266 results about "Surface wave" patented technology

The invention discloses a mountainous area wind field downscaling optimization method based on high-precision simulation, and relates to the technical field of meteorological numerical simulation, and the method comprises the steps: obtaining the terrain elevation data and meteorological monitoring data of a target mountainous area, recognizing slope abrupt change points, constructing a spiral sampling path, calculating a slope change value, determining the distance between sampling points, and generating target sampling data; performing orthogonal decomposition on the sampled data to obtain a frequency component, calculating a surface fluctuation coefficient, and constructing a boundary disturbance equation to obtain surface stress distribution; calculating an airflow motion state based on surface stress distribution, solving a vorticity equation to obtain vorticity characteristics of a leeward area, and calculating airflow motion correction parameters; and carrying out downscaling iterative operation on the corrected parameters and the meteorological monitoring data to generate target area wind field data with hectometer-magnitude spatial resolution. The simulation precision of the local wind field under the complex terrain condition is improved.

The invention provides a photovoltaic power generation optimization method for a fishing-light complementary site and a related device. The method comprises the following steps: acquiring a photovoltaic panel sunlight angle, a water surface wind speed, a water surface wave height, a water depth, a photovoltaic panel core parameter, a reflector parameter and double-measuring-point actually-measured light intensity data; determining the initial receiving radiation quantity of the photovoltaic panel according to the sunlight angle of the photovoltaic panel, the core parameters of the photovoltaic panel, the parameters of the reflector and the actually measured light intensity data of the double measuring points; according to the water surface wind speed, the water surface wave height, the water depth, the double-measuring-point actually-measured light intensity data and the reflector parameters, the water surface correction reflection coefficient is determined; correcting the initial received radiation quantity of the photovoltaic panel by adopting the water surface correction reflection coefficient to obtain the actual received radiation quantity of the photovoltaic panel; and according to the actually received radiation quantity of the photovoltaic panel, the inclination angle of the photovoltaic panel is adjusted, and then the photovoltaic power generation process of the fishing-light complementary site is optimized. Excessive concentration of local radiation quantity caused by secondary reflection of sunlight through a water surface-reflector can be avoided, and generation of hot spots on the photovoltaic panel is inhibited.

The invention relates to the technical field of pressure vessel health monitoring and nondestructive testing, in particular to an electromagnetic acoustic surface wave-based pressure vessel intergranular corrosion non-contact detection system, which comprises the following modules: a multi-field coupling electromagnetic acoustic surface wave detection module, which comprises a plurality of detection unit arrays, each detection unit comprises a magnetic biasing module and an impedance matching module and is used for generating a local magnetic field on the surface of the pressure vessel and optimizing signal excitation and receiving; and the signal acquisition and preprocessing module is used for acquiring the surface wave signal of the detection module and carrying out denoising, filtering, curved surface coupling difference correction and lift-off correction on the signal to obtain high-quality signal data. According to the method, non-contact quantitative detection of the intergranular corrosion of the pressure vessel is realized through multi-field coupling electromagnetic acoustic surface wave detection and microscopic and macroscopic mapping and inversion, so that the problem that early corrosion is difficult to quantify due to the fact that contact ultrasound is mostly adopted in traditional pressure vessel detection and grain boundary micro-damage cannot be effectively identified is solved.

The invention discloses a circumferential liquid film surface wave observation device and method based on a miniature high-speed camera. The circumferential liquid film surface wave observation device comprises a centrifugal nozzle, a laser, the high-speed miniature camera and a synchronizer, the centrifugal nozzle can spray a conical liquid film; the high-speed miniature camera is located at the central gas nucleus of the conical liquid film, and the optical axis coincides with the axis of the centrifugal nozzle; a narrow-band optical filter is arranged on the surface of an optical lens of the high-speed miniature camera; the laser can emit plane laser perpendicular to the axis of the centrifugal nozzle to the conical liquid film; wherein the wavelength of the planar laser is equal to the central wavelength of the narrow-band optical filter; and the synchronizer is respectively connected with the laser and the high-speed miniature camera. According to the method, a frozen instantaneous circumferential liquid film form without background interference can be obtained, a surface wave growth factor and a breaking critical criterion can be accurately quantified, and the development and evolution process of the circumferential surface wave of the liquid film is further obtained through high-speed shooting.

The invention relates to a method for calibrating an ultrasonic flowmeter, which is coupled to a pipe (1), for measuring a flow velocity or a volumetric flow rate of a fluid by means of two ultrasonic transducers (2, 3) spaced apart from one another, wherein the main directions of the ultrasonic transducers (2, 3) are oriented at an angle to one another in a symmetrical V shape. The aim of the invention is to provide an improved method which allows the ultrasonic flowmeter to be installed on a pipe with minimal effort, even by untrained personnel, without the accuracy of the measurement being impaired. For this purpose, the invention proposes the following steps: - ascertaining the propagation speed of an ultrasonic signal propagating through the pipe wall as a surface wave; - ascertaining the wall thickness of the pipe by determining the propagation time of an ultrasonic signal through the pipe wall; - ascertaining the inner diameter of the pipe by deriving it from the value of the adjusted angle and the distance of the ultrasonic transducers, - adjusting the angle to the ascertained pipe geometry by means of at least one motorized actuating drive (5) which sets the angle and an electronic calibration device (6) which interacts with the actuating drive (5).

The present invention is directed to an analytical method, using surface waves excited in a liquid system forming part of a sensor, to determine a property of a test substance. An aspect of the disclosure provides a method for controlling a sensor for determining a property of a test substance, the sensor having a sensitivity and dynamic range, the sensor comprising: a liquid system comprising: a bulk liquid phase carrying a thin film on the surface of the bulk liquid phase: wherein the thin film comprises a film material and wherein the thin film exhibits an electrical response to mechanical stress and vice versa wherein said response depends on the thermodynamic state of the liquid system, the sensor configured to: contact the surface of the liquid system with the test substance thereby to generate a surface wave on the liquid system: and, determine the property of the test substance based on parameters of the surface wave: wherein the method for controlling the sensor comprises: controlling the sensitivity by changing a thermodynamic parameter of the liquid system.

The utility model provides a waveguide antenna structure with a frequency selective surface structure and a waveguide radar, and the structure comprises a waveguide antenna which is provided with a waveguide slot array and a frequency selective surface structure; the waveguide slot array is arranged on the waveguide antenna in a penetrating manner, and the frequency selective surface structures are distributed on the peripheral side of the waveguide antenna; the frequency selective surface structure comprises surface structure units, and the frequency selective surface structure is formed by arranging a plurality of surface structure units. According to the utility model, the frequency selective surface structure absorbs reflection between the top surface of the antenna and the antenna housing and reduces distortion of a directional diagram; surface waves can be reduced, space coupling between the antennas is reduced, and the isolation between the antennas is improved; the beam directivity can be adjusted, and beam performance specific directivity can be shaped.

The invention relates to an environment-friendly switch vacuum arc-extinguishing chamber contact temperature monitoring method and system based on surface acoustic wave array sensing and inversion, and belongs to the field of electrical monitoring. In order to solve the problem that in the prior art, non-intrusive and high-reliability monitoring of the contact temperature of the vacuum arc-extinguishing chamber is difficult to realize due to vacuum sealing and metal shielding, the technical scheme of the invention is as follows: an acoustic surface wave sensor array comprising three or more sensing nodes is constructed on the outer wall of the vacuum arc-extinguishing chamber, and the longitudinal temperature gradient distribution of the outer wall is captured in a lossless manner. A narrow-band flat-plate reader antenna is adopted to realize array signal parallel transmission with a high signal-to-noise ratio, and the steady-state temperature of an internal contact is accurately inverted through a pre-trained physical information neural network (PINN) model by utilizing multi-source data fusion and array characteristics. According to the method, a non-intrusive monitoring function from external sensing to internal deduction is realized, the problem that the temperature of the contact cannot be measured in a high-voltage closed environment is solved, and a key technical support is provided for safe operation of environment-friendly switch equipment.

The invention belongs to the field of earth exploration, and provides an urban underground collapse hidden danger area rapid detection system and method.The urban underground collapse hidden danger area rapid detection system comprises a miniature intelligent sensor array and a central processing unit, the miniature intelligent sensor array comprises a plurality of detection lines arranged side by side, and each detection line comprises a plurality of miniature intelligent sensors arranged at intervals; the adjacent micro intelligent sensors on the same detection line are connected through a towing cable; the distance between the adjacent micro intelligent sensors is adjustable; and the central processing unit is used for receiving the vibration data acquired by each miniature intelligent sensor, performing inversion on the vibration data by using a background noise surface wave imaging algorithm to obtain an underground transverse wave velocity structure model, and identifying a low-speed abnormal region as a collapse hidden danger region. According to the invention, efficient, accurate, wide-coverage and non-sensitive detection of urban underground collapse hidden dangers can be realized.

The invention discloses a surface acoustic wave device and a radio frequency front end module, the surface acoustic wave device comprises a piezoelectric layer, a sound velocity layer and an interdigital electrode, and the interdigital electrode comprises a plurality of electrode fingers. The piezoelectric layer is provided with a first surface and a second surface which are oppositely arranged, the interdigital electrode is arranged on the first surface of the piezoelectric layer, and the sound velocity layer is arranged on the second surface of the piezoelectric layer; sound waves generated when the surface acoustic wave device works comprise surface acoustic waves and body waves; the surface acoustic wave device has a first characteristic depth, and the thickness of the piezoelectric layer is smaller than the first characteristic depth; wherein the first characteristic depth is related to the midline distance between two adjacent electrode fingers of the interdigital electrode, the bulk wave sound velocity of the piezoelectric crystal in the x direction and the working frequency. The sound velocity layer is directly arranged below the piezoelectric layer, the thickness of the piezoelectric layer is limited to be smaller than the first characteristic depth, and the thickness of the piezoelectric layer is reasonably reduced, so that the sound velocity of the surface wave is obviously improved or reduced, and meanwhile, the influence on the effects of other functional layers is avoided.

The present application belongs to the technical field of stealth design of aircraft shape and structure, and discloses a surface wave electromagnetic scattering characteristic quantitative analysis method based on a two-port transmission model. The surface wave electromagnetic scattering characteristic quantitative analysis method based on the two-port surface wave transmission model has an electromagnetic discontinuous structure. By loading the electromagnetic discontinuous structure, the scattering parameters of the port network are monitored, and by changing the structural parameters of the electromagnetic discontinuous structure, the influence of the structural parameters of the electromagnetic discontinuous structure on the surface wave scattering characteristic is quantitatively studied. The surface wave electromagnetic scattering characteristic quantitative analysis method can separate the spatial electromagnetic scattering component when the spatial electromagnetic wave is directly irradiated, and can analyze the electromagnetic scattering characteristic of the surface wave in the discontinuous electromagnetic structure alone, thereby laying a foundation for studying the surface wave electromagnetic scattering characteristic of the electromagnetic discontinuous structure such as a curved surface, a gap and a step, and providing guidance for the stealth design of the aircraft shape and structure.

The invention provides an elastic wave CT (Computed Tomography) signal denoising method for improving the inversion precision of karst cave exploration, which belongs to the technical field of engineering exploration and comprises the following steps of: performing normalization preprocessing on a received signal, suppressing random noise by adaptive filtering, converting a time domain signal into an F-K domain and identifying a surface wave, filtering a surface wave signal by a Gaussian band elimination filter, and converting the F-K domain signal back to the time domain. The method comprises the following steps of: highlighting a take-off characteristic of a weak P wave covered by a strong surface wave through normalization; using a minimum mean square error adaptive filter to accurately filter random noise; subsequently converting to an F-K domain, and smoothly attenuating the surface wave through a Gaussian band elimination filter by utilizing the frequency wave number distribution difference of the surface wave and the P wave; the method realizes layered removal of random noise and surface waves, finally outputs high-purity direct P-wave signals, greatly improves P-wave travel time pickup and wave velocity calculation precision, and remarkably improves inversion precision of an elastic wave CT exploration method in detection of geologic bodies such as karst caves and fracture zones.

The application provides a high-efficiency damping device and method based on a surface wave damping mechanism phononic crystal sandwich structure, and belongs to the field of ship damping and noise reduction. The device solves the problems of poor low-frequency damping effect, narrow damping frequency band and high cost-effectiveness ratio of existing damping devices. The device comprises a high-damping bearing panel, a damping liquid capsule, a phononic crystal sandwich panel and a bottom plate structure. The bottom plate structure is connected with a ship plate, the phononic crystal sandwich panel is fixed on the bottom plate structure, the damping liquid capsule is arranged on the phononic crystal sandwich panel, and the high-damping bearing panel is arranged on the damping liquid capsule. The damping liquid capsule comprises a liquid capsule body and a liquid capsule limiting mechanism. The liquid capsule limiting mechanism is fixed on the phononic crystal sandwich panel, the liquid capsule body is arranged in a space surrounded by the liquid capsule limiting mechanism, and the liquid capsule body is filled with fluid medium. The phononic crystal sandwich panel comprises an upper panel, a lower panel and a phononic crystal array. The phononic crystal array comprises a plurality of local resonance phononic crystals. The application is suitable for effective damping of ship mechanical equipment during operation.

The application discloses a method for controlling surface wave of a stamping cover outer plate reverse-drawing forming area, which comprises position control of effective line round of the reverse-drawing forming area of a process piece; after the first surface of the process piece is centered in a forming die, the first surface of the reverse-drawing forming area of the process piece is forcibly corrected in a bulging state, the forming die convex model surface is first reduced, then the forming die pressure material surface is correspondingly compensated; when the first surface of the reverse-drawing forming area of the process piece is in the bulging state, the forming die pressure material surface corresponding to the reverse-drawing forming area of the process piece is finally matched and researched at high speed for production verification. The application takes the accurate process piece position as a prerequisite, and correspondingly reduces the forming die convex model surface and correspondingly compensates the forming die pressure material surface, so that the forming die pressure material matching state can be controlled and high-speed production verification can be realized, thereby effectively and stably solving the surface wave problem of the stamping cover outer plate reverse-drawing forming area.

This application discloses an electromagnetic absorber and an electromagnetic wave absorption method. The electromagnetic absorber includes: a reflective phase gradient metasurface array, comprising a first dielectric layer, a first metal backplate layer, and multiple metal resonant units. The first dielectric layer is disposed on the upper surface of the first metal backplate layer, and the multiple metal resonant units are arrayed on the first dielectric layer. Each metal resonant unit includes n metal H-shaped structures of different sizes. The reflective phase gradient metasurface array is used to convert plane waves into surface waves. A surface plasmon polariton coupler is used to converge and absorb the energy of the converted surface waves. This application can achieve effective convergence and absorption of surface wave energy.

The invention provides a Sigmoid modulation phase correlation surface wave full waveform inversion method and system. The method comprises the following steps: acquiring a surface wave seismic record and constructing an initial S wave velocity model; performing forward modeling to generate a synthetic record; calculating instantaneous phase correlation of observation and synthetic records to construct an amplitude-independent target function; modulating the target function by using a Sigmoid function, and mapping the value of the target function to a predetermined interval; and calculating a gradient based on the modulated target function and iteratively updating the speed model until a termination condition is met, and outputting a final model. According to the method, the smooth saturation and bounded output characteristics of the Sigmoid function are utilized, the target function response is converted into a self-adaptive gradient scaling mechanism, a self-stabilization optimizer is introduced for the inversion process, and the convergence domain is widened by applying smooth constraint, so that the dependence on the initial model precision is reduced, and the first success rate and the result reliability of inversion under complex conditions are improved.

The invention discloses a surface acoustic wave filter multi-dimensional defect identification system and method based on machine learning, and relates to the field of multi-dimensional defect identification, and the system comprises a data acquisition and processing module, a feature extraction module, a defect analysis module, a defect verification module and a defect evaluation module. The method comprises the following steps: acquiring multi-dimensional data of a surface wave filter, and performing time synchronization and processing analysis to obtain a processed device surface microscopic image, enhanced device three-dimensional morphology data and an enhanced device S parameter frequency spectrum; performing electrode geometric feature extraction and spectrum anomaly detection to obtain a first geometric feature vector and a second spectrum feature vector; performing defect candidate analysis to obtain a defect candidate region set; and feature relation graph construction and physical verification analysis are carried out on each defect candidate region to obtain defect parameters after physical verification, defect classification, positioning and severity evaluation are carried out to obtain a filter defect multi-dimensional evaluation result, and the physical position and geometric morphology of the defect can be accurately positioned.

The application provides a background noise high-order surface wave dispersion extraction method, and belongs to the technical field of seismology. The method first calculates the cross-correlation function of continuous noise data and performs preprocessing to obtain an original dispersion energy spectrum; then a reference phase shift curve between the energy of the base order and the first high-order mode is extracted; the cross-correlation function is phase-shifted based on the curve, so that the base order and the high-order surface wave are separated in time, the high-order part at the negative time is retained and inverse phase shift is performed, and a cross-correlation function containing only the high-order surface wave is obtained; then the high-order surface wave dispersion energy spectrum is obtained through frequency-Bessel transformation, and is spliced with the base order part in the original spectrum to form an enhanced dispersion energy spectrum; finally, the base order and the high-order dispersion curves are extracted after quality control. The application can effectively suppress the interference of the base order sidelobe on the high-order mode, and significantly improve the continuity and signal-to-noise ratio of the high-order surface wave dispersion energy.

The invention discloses a high-performance broadband band-stop filter, and relates to the technical field of filters, and the filter comprises a microstrip circuit and a shielding cavity. The microstrip band-stop filter is composed of a novel spiral stepped impedance resonance unit and cascade transmission lines with different impedances, and in order to reduce the area of the filter, a spiral low-impedance structure of the resonance unit and a main transmission path are bent. The filter has the advantages that in order to suppress spurious coupling and surface waves introduced by the spiral structure and expand the upper passband, the parasitic conductor sheets are introduced between the resonance units, miniaturization of the filter is achieved, and the comprehensive high performance of the wide upper passband, high suppression depth and low insertion loss is obtained.

This invention provides a method and system for suppressing surface waves in converted waves. The method includes acquiring a longitudinal wave and its converted form; acquiring the surface wave within the longitudinal wave; adjusting the phase of the surface wave based on the phase difference between the longitudinal and converted waves; and subtracting the adjusted surface wave from the converted wave to suppress the surface wave within the converted wave, where the surface wave is the subtrahend. By acquiring and correcting the surface wave within the longitudinal wave to suppress the surface wave in the converted wave, the method effectively suppresses the surface wave in the converted wave, and the suppressed converted wave retains more effective reflection information.

The application discloses a seawall protection structure design method and system based on a winding space metasurface technology, relates to the technical field of seawall protection engineering, and comprises the following steps: selecting a suitable winding space metasurface unit model according to frequency parameters and wave height parameters of sea waves; designing and optimizing the winding space metasurface unit model based on a preset refractive index distribution; arranging and installing the designed winding space metasurface unit model array outside a seawall and debugging; and adjusting the arrangement and refractive index of the winding space metasurface unit model to cope with different sea wave conditions by monitoring sea conditions in real time. The application modulates the energy distribution of water surface waves, realizes focusing, scattering or absorption of the waves, effectively reduces the direct impact of the sea waves on the seawall, enhances the protection effect, and reduces the long-term maintenance cost.

The present application provides a kind of complex stratum structure and topographic effect considering slope microseismic event 3D positioning method, the technical scheme includes S1: the theoretical travel time model suitable for complex slope environment is built;S2: the actual travel time difference is extracted from slope monitoring data;S3: based on the 3D positioning of theoretical and observed travel time difference matching, the ambient noise surface wave tomography technology is applied to slope velocity modeling, without artificial seismic source, high resolution velocity structure can be obtained;Realize 3D ray tracing under the constraint of digital elevation model, ensure that wave propagation path meets physical law, positioning accuracy reaches 3 m, can reach 1.5 m in dense array coverage area, compared with traditional method, it is improved by one order of magnitude;Successfully applied to complex environment with more than 700m topographic relief and extreme velocity variation, can be applied to microseismic monitoring in various complex geological environments.

This invention relates to the field of numerical simulation and computational technology for seismic wave propagation, and discloses a method and apparatus for generating seismic ground motions based on target spectra and Green's functions. It aims to address the difficulty in achieving a balance between physical consistency, computational efficiency, and spectral compatibility in existing methods. The scheme mainly includes: preprocessing environmental noise records and extracting empirical Green's functions through unsupervised clustering; constructing a spatially continuous propagation tensor by performing depth correction and gradient interpolation based on surface wave eigenfunctions; discretizing the kinematically finite fault model into sub-source units and generating long-period seismic ground motions including path effects using propagation tensor convolution; optimizing source parameters through Bayesian inversion using the GMPE target spectrum as a constraint; and finally generating high-frequency components and fusing them with the long-period waveform to obtain a broadband seismic ground motion time history. This invention achieves a unification of physical propagation mechanisms and statistical spectral constraints, significantly improving computational efficiency while ensuring spectral compatibility, and is particularly suitable for basin areas.

The present application belongs to the technical field of geophysical exploration data processing, and relates to a surface wave dispersion curve inversion method based on sensitivity information constraint deep learning, a medium and equipment, the method comprising constructing a Senformer network model, making a data set, optimizing a training process and inversion testing; the method is based on the Senformer network model introducing sensitivity information, by inputting the dispersion curve and its corresponding sensitivity features into the network model, using convolution layers and multi-layer Transformer encoders to extract local and global features, and combining cross attention mechanisms to realize effective constraint of sensitivity information on the inversion process. The present application proposes a SmoothL1 loss function based on sensitivity information weighting, which improves the stability and accuracy of the key horizon shear wave velocity inversion. Through large-scale forward data set training and optimization, the present application can efficiently and stably realize modeling of complex velocity structures, and has significant advantages in noise resistance, stability and inversion accuracy.

The application belongs to the field of oil and gas geophysical exploration, and discloses a kind of geophone combination to improve the calculation method of signal-to-noise ratio degree of single shot data, and the signal-to-noise ratio of geophone combination is improved multiple times compared with geophone single point G , the surface wave suppression amplitude value of geophone combination b 1, the refraction wave suppression amplitude value b 2, the reciprocal of the signal-to-noise ratio of geophone combination suppression random interference wave b 3, the amplitude ratio of surface wave and refraction wave k , the surface wave suppression coefficient, refraction wave suppression coefficient and random interference wave suppression coefficient of geophone combination are obtained, and finally the formula of the signal-to-noise ratio improvement multiple of geophone combination compared with geophone single point is obtained.The application is suitable for calculating the degree of signal-to-noise ratio of single shot data improved by geophone combination, the calculation result is clear, the reliability is strong, the calculation method is fast, and the quantitative basis can be provided for the selection of geophone combination number and group distance in seismic acquisition engineering technical design.

A method of convolutional neural network (CNN) based inversion of wave radar images and use thereof pertain to the field of sea-state monitoring, in which a CNN autoencoder is employed. A training dataset produced by a simulation tool is input to the CNN autoencoder for supervised training, with X-band radar images of an inversion region being taken as input to the training dataset and with corresponding ocean surface wave height maps being taken as output from the training dataset, thereby deriving a model defining a mapping of them. The CNN autoencoder includes an encoder, fully connected layers and a decoder. The encoder includes five convolutional layers and five max-pooling layers, which are connected alternately. There are two symmetric fully connected layers, and the decoder includes five deconvolutional layers. A CNN-based deep learning algorithm is used to provide good reconstruction of the nonlinear components. The autoencoder technology is employed, which can directly reconstruct real-time ocean surface wave height maps from X-band radar wave images with minor errors, which provide more comprehensive sea-state information.

The invention discloses a steel plate contour detection method and system, electronic equipment and a storage medium. The method comprises the following steps: respectively acquiring edge image information and full-section height contour information when a steel plate passes through a first detection position and a second detection position with a preset distance; performing scale correction on the edge image information according to the full-section height contour information so as to eliminate imaging distortion caused by surface wave fluctuation of the steel plate, and generating first physical contour data and second physical contour data; time sequence matching is conducted on the two physical contour data based on the steel plate conveying speed; according to the transverse position difference between the matched physical contour data, the transverse migration amount of the steel plate is determined; and compensating the first physical contour data based on the transverse migration amount to obtain a corrected geometric contour of the steel plate. According to the method, the interference of plate surface waves and transverse snakelike deviation is effectively decoupled by fusing height field correction and a double-position difference technology, and high-precision reduction of the real geometric contour of the steel plate is realized.

The application is suitable for the technical field of batteries, and provides a battery internal temperature monitoring method and system based on multi-feature decoupling and deep learning. The method comprises the following steps: obtaining a multi-dimensional acoustic feature set of an ultrasonic detection battery, wherein the multi-dimensional acoustic feature set comprises a time of flight, a surface wave amplitude and a bottom wave phase shift; performing decoupling processing on the multi-dimensional acoustic feature set to eliminate the coupling interference of SOC on the acoustic feature, to obtain a decoupled acoustic feature; and inputting the decoupled acoustic feature into a pre-trained deep learning model to output the internal temperature of the battery. The application eliminates the coupling interference of non-temperature factors such as SOC on the original ultrasonic feature, and realizes high-precision estimation of the internal temperature.