23 results about "Multi resolution analysis" patented technology

The invention discloses an I-Nodal node instrument battery pack aging test method, which combines relaxation time distribution (DRT) and multi-resolution analysis (MRA) technologies, performs multi-time scale separation on electrochemical impedance spectroscopy (EIS) data of a node instrument battery pack, and constructs an equivalent circuit model (ECM) with strong physical interpretability and unique structure. And high-precision online estimation of the SOC is realized based on an optimization algorithm and extended Kalman filtering (EKF). Meanwhile, SOC and DRT high-order features are combined and input into a machine learning model, and collaborative prediction of SOH is achieved. According to the method, the false peak occurrence rate is lower than 3%, the SOC estimation error does not exceed + / -1.5%, the SOH prediction RMSE does not exceed 0.015, high precision and high robustness are kept under the complex working conditions of low temperature, high temperature, dynamic load and the like, and the method is suitable for an unattended node instrument energy management system running for a long period.

The invention relates to the technical field of data fusion, and particularly provides a multi-scale eco-hydrological parameter joint inversion method and system based on unmanned aerial vehicle and satellite-ground data fusion, and the method comprises the steps: obtaining multispectral, hyperspectral and thermal infrared data of a research region through a high-resolution sensor carried by an unmanned aerial vehicle; the method comprises the following steps: acquiring unmanned aerial vehicle data, acquiring satellite remote sensing data, performing radiation correction on the unmanned aerial vehicle data and the satellite data, and performing feature extraction and space-time fusion on the unmanned aerial vehicle data and the satellite data by using a deep learning algorithm to generate high-resolution fusion data; through a multi-resolution analysis or spatial interpolation technology, coordinating differences of unmanned aerial vehicle data and satellite data in space and time scales, and constructing a multi-scale data set; based on a physical model and a data driving model, combined with fusion data, an inversion result is visually displayed, and the method has the effects of meeting the hydrological monitoring requirement of high time resolution, and particularly providing real-time monitoring data in the hydrological process of rapid change.

The application relates to the technical field of driving behavior analysis, and particularly provides a multi-resolution driving working condition identification and classification method. A plurality of time length sliding windows are set to perform multi-scale division on a multi-channel driving time sequence data stream, and a multi-resolution analysis system is constructed; longitudinal driving working conditions are identified and classified according to a yaw angular velocity energy index; a dynamic time warping algorithm is used to match data segments with transverse working condition templates, so that the identification and classification of the transverse driving working conditions are realized; and key driving events are calibrated, thereby providing fine data support for subsequent driving style analysis. The application combines the multi-scale sliding window and time sequence similarity measurement technology, effectively improves the driving working condition identification precision, and significantly reduces the misjudgment rate in complex scenes.

The invention provides a knowledge asset traceability tracking method based on digital watermarking, and the method comprises the steps: obtaining to-be-protected knowledge assets, and extracting the multi-modal feature representation of the knowledge assets; according to the method, spatial intensity mapping is dynamically generated by combining a prediction model, intelligent embedding is realized, a DWT-SVD mixed domain core technology is adopted, the multi-resolution analysis capability of discrete wavelet transform and algebraic stability of singular value decomposition are fully played, tracing anchor points are provided for watermarks, and meanwhile, a multiple security guarantee system is constructed, so that the security of the watermarks is improved. And finally, an asset identification module, a watermark generation module, an intelligent embedding module, a traceability verification module and an audit report module are integrated through end-to-end systematic design, so that a complete management closed loop is formed, and the system universality is improved. The full-life-cycle management function enables intellectual property risk management and control through log auditing and a visual report, so that the concealment and safety of the digital watermark are improved.

The application relates to the technical field of intelligent distribution of educational resources, and discloses a dynamic distribution management system of educational teaching resources based on machine learning. The system comprises the following steps: collecting, through a data acquisition module, resource request time stamps, transmission rates and computing load data of learning terminals in real time; processing the data by a multi-resolution analysis module to generate a resource use mode atlas containing time, space and content dimensions; analyzing the atlas by a resource demand mapping module using a pre-trained deep belief network to output accurate resource quota suggestions; optimizing the suggestions based on network topology by a delay compensation module to form a delay-resistant distribution scheme; executing the distribution by a resource scheduling module and starting audit tracking; and updating network parameters according to the audit data by an adaptive optimization module. The system realizes accurate prediction and dynamic adaptive optimization of resource demand, and improves resource utilization efficiency and teaching service quality.

This invention relates to the field of well logging data processing technology, and particularly to a method, system, and apparatus for improving the resolution of well logging data in thin sand layers. The method includes the following steps: S1, acquiring well logging data from thin sand layers in the area to be analyzed; S2, performing data preprocessing; S3, using wavelet transform technology for multi-resolution analysis to extract characteristic signals of the thin sand layers and enhance their resolution; S4, using a chart correction method to improve accuracy; S5, evaluating whether the characteristic signals of the thin sand layers processed in step S4 are acceptable. If the evaluation is unacceptable, steps S1-S5 are iteratively performed until the evaluation is acceptable. When the evaluation is acceptable, it indicates that the characteristic signals of the thin sand layers processed in step S4 represent well logging data with improved resolution. This achieves rapid and accurate high-resolution processing of acoustic logging data.

This application provides a TDLAS gas sensor and its anti-interference filtering and noise reduction method, relating to the field of gas concentration detection technology. The method includes: acquiring the original analog-to-digital conversion data of the gas to be measured; using an adaptive median filtering algorithm to filter, reduce noise, and correct the baseline of the original data to obtain a time-domain signal; and calculating the gas concentration based on Beer-Lambert's law. The adaptive median filtering algorithm uses multi-resolution analysis to decompose the signal into low-frequency and high-frequency components, identifies noise regions and absorption peak regions by calculating local gradient changes, and performs multi-scale reconstruction after adaptive threshold classification. This invention addresses the problem of TDLAS gas sensors being susceptible to interference from environmental temperature and pressure fluctuations. By protecting the absorption peak region while filtering out the noise region, it significantly improves the signal-to-noise ratio and detection stability, and has the advantages of strong anti-interference capability, fast response speed, and significant noise reduction effect.

The invention relates to the technical field of intelligent aided driving, and particularly provides a multi-time-scale driving style analysis method, which comprises the following steps of: acquiring driving time sequence segments in seconds by a multi-resolution analysis method, and classifying working conditions; labeling a short-time driving style label through a driving behavior clustering method, and constructing and training a short-time driving style classification model; setting a medium-and-long-time driving task window with minute or hour as a unit, extracting a short-time driving style by using the trained short-time driving style classification model, acquiring a distribution vector according to a short-time driving style sequence in the medium-and-long-time driving task window, and mapping the distribution vector to a predefined medium-and-long-time style mode space, identifying a corresponding medium-time and long-time style mode through the clustering model; setting a long-time style window with weeks, months, seasons or years as units, counting medium and long-time style mode sequences in the long-time style window to obtain a distribution vector, mapping the distribution vector to a predefined long-time style evolution space, and realizing long-time style evolution analysis of the driver through a clustering classification model.

Embodiments of the present application disclose an identity authentication method, device and equipment, and a storage medium. The method determines a first key point of a first signature handwriting through a multi-resolution analysis manner; performs key point matching on the first key point and a second key point to obtain a key point matching pair; determines a matched first handwriting segment and a second handwriting segment according to the key point matching pair; and authenticates the first signature handwriting according to a distance between the matched first handwriting segment and the second handwriting segment. That is, the embodiments of the present application use signature handwriting to perform identity authentication, which can effectively avoid adverse consequences caused by username and password leakage, and at the same time, the key points of the first signature handwriting are determined by using a multi-resolution analysis manner, the influence of different resolutions on the key points is considered, and the accuracy of the key points is improved. Therefore, the accuracy of an authentication result can be improved when the first signature handwriting is authenticated based on the key points in the subsequent process, and thus the security of identity authentication can be improved.

The invention relates to the technical field of fault diagnosis and prediction, in particular to a power distribution network early fault diagnosis and prediction method based on transient signal feature mining and transfer learning. The method comprises the following steps: acquiring transient signals of key equipment of the power distribution network in normal and slightly abnormal states, and preprocessing the transient signals; extracting a multi-resolution feature vector based on the preprocessed transient signal, a wavelet packet, multi-scale Fourier and empirical mode decomposition, inputting the multi-resolution feature vector to a sparse auto-encoder, and extracting a key feature subset representing a fault stage; a feature distribution difference metric between the source domain device and the target device is constructed based on the key feature subset. According to the method, multi-resolution analysis means such as a wavelet packet, multi-scale Fourier transform and empirical mode decomposition are fused, and impact, oscillation and frequency spectrum characteristics reflecting slight abnormality of equipment are deeply excavated from transient voltage / current signals.

The invention discloses a distributed spectrum sensing noise stripping method based on wavelet gradient, and belongs to the technical field of communication and artificial intelligence crossing. The method comprises the following steps: acquiring original spectrum data through a distributed cognitive radio node; performing sliding window segmentation, Hanning window weighting and power spectrum density calculation on the data; the preprocessed data are input into a differentiable wavelet noise separation layer, the layer serves as a learnable one-dimensional convolution kernel through a parameterized biorthogonal wavelet filter, and end-to-end trainable multi-resolution analysis is achieved in a deep learning framework; calculating the power spectrum density gradient of the high-frequency detail coefficient in real time, and quantifying the noise abrupt change intensity based on a central difference method; dynamically generating a gating weight, and selectively suppressing the wavelet coefficient of the high-gradient frequency point; inputting the processed data into a one-dimensional convolutional neural network with residual connection for classification; and results are fused by adopting a clustering type collaborative decision-making mechanism.

The application discloses a GIS device-based detection method for the synchronization of the state of a knife switch and the action of a three-phase knife switch, comprising the following steps: 1, preprocessing current data and dividing data sets; 2, designing a CNN network based on a double-layer LSTM neural network with an attention mechanism and a dynamic time warping algorithm; 3, constructing the CNN network based on the double-layer LSTM neural network with the attention mechanism and the dynamic time warping algorithm; and 4, obtaining the output result of a test set sample based on the CNN network based on the double-layer LSTM neural network with the attention mechanism and the dynamic time warping algorithm. The application can provide multi-scale and multi-resolution analysis of time series, dynamically capture the characteristics of data in the time domain and the frequency domain, improve the detection accuracy of the synchronization of the state of a GIS device knife switch and the action of a three-phase knife switch, and thus meet the actual requirements of accuracy and rapidity.

The invention provides an arc fault signal feature extraction method based on wavelet analysis and a related device, and relates to the technical field of electrical safety monitoring. According to the method, self-adaptive filtering is achieved by collecting current and voltage signals and combining load type recognition, and an analysis window is dynamically adjusted according to the signal-to-noise ratio; carrying out multi-resolution analysis by adopting wavelet transform, and extracting typical features such as energy distribution and spectrum abrupt change points and wavelet entropy auxiliary features; and fault judgment is completed through deep learning and a support vector machine cascade model, confidence coefficient verification is carried out by fusing adjacent user data, and finally early warning information is uploaded. According to the scheme, the detection sensitivity and the anti-interference capability of weak arc are improved, the problems that a traditional circuit breaker has many recognition blind areas and the misoperation rate is high are effectively solved, and the circuit breaker is suitable for early fire early warning of an intelligent power distribution system.

The invention discloses an RLBI high-resolution angle parameter estimation method and device based on adaptive CS-STFT-IRT, and the method comprises the steps: receiving a target signal through employing double array elements of a rotating long baseline interferometer, and calculating a cross-correlation signal; multi-resolution analysis is carried out under the condition of multiple preset window lengths, and an adaptive compressed sensing hybrid algorithm is introduced to generate a time-frequency power spectrum matrix. And then, respectively executing inverse Radon transformation on the time-frequency power spectrum matrixes under different window lengths to obtain corresponding inverse Radon domain images, and extracting peak value information through an intelligent peak searching algorithm. And scoring each window length processing result according to a preset quality evaluation criterion, and adaptively selecting an optimal inverse Radon domain image. And accurately calculating the pitch angle and the azimuth angle of the target according to the peak point coordinates in the optimal image. According to the method, the limitation of the traditional method in the aspects of resolution and robustness is effectively overcome, and the angle estimation precision and reliability under the adjacent information source condition are remarkably improved.

The present application belongs to the field of acoustic signal processing, deep learning and intelligent operation and maintenance of industrial equipment, and discloses a voiceprint anomaly detection method and system based on wavelet convolution time domain feature extraction. In view of the technical bottlenecks such as poor robustness of voiceprint feature extraction and weak model generalization ability in the industrial scene, the multi-resolution analysis ability of wavelet packet transform and the end-to-end learning ability of convolutional neural network are deeply integrated to construct a wavelet convolution time domain feature extraction module with strong robustness, and an unsupervised anomaly classification module is built in combination with a variational autoencoder to form an end-to-end integrated model of feature extraction and anomaly classification. The present application only needs voiceprint samples of normal operation of equipment to complete model training, and in the industrial scene with strong background noise, it can not only accurately capture the transient time domain features of early weak faults of equipment, but also realize unsupervised and high-accuracy anomaly state classification, effectively solving the industry pain points of low detection accuracy under strong noise interference and lack of abnormal samples in the industrial scene.

This application provides a construction waste detection method and system based on YOLOv11 and wavelet convolution, relating to the field of computer vision. The method includes: constructing a target detection model; inputting acquired construction waste images into the Backbone layer to extract multi-scale features and generate a first feature map; inputting the first feature map into the Neck layer, fusing first feature maps of different depths to capture and enhance feature information at different frequencies, dynamically learning channel and spatial attention weights, and generating a second feature map for target detection of construction waste through the Head layer. This application embeds wavelet convolution modules and CBAM attention modules into the Backbone and Neck layers of YOLOv11 to enhance high-frequency details and cross-scale feature interaction capabilities. Through multi-resolution analysis and parallel detection heads, it can improve the detection accuracy of construction waste in complex scenes.

The invention provides a harmonic detection method for a charging pile, and relates to the technical field of harmonic detection, and the method comprises the following steps: 1, signal collection; step 2, wavelet decomposition; step 3, signal reconstruction; step 4, interference positioning; step 5, acquiring a fundamental wave frequency; step 6, building an Adaline network; 7, adjusting a weight vector; according to the method, the multi-resolution analysis characteristic of wavelets is combined and utilized, noise is effectively removed, meanwhile, useful components of the signals are reserved, the Adaline improved network is combined, the denoised signals serve as input, expected output is known harmonic components, the precision and efficiency of harmonic detection are improved, and the method has the advantages that the method is simple and convenient to operate, and the method is suitable for large-scale popularization and application. And the adaptability and the real-time performance of the system are enhanced.

The invention relates to the technical field of digital image processing, in particular to a quaternion representation-based color image denoising method for special affine matrix wavelets, which comprises the following steps of: for a to-be-denoised color image, firstly, enabling R, G and B components of the color image to correspond to three imaginary parts of a quaternion so as to represent the three imaginary parts as quaternion signals; secondly, mapping the quaternion signal into a second-order complex matrix value signal through an equidistant operator, decomposing the matrix value signal by using multi-resolution analysis related to special affine convolution in a matrix value function space, performing threshold processing on detail coefficients, reconstructing the processed coefficients by using a fast algorithm, and finally obtaining a reconstructed quaternion signal; and finally, restoring the matrix value signal into a quaternion signal through inverse mapping of an equidistant operator, reading component values of each channel, and outputting a denoised color image. According to the method, the color image is processed as a whole, the complexity of quaternion convolution is avoided, and the defects in the prior art are overcome.

The invention relates to the technical field of driving behavior analysis, and particularly provides a multi-resolution driving condition identification and classification method. The method comprises the following steps of: performing multi-scale division on a multi-channel driving time sequence data stream by setting a sliding window with multiple time durations, and constructing a multi-resolution analysis system; longitudinal driving conditions are identified and classified according to the yaw velocity energy index; a dynamic time warping algorithm is used for matching the data fragments with the transverse working condition template, and recognition and classification of the transverse driving working condition are achieved; key driving events are calibrated, and refined data support is provided for follow-up driving style analysis. According to the method, a multi-scale sliding window and time sequence similarity measurement technology is fused, the driving condition recognition precision is effectively improved, and the misjudgment rate in a complex scene is obviously reduced.

The invention relates to the technical field of intelligent distribution of educational resources, and discloses a dynamic distribution management system for educational teaching resources based on machine learning. According to the system, a data acquisition module collects a resource request timestamp, a transmission rate and calculation load data of a learning terminal in real time; the multi-resolution analysis module is used for processing the data to generate a resource use mode graph containing time, space and content dimensions; the resource demand mapping module analyzes the map by using a pre-trained deep belief network and outputs an accurate resource quota suggestion; the delay compensation module optimizes the suggested value based on the network topology to form an anti-delay distribution scheme; the resource scheduling module executes allocation and starts auditing tracking; and the adaptive optimization module updates network parameters according to the audit data. According to the system, accurate prediction and dynamic adaptive optimization of resource demands are realized, and the resource utilization efficiency and the teaching service quality are improved.

The present application relates to the technical field of intelligent auxiliary driving, and specifically provides a multi-time-scale driving style analysis method, which obtains driving time sequence segments in seconds through a multi-resolution analysis method and classifies working conditions; short-time driving style labels are marked through a driving behavior clustering method, a short-time driving style classification model is constructed and trained; a medium-long-time driving task window in minutes or hours is set, short-time driving styles are extracted using the trained short-time driving style classification model, distribution vectors are obtained according to short-time driving style sequences in the medium-long-time driving task window and mapped to a predefined medium-long-time style mode space, and a corresponding medium-long-time style mode is identified through a clustering model; a long-time style window in weeks, months, seasons or years is set, distribution vectors are obtained by counting medium-long-time style mode sequences in the long-time style window and mapping to a predefined long-time style evolution space, and long-time style evolution analysis of a driver is realized through a clustering classification model.

This application discloses an electromagnetic transient signal processing method, apparatus, and storage medium based on wavelet transform. The method achieves an adaptive balance between time-domain and frequency-domain resolution by dynamically adjusting the center frequency and time decay parameters of the mother wavelet, thereby improving the ability to identify signal components in different frequency bands. Then, multi-resolution analysis (MRA) is introduced as a preprocessing filtering method to suppress the interference of low-frequency components on high-frequency components, enhancing the recognizability of high-frequency features in the transform result. Based on this, while maintaining the good time-frequency localization characteristics of wavelets, a further method is introduced... Q The dynamic factor adjustment mechanism and L1 normalization strategy effectively improve the extraction accuracy and robustness of high-frequency feature components. This application can achieve high-precision identification of the natural frequency of electromagnetic transient fault signals, and has good engineering application value.

The invention discloses a low-frequency oscillation identification method and system based on PMU data, and belongs to the technical field of power system operation monitoring, and the method comprises the steps: collecting PMU data from a synchronous phasor measurement device through a communication interface; establishing a global data buffer area, and setting a multi-resolution analysis window covering different oscillation frequency bands according to a PMU sampling rate; performing peak value and valley value detection on the data in each analysis window, setting a neighborhood minimum distance parameter to identify extreme points according to the type of each window, and generating a corresponding extreme point sequence; calculating oscillation frequency and oscillation amplitude according to the extreme point sequence; and judging the oscillation state according to the oscillation frequency, the oscillation amplitude and the noise level obtained by each analysis window, and outputting a detection result. According to the method, the false detection rate is reduced from 30% to 5% or below through dynamic noise estimation, the omission ratio is reduced from 25% to 3% or below, and the method can adapt to complex noise scenes such as new energy output fluctuation and load impact.