162 results about "Wavelet thresholding" patented technology

A leakage sound signal denoising method based on a combination of optimized VMD and an improved wavelet threshold, for use in solving the problem in existing noise processing methods of low identification accuracy in processing leakage sound signals of water supply pipe networks. The present invention comprises: acquiring leakage sound signals of a real water supply pipe network, and analyzing noise components and ranges of the leakage sound signals; on the basis of a goshawk optimization algorithm, performing parameter optimization on the number K of decomposition modes and a penalty factor α of VMD to obtain optimal parameters, and using the optimal parameters to construct a variational model; using the variational model to decompose the leakage sound signals to obtain a plurality of intrinsic mode components; using a correlation coefficient method to screen the plurality of intrinsic mode components to obtain high-frequency components and low-frequency components; performing wavelet threshold denoising processing on the high-frequency components to obtain denoised high-frequency components; and reconstructing the low-frequency components and the denoised high-frequency components to obtain denoised leakage sound signals. The beneficial effects are that the signal-to-noise ratio of denoising processing is improved, and the identification accuracy is improved.

The invention relates to the technical field of high-voltage circuit breaker fault diagnosis, and discloses a multi-feature optimization fusion high-voltage circuit breaker fault diagnosis method. The method comprises the following steps: adaptively optimizing variational mode decomposition parameters by adopting a particle swarm optimization algorithm, and accurately decomposing an original vibration signal; performing noise dominant and fault feature dominant classification on the intrinsic mode function based on permutation entropy; aiming at the two types of modes, respectively taking signal-to-noise ratio maximization and kurtosis maximization as targets, and implementing differential wavelet threshold denoising; after reconstructing the signal, extracting an energy entropy, a singular value entropy and a power spectrum entropy to form a multi-dimensional feature vector; and inputting the data into a support vector machine classifier subjected to particle swarm optimization hyper-parameter for state diagnosis. According to the invention, through full-chain collaborative optimization, the accuracy and robustness of fault diagnosis in a strong noise environment are significantly improved.

The invention discloses a numerical control machine tool dynamic error cooperative compensation control method adaptive to high-speed machining, and relates to the technical field of numerical control machine tool error control. According to the method, a multi-source dynamic error sensing system comprising a grating displacement sensor, a six-dimensional force sensor and the like is constructed to acquire data; after wavelet threshold denoising and Kalman filtering preprocessing, inputting a three-layer LSTM error coupling prediction model combined with an attention mechanism, embedding a servo motor load characteristic curve in the model, and outputting three types of error compensation amounts; through servo-level compensation and machining-level compensation, the position of a feed shaft, the rotating speed of a main shaft, the cutting feed rate and the behavior of a micro-displacement actuator are corrected, and machining errors caused by deflection and vibration conduction of the main shaft are counteracted. And iteratively updating model parameters by using a gradient descent algorithm. According to the method, through multi-source error synchronous sensing, error coupling modeling and hierarchical cooperative compensation, dynamic error cooperative control more adaptive to a high-speed processing scene is realized, and the method has a wide application value.

The invention discloses a transformer abnormity identification method based on voiceprint feature analysis, and belongs to the field of power equipment state monitoring and intelligent diagnosis. The method comprises the following steps: firstly, analyzing an iron core acoustic mechanism based on a magnetostrictive effect, and establishing a three-dimensional model through finite element simulation to obtain vibration and sound field characteristics; in a complex substation environment, a hybrid noise reduction method combining density peak clustering and a CEEMDAN-wavelet threshold is provided, and the signal-to-noise ratio is effectively improved. Then extracting Mel-frequency cepstrum coefficients (MFCC) and spectrum features, and performing local linear embedding (LLE) dimension reduction to form a compact feature set; in the recognition stage, a convolutional neural network framework is designed, specifically, a spectrogram and an energy spectrum are modeled through a two-dimensional CNN, an MFCC tensor obtained after dimensionality reduction is modeled through a three-dimensional CNN, and accurate diagnosis of mechanical faults such as core looseness is achieved. The method has the advantages of being non-contact, anti-noise and high in recognition precision, and real-time diagnosis and early warning of mechanical abnormity of the transformer can be achieved under complex working conditions.

The invention discloses a remote monitoring method and system for an explosion-proof distribution box, and the method comprises the steps: synchronously collecting an electrical operation parameter, an explosion-proof structure state parameter and an environment related parameter, carrying out the wavelet threshold noise reduction processing and coupling correction, improving the data precision, encrypting, adding a check code, and transmitting to a remote monitoring center through dual-mode transmission. And the remote monitoring center verifies the data integrity and decrypts the data, carries out graded early warning based on a preset threshold system and a parameter change rate, and sends a corresponding intervention instruction for abnormity of an early warning grade and above. All-dimensional monitoring is achieved, safety and accuracy of data transmission are guaranteed, risks are pre-judged in advance, remote risk control is achieved, the operation safety and operation and maintenance efficiency of the anti-explosion distribution box are improved, and the system is suitable for flammable and explosive dangerous places.

The method comprises the following steps: obtaining a power quality signal containing noise; selecting permutation entropy as an adaptive function of genetic algorithm, calling variational mode decomposition through genetic algorithm, and iteratively optimizing a penalty factor α and a decomposition mode number k of the variational mode decomposition to determine optimal parameters; decomposing signal data into k mode components through the variational mode decomposition, and determining effective mode components and noise mode components through a correlation coefficient; for improved wavelet threshold, a parameter-adjustable threshold function is proposed, and the concept of wavelet energy entropy is introduced into the threshold function; the noise mode components are denoised through the improved wavelet threshold, and the effective mode components and the denoised noise mode components are reconstructed to obtain a denoised power quality disturbance signal. The method can effectively remove noise interference while retaining singular information of mutation points of the collected signal, and provides help for subsequent analysis and treatment of the power quality disturbance signal.

The invention discloses a geophysical prospecting signal denoising method based on VMD (variational mode decomposition) combined with an improved wavelet threshold function, and belongs to the technical field of mineral exploration geophysical prospecting signal process.The method includes the steps that firstly, a decomposition mode number K of a signal is determined through VMD in a self-adaptive mode, a plurality of IMFs (intrinsic mode components) are obtained, and then according to the frequency characteristic and noise distribution of each IMF component, a wavelet threshold function is obtained; and carrying out targeted noise suppression by adopting an improved wavelet threshold function containing an adjustment parameter alpha, and finally, carrying out linear superposition reconstruction on all the processed IMF components to obtain a de-noised geophysical prospecting signal. Experimental verification shows that compared with a traditional method, the method has the advantages that the signal-to-noise ratio and the correlation coefficient of the noisy geophysical prospecting signals can be effectively increased, the root-mean-square error can be effectively reduced, the inherent defects of the traditional method are overcome, the geologic features of the geophysical prospecting signals can be effectively reserved, the method is suitable for various mineral exploration scenes, and reliable data support is provided for anomaly recognition in mineral exploration.

The invention belongs to the technical field of power transmission line galloping monitoring, and particularly relates to a power transmission line icing galloping on-site monitoring and early warning method based on edge computing, and the method comprises the steps: employing an industrial eMMC storage and "ARM + FPGA" low-power-consumption heterogeneous architecture, filtering strong electromagnetic interference through wavelet threshold denoising, and improving the data quality so as to reduce the equipment misjudgment; an FPGA three-level assembly line framework is used for accelerating calculation-intensive tasks such as FFT spectrum analysis and image segmentation, an ARM is used for being responsible for scheduling and storage management, the computing power bottleneck of low-power-consumption hardware is broken through, a four-dimensional data structure form of multi-modal sensor data is used, a lightweight prediction model subjected to knowledge distillation optimization is adopted for data uploaded by multiple sensors, and a multi-modal multi-sensor multi-dimensional prediction model is used for prediction of the data uploaded by multiple sensors. And the calculation amount is reduced while the icing identification precision is maintained.

The invention discloses a new energy station cable terminal partial discharge signal identification method and system, and the method comprises the following steps: collecting an original signal, carrying out the preprocessing of the original signal, and carrying out the wavelet threshold noise reduction processing, and obtaining a noise reduction signal; performing sliding slicing processing on the denoised one-dimensional long time sequence signal, and inputting the processed signal into the constructed partial discharge identification model to train the model; and inputting the target signal into the trained partial discharge identification model to obtain a time position and a continuous range of a real partial discharge event in the long time sequence signal, thereby realizing effective identification and separation of the partial discharge signal and corona interference of the cable terminal of the new energy field station. Wavelet noise reduction, a time window and one-dimensional convolutional network depth feature recognition are integrally designed, partial discharge signals can be stably recognized in the strong noise and mixed pulse scene of the new energy station cable terminal, and a reliable data basis is provided for insulation state evaluation and operation and maintenance early warning of the new energy station cable terminal.

The invention discloses a gas pipe network leakage point accurate positioning method based on a multi-source signal attenuation model, and belongs to the technical field of gas pipe network safety monitoring. The method comprises the following steps: arranging monitoring nodes integrating pressure waves, sound waves and an optical fiber vibration module according to a triangular coverage principle, and synchronously acquiring signals through a GPS (Global Positioning System) or the Ethernet; performing targeted denoising on the three types of signals by adopting a wavelet threshold method, a self-adaptive noise cancellation method and an empirical mode decomposition method; constructing a single signal attenuation sub-model associated with the fuel gas viscosity, the density, the pipe diameter and the sound wave dominant frequency, and fusing the single signal attenuation sub-model into a unified attenuation model through information entropy dynamic weight; solving a leakage point coordinate enabling the error between the theoretical value and the measured value to be minimum by utilizing a gradient descent method; through actual coordinate verification, if an error is greater than 5 meters, attenuation coefficient iterative optimization is adjusted. The system adapts to different pressure grades, gas types and complex working conditions, has the advantages of being high in anti-interference capacity and low in operation and maintenance cost, and is suitable for daily operation and maintenance and emergency disposal of the pipe network.

The invention discloses a damage identification method and device for an in-service steel wire rope type horizontal lifeline, and belongs to the technical field of high-altitude operation safety facilities. The method comprises the following steps: synchronously acquiring a magnetic flux leakage signal and a surface image of an in-service steel wire rope through magnetic flux leakage detection equipment and a high-definition camera which are carried on a steel wire rope inspection robot; preprocessing the acquired magnetic flux leakage signal, wherein the preprocessing comprises singular value elimination and trend term removal processing; carrying out de-noising processing on the pre-processed signal by adopting an improved wavelet threshold de-noising algorithm fused with a Sigmoid function; extracting a characteristic value for representing the damage of the steel wire rope, and performing normalization processing to form a characteristic vector; and inputting into a BP neural network identification model optimized by a genetic algorithm for identification, and outputting an assessment result of the damage type and positioning of the steel wire rope. The method can realize automatic and quantitative detection and accurate identification of internal and external damages of the steel wire rope.

This invention belongs to the field of ship shafting condition monitoring and fault diagnosis technology, specifically relating to a bearing load measurement device and its data acquisition and transmission method. This invention effectively suppresses temperature drift, mechanical vibration, and electromagnetic interference by rationally arranging strain gauges, employing high-precision synchronous sampling, and combined denoising processing, thereby improving the accuracy of signal acquisition. Embedding moment balance and beam strain consistency equations into the machine learning model significantly improves the accuracy of load prediction. High-speed multi-channel synchronous sampling technology ensures data time alignment, and a multi-algorithm denoising scheme combining wavelet thresholding and bandpass filtering effectively filters out mechanical vibration and electromagnetic interference. A multi-mode communication module enables separate channel transmission of real-time load data and raw strain data, balancing the low-latency requirements of online monitoring with the large-scale data archiving requirements of offline analysis. The introduction of edge computing significantly reduces cloud transmission pressure and improves the real-time performance of load measurement.

The application discloses a signal processing method and device, and relates to the field of electric data processing; wherein, the method comprises: collecting acceleration data of a first device by using an acceleration sensor to obtain first output data; the first device is a device where the acceleration sensor is located; performing wavelet threshold denoising processing on the first output data to obtain denoising data; and performing synchronous adaptive filtering on the denoising data based on the rotation speed of the first device to obtain second output data. The signal processing method and device provided in the application embodiment can improve the electromagnetic interference suppression effect of a sensor, thereby improving the measurement accuracy and reliability of the sensor.

The application discloses a motion electrocardio processing method and system, and relates to the technical field of electrocardio signal processing. The motion electrocardio processing method provided by the application comprises the following steps: acquiring electrocardio signals under different motion states; performing empirical mode decomposition on the motion electrocardio to decompose the electrocardio signals into a plurality of intrinsic mode functions, and performing high-pass filtering operation on the low-frequency intrinsic mode functions to suppress low-frequency noise in the motion electrocardio; then, performing variational mode decomposition on the remaining components to more accurately extract variational mode functions of different frequencies, and performing center frequency judgment on each variational mode function; for the mode functions smaller than the center frequency, non-local mean noise reduction is adopted; for the mode functions greater than or equal to the center frequency, singular value decomposition is adopted to reduce noise and realize baseline interference suppression; finally, the mode functions after noise reduction are reconstructed, the wavelet threshold method is adopted to reduce noise for the electromyographic interference noise in the motion electrocardio, so that a clean motion electrocardio signal waveform after noise interference suppression is obtained, and subsequent further analysis is facilitated.

The application provides a signal denoising method based on a dung beetle optimizer (DBO) optimized wavelet threshold, and belongs to the technical field of signal processing. The method comprises the following steps: firstly, performing CEEMDAN decomposition on a signal to obtain a plurality of IMF components; adopting a dung beetle optimizer (DBO) to select an optimal threshold for a wavelet threshold denoising method; for an IMF component with a relatively small correlation coefficient in CEEMDAN decomposition, adopting the threshold selected by the dung beetle optimizer to perform wavelet threshold denoising; and reconstructing signals of the denoised IMF component and other IMF components to obtain a denoised signal. The application has applicability, can effectively solve the problems of threshold selection difficulty and signal noise removal, retains useful information in the signal, and improves the effectiveness of the signal.

The invention relates to the field of electric reactor fault diagnosis, in particular to an electric reactor mechanical fault diagnosis method based on parameter adaptive optimization, which comprises the following steps: preprocessing vibration signals generated when an electric reactor has a mechanical fault through a wavelet threshold denoising method, extracting vibration signal characteristics through Fourier transform and wavelet packet transform, and calculating the mechanical fault of the electric reactor according to the vibration signal characteristics; according to the method, the high-voltage electric reactor is subjected to fault diagnosis, screening is carried out through a random forest method, fault diagnosis is mainly carried out through a convolutional neural network-Transform hybrid model (CNN-Transform), and accurate diagnosis of the fault of the high-voltage electric reactor is realized by utilizing the local and structured feature extraction capability of the CNN model and the global context and long-distance dependency relationship establishment capability of the Transform model. And an improved dung beetle optimization algorithm (MDBO) is introduced, internal parameters of the hybrid model are dynamically adjusted, parameter adaptive optimization is realized, and the diagnosis accuracy is improved.

The application discloses a landslide early warning method based on data mining, comprising the following steps: obtaining historical monitoring data of a target position, and storing the obtained data in a database; performing variational mode decomposition on obtained ground surface absolute displacement data to obtain a limited number of intrinsic mode components; performing wavelet threshold denoising on each intrinsic mode component obtained through decomposition, and finally reconstructing the denoised components to obtain denoised and reconstructed displacement data; predicting the displacement of the denoised displacement data by using a long short-term memory neural network method; constructing a deep belief neural network model, and using landslide displacement prediction data to perform early warning on whether a landslide occurs. The method solves the problem of poor prediction accuracy in landslide displacement early warning in the prior art, thereby realizing a more comprehensive and scientific early warning method.

This invention discloses a predictive maintenance system for medical X-ray equipment, belonging to the field of medical equipment maintenance technology. It includes a multi-source data acquisition module, a feature construction module, a coupled degradation modeling module, a risk assessment module, and a maintenance strategy generation module. Based on voltage distortion rate, current harmonic components, and temperature field gradient, this invention extracts the standard deviation of voltage distortion rate, the total distortion coefficient of current harmonics, and the rate of change of temperature gradient after denoising using wavelet thresholding, and fuses them into a feature vector. Combining a long short-term memory network and a Bayesian network, it calculates a comprehensive degradation index of multi-parameter coupling; subsequently, it constructs a multi-parameter feature space and outputs a comprehensive risk level through unsupervised learning methods; finally, it generates targeted maintenance strategies based on the risk level and optimization algorithms. This invention achieves accurate prediction and intelligent maintenance of medical X-ray equipment faults, reduces sudden failures, lowers maintenance costs, and improves equipment operational reliability and diagnostic and treatment safety.

The invention provides a self-adaptive wavelet noise reduction method and system based on mass spectrum signal processing, and the method comprises the following steps: S1, collecting a data set outputted by a mass spectrometer, and inputting the data set into a noise reduction process in the form of a text document; s2, reading related data in the text document, analyzing spectral peak characteristic parameters, and initializing related parameters; s3, performing multilayer wavelet decomposition on the document data, and outputting an approximate component and a detail component of each layer; s4, calculating the noise intensity of different layers according to the output approximate component and the detail component, and adaptively calculating a wavelet threshold value based on the signal length and the noise intensity; s5, threshold processing is applied to the detail components, and wavelet signals are reconstructed; and S6, calculating signal-to-noise ratios under different decomposition layer numbers, and selecting the optimal decomposition layer number to output the mass spectrum data after noise reduction. According to the method, the related spectrogram information output by the mass spectrometer is denoised, and the signal-to-noise ratio of the mass spectrum data is improved while the spectrum peak information is reserved to a great extent.

The invention discloses a soot blowing pipeline wall thickness online monitoring method based on temperature self-adaption, and relates to the technical field of industrial pipeline nondestructive testing. The problems that in the prior art, a detection signal is unstable in a high-temperature environment, and the micro corrosion thinning recognition precision is insufficient can be at least partially solved. The method comprises the steps that the surface temperature of a pipeline is collected, and the force contribution ratio of Lorentz force to magnetostriction force is calculated; dynamically optimizing electromagnetic ultrasonic body wave excitation parameters according to the force contribution ratio; body waves are excited point by point in the axial direction of the pipeline, and echo signals are collected; extracting bottom wave features by using empirical mode decomposition and wavelet threshold combined noise reduction; calculating the wall thickness of each measuring point based on the temperature correction sound velocity; and generating a B-scan image and carrying out grading evaluation according to the percentage of the thinning amount. According to the method, the wall thickness is accurately measured under the high-temperature working condition, signal stability is ensured through temperature self-adaptive parameter optimization, the signal-to-noise ratio is remarkably improved through combined noise reduction, wall thickness distribution is visually presented through B scanning imaging, and reliable data support is provided for safe operation and maintenance of a pipeline.

The application belongs to the technical field of sensors and particularly relates to a water jet impact sensor and a use method thereof. An LED lamp indication area is arranged on a target plate surface, a pressure sensing unit with a fence type grid node is adopted, cylindrical weights with different masses and different round bottom areas are used to drop and impact the target plate from different heights, the water jet impact target plate is simulated under different pressures, the node pressure information, the node response coordinates and the drop height data of the drop from different heights are used as training data input values, the impact pressure is theoretically calculated, the theoretical calculation impact area is used as an output value, a multi-objective fast non-dominant sorting genetic algorithm model is trained, a database is established for predicting the jet area and the effective jet pressure mean value generated by the impact, prediction values are provided for water jet impact tests at different distances, wavelet threshold processing data in a real test process is checked, and the impact area and the impact pressure mean value in different areas are given.

The invention provides a vibration signal denoising method, electronic equipment and a storage medium, and relates to the technical field of signal denoising. The method comprises the following steps: determining a target parameter of variational mode decomposition by adopting an improved traveler optimization algorithm; wherein the target parameters comprise a penalty factor and the number of components; performing variational mode decomposition on the original vibration signal based on the target parameter to obtain a plurality of intrinsic mode components; screening the plurality of intrinsic mode components based on a correlation coefficient method to obtain a plurality of effective components; de-noising each effective component by adopting an improved wavelet threshold de-noising method to obtain a plurality of pure components; and reconstructing the plurality of pure components to obtain a target vibration signal. According to the method, parameters of variational mode decomposition are adaptively determined, and decomposition is more reasonable; and meanwhile, denoising is performed in combination with a wavelet threshold value, and the denoised signal has the highest signal-to-noise ratio and the minimum root-mean-square value, so that the method has better denoising superiority and is suitable for non-stationary vibration signal denoising.

The invention discloses an aluminum plate ultrasonic Lamb wave denoising method based on ICPO-VMD combined improvement of a wavelet threshold, and the method comprises the steps: collecting an ultrasonic echo signal of an aluminum plate, carrying out the adaptive optimization through an improved crown porcupine optimization algorithm, and obtaining an optimal parameter combination; performing variational mode decomposition on the ultrasonic echo signal by using the optimal parameter combination to obtain a plurality of intrinsic mode function components; calculating a correlation coefficient of each intrinsic mode function component and the original ultrasonic echo signal, and dividing all the components into a signal dominant component, a mixed component and a noise dominant component according to a preset correlation coefficient threshold; de-noising processing is carried out on the mixed component by adopting an improved wavelet threshold function; and reconstructing the signal dominant component and the denoised mixed component to obtain a denoised Lamb wave signal. According to the invention, high-fidelity and high-reliability de-noising processing of the ultrasonic Lamb wave signal of the aluminum plate is realized, and the accuracy and robustness of subsequent defect detection are improved.

The invention provides an oil and gas pipeline leakage detection method and system fusing multi-modal characteristics, and belongs to the field of pipeline leakage detection. The invention aims to solve the problems that in a signal conversion link during pipeline leakage detection, a traditional Grubrum angle field does not consider local time sequence correlation sufficiently to restrict feature representation, single-mode processing has information one-sided, multi-mode fusion lacks deep interaction, and information redundancy is difficult to effectively reduce. The method comprises the following steps of: performing conversion from a one-dimensional time sequence signal to a two-dimensional image on a pipeline signal by adopting a wavelet threshold filtering and angle calculation weighting improvement-based Gramb angle difference field method; extracting the spatial characteristics of the two-dimensional GADF image through a Swin Transform, and obtaining the time sequence characteristics of the one-dimensional time sequence signal through a gating circulation unit; and finally, carrying out weighted fusion on the spatial features and the time sequence features by utilizing a weighted cross attention mechanism module, capturing cross-modal relevance, carrying out classification by utilizing fused features, and identifying different working conditions of the pipeline.

This invention discloses a partial discharge (PD) signal denoising method based on image information entropy and multivariate variational mode decomposition (MMD). The method involves converting the noisy signal into a grayscale image, calculating the image information entropy, and optimizing the number of modes K in the MMD by combining Pearson correlation coefficient and execution efficiency to determine the optimal value. The noisy PD signal is then decomposed. The kurtosis value of each intrinsic mode component is calculated, and the nature of the mode component is determined based on a threshold, classifying it as either a dominant PD component or a noise component. A mathematical statistical method using the 3σ criterion is employed to filter out normally distributed white noise. The reconstructed signal is then denoised using an improved wavelet thresholding method to obtain the denoised PD signal. This denoising method accurately reduces noise in noisy PD signals, achieving good noise suppression and restoring the waveform characteristics of the PD signal while maintaining high execution efficiency.

This invention relates to a wavelet threshold-based method and system for denoising cold test vibrations, comprising the following steps: constructing a vibration parameter database based on the acquired diesel engine cold test vibration signal; performing wavelet decomposition on the vibration parameters in the database according to the selected wavelet basis function and decomposition level to obtain wavelet coefficients; performing wavelet reconstruction on the vibration parameters based on a threshold function to obtain denoised cold test vibration parameters, specifically: shrinking the wavelet coefficients within the threshold range to zero, while keeping the wavelet coefficients outside the threshold unchanged; and processing the acquired diesel engine cold test vibration signal using the denoised cold test vibration parameters to obtain a denoised cold test vibration signal. The threshold function is used to solve the oscillation and distortion problems existing in the denoising process, thereby improving the denoising effect of the cold test vibration signal.

The application discloses a kind of millimeter wave sign detection methods based on swarm intelligence and improved wavelet threshold value, wherein the method includes: obtaining the original vital sign signal collected by millimeter wave radar;Construct the multi-objective fitness function of fusion sample entropy, pearson correlation coefficient and kurtosis;The multi-objective fitness function is optimized using the improved Harris eagle optimization algorithm, and the optimal parameter combination of CEEMDAN decomposition algorithm is adaptively solved;Based on the optimal parameter combination, the original vital sign signal is decomposed by CEEMDAN, and a plurality of intrinsic mode function components are obtained.The application constructs the cascade processing framework of "parameter optimization-signal separation-noise suppression", solves the problem that CEEMDAN parameter depends on artificial experience, respiratory and heartbeat signal band aliasing and the problem of insufficient performance of traditional wavelet threshold denoising.

The invention relates to the technical field of agricultural / forestry pest monitoring, in particular to a trunk borer early warning detection method based on audio signal time-frequency feature fusion, which comprises the following steps: acquiring an audio signal generated by boring vibration of trunk borers on the surface of a trunk, sequentially carrying out noise reduction, pre-emphasis, framing and windowing treatment on the audio signal, and sending the audio signal to the trunk borer. Generating a bidirectional logarithmic Mel spectrogram through a bidirectional Mel filter; wherein the noise reduction adopts a wavelet threshold noise reduction algorithm. According to the method, audio frequency domain and time domain features are respectively extracted through the double-branch network, time frequency information complementation is realized after fusion, the complex features of the trunk borer audio can be better captured compared with a single model, the early weak signal recognition rate is improved, the model parameter quantity is reduced to 0.3 M or below through convolutional layer pruning, lightweight convolution (DWConv + GConv) and parameter-free fusion, the calculation amount is greatly reduced, and the method is suitable for large-scale popularization and application. The method can be deployed in an embedded edge device, and the problems of'recalculation power and difficulty in landing 'of a traditional model are solved.

A transformer internal partial discharge positioning method based on an optical fiber sensing array, comprising: processing a triangular ultrasonic sensing array, wherein the triangular ultrasonic sensing array comprises: at least 3 optical fiber Fabry-Perot sensors; connecting the output end of a wavelength tunable laser to a 1*3 optical fiber coupler, and connecting 3 optical fibers from the 1*3 optical fiber coupler to 3 optical fiber circulators respectively; connecting the 3 optical fiber circulators to the optical fiber Fabry-Perot sensors, and connecting the 3 optical fiber circulators to 3 photodetectors respectively; connecting the output ends of the 3 photodetectors to the input ends of a signal acquisition card, storing signal data, storing the data in the signal acquisition card into a computer; carrying out wavelet threshold denoising on the collected signal data; using a generalized cross-correlation function on the denoised signal data to extract time delay information; and using an artificial firefly and clustering analysis joint optimization algorithm to solve the accurate position of the partial discharge source according to the obtained time delay information.