16 results about "Marginal spectrum" patented technology

The invention relates to the technical field of nondestructive testing and performance analysis of engineering materials, in particular to a nondestructive testing and performance degradation analysis method for bridge structure materials. The method comprises the following steps: acquiring material nondestructive testing monitoring data, and executing unified alignment, noise portraying and quality labeling; carrying out combined noise reduction and component evaluation, and generating a noise reduction parameter snapshot; extracting a marginal spectrum and characteristic energy ratio, and establishing a material characterization characteristic index dictionary; calculating a variation index, judging material performance degradation, and constructing a supervision signal; and training the prediction network, generating a trend and a residual error, and completing early warning fusion by adopting a time neighborhood consistency strategy to obtain a material performance degradation early warning level sequence. According to the method, continuous nondestructive monitoring and quantitative characterization of material levels are realized, characteristics and parameters are traceable, cross-channel and cross-time evaluation is consistent, prediction and early warning are sensitive and stable, and the method is suitable for long-term service safety evaluation.

The invention provides a vibration nonlinear signal energy analysis method and system based on variational mode decomposition, and relates to the technical field of signal processing, and the method comprises the following steps: obtaining a monitoring signal of a vibratory roller, determining a corresponding state based on root-mean-square data of the monitoring signal, and determining the state of the monitoring signal; performing segmentation processing on the monitoring signal based on the state corresponding to the monitoring signal to obtain a signal segmentation result; performing variational mode decomposition processing on the signal segmentation result to obtain at least two second mode components; performing Hilbert transformation processing on the second modal component, and combining the instantaneous frequency and the instantaneous amplitude of each modal component obtained through transformation to obtain frequency spectrum information of the monitoring signal; and performing marginal spectrum calculation and integration on the frequency spectrum information to obtain the total energy of the monitoring signal. According to the method, interference signals can be efficiently identified and eliminated in the vibration signals, so that the precision and robustness of compaction quality evaluation are improved.

The application relates to a self-adaptive micro-milling chatter detection method, which belongs to the technical field of self-adaptive micro-milling chatter detection methods. Firstly, acceleration signals at workpiece and machine positions are acquired simultaneously during machining; then, the workpiece acceleration signal and the machine acceleration signal are respectively taken as an expected signal and a reference input signal and are sent into a variable-forgetting-factor recursive least square adaptive filter, so that chatter irrelevant components contained in the workpiece acceleration signal are filtered out; subsequently, a variable mode extraction algorithm is used to process the filtered signal, the initial value of the central frequency is adaptively determined according to the power spectral density corresponding to the filtered signal, and only one eigenmode function is obtained after the variable mode extraction; then, the amplitude of the filtered signal and the amplitude of the marginal spectrum corresponding to the eigenmode function are calculated as chatter characteristics, and the calculated characteristics are compared with a threshold set in advance, so that the occurrence of chatter can be accurately detected.

The invention discloses an ensemble learning intracardiac ultrasonic signal classification method based on multi-feature fusion. The method comprises the steps that original cardiac blood flow ultrasonic signals are collected to obtain ultrasonic digital signals, and the ultrasonic digital signals are preprocessed; processing the preprocessed ultrasonic digital signal and extracting a Mel-frequency cepstral coefficient as a first feature vector; performing framing processing on the preprocessed ultrasonic digital signal to obtain an envelope self-correlation feature, and taking the envelope self-correlation feature as a second feature vector; extracting an intrinsic mode component of the preprocessed ultrasonic digital signal, and performing Hilbert transform on the intrinsic mode component to obtain a Hilbert marginal spectrum as a third feature vector; extracting a wavelet scattering coefficient as a fourth feature vector; and combining the first feature vector, the second feature vector, the third feature vector and the fourth feature vector to obtain a fusion feature vector, classifying the four features by adopting a K-nearest neighbor algorithm, a support vector machine and a neural network, and performing voting ensemble learning on the obtained three classification results to obtain a final classification result.

The invention relates to the technical field of ultrasonic road surface recognition, in particular to a road surface pothole area recognition method for road repairing and flattening. The method comprises the following steps: acquiring an ultrasonic echo signal sequence; after the ultrasonic echo sequence is equally divided, the local scattering degree is determined based on the equally divided waveform entropy difference; the waveform entropy of the ultrasonic echo signal sequence forms an entropy sequence, after coarse graining is conducted on the entropy sequence, the optimal time delay and the optimal embedding dimension are obtained, and then a state vector is determined; constructing a recursive matrix based on the similarity of the state vectors, and determining a first surface feature based on the feature of the recursive matrix and the local scattering degree; a second surface feature based on an entropy value of frequency energy in a Hilbert marginal spectrum converted based on an ultrasonic echo signal sequence and a Hilbert spectrum time point amplitude; complexity is determined based on the surface features, the complexity serves as a weight to adjust an amplitude threshold value, and then the signal is enhanced; and identifying the pothole area by comparing the enhanced signal with the safety signal. According to the invention, the detection precision of the pothole area is improved.

This invention relates to the field of geological hazard identification technology and provides a method for identifying site liquefaction. The method includes: filtering collected seismic records based on surface acceleration in the horizontal direction; performing a Hilbert-Huang Transform (HHT) on the acceleration signals recorded in "time-acceleration" format to obtain the corresponding Hilbert time-frequency plot; and determining the dominant frequency time history curve and marginal spectrum based on the Hilbert time-frequency plot. Then, calculating the average dominant frequency decrease rate (MEFDr) based on the average dominant frequency (MEF) before and after the occurrence of peak ground acceleration; and determining the proportion of low frequencies (R) in the seismic record based on the marginal spectrum. L Finally, the possibility of liquefaction is determined by comprehensively considering the average dominant frequency decline rate and the proportion of low frequencies. Compared with the site liquefaction identification method in the current "Code for Seismic Design of Buildings" GB50011-2010 (2016), the identification method provided by this invention has the advantages of wide applicability, speed, and reliability.

The invention discloses a sea clutter denoising method and device and a storage medium. The method comprises the following steps of: decomposing a signal to be detected by adopting an optimized CEEMDAN to obtain an intrinsic mode component; carrying out HHT (Hilbert-Huang Transform), and calculating an instantaneous frequency mean value and a marginal spectrum peak value energy ratio of the intrinsic mode component; abandoning the high-frequency noise dominant component according to a calculation result, and filtering the intermediate-frequency signal-noise mixed component to obtain a processed signal; dividing the processed signal into training data and test data, and performing phase-space reconstruction and normalization processing on the processed signal to obtain a new sequence; optimizing the least square support vector machine by using a dream optimization algorithm to obtain a DOA-LSSVM model; and inputting the processed signal into the model, and outputting a prediction signal. The method solves the problems that a feature extraction target detection method is difficult to design and the model is unstable, and effectively improves the detection probability and detection performance of the sea surface small target.

This application relates to the field of ultrasonic pavement recognition technology, specifically to a method for identifying pothole areas in road repair and leveling. The method includes: acquiring an ultrasonic echo signal sequence; dividing the ultrasonic echo sequence equally and determining the degree of local dispersion based on the waveform entropy difference of the division; constructing an entropy sequence from the waveform entropy of the ultrasonic echo signal sequence, coarsening it, obtaining the optimal time delay and optimal embedding dimension, and then determining the state vector; constructing a recursive matrix based on the similarity of the state vectors, and determining the first surface feature based on its features and the degree of local dispersion; determining the second surface feature based on the entropy value of the frequency energy in the Hilbert marginal spectrum transformed from the ultrasonic echo signal sequence and the amplitude at time points in the Hilbert spectrum; determining the complexity based on the surface features, using it as a weight to adjust the amplitude threshold, thereby enhancing the signal; and identifying pothole areas by comparing the enhanced signal with a safe signal. This application improves the detection accuracy of pothole areas.

The application relates to the field of intelligent control of high-voltage isolator operating mechanisms, and discloses an intelligent monitoring system for mechanical characteristics of a high-voltage isolator operating mechanism. The system comprises: a multi-source signal synchronous acquisition end which synchronously acquires a driving motor current signal and a transmission shaft vibration signal; a time-frequency characteristic coupling extraction end which adopts adaptive noise auxiliary ensemble empirical mode decomposition to process the vibration signal to extract marginal spectrum characteristics, adopts dynamic time warping calculation to extract dynamic deformation characteristics of the current signal, orthogonally fuses the marginal spectrum characteristics and the dynamic deformation characteristics to construct a time-frequency domain coupling characteristic vector; and a state evolution prediction end which inputs the time-frequency domain coupling characteristic vector into a hidden Markov model based on dynamic correction of a state transition probability matrix, drives a forward-backward calculation process based on a current observation sequence to calculate a hidden state probability distribution, extracts a maximum probability hidden state evolution slope to output a trend prediction index. The application realizes the conversion of mechanical characteristics from post-alarm to trend prediction.

The application discloses a kind of based on multi-transform domain feature fusion's cross-domain radiation source individual identification method, first parallel extraction three kinds of transform domain features to radiation source signal: rectangular integral bispectrum feature, fuzzy function orthogonal slice feature and hilbert marginal spectrum feature, and convert into two-dimensional image.Then, a fusion identification model is constructed by multiple ResNet branches and an MLP.Multiple ResNet branches are used as base learner, and three kinds of feature images are extracted respectively; MLP is used as meta learner, and the extracted high-level feature vector is fused and classified.To cope with cross-domain data distribution difference, the training of the model is first independently pre-trained each ResNet branch on source domain data;When fine-tuning on target domain data, the ResNet backbone network is frozen, and only the adaptation layer at the end of each branch and the MLP parameters are updated, so as to efficiently realize knowledge transfer.The application significantly improves the accuracy and robustness of the radiation source individual identification model in the cross-domain scene.

The invention discloses an electric power system broadband oscillation identification method and device, and can be used in the technical field of electric power systems. The method comprises the following steps: acquiring an electric signal of a power system based on a Nyquist sampling theorem, and preprocessing the electric signal to obtain a preprocessed electric signal; wavelet transformation is carried out on the preprocessed electric signals, a wavelet feature matrix is constructed according to a wavelet transformation result, and the wavelet feature matrix comprises wavelet time-frequency energy distribution, a scale energy spectrum and a marginal spectrum; and inputting the wavelet feature matrix into a recognition model constructed based on a convolutional neural network, so that the recognition model performs broadband oscillation recognition on the power system and outputs a recognition result, the recognition model is obtained by training the convolutional neural network according to a wavelet feature matrix constructed based on an electric signal of the power system in a training set.

This invention belongs to the field of power system automation technology, specifically proposing a fault arc detection method based on variational mode decomposition (VMD) and Hilbert-Huang transform (HHT) multi-feature fusion. The method first performs VMD on the acquired current signal to extract multiple intrinsic mode functions (IMFs) of different frequencies. Then, it performs marginal spectrum analysis on each MIF component. For the selection of MIF marginal spectra, a method based on multi-feature fault discriminative power is proposed, selecting features with high fault discriminative power for each MIF marginal spectrum. To reduce feature redundancy, linear component analysis is used for feature fusion, and finally, the results are imported into a neural network for classification to verify the detection accuracy.

The invention relates to the technical field of rolling bearing digital twinning and prediction maintenance, and discloses a cloud side hierarchical computing power scheduling and hierarchical updating system and method for a rolling bearing digital twinning system, and the method comprises the steps: extracting time domain statistical features and marginal spectrum frequency domain features of initial vibration and temperature data based on a cloud side collaborative architecture; a compact feature vector is generated through fusion, and a health curve is constructed; the end side constructs a degradation model based on a historical health curve, and adopts a Bayesian adaptive sampling mechanism to adjust sampling density so as to compress data; and after the edge side iteratively updates the health curve, calculating a risk index by combining the relative variation of the RUL prediction error in the sliding window and the variation of the health degradation speed, and triggering computing power scheduling and model updating strategies of different risk levels. According to the method, layered precise adaptation of computing power resources is realized, the data transmission overhead is reduced, the real-time performance and reliability of the digital twin system are improved, and the precision of predictive maintenance of the rolling bearing is effectively guaranteed.

The invention relates to the technical field of track slab construction quality detection, and provides a track slab defect detection and evaluation method and system based on a vibration energy spectrum.The method comprises the steps that vibration acceleration data are measured in a partitioned mode, the average damping ratio is calculated according to signals of all areas, and areas with defects preliminarily are screened out; newly adding supplementary measuring points, performing fast Fourier transform on vibration acceleration data at the supplementary measuring points, and screening out key supplementary measuring points; and performing variation mode decomposition and Hilbert transform calculation according to the vibration acceleration data of the key supplementary measurement point, and obtaining a defect evaluation result according to the characteristic parameters of the Hilbert marginal spectrum frequency sequence. According to the high-robustness track slab defect detection and identification method, through combination of regional point distribution of centroid point excitation fused with four-corner vibration pick-up and damping ratio screening of half-cycle energy, in cooperation with fast Fourier transform double-peak / peak migration identification and multi-parameter quantitative evaluation of modal decomposition fused with Hilbert transform, high-robustness track slab defect detection and identification adapting to a complex structure are achieved.

The invention provides a power adaptive allocation method of a hybrid energy storage system, which comprises the following steps of: performing frequency domain analysis on a hybrid energy storage total power task signal by adopting variational mode decomposition and a Hilbert marginal spectrum, and further determining a frequency domain division point of primary power allocation; in the secondary distribution, a filtering algorithm is combined with fuzzy control, feedback adjustment is carried out on the charge state of energy storage of the super-capacitor, the purpose of improving the running state of the energy storage of the super-capacitor is achieved, frequency domain division points of power distribution are adjusted in a self-adaptive mode, and therefore self-adaptive distribution of hybrid energy storage power is achieved. According to the method, the power tasks distributed by the two energy storage media conform to the technical characteristics of the media, and through comparative analysis with a control group which is not subjected to fuzzy control, it is proved that the proposed adaptive strategy can improve the energy operation state of the super capacitor energy storage, and the energy capacity configuration requirement of the system for the super capacitor energy storage is reduced.