640 results about "Wavelet packet decomposition" patented technology

The invention relates to an eccentric pump vibration accidence fusion diagnose method and relative vibration signal collector, wherein said invention is characterized in that: it uses the eccentric pump vibration signal collector to collect the normal state, the quantity imbalance, asymmetry rotate and loose base of eccentric pump; uses wavelet decomposition and reconstruction to extract the character of vibration signal; and inputs the character vectors into sub fuzzy neural networks I and II; to be treated and replace the relation factor matched with sensor signal function; the whole fuzzy neural network comprises data fuzzy layer, input layer, hidden layer and output layer; uses D-S theory to obtain the fused signal function distribution, realize the fusion diagnose on normal state, quantity imbalance, asymmetry rotate and loose base. The invention has simple structure and high effect.

The invention relates to a fault diagnosis method, in particular to a rolling bearing fault diagnosis method based on the vibration detection. The method comprises the following steps of firstly decomposing the rolling bearing data collected by an acceleration sensor into three layers of wavelet packets, solving the energy of a third layer of wavelet packet coefficient rebuilding signals, selecting a frequency band with centralized energy to rebuild approximate evaluation of an original signal according to the variation of energy values of each frequency bands of the third layer; and utilizing a cepstrum to further analyze the rebuilt signal, and comparing the rebuilt signal with a theoretically-computed fault characteristic frequency and an edge frequency characteristic. By combining multiple resolutions of the wavelet packet and the cepstrum, the periodic component on a power spectrum, a separated-side frequency-band signal and the characteristics which are slightly subjected to the transmission route can be well detected. Meanwhile, the method is strong in manipulability and practicability.

A method and apparatus for improving the signal to noise ratio of an information carrying signal wherein a wavelet transform up to a predetermined level is computed, a frequency thresholded signal which is indicative of noise is derived from the wavelet transform, and the frequency thresholded signal is subtracted from the information carrying signal.

The invention dislcoses a single-phase earth fault line selection method based on transient state high-frequency component correlation analysis. The method comprises the steps that whether or not a single-phase earth fault happens is judged according to the magnitude of a busbar zero-mode voltage instantaneous value, db10 wavelets are adopted for performing five-layer wavelet packet decompositionon zero-mode current of two work frequency periods after each feeder line fault, after the minimum frequency band is removed, node wavelet packet deposition coeffiences are reconstructed and summeredto obtain a fault transient high-frequency capacitance-current component, and a correlation coeefient matrix M between every two feeder lines is obtained; Si is set as a correlation accumulation coefficient for the ith feeder line fault transient high-freuqency capacitance-current component, when rho ij is larger than rho set, Si is equal to 1, 1 is subtracted from Si, and a correlation accumulation coefficient matrix S can be obtained; if Si is larger than 0 constantly, the busbar breaks down; if Si of only one feeder line is smaller than 0, the circuit is a fault circuit; if Si is smaller than 0 constantly, the circuit with the maximum high-frequency-band wavelet packet energy sum is determined as the fault circuit. According to RTDS simulation experimental verification, the method has the good accuracy, adaptability and the like.

The invention provides a capacity configuration method of a hybrid energy storage system for stabilizing wind power fluctuation. The hybrid energy storage system comprises a power type energy storage system and an energy type energy storage system. The method includes the steps that (1) the grid connection active power of wind power and the active power P (t) of the hybrid energy storage system are acquired, and a wavelet packet decomposition method is utilized to acquire power type energy storage power and energy type energy storage power respectively; (2) the hybrid energy storage system at different rated power P and under different capacities is configured, and the stabilizing effect of the hybrid energy storage system is analyzed; (3) according to the stabilizing effect and an improved particle swarm algorithm, the capacity of the hybrid energy storage system is configured. Compared with the prior art, according to the capacity configuration method of the hybrid energy storage system for stabilizing wind power fluctuation, a control policy is built according to the current electric quantity conditions, power magnitude required to be exerted and the rated power of the power type energy storage system and the energy type energy storage system and the improved particle swarm algorithm, and wind power fluctuation is stabilized and effectively controlled.

The invention discloses a health assessment and fault diagnosis method for rotating machinery based on fisher discriminant analysis and a mahalanobis distance, which belongs to the technical field of condition-based maintenance of the rotating machinery. The method comprises the steps of extracting an energy eigenvector based on wavelet packet decomposition, constructing a discriminant analysis function, conducting health status assessment, conducting fault detection on the rotating machinery, and finally conducting fault diagnosis on the rotating machinery. The method constructs a comprehensive frame integrating the status assessment, the fault detection and the fault diagnosis, solves the hotspot problem in comprehensive health management of the rotating machinery at present, achieves intelligent maintenance of the rotating machinery, can establish an assessment and diagnosis model without full life status monitoring data of the rotating machinery, reduces the dependence on historical data, and is very high in engineering applicability.

The invention relates to a failure line selection self-adapting method for a mixed line of a distribution network line-cable by utilizing the relative energy of a characteristic frequency band. The method is as follows: when the instant value of the zero sequence value of a bus is out of limit, a failure line section device instantly starts and records waves; a morphological filter is used for carrying out filter pre-treatment on the transient zero-sequence currents of temporary state of each line; a wavelet packet is applied for decomposing, the characteristic frequency bands of the transient zero-sequence currents of temporary state of each line are confirmed, the component of a stable state and the information of other frequency bands are eliminated and the line selection margin is improved according to the view of energy maximizing; the sizes of the relative energies in the front 1/4 period and the last 1/4 period in the back period of the failure under the characteristic frequency bands are compared according to the principle that the capacitance and current of the failure line under the temporary state attenuates fast in the characteristic frequency bands, thus forming the criterion for failure line selection. Principle analysis and imitation show that the relative energy of the first 1/4 period and the last 1/4 period in the back period of the failure is utilized for realizing the line selection, thus amplifying the temporary characteristics of the failure, avoiding the effect of an intermittent corner on the accuracy of the line section caused by the saturation of CT. The method is accurate and reliable for line selection.

The invention belongs to the technical field of circuit-breaker failure diagnosis, and particularly relates to a method and device for diagnosing mechanical characteristic failures of a high-voltage circuit-breaker. The device comprises the circuit-breaker and further comprises a vibration sensor, a voltage conditioning element, an AD conversion element, a clock element, a power element, a central processing unit, a communication unit and a failure diagnosis upper computer. According to mechanical vibration signals in the motion process of the circuit-breaker, the vibration sensor, the voltage conditioning element, the AD conversion element, the clock element, the power element, the central processing unit, the communication unit and the failure diagnosis upper computer are utilized for achieving the mechanical characteristic failure diagnosis of the circuit-breaker. The method for diagnosing mechanical characteristic failures comprises the steps of conducting wavelet packet decomposition on vibration signals in the operation process of the high-voltage circuit-breaker, extracting characteristic vectors of the vibration signals in spectral entropy of each frequency band, and adopting a relevance vector machine algorithm to conduct failure diagnosis on the mechanical characteristics of the high-voltage circuit-breaker. The method and device can effectively diagnoses the mechanical characteristic failures of the circuit-breaker, and provide a basis for the state maintenance of the circuit-breaker.

The invention discloses a fault diagnosis method and device for a rolling bearing of a running gear of a locomotive. The method includes the steps of collecting vibration acceleration data of the rolling bearing of the running gear of the locomotive under different fault types, and grouping the data according to the fault types; obtaining frequency domain signals of the vibration acceleration data according to the grouped vibration acceleration data; conducting three-layer wavelet packet decomposition on the frequency domain signals, and constructing fault characteristic sets; randomly arranging the fault characteristic sets, using the front B sets as the training sets, and using the rear C sets as the testing sets, wherein the sum of B and C is equal to A, and B is larger than C; training the B training sets through a Naive Bayes classifier, and establishing fault diagnosis model based on Naive Bayes for the rolling bearing of the running gear of the locomotive; classifying the C testing sets according to the fault diagnosis model, and evaluating the classification performance of the fault diagnosis model according to the classification result and through the combination with the fault characteristic sets.

The invention discloses a high-voltage circuit breaker mechanical state monitoring and fault diagnosis method. The method comprises the following steps of 1) according to the historical fault data statistics result of high-voltage circuit breakers, carrying out an artificial fault simulation experiment on some common high-voltage circuit breakers to obtain fault data; 2) analyzing the fault current data, and extracting the current data characteristic quantity of each mechanism fault to be used as one of state diagnosis classification basis; 3) analyzing a fault vibration signal, adopting wavelet packet decomposition and sample entropy for processing high-frequency and low-frequency components to obtain corresponding wavelet packet relative energy and sample entropy respectively to be usedas vibration signal characteristic quantities; and 4) performing dimensionality reduction on the vibration signal characteristic quantities through principal component analysis to be used as one of state diagnosis classification basis, and carrying out state diagnosis on the circuit breaker by a support vector machine. By adoption of the method, the multi-dimensional information of the fault statecan be effectively utilized, so that the development of multi-parameter multi-dimensional mapping fault diagnosis of the circuit breaker can be promoted.

The invention discloses a method for predicting wind speed and power of a wind farm based on wavelet decomposition and a support vector machine. The method comprises: acquiring wind speed and power historical data of a whole wind farm in a preset time, to obtain a historical wind speed time sequence and a historical power time sequence of the wind farm; using a wavelet packet decomposition technology to perform wavelet packet decomposition on the historical wind speed time sequence, to obtain a low-frequency stage component, a middle-frequency stage component, and a high -frequency stage component of the historical wind speed time sequence; using a grey support vector machine prediction model to predict each component of the historical wind speed time sequence, and then using wavelet packet reconstruction to obtain short-period wind speed prediction data; using historical wind electricity power data and numerical weather prediction wind speed data as a training set to establish a grey support vector machine model, predicting wind electricity power; predicting the obtained wind speed prediction data and the wind electricity power prediction data through a RBF neural network, to obtain a final prediction value of the wind electricity power.

The invention discloses a voltage sag source identification method based on Hilbert-Huang transformation and wavelet packet energy spectra, and belongs to the field of electric energy quality analysis of electric power system. The method includes the steps: firstly, performing EMD (empirical mode decomposition) for a three-phase voltage signal to obtain IMF (intrinsic mode function) components; secondly, performing n-layer wavelet packet decomposition for the IMF components to obtain energy spectra of frequency bands; thirdly, setting a larger wavelet packet coefficient of low-frequency band energy into zero, and reconstructing wavelet packet coefficients corresponding to other frequency bands to obtain an IMF without low-frequency illusive components; finally, performing Hilbert transformation on the IMF without the illusive components to obtain an HH (Hilbert-Huang) spectrogram, and identifying voltage sag sources according to catastrophe points, amplitudes, harmonic waves and frequencies of the HH spectrogram. Different characteristics of different voltage sag sources can be identified from the HH spectrogram only by taking the amplitudes, the catastrophe points and the harmonic waves as characteristics, the voltage sag sources are differentiated, so that times of non-identification and mistaken identification are effectively decreased, and identification efficiency is improved.

The invention discloses a wireless sensor network fault diagnosis method, which comprises the following steps of: acquiring link quality signals of a wireless sensor network in a normal state and a fault state; performing wavelet packet decomposition and coefficient reconstruction by using a wavelet transform method, and extracting a characteristic vector of a fault; constructing a coding matrix by adopting an error correcting output coding method to realize network fault multi-classification; constructing a decision function of multi-classification problems by using an LSSVC learning mechanism, and establishing a relationship model between the system state and the characteristic vector; and identifying, diagnosing and processing a generated fault, a potential fault type and an area according to a network running decision function value. The method has wide application prospect in small and medium-scale WSN application system.

The invention discloses a probabilistic neural network-based tolerance-circuit fault diagnosis method, which comprises the following steps of: selecting a pulse signal source as the energization of a fault circuit to be detected; carrying out Monte Carlo analysis on the fault circuit so as to obtain an amplitude-frequency response signal of the fault circuit to be detected; carrying out three-layer wavelet packet decomposition on the amplitude-frequency response signal of the fault circuit so as to obtain low and high frequency coefficients of the amplitude-frequency response signal, carryingout threshold quantification on the wavelet packet decomposition coefficients, then carrying out wavelet packet reconstruction according to the lowest-layer low frequency wavelet packet decompositioncoefficients and the high frequency wavelet packet decomposition coefficients subjected to threshold quantification so as to complete the de-noising processing of the wavelet packet; calculating the band-gap energy of the response signal according to the low and high coefficients obtained after wavelet packet reconstruction, and constituting a fault characteristic vector by using the band-gap energy; and inputting the fault characteristic vector in a fault grader of the probabilistic neural network to realize circuit fault diagnosis. The method has the advantages of high right fault diagnosisrate, simple structure, short training time, high fault tolerance and strong extrapolation ability.

The invention belongs to the technical field of bridges, and discloses a method for identifying damage on inhaul cables of long-span cable-stayed bridges. The method includes building finite element models of cable-stayed bridges; applying simulated wind load to the finite element models and acquiring wind speed time-history curves of the inhaul cables; computing stress time histories of the inhaul cables under wind load effect on the basis of the wind speed time-history curves; carrying out lifting wavelet packet decomposition on the stress time histories and stress time histories of bridge inhaul cables in non-damage states, extracting wavelet packet signal component energy and utilizing energy accumulation variation values as characteristic values for identifying damage positions of thestay cables; acquiring lifting wavelet packet component energy difference, building BP-AdaBoost models for identifying structural damage degrees and computing the fatigue reliability of the inhaul cables on the basis of the structural damage degrees. The method for identifying the damage on the inhaul cables of the long-span cable-stayed bridges has the advantages of excellent adaptability and identification reliability.

The invention discloses an X-ray chest radiograph bone suppression processing method based on wavelet decomposition and a convolutional neural network. By adopting a convolutional neural network structure and using a chest radiograph image wavelet coefficient as the input, a wavelet coefficient image of a corresponding bone image or soft tissue image is predicted. The existing bone image or soft tissue image artificial neural network prediction method processes an original chest radiograph image by adopting a relatively complex contrast normalization method, whereas this method processes the input chest radiograph image in a wavelet domain, and can normalize the amplitude by adopting a simple method; and the existing bone image or soft tissue image artificial neural network prediction method needs to design an image feature extraction method as the input of the artificial neural network, whereas this method completes an image feature extraction process by directly using the wavelet decomposition image of the chest radiograph image as an input, training the convolutional neural network to learn automatically and optimizing the convolution kernel, so the image feature extraction method does not need to be designed.

The invention discloses a rotating machinery bearing fault diagnosis method. The method is characterized by, to begin with, carrying out wavelet packet decomposition on an original signal, and extracting first half of wavelet coefficients obtained after wavelet packet decomposition for reconstruction to obtain a reconstruction signal set; then, extracting corresponding characteristic values for reconstruction signals on the time domain and frequency domain, and carrying out pattern recognition by utilizing a BP nerve network to obtain fault classification weight values; fusing the fault classification weight values obtained by the time domain and frequency domain through a D-S evidence theory to obtain a final fusion result; and finally, selecting the maximum value of the fusion result asa decision making result of fault diagnosis, and obtaining a final result of unit diagnosis. The rotating machinery bearing fault diagnosis method not only greatly improves accuracy of fault diagnosis, but also can judge, diagnose and predicate different fault types of a rotating machinery bearing; and the method is better in effect than independent time domain and frequency domain analysis, and can improve fault classification accuracy and stability.

The invention discloses an aero-engine bearing fault diagnosing method. The method comprises: first, acquiring the vibration signal of a turbojet engine, the engine speed, the engine rotation speed, the engine exhaust temperature, the fuel flow, and the engine thrust; extracting the classical time-domain statistical characteristics, the frequency-domain characteristics of the various signals and obtaining the time-frequency domain characteristics based on wavelet packet decomposition; then using the deep Boltzmann machine to perform characteristics learning to the characteristic parameters of the various signals; then, proceeding to use the data integration technology to integrate the characteristics of the various sources learned by the deep Boltzmann machine; and finally, using the integrated characteristic parameters as the input of the classifier to the support vector machine, and classifying and identifying the engine fault. The method of the invention improves the identification precision and stability of the turbojet engine bearing fault, effectively mining the essential characteristics of data and greatly increasing the fault precision of the turbojet engine bearing.

The invention aims at providing a linear frequency modulation (FM) signal parameter estimation method based on small-wave-packet denoising and power spectral entropy, which includes the following steps: denoising signals in a multi-dimension small-wave-packet mode, and determining small-wave-packet function and small-wave-packet decomposition level; calculating power spectral entropy of signals denoised in a small-wave-packet mode, and setting an entropy feature data base of linear FM signals with different FM slope under the condition of different signal to noise ratios; carrying out interpolation operation for obtained discretized entropy features; fitting the curve after interpolation of a cubic spline function with a polynomial function, and obtaining FM slop of linear FM signals under the condition of different signal to noise ratios and relational expression with input entropy features; and estimating FM slop of linear frequency modulation (LFM) signals received by a receiver by utilizing the fit expression. The linear FM signal parameter estimation method based on small-wave-packet denoising and power spectral entropy is small in calculated amount and capable of estimating FM slop of LFM in real time under the premise of meeting the requirement for parameter estimation accuracy.

The invention discloses a module transfer method based on multiscale modeling. The method comprises the following steps: collecting original spectra of a host instrument and a slave instrument; by combining the characteristic of wavelet basis and the characteristic of the original spectrum of a sample, selecting the optimal wavelet basis to carry out wavelet multiscale decomposition on the spectrum to obtain wavelet coefficient; reconstructing the wavelet coefficient; respectively performing multivariate calibration on each layer of reconstructed spectrum; setting up a prediction model based on partial least squares method and leaving one cross-validation method for the spectrum after performing multivariate calibration to obtain a cross-validation root-mean-square error of the prediction model; performing model fusion on the prediction model by using weight number, and calculating the prediction root-mean-square error and related coefficient to evaluate the model transfer effect. Compared with a conventional model transfer method, the method greatly improves the model transfer efficiency and performance, and can be widely applied to fields of near-infrared and Raman spectrum.

The invention relates to an island detection method based on the wavelet packet energy spectrum. In the method, the wavelet theory is applied to decompose the signal into different frequency components, so that the fault information can be obviously displayed. The method is characterized by comprising the stages of signal processing and island identification and comprising the following specific steps: 1) directly measuring the voltage signal at the point of common coupling (PCC) and carrying out wavelet packet decomposition on the detected voltage signal; 2) reconfiguring the wavelet packet decomposition coefficient and extracting the signals in the frequency band ranges; 3) computing the energy characteristic value of each frequency band signal according to the energy expression shown in the specification; 4) constructing the fault characteristic vector T with number of dimensions being 2<j> by adopting the energy of the frequency band signals as the elements; 5) establishing a sample model and then determining the fault characteristic vector P according to the statistical average of the sample space; and 6) establishing mapping relationships between the energy characteristic vectors and the fault conditions, making a fault query table with the congruent relationships between the fault conditions and the parameter variation and storing the fault query table, identifying the faults based on the fault query table and simultaneously displaying the diagnosis results.

The invention discloses a composite optical fiber sensing system and a sensing method. By adopting the system and the method, the same positioning precision as phase-sensitive OTDR can be achieved. Moreover, high-frequency details of vibration can be obtained, the type of vibration can be identified accurately, and the false alarm rate of the system is effectively reduced. The phase-sensitive OTDR carried out detection by using reverse Rayleigh scattered light, the intensity of reflected light is extremely low, and the light intensity power of an interferometer is high. Therefore, light signals of the phase-sensitive OTDR can be easily submerged in signals of the interferometer. By introducing a FBG, the system successfully combines light paths and separates light signals of the interferometer and a scatterometer, and the system is relatively simple in structure and low in cost. By performing an improved moving average algorithm and a wavelet information entropy algorithm on Rayleigh scattered signals of a laser light source with ultra narrow line width, the accurate position of vibration can be worked out. Interference signals of the laser light source with ultra narrow line width contain rich frequency information, and through wavelet packet decomposition on the interference signals, the type of vibration can be identified via a neural network. The rate of false alarm is reduced.