21 results about "Wavelet entropy" patented technology

The invention discloses a GIS partial discharge intelligent diagnosis system and method based on one-dimensional ultrahigh frequency signal analysis, and relates to the technical field of power electrical equipment intelligent monitoring, and the system comprises a signal collection and preprocessing module which is used for collecting ultrahigh frequency signals of GIS equipment and obtaining preprocessed signal data through a dynamic threshold algorithm; the discharge initial judgment module is used for performing multi-dimensional sequential judgment to eliminate interference discharge data so as to obtain effective discharge signal data; the feature extraction module is used for performing time domain kurtosis and pulse width analysis, frequency domain energy distribution analysis and time-frequency domain wavelet entropy calculation based on the multi-dimensional features of GIS partial discharge, and generating an optimized feature subset; and the type identification module is used for identifying the partial discharge type by using the integrated learning model to obtain a diagnosis result. According to the invention, the problem of unstable recognition accuracy caused by insufficient signal preprocessing, single feature representation and single classification algorithm in the prior art is solved.

The invention relates to the technical field of power distribution network fault detection, and discloses a power distribution network high-resistance grounding fault intelligent detection method, system and device and a medium, and the method comprises the steps: collecting a power distribution network line transient signal which comprises a transient zero-sequence voltage signal and a transient zero-sequence current signal; preprocessing the transient signal and extracting a multi-dimensional feature set for representing high-resistance grounding fault characteristics, wherein the multi-dimensional feature set comprises a transient energy feature, a wavelet entropy feature and a harmonic component feature; and inputting the extracted multi-dimensional feature set into a pre-trained machine learning model, and simultaneously outputting a judgment result of the high-resistance grounding fault and an estimated value of the grounding resistance through the machine learning model. According to the method, the transient energy, the multi-scale wavelet entropy, the odd harmonic amplitude and the phase, which are derived from different analysis domains and have complementary physical meanings, are deeply fused, so that the problem that a single feature is weak in characterization capability and easy to fail under the conditions of high noise and high resistance is effectively solved.

The invention discloses an AUV (Autonomous Underwater Vehicle) propeller fault diagnosis method based on wavelet entropy and APN (Access Point Name), and aims to solve the problems of large signal noise interference, inaccurate fault feature extraction and weak generalization ability in a small sample scene in AUV propeller fault diagnosis. The method sequentially comprises the following steps: S1, discretizing a multi-layer wavelet decomposition original signal, determining an optimal reconstruction scale by means of wavelet Shannon entropy, and reconstructing an enhanced signal by a single branch; s2, the enhanced signal is input into a CNN containing an attention module, and key fault features are focused; and S3, constructing a prototype network of joint loss optimization, and combining a pseudo-label mechanism to use unlabeled samples, thereby improving the generalization ability of small samples and realizing efficient and accurate diagnosis. According to the method, noise interference can be effectively filtered out, fault features can be accurately extracted, efficient and accurate diagnosis of AUV propeller faults is achieved under the small sample condition, and reliable technical support is provided for safe and stable operation of an AUV propulsion system.

The invention discloses an electric power aerial patrol operation data mining method, and belongs to the technical field of intelligent patrol. Coordinate values and temperature data of target equipment are synchronously collected through an infrared thermal imager, a visible light camera and a vibration sensor carried by power equipment, infrared coordinates and visible light coordinates are projected to the same geographic coordinate system through affine transformation, space registration is achieved, continuous wavelet transformation is conducted on collected vibration signals, and the temperature of the target equipment is obtained. The method comprises the following steps: extracting vibration feature vectors including global vibration intensity, wavelet energy spectrum and wavelet entropy, calculating the weight of each feature through image quality, carrying out weighted fusion to calculate a state index representing the health state of equipment, judging the state index according to a dynamic threshold value, judging that the equipment is abnormal if the state index exceeds the threshold value, and judging that the equipment is abnormal if the state index does not exceed the threshold value. And a feedback mechanism is triggered to collect data again to monitor the trend, otherwise, the data is stored for subsequent analysis. According to the invention, the precision and reliability of abnormal state identification in electric power aerial patrol operation and the robustness to a complex field environment are significantly improved.

The invention provides a transformer turn-to-turn short circuit detection method based on high-frequency current time-frequency energy distribution characteristics. The transformer turn-to-turn short circuit detection method comprises the following steps: Step 1, sensor installation and signal acquisition; step 2, spectrum analysis and optimal hierarchy selection are carried out; performing spectral analysis on the signal and determining an optimal level of wavelet decomposition, performing wavelet transform discretization and reconstruction, and performing multi-scale decomposition on the signal to obtain a high-frequency component and a low-frequency component under each scale; step 3, carrying out signal de-noising processing; step 4, extracting a characteristic value; extracting three indexes including a pulse amplitude ratio RA, a high-frequency energy focusing degree Ef and a wavelet entropy variation degree CVH; and the turn-to-turn short circuit detection condition of the transformer is judged according to the characteristic value through a three-level diagnosis rule. The number of wavelet analysis dynamic decomposition layers is determined in combination with FFT frequency domain analysis, and collaborative optimization of noise suppression and fault feature enhancement is realized by using a scale adaptive wavelet threshold denoising algorithm. And a time domain-frequency domain-time frequency combined characteristic system is further constructed, a quantitative grading diagnosis standard is established, and the detection capability and the diagnosis reliability of the slight short circuit are remarkably improved.

The application discloses a kind of based on gateway machine's intelligent auxiliary control monitoring system of substation, including data acquisition module, protocol self-adapting adjustment module, abnormality detection module, fault early warning module and intelligent operation control module.The application relates to the technical field of intelligent management of substation, specifically refers to a kind of based on gateway machine's intelligent auxiliary control monitoring system of substation, the present scheme utilizes self-supervised contrast learning and second-order Markov chain automatically extracts and predicts protocol features, combines confidence and delay decision, realizes no label fast switching, high reliable communication;Fusion sliding window transfer entropy and kernel PCA reconstruction residual, unsupervised detection and positioning electrical, network and environmental anomaly;With the help of multi-scale Morlet wavelet entropy and DBSCAN rare cluster identification, unknown fault precursor spontaneous early warning is realized;Based on real-time apparent power autoregressive prediction and mixed integer convex optimization, peak suppression, load smoothing and temperature constraint are considered, and scheduling strategy is optimized.

The invention discloses an obstacle avoidance stable grabbing method for any object in a disordered scene, and the method comprises the steps: carrying out the obstacle avoidance grabbing pose planning of any object in a disordered environment before grabbing; in the grabbing process, tactile force prediction and self-adaptive clamping control are carried out. Before grabbing, obstacle avoidance grabbing pose planning for any object in the disordered environment mainly can be divided into two sub-tasks of target object segmentation and grabbing pose determination. In the grabbing process, gradient variance, gravity center displacement and wavelet entropy features of a pressure matrix are extracted in real time by using a multi-dimensional tactile feature fusion method, and a grabbing state is divided into three modes including a stable mode, a sliding mode and a deformation mode in combination with a support vector machine (SVM) classification model. And a double-PID adaptive control strategy is adopted for different states. The grabbing efficiency and safety can be effectively balanced, and objects are prevented from being damaged or slipping off.

This invention discloses an interface call optimization method and system under a microservice architecture, comprising the following steps: collecting runtime data of each interface node in the microservice architecture; performing wavelet entropy joint perturbation-sensitive coding on the state sequences corresponding to each interface node to generate an interface call vulnerability view; constructing an original call graph based on the call relationships between each interface node, and constructing a multi-domain coupling dependency graph by combining anomaly propagation relationships and resource contention relationships; inputting the interface call vulnerability view and the multi-domain coupling dependency graph into an improved STG-Mamba model to generate interface congestion risk values ​​and call benefit values ​​corresponding to each candidate interface call action; further generating a candidate call decision set and a target call orchestration result, and iteratively updating based on the execution feedback results. This invention can improve the stability, benefit, and adaptive optimization capability of interface call orchestration, and is suitable for intelligent call control scenarios in microservice systems.

This invention relates to the field of performance testing technology, specifically to a method and system for testing the electrical performance of data cables based on machine learning. The method includes: obtaining local instability characterization values ​​for each parameter point based on the standard deviation, maximum coefficient of variation, autocorrelation decay time, and EMD decomposition results of the local signal segments; obtaining local information content characterization values ​​for each parameter point based on the Shannon entropy, the number of significant peaks in the power spectrum, wavelet entropy, and the proportion of the main frequency band energy of the local signal segments; obtaining the target scale for each parameter point based on the scale indicator factor, local instability characterization values, and local information content characterization values; extracting features from the corresponding electrical parameter signals based on the target scale of each parameter point on the electrical parameter signals; and detecting and identifying the electrical performance of the data cable under test based on the extraction results. This invention improves the accuracy and reliability of data cable electrical performance detection and identification.

The present application relates to a kind of diaphragm myoelectric signal noise reduction method, comprising the following steps, S1, by means of acquisition device obtains diaphragm myoelectric signal and reference electrocardio noise signal;S2, diaphragm myoelectric signal and reference electrocardio noise signal are carried out wavelet transform, obtain first wavelet coefficient sequence;S3, first wavelet transform coefficient sequence is handled using independent component analysis method for first noise reduction, obtain second wavelet coefficient sequence;S4, second wavelet coefficient sequence is handled using wavelet entropy method for second noise reduction, obtain third wavelet coefficient sequence;S5, third wavelet coefficient sequence is carried out wavelet inverse transform, obtain the diaphragm myoelectric signal of noise reduction.The present application uses independent component analysis one-time noise reduction superposition wavelet entropy secondary noise reduction double noise reduction technology, can effectively inhibit and reduce the influence of electrocardio noise on diaphragm myoelectric signal acquisition, improve the effectiveness and accuracy of diaphragm myoelectric signal acquisition.

The invention relates to the technical field of power grid inertia evaluation, in particular to a power grid inertia evaluation disturbance identification method and system based on self-adaptive wavelet transform, and the method comprises the steps: obtaining active power data in a power system, carrying out the preprocessing of the data, carrying out the self-adaptive wavelet transform of the preprocessed data, and carrying out the disturbance identification of the power grid inertia evaluation. Extracting a wavelet detail coefficient and an approximation coefficient; step disturbance is identified by using a detail coefficient through a multi-scale digital-analog maximum value method; for slope disturbance, carrying out sliding window linear goodness-of-fit threshold value identification on the data after the step disturbance identification part is carried out; for noise-like disturbance, performing disturbance identification through mean value stability and variance stability dual-stability detection and wavelet entropy verification; and outputting types, time windows and key parameters of various disturbances. The method can quickly decompose the measurement data to different frequency bands, provides accurate and reliable disturbance data for system inertia evaluation, and is helpful for maintaining the system frequency stability.

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 relates to the technical field of power system protection, in particular to a lightning stroke fault detection method and system based on improved wavelet transform threshold denoising and wavelet entropy recognition, and a storage medium. An improved wavelet threshold function is adopted to carry out noise reduction processing on originally-collected traveling wave signals, so that remarkable jump characteristics in lightning stroke waveforms are enhanced, a wavelet entropy segmentation mechanism based on peak detection is further provided on the basis, and the entropy function change of each scale signal under wavelet decomposition is constructed, so that the wavelet entropy segmentation mechanism is optimized. Sudden change information brought by a lightning stroke wave head is automatically identified, and high-robustness identification of a lightning stroke fault and a non-lightning stroke fault is realized. The invention aims to solve the problem of how to identify lightning stroke faults.

The invention relates to the technical field of electrical equipment insulation state detection, in particular to an insulation packaging material deterioration detection method and system based on molecular vibration, and the method comprises the steps: applying a periodic high-voltage square-wave pulse voltage to a to-be-detected insulation packaging material sample; the method comprises the following steps: detecting a molecular vibration sound wave signal of a to-be-detected insulation packaging material excited by a transient electric field force, capturing a transient molecular vibration waveform in a specific acquisition window after a pulse edge is captured, performing multi-dimensional feature extraction on the acquired transient molecular vibration waveform, and extracting the multi-dimensional features of the extracted transient molecular vibration waveform according to the multi-dimensional features of the transient molecular vibration waveform. And inputting to a pre-constructed evaluation model or comparing with a preset threshold value, and outputting the current degradation degree or degradation evaluation result of the to-be-tested insulation packaging material. The time domain amplitude, the waveform form, the relaxation time and the wavelet entropy of the vibration waveform are extracted through multi-dimensional features, and the degradation degree evaluation of the insulation packaging material is realized by adopting double criteria of mechanical destruction and energy dissociation.

The invention relates to a multi-objective optimization enhanced industrial equipment signal processing and intelligent health diagnosis method. The method comprises the following steps: acquiring a vibration signal of detected equipment; an AMOPSO algorithm is adopted to optimize hyper-parameters of the SVR model; performing bidirectional extension on the vibration signal by using the optimized SVR model; performing empirical mode decomposition on the extension signal, and extracting a plurality of first intrinsic mode function components to construct a three-dimensional feature tensor; fusing the wavelet entropy and the sample entropy of each intrinsic mode function component in the three-dimensional feature tensor through linear transformation to form a double-entropy feature vector; inputting the double-entropy feature vector into a deep neural network, and training a diagnosis model; the deep neural network adaptively captures the global and dynamic dependency relationship of the fault impact response sequence by fusing two parallel paths of a global perception attention module and a dynamic perception attention module. According to the invention, high-precision intelligent health diagnosis of the rotating mechanical bearing is realized.

The invention discloses a disturbance detection method and device based on wavelet entropy denoising and empirical mode decomposition. The method comprises the following steps: acquiring an initial voltage signal; performing multi-scale analysis on the time domain local feature of the initial voltage signal to obtain multi-scale high and low frequency components; according to the high-frequency coefficients in the multi-scale high and low frequency components, analyzing wavelet entropies of different scales to obtain corresponding wavelet thresholds, and performing denoising reconstruction on the multi-scale high and low frequency components in combination with the high-frequency coefficients of different scales to obtain voltage reconstruction signals; decomposing the voltage reconstruction signal by adopting an empirical mode decomposition model to obtain a plurality of intrinsic mode function components; in combination with sensitivity evaluation indexes, sorting the intrinsic mode function components, screening out disturbance characteristic components, determining disturbance starting and ending time of the disturbance characteristic components, and completing disturbance detection, so that rapid and accurate identification of the voltage disturbance event is realized; and the adaptability and reliability of voltage disturbance detection in a complex noise environment and under a multi-type disturbance condition are improved.

The application discloses an AUV propeller fault diagnosis method based on wavelet entropy and APN, and aims to solve the problems of large signal noise interference, inaccurate fault feature extraction and weak generalization ability in the AUV propeller fault diagnosis. The method sequentially comprises the following steps: S1, a discrete multi-layer wavelet is used to decompose an original signal, a wavelet Shannon entropy is used to determine an optimal reconstruction scale, and a single branch reconstruction is used to enhance a signal; S2, the enhanced signal is input into a CNN containing an attention module, and key fault features are focused; and S3, a prototype network optimized by a joint loss is constructed, unlabeled samples are combined with a pseudo-label mechanism, the generalization ability of small samples is improved, and efficient and accurate diagnosis is realized. The application can effectively filter out noise interference, accurately extract fault features, realize efficient and accurate diagnosis of the AUV propeller fault under the condition of small samples, and provide reliable technical support for the safe and stable operation of the AUV propelling system.

The invention discloses a BIM-based radar water level monitoring method and system, and relates to the technical field of liquid level measurement, and the method comprises the steps: obtaining an original signal reflected by a radar, and decomposing the original signal into a plurality of IMF components; respectively carrying out time domain feature extraction, wavelet entropy feature optimization extraction and fractal dimension feature extraction on the first A IMF components, combining the extracted features of each IMF component into a feature matrix, and carrying out dimension reduction processing on the feature matrix by adopting a principal component analysis method to obtain a fusion feature vector; inputting the fused feature vector into a preset water level dynamic prediction model to obtain a predicted water level; and mapping each predicted water level to a BIM model in real time, and generating an underground water distribution thermodynamic diagram with a time axis. According to the invention, accurate monitoring of the water level of the building foundation pit under different conditions is realized.

The invention discloses an expressway reconstruction and extension project existing structure evaluation system based on visual analysis, and belongs to the technical field of project supervision and evaluation. The method and the device are used for solving the technical problem of poor evaluation accuracy and system robustness during implementation of an existing scheme. Through empirical mode decomposition and wavelet entropy denoising, based on an inverse calculation method of a digital twinborn model, quantitative grading of damage degrees is realized through a strain concentration coefficient, and a three-dimensional thermodynamic diagram is constructed, so that damage space distribution can be intuitively presented; the adaptability to different environmental noises can be effectively improved through a self-adaptive threshold algorithm, abstract deformation data is converted into quantitative indexes according to structural stability, and subjectivity of traditional experience judgment can be avoided; emergency maintenance and reinforced monitoring are distinguished through a first-level early warning mechanism and a second-level early warning mechanism, quantitative evaluation and accurate decision making of the structural stability are achieved in combination with segmented data of a thermodynamic diagram and an automatically-generated defect report, and core technical support can be provided for engineering safety and maintenance resource optimization.

The invention belongs to the technical field of control engineering, and discloses an electric carry-scraper cable dragging tension online monitoring platform comprising a data acquisition module used for acquiring cable operation related data; the data processing module is used for carrying out abnormal value processing on the cable operation related data to obtain cable operation characteristic data; the method comprises the following steps: decomposing signals in cable operation characteristic data by using discrete wavelet transform, respectively constraining scale parameters and displacement parameters in the signals, carrying out dynamic thresholding de-noising processing on detail coefficients in the signals, calculating signal energy and wavelet entropy of the de-noised detail coefficients, and calculating the signal energy and wavelet entropy of the de-noised detail coefficients; extracting and integrating to obtain a cable comprehensive performance feature data set; the dragging tension prediction module is used for training according to the cable comprehensive performance characteristic data set to obtain a dragging tension prediction model, and predicting through the dragging tension prediction model to obtain a cable dragging tension coefficient; the cable dragging tension is effectively monitored and evaluated, and the risk of equipment and operators is reduced to the maximum extent.