palmprint curve template, and generating a Bézier curve on the basis of the plurality of control points; on the basis of the Bézier curve, generating a palm crease energy map having crease information, the palm crease energy map comprising a palm crease having a crease distribution same as that of the Bézier curve and a crease type different from that of the Bézier curve, wherein the crease type is used for describing the crease information and corresponds to crease direction energy of each pixel on the palm crease; and on the basis of the palm crease energy map, generating a photorealistic palmprint image having detailed texture information.

The invention discloses a liquid identification method and device, a storage medium and electronic equipment. The method comprises the steps that a high-energy diagram, a low-energy diagram, an atomic number diagram and an RGB diagram generated after a detected object is irradiated by X rays are acquired; cutting based on the high-energy diagram, the low-energy diagram, the atomic number diagram and / or the RGB diagram to obtain a background region diagram and at least one aliasing foreground region diagram of the to-be-detected liquid; extracting background feature information by using a background analysis network, and extracting aliasing foreground feature information by using an aliasing foreground analysis network; based on the background feature information and the aliasing foreground feature information, using a first subtraction network to analyze interference of the background to the foreground, and based on an analysis result and the atomic number diagram, using a first de-aliasing network to perform background interference stripping to obtain foreground feature information; and based on the foreground feature information, utilizing a first component analysis network to determine liquid components. By applying the method and the device, liquid identification in non-shielding and various shielding scenes can be supported, and the performance of liquid identification and detection is improved.

The invention relates to the technical field of geophysical exploration, and discloses a common station pair coherent superposition enhancement method for active source seismic surface waves with a low signal-to-noise ratio. Comprising the following steps: generating a Green function according to a relative relationship between a seismic source position and a station pair: when the station pair is located at the same side of a seismic source, calculating the cross-correlation of seismic records of two stations in the station pair, and generating a cross-correlation Green function; when the station pair is located on the different side of the seismic source, the cross correlation between the seismic records of the two stations in the station pair and the seismic record of the reference station at the seismic source is calculated, then convolution calculation is carried out, and a convolution Green function is generated; frequency dispersion energy diagrams are respectively calculated based on the superposed cross-correlation Green function and convolution Green function; and superposing the two types of frequency dispersion energy diagrams to generate a final frequency dispersion diagram for extracting a frequency dispersion curve. According to the active source seismic surface wave signal co-station pair coherent superposition enhancement method provided by the invention, the surface wave signal-to-noise ratio and the frequency dispersion diagram quality are effectively improved on the premise that the data acquisition cost is not increased.

The present invention discloses a flat plate damage detection method and system based on the analysis of the singular components of the out-of-plane velocity field. The steps include: measuring the out-of-plane velocity field of the flat plate structure; selecting the time window to be analyzed according to the out-of-plane velocity field energy function; performing attenuation compensation on the out-of-plane velocity field within the selected time window; performing a TKEO (Teager-Kaiser energy operator) transform on the attenuated and compensated out-of-plane velocity field; calculating the energy map after the TKEO transform of the out-of-plane velocity field; and determining the damage location and size according to the singular peak positions in the energy map after the TKEO transform of the out-of-plane velocity field. The present invention can be used to analyze the out-of-plane velocity field of the flat plate structure, and then perform structural damage imaging. The present invention can be used in combination with advanced instruments such as a laser scanning vibrometer and is widely applied to the damage detection of flat plate structures.

The invention discloses a plant growth state prediction method and device, equipment, a medium and a product, and relates to the field of plant growth state prediction.The method comprises the steps that a first electric signal of a plant is obtained, and frequency domain analysis processing is conducted on the first electric signal to obtain a first energy diagram; establishing a data set according to the first energy diagram and a corresponding preset label, and training a preset classification model according to the data set to obtain a growth state prediction model; obtaining a second electric signal of the plant to be detected, and performing frequency domain analysis processing on the second electric signal to obtain a second energy diagram; and inputting the second energy diagram into a growth state prediction model to obtain a prediction result. According to the invention, the plant growth state can be accurately predicted.

The invention provides a household power station energy diagram state control method, device and system and a program product. The method comprises the following steps: monitoring an operation behavior of opening a household power station energy diagram interface by a user; responding to an operation behavior of opening a household power station energy diagram interface by a user, and sending a checking instruction to a server; the viewing instruction is used for requesting to view analysis data of the household power station in a household power station energy diagram interface; receiving first data of the household power station sent by the server at a second reporting frequency; wherein the second reporting frequency is higher than the first reporting frequency; the first reporting frequency is an initial reporting frequency; the first data is operation data of the household power station or analysis data obtained based on the operation data; and displaying the analysis data in a household power station energy diagram interface. According to the invention, the user can obtain the operation data of the power station more timely, and the mastering degree of the state of the household power station is improved.

This invention discloses an inversion method for S-wave velocity structure based on dense micromotion observations, belonging to the field of geophysical exploration and engineering geological exploration technology. The method includes: acquiring micromotion data; performing segmented preprocessing and cross-correlation calculations; constructing a phase consistency metric function based on the instantaneous phase information of the cross-correlation function for each time period; generating adaptive weighting coefficients; and then constructing an empirical Green's function through weighted superposition. Subsequently, time-frequency analysis is performed to obtain a time-frequency energy map; preliminary extraction of candidate dispersion velocities for each frequency is performed, and their comprehensive confidence level is calculated; after verification, a reliable dispersion curve is obtained. Based on the dispersion curve, a model parameter vector is established, and a joint objective function is constructed. A differential evolution algorithm is used for parallel global optimization inversion to obtain a one-dimensional S-wave velocity structure model below each station pair. The one-dimensional models are interpolated and fused to generate a two-dimensional S-wave velocity structure profile. This invention has the advantages of high inversion stability, high computational efficiency, and a high degree of automation.

The invention discloses a ship identification method and system based on dual physical model fusion verification, and relates to the technical field of optical fiber sensing and ocean monitoring. The method aims at solving the problems that ship noise in submarine optical cable DAS signals is prone to interference of environment noise such as low-speed guided waves, the false alarm rate is high, and accurate positioning cannot be achieved. The method comprises the steps that DAS phase data is acquired and preprocessed to generate a channel-time energy diagram; suppressing low-speed guided wave noise through frequency-wavenumber domain slowness scanning, detecting an energy ridge line on the purified energy diagram, and calculating an observation apparent velocity; acquiring AIS data to calculate and predict the apparent velocity; the relative error of the observed apparent velocity and the predicted apparent velocity is firstly matched, and then linear regression is carried out on the arrival time of the candidate ridge line and the AIS distance to verify and fit the root mean square error; the validated ridge line is confirmed as an effective ship event and a directory is generated. According to the technical scheme, through physical mechanism denoising and dual model verification, the accuracy and reliability of ship identification are effectively improved.

The invention belongs to the technical field of electricity-to-water metering and intelligent analysis of a water pumping system. The invention provides a water taking metering power consumption correction method based on a multi-dimensional operation signal and deep learning, aiming at solving the problem of water volume false report caused by increase of actual water demand and increase of power consumption due to efficiency degradation / fault of a water pump, which cannot be distinguished by converting electricity into water in the prior art. The invention provides the water taking metering power consumption correction method based on the multi-dimensional operation signal and deep learning. According to the method, vibration, sound, voltage / current waveform and other signals are collected, an electrical-mechanical-hydraulic three-layer initial atlas is constructed, a cross-layer hypergraph is generated, hyperedge and pump curve prior constraints are indicated through load consistency and loss, a load or loss event is judged on the hypergraph, and an event gating signal is output; further aggregating energy semantics on the edge-level energy diagram along a physical consistent path of electricity, machine and water, decomposing the total power consumption into effective and invalid power consumption, marking the source of the invalid power consumption, and mapping the water quantity by the effective power consumption; according to the method, fault energy consumption can be avoided, water consumption is counted, and meanwhile, supervision and operation and maintenance bases are provided.

The invention discloses a power station operation site safety monitoring method and device and a storage medium. Comprising the following steps: in response to a safety monitoring signal of a target substation operation site, acquiring an operation video of the target substation operation site in real time at multiple angles; encoding the operation video to obtain a space-time energy diagram, and extracting gait features of the target power transformation personnel from the space-time energy diagram; on the basis of the position information of the skeleton key points in each video frame, determining limb action features of the target power transformation personnel; extracting a three-dimensional image pair in the same scene corresponding to the same moment from the operation video, respectively extracting a personnel feature point pair of the target power transformation personnel and an equipment feature point pair of the power equipment from the three-dimensional image pair, and determining the position information of the target power transformation personnel and the equipment feature point pair based on the position information of the personnel feature point pair and the equipment feature point pair; determining a near electric distance between the target power transformation personnel and the power equipment; and based on the gait feature, the limb action feature and the near electric distance, determining the safety of the target substation operation site.

The present invention discloses a method for efficiently and accurately predicting stall flutter based on an energy graph and a deep neural operator network, and belongs to the technical field of aeroelastic analysis. The present invention constructs and trains a data-driven model for rapid prediction of unsteady aerodynamic torque of a dynamic stall cycle taking into account changes in wind speed, amplitude, and frequency based on a deep neural operator network, and implements efficient and accurate prediction of stall flutter response by rapidly calculating an energy graph based on a data-driven model and iteratively correcting stall flutter response taking into account aerodynamic stiffness correction. The present invention can predict stall flutter response under different incoming flow velocities, different structural natural frequencies, and damping coefficients with high accuracy, while greatly reducing the calculation time required for response prediction.

The application discloses a tooth profile grinding three-dimensional heat distribution reconstruction and structure evaluation method and system, establishes a three-dimensional tooth surface discrete grid in combination with a grinding wheel motion track, tooth surface geometric appearance and grinding wheel macrostructure, generates a contact unit set with a time label through track mapping and path continuity, combines grinding energy input and grinding wheel abrasive particle distribution difference, constructs a weighted energy graph, forms a directed energy transmission path under a grid adjacency relation, and obtains an energy flow mode through iterative diffusion, introduces a time sequence convolution and offset extraction mechanism, generates a heat migration disturbance condition reflecting local heat diffusion abnormalities, is coupled with the three-dimensional grid, drives a non-steady-state heat conduction solver to obtain a tooth surface heat distribution field, extracts a tooth surface potential sensitive area set by using a structure evaluation operator, and realizes comprehensive evaluation of heat-force response and structure risk.

The present application relates to the field of power distribution cabinet monitoring, and more particularly to a power distribution cabinet intelligent monitoring method and system. The method comprises the following steps: first, acquiring an acoustic time sequence signal representing the operating state of the power distribution cabinet and generating a time-frequency energy graph; then, using a variational autoencoder model trained only with normal state data, performing anomaly detection on the time-frequency energy graph to identify an acoustic anomaly event to be verified; subsequently, synchronously acquiring electrical operating parameters near the time point of the event, and calculating an alarm confidence score based on the parameters; then, combining the severity of the acoustic anomaly event with the alarm confidence score to obtain a comprehensive risk score; finally, executing a graded warning or disposal based on the comprehensive risk score. This method can accurately identify power distribution cabinet anomalies and improve the reliability of early warnings, providing effective support for power distribution cabinet operation and maintenance.