88 results about "Vibration signal processing" patented technology

The invention provides an earth surface anomaly monitoring data fusion system based on vibration signal processing, and relates to the technical field of earthquake precursor monitoring, and the system comprises a data collection module which is used for carrying out the real-time monitoring of the earth surface through a distributed multi-parameter sensor network, and obtaining the time sequence monitoring data related to the earthquake precursor; the signal processing module is used for processing the time sequence monitoring data by adopting a two-parameter joint optimization algorithm and outputting a separation signal component containing precursor information; the data fusion and state inversion module is used for carrying out fusion processing on the separated signal components by adopting a dual-time scale analysis framework and outputting a multi-scale precursor state estimation result and an uncertainty quantitative index; and the monitoring and early warning module is used for outputting earthquake precursor grading early warning information through a three-layer anomaly recognition architecture and probabilistic risk assessment. According to the invention, high-precision separation and identification of earthquake precursor related signals can be realized, and the false alarm phenomenon is reduced through an intelligent early warning mechanism.

The invention belongs to the field of aero-engine bearings, and provides a method and system for predicting the remaining service life of an aero-engine bearing, and the method comprises the steps: carrying out the processing of an original vibration signal collected in the operation process of the engine bearing through a Pearson correlation analysis method, carrying out feature extraction to obtain a plurality of feature sequences of common bearing RUL prediction statistics; smooth processing and cumulative transformation are carried out on the statistical feature sequence, monotonicity and tendency values are calculated, screening is carried out, and a screened cumulative feature sequence is obtained; and inputting the screened accumulated feature sequence into an attention full convolutional network (AFCN) model based on physical information to predict a life ratio, and calculating a residual service life prediction value through the life ratio. According to the method, through the full convolutional network fusing the bearing physical degradation mechanism and the attention mechanism, the key feature capturing capability and prediction precision in the long-time-sequence degradation process are improved, and technical support is provided for safe operation and maintenance of an aero-engine.

The invention relates to the technical field of gas extraction drilling machine vibration signal processing, in particular to a gas extraction drilling machine vibration signal self-adaptive noise reduction method based on multi-scale feature fusion. The method comprises the steps of collecting a vibration signal, converting the vibration signal into a two-dimensional waveform image, recognizing a drilling working condition area, constructing a multi-scale objective function to optimize VMD parameters, decomposing the signal and screening a dominant IMF component for reconstruction. Through multi-objective optimization and multi-feature fusion strategies of energy distribution and transient impact characteristics, the problems that in a traditional method, the noise reduction effect is poor, and the coal rock character recognition precision is insufficient are solved, the waveform similarity, the power spectrum density coincidence degree and the correlation coefficient are remarkably improved, and reliable guarantee is provided for coal mine safety production.

The invention relates to the technical field of transformer energy efficiency optimization, and discloses a dynamic energy efficiency optimization method and system for a transformer under multiple working conditions, and the method comprises the steps: obtaining a historical vibration signal of the transformer, carrying out the feature extraction and nonlinear analysis, and obtaining a frequency spectrum feature and a nonlinear feature; according to the spectrum features and the nonlinear features, a finite element model based on core lamination gap changes is established; acquiring a real-time vibration signal of the transformer, inputting the real-time vibration signal into the finite element model, calculating gap data of the iron core laminations, and calculating an energy efficiency influence coefficient of gap change on the energy efficiency of the transformer according to the gap data; and according to the energy efficiency influence coefficient, a self-adaptive compensation mechanism is adopted to adjust the operation parameters of the transformer. According to the method, vibration signal processing, nonlinear dynamics and energy efficiency optimization are deeply combined, the evaluation precision and optimization effect of the energy efficiency of the transformer are effectively improved, an efficient solution is provided for operation and maintenance of the transformer, and the operation efficiency and reliability of the transformer are improved.

The invention discloses a time-frequency analysis method for impact signal positioning based on transient scale extraction transformation, and belongs to the technical field of mechanical vibration signal processing. The method comprises the following steps: collecting a rotating machine fault vibration signal, and reconstructing a signal model through Hilbert transform and a Dirac function; a transition matrix is generated by using a Gaussian window function traversal model, and matching and Fourier transform are carried out in combination with a discretized scale basis function; solving a frequency partial derivative of a transformation result to generate a time redistribution operator, and redefining by a Dirac function to obtain a transient scale extraction operator; based on the sub-time-frequency representation of scale-based rotation discretization, screening optimal matching results of each time center through a maximum kurtosis value, and integrating the optimal matching results into a complete time-frequency representation; and finally, redistributing a time-frequency coefficient by using a transient extraction operator to realize accurate positioning of the impact component. According to the method, the problems of serious impact energy diffusion and insufficient positioning precision in existing time-frequency analysis are solved, and the time-frequency representation readability and the impact positioning reliability are remarkably improved.

The invention discloses a fault identification method and device for a rotating mechanism, computer equipment and the rotating mechanism. The method comprises the following steps: acquiring rotating speed information and a time domain vibration signal of the rotating mechanism; converting the time domain vibration signal into an angular domain vibration signal based on the rotating speed information; performing feature extraction on the angular domain vibration signal based on the autocorrelation matrix of the angular domain vibration signal and the filter coefficient to update the filter coefficient and obtain a target filter coefficient; and determining fault characteristics of the rotating mechanism based on a target vibration signal obtained by processing the angular domain vibration signal based on the target filtering coefficient. According to the method provided by the invention, the fault features of the unsteady vibration signals of the rotating mechanism can be effectively extracted, so that reliable fault diagnosis of the rotating mechanism is realized.

The invention discloses a vibration signal processing method based on self-adaptive wavelet packet and deep learning fusion, and belongs to the field of sewage plant equipment fault diagnosis. The method aims at solving the problems that traditional signal processing is poor in flexibility, the non-stationary signal processing capacity is weak, the deep learning data requirement is large, and the high-frequency weak feature capturing capacity is limited. According to the method, the high-frequency acceleration sensor is adopted, the vibration signals of the sewage plant equipment are accurately collected, the self-adaptive wavelet packet decomposition technology is applied, the primary function is dynamically selected, the number of decomposition layers is optimized, self-adaptive threshold noise reduction is achieved, and the signal processing quality is improved. Meanwhile, in combination with a one-dimensional convolutional neural network and a bidirectional LSTM model, local and global features of the signal are extracted respectively, and pre-processed data are formed through gating weighted fusion. According to the method, the signal-to-noise ratio and the weak fault detection rate are remarkably improved, feature redundancy and data requirements are reduced, the calculation efficiency and diagnosis accuracy are improved, the method is suitable for sewage plant equipment fault diagnosis, and the industrial applicability is enhanced.

The invention belongs to the field of hydroelectric generating set monitoring, and discloses a set vibration signal noise reduction and feature extraction method based on IAVMD and WOA, and the method comprises the steps: constructing a comprehensive evaluation index comprising an energy difference, an average energy entropy and a center frequency variation coefficient; combining an adaptive variational mode decomposition method and a whale optimization algorithm to obtain an optimal decomposition layer number K and a penalty factor; calculating an energy entropy and a Pearson correlation coefficient of each intrinsic mode component; screening the K intrinsic mode components through a double-threshold mechanism; and calculating to obtain a denoised unit vibration signal time sequence and fault features according to the screened intrinsic mode components. According to the method, the problems of large noise interference, fuzzy characteristics, parameter dependence on experience and the like in a traditional method are solved, the precision and efficiency of unit vibration signal processing are remarkably improved, nonlinear dynamic characteristics in unit vibration signals are captured through multi-scale analysis, and the sensitivity and diagnosis accuracy of early weak faults can be improved.

The invention provides an intelligent anomaly detection method and system based on a convolutional flow adversarial network, and relates to the technical field of anomaly detection, and the method comprises the steps: collecting a full-life-cycle vibration signal of equipment, processing the full-life-cycle vibration signal into a time-frequency diagram, and dividing the time-frequency diagram into a normal training set and a full-cycle test set; constructing a convolutional flow adversarial network comprising a generator and a discriminator; pre-training the generator, and alternately optimizing the discriminator and the generator; and constructing an abnormal state detection model by using the trained generator to realize full-cycle test set online detection. The method can accurately capture normal features, is sensitive to early abnormality, reduces the risk of mode collapse, is high in stability, provides a probability reference to reflect fault evolution, can filter noise, and is good in robustness.

The invention belongs to the technical field of engineering machinery intelligence and construction quality detection, and provides an intelligent compaction degree detection system and method integrated on a road roller. The detection system comprises a multi-mode sensing unit which comprises a vibration sensing module, a machine vision module, an inertia measurement positioning module and a flatness detection module; the detection method comprises the following steps: S1, synchronously collecting data; s2, vibration signal processing and compaction index calculation; s3, image analysis and apparent feature extraction; s4, a multi-source data fusion and machine learning model; s5, positioning and drawing; in conclusion, the invention provides the intelligent compaction degree detection system and method integrated on the road roller. The method is reasonable in design and simple to operate, can realize real-time, comprehensive, lossless and high-precision detection of the compaction degree, and can evaluate the construction apparent quality at the same time, so that the method is suitable for industrial popularization.

The invention discloses a fault diagnosis system for an aviation turboshaft engine, and relates to the technical field of fault diagnosis. An acquisition module acquires horizontal, vertical and axial vibration signals; the processing module is used for generating real-time feature vectors by introducing dynamic short-time Fourier transform, variational mode decomposition and singular value decomposition of an unfixed-width Gaussian window; the incremental diagnosis module calculates the matching degree between a real-time feature vector or a prediction feature vector and a known class through a dynamic expansion network, selects to belong to the known class or triggers an expansion mechanism according to an adaptive resonance theory, constructs joint loss by using a Bayesian learning framework after expansion, and performs Gaussian process modeling; loss is determined through Bayesian optimization, and network parameters are updated; the prediction module generates a prediction feature vector when there is no fault; the maintenance module sends or stores a maintenance scheme according to needs, self-adaptive recognition of known classes and new fault classes is achieved, the state can be pre-judged in advance, the operation safety of the engine is effectively guaranteed, and the maintenance cost is reduced.

The invention discloses a fracturing pump multi-cylinder vibration signal processing method and device, equipment, a medium and a product. A vibration data sequence and a key phase pulse signal are obtained, and the vibration data sequence is vibration data collected by a vibration sensor installed between adjacent cylinder bodies of a fracturing pump; the key-phase pulse signals are key-phase pulse signals collected by a phase sensor installed at the crankshaft part of the fracturing pump, then carrying out decorrelation on the vibration data sequence to eliminate the correlation of the vibration data sequence, then carrying out independent analysis on the vibration data sequence after decorrelation, outputting a plurality of vibration data sequences to be matched, and outputting the vibration data sequences to be matched; and finally, based on the key phase pulse signal, matching the plurality of to-be-matched vibration data sequences with the adjacent cylinders to obtain a target vibration data sequence corresponding to each cylinder, so that vibration data with stronger feature information can be extracted while the use amount of sensors is remarkably reduced and the cost and complexity are reduced, and the accuracy of the vibration data is improved. Therefore, the accuracy and timeliness of fault diagnosis of the fracturing pump are effectively improved.

The invention discloses a vibration signal processing method, device and equipment and a computer readable storage medium, and belongs to the technical field of signal processing. The method comprises the steps that an original vibration signal matrix is obtained, the original vibration signal matrix comprises a plurality of first matrix elements, and any first matrix element comprises a vibration signal obtained by any sampling of any sampling point at any time; the original vibration signal matrix is processed, a representative vibration signal matrix is obtained, the representative vibration signal matrix comprises a plurality of second matrix elements, and any second matrix element comprises a vibration signal of any sampling point at any time; determining a third matrix element in the second matrix elements; determining a fourth matrix element in the original vibration signal matrix according to the sampling point and time corresponding to the third matrix element; and according to the sampling point, the time and the vibration signal corresponding to the fourth matrix element, determining a fifth matrix element meeting the condition in the fourth matrix element. The method improves the processing efficiency of the vibration signal.

The application discloses a kind of transfer learning methods considering non-common category sample, it is related to bearing fault diagnosis method technical field.The method includes the following steps: first, the original vibration signal is processed into graph sample;Then it is extracted using recursive multi-head graph attention residual network;Finally, using MDD dynamic migration mode, the source domain feature is migrated to target domain, wherein, in the process of dynamic migration, non-target domain class filter is used to realize non-target domain class migration;The method can improve the utilization efficiency of big data source domain and fault diagnosis precision.

A stylus includes a vibration device, a driving circuit, a detection circuit, and a processor. The vibration device generates vibrations. The driving circuit generates a driving signal that drives the vibration device. The detection circuit detects an actual vibration of the vibration device and generates a vibration signal corresponding to the actual vibration. The processor compares the driving signal with the vibration signal, and performs feedback control on the driving signal based on a result of comparing the driving signal with the vibration signal. The processor performs the feedback control such that a phase difference between the driving signal and the actual vibration becomes substantially π / 2.

The present invention discloses a distributed acoustic wave sensing device and method for monitoring wave impact force. The device includes a vibration sensing optical fiber, an anchoring unit, a distributed optical fiber acoustic wave sensing demodulator, a vibration signal processing unit, and an ocean wave impact force inversion unit. The method comprises: fixing the vibration sensing optical fiber to the coast impacted by waves via the anchoring unit; the distributed optical fiber acoustic wave sensing demodulator transmits the monitored ocean wave vibration signal to the vibration signal processing unit for preprocessing; the vibration signal processing unit transmits the processed optical fiber vibration amplitude signal to the ocean wave impact force inversion unit; a calibration experiment obtains an optical fiber vibration amplitude signal and an ocean wave impact force training dataset, constructs an attention convolutional neural network model for training; and the ocean wave impact force inversion unit uses the attention convolutional neural network model to establish a correspondence between the optical fiber vibration amplitude signal and the ocean wave impact force, thereby obtaining the actual ocean wave impact force on the coast. The present invention achieves accurate monitoring of ocean wave impact force on the coast.

The invention discloses a mixed-flow water turbine vibration signal processing method based on adaptive enhanced EEMD (ensemble empirical mode decomposition), and relates to the technical field of vibration signal analysis and processing. A vibration signal of the mixed-flow water turbine is collected, and wavelet noise reduction is carried out; self-adaptive frequency band weighted noise is injected into the noise-reduced signal, and a noise-added signal is obtained; eMD decomposition is carried out on the signal after noise adding, a stopping condition is modified into a double-constraint mode stopping criterion in the EMD decomposition process, and an IMF component set and a residual error are obtained by using double constraints of the number of extreme points and the residual error energy change rate; and effectively screening IMF components of the IMF based on a fault sensitivity index, and introducing a compensation item into a residual error to obtain a final decomposition result as a vibration signal processing result. Background noise is effectively suppressed through frequency band weighted noise injection, and modal aliasing is effectively suppressed through a double-constraint stop criterion and fault sensitivity screening, so that fault features can be separated more accurately, and the signal-to-noise ratio can be improved.

The invention discloses a power equipment vibration signal processing method based on an interpretable wavelet threshold network. The method comprises the following steps: acquiring vibration data of key parts of power equipment; inputting the vibration data into a pre-trained fault diagnosis model, and detecting a fault feature matrix of each frequency band channel of the vibration data by using each wavelet threshold network; integrating the fault feature matrixes of different channels by using a channel-frequency dual-domain collaborative attention network, and performing weighted fusion on the fault feature matrixes of different frequency bands to obtain fusion features; using a global energy pooling layer to extract an average energy feature of each frequency band channel from the fusion feature as a discriminative feature; processing the discriminative features by using a fault classification layer, and predicting a fault type classification result; according to the method, noise robustness enhancement and fault sensitive feature depth extraction can be realized, and the fault classification precision and the reliability of a diagnosis result are remarkably improved.

The invention discloses a vibration signal de-noising method and device, and belongs to the technical field of vibration signal processing, and the method comprises the steps: determining an initial de-noised slice signal of a slice signal, a frequency domain feature of the slice signal, and a frequency domain feature of the initial de-noised slice signal according to a plurality of continuous slice signals of a target vibration signal; determining a noise spectrum of each slice signal according to the frequency domain characteristics of the slice signals and the frequency domain characteristics of the initial de-noised slice signals, and iteratively optimizing de-noising parameters according to the noise spectrums to obtain optimal de-noising parameters; and performing denoising reconstruction on the slice signal according to the optimal denoising parameter to obtain a denoised signal of the target vibration signal. According to different frequency domain characteristics of each slice vibration signal, the denoising parameters are dynamically adjusted, and the accuracy and efficiency of vibration signal denoising are improved.

The invention relates to the technical field of household small stirrers, and discloses a balance weight balanced stirrer control system, which comprises a vibration signal processing module used for carrying out filtering and fast Fourier transform processing on a vibration signal; the unbalance judgment module is used for comparing the amplitude value with a preset threshold value, judging whether the food materials are in balance weight unbalance or not, synthesizing the amplitude, frequency and phase characteristics and outputting an unbalance coefficient; the rotating speed adjusting module is used for adjusting the rotating speed of the motor according to an unbalance coefficient if the balance weight is judged to be unbalanced, starting periodic positive and negative rotation, and correcting a PID parameter of the output torque of the motor by adopting a self-adaptive PID algorithm until the amplitude value is recovered to be below a preset threshold value; the control parameter determination module is used for recording the vibration characteristics and control parameters corresponding to the food material types and the use amounts, and determining optimal control parameters based on a multi-parameter optimization algorithm of a support vector machine; accurate recognition and rapid correction of balance weight unbalance are achieved, vibration noise is reduced, the service life of equipment is prolonged, and the stirring uniformity is improved.

The invention relates to the technical field of vision measurement and vibration signal processing, in particular to a structure vibration signal extraction method under adverse environment interference. The method comprises the steps of collecting a structure vibration image through a camera, preprocessing the image and constructing a space-time matrix, and realizing noise reduction by using singular value decomposition. And compressing the space-time matrix into a one-dimensional vibration time sequence through displacement field estimation and space averaging. According to a delay embedding method, a one-dimensional vibration time sequence is reconstructed into a two-dimensional phase space matrix, singular value decomposition is applied again, and effective separation of a real vibration signal and a camera motion interference signal is achieved. By introducing the singular value decomposition and embedding reconstruction technology, accurate and efficient structural vibration signal extraction is realized, and the requirements for accuracy and real-time performance of vibration data in engineering application are met.

The application discloses a kind of fracturing pump multi-cylinder vibration signal processing method, device, equipment, medium and product, by obtaining vibration data sequence and key phase pulse signal, vibration data sequence is the vibration data collected by vibration sensor installed between adjacent cylinder body of fracturing pump, key phase pulse signal is the key phase pulse signal collected by phase sensor installed in crankshaft part of fracturing pump, then the correlation of vibration data sequence is eliminated by decorrelating vibration data sequence, the vibration data sequence after decorrelation is analyzed independently, output multiple vibration data sequences to be matched, finally based on key phase pulse signal, multiple vibration data sequences to be matched are matched with adjacent cylinder, the target vibration data sequence corresponding to each cylinder is obtained, can significantly reduce the amount of sensor, reduce cost and complexity while extracting the vibration data with stronger feature information, to effectively improve the accuracy and timeliness of fracturing pump fault diagnosis.

The application belongs to the field of big data learning models and provides a rotating machinery characteristic frequency extraction method under strong interference, which is based on the optimal balance parameter alpha in VMD decomposition roughly positioned according to the set reference modal correlation 最优 The balance parameter alpha of each decomposition is locally optimized by combining the sparrow search optimization algorithm. The modulus K of decomposition is adaptively determined by the iteration decomposition times, and the improved recursive VMD method avoids the influence of the inaccurate preset decomposition number and the balance parameter on the decomposition effect. The application is applied to the constructed simulation signal to achieve the optimal decomposition effect that can be achieved by the VMD method, and is applied to the pump cavitation flow-induced vibration signal processing to successfully achieve the effective extraction of the fluid machinery flow-induced vibration characteristic frequency under the condition of low signal-to-noise ratio.

The application discloses a vortex flowmeter anti-vibration signal processing method, and relates to the technical field of vortex flowmeter signal processing. The original voltage signal of the vortex flowmeter is collected, and after frame division, pre-emphasis and windowing preprocessing, time-frequency characteristic parameters reflecting the signal state are extracted and an observation sequence is formed. The sequence is input into a probability model trained by samples, and the probability distribution belonging to each predefined working condition is obtained. Finally, the most possible working condition is determined through state inference, the accurate identification of the working condition of the vortex flowmeter is realized, and the vibration interference mark is marked. The application realizes dynamic identification and tracking of the working condition by constructing a hidden Markov model, breaks through the limitation of traditional static filtering, adopts a joint time-frequency characteristic fusion method, constructs an accurate signal fingerprint from multiple dimensions, significantly improves the identification sensitivity, utilizes the time sequence characteristics of the model, decodes the state sequence, and makes the identification result more in line with the physical process law, so that the anti-interference ability and reliability are greatly improved.

The invention discloses a heading machine inertial navigation positioning measurement method, and relates to the field of image identification and positioning measurement, and the method comprises the following steps: asymmetrically arranging permanent magnet beacons along a tunnel according to a preset interval, measuring and recording accurate coordinates and magnetic characteristic parameters of each beacon, and constructing an underground magnetic fingerprint map; motion parameters, geomagnetic field data and vibration signals of the heading machine are collected through an inertial measurement unit, a magnetometer and a vibration sensor; processing the geomagnetic field data, identifying a preset magnetic beacon by detecting the sudden change of the geomagnetic field intensity, and obtaining an absolute position reference point; analyzing the spectrum characteristics of the vibration signals, and estimating the slip rate of the cutterhead according to the mapping relation between the characteristic frequency and the rock stratum hardness; and carrying out data fusion on the absolute position reference point, the slip rate observation value and an inertial navigation calculation result. The method is used for solving the technical problem that in the prior art, displacement measurement is not accurate due to slipping when a heading machine cutterhead conducts heading in a complex rock stratum.

The present invention discloses a method for constructing a bearing vibration signal processing model, a model and a signal classification method. By calculating the distances of multiple feature vectors, time-domain and frequency-domain loss functions are constructed, which are then used to train an encoder. By minimizing the difference in different distances in the time-domain and frequency-domain loss functions, the present invention can guide the encoder to extract similar feature representations in the signal, causing them to aggregate in the feature space while separating dissimilar features. When the trained encoder (a convolutional neural network with an attention mechanism) in the present invention processes vibration signals of unknown fault types, it can find that some feature representations in the signal are different from those of other signals, thus aggregating these feature representations in the feature space and distancing them from the feature representations of other signals, thereby effectively realizing the recognition of vibration signals of unknown fault types.

The present application relates to the technical field of fault detection, in particular to a fault detection system for a smart wharf and a building method, the fault detection system comprises: a data acquisition module for acquiring vibration signals of port equipment; a processing module for signal processing of the vibration signals, judging whether the vibration signals after signal processing are fault data; an extraction module for extracting fault features of the fault data according to a deep learning method, judging the fault type of the port equipment according to the fault features; a maintenance module for maintaining the port equipment according to the fault type, and changing the fault data after maintenance into normal data. The present application solves the problem of not timely discovering the fault of the port equipment in the prior art, which affects the safety of the equipment and the person or causes an accident.

The utility model discloses a vibration transmitter, belongs to the technical field of instruments and meters, and particularly relates to a two-wire system vibration transmitter based on an HART protocol, which comprises a magnetoelectric vibration sensor, a vibration signal processing module, a master control CPU, a current output module and a communication module. The magnetoelectric vibration sensor collects signals, the output end of the magnetoelectric vibration sensor is connected with the input end of the vibration signal processing module, the main control CPU is connected with the output end of the vibration signal processing module, the current output module and the communication module are connected with the main control CPU, and the current output module is connected with the communication module. According to the utility model, the field programmability of the measuring range is realized through the HART protocol, a user can freely adjust the measuring range according to actual requirements, the requirement of frequently replacing a transmitter due to mismatching of the measuring range is avoided, the long-term operation cost is reduced, the operation process of measuring range adjustment is simplified, and the working efficiency is improved.

This application discloses a fault identification method, apparatus, computer equipment, and rotating mechanism for a rotating mechanism. The method includes: acquiring the rotational speed information and time-domain vibration signal of the rotating mechanism; converting the time-domain vibration signal into an angular-domain vibration signal based on the rotational speed information; extracting features from the angular-domain vibration signal based on the autocorrelation matrix and filtering coefficients to update the filtering coefficients and obtain target filtering coefficients; and determining the fault characteristics of the rotating mechanism based on the target vibration signal obtained by processing the angular-domain vibration signal using the target filtering coefficients. The method provided in this application can effectively extract fault characteristics from the unsteady-state vibration signal of a rotating mechanism, thereby achieving reliable fault diagnosis of the rotating mechanism.

The invention relates to the field of rotary mechanical equipment vibration signal processing and rotor fault diagnosis, and provides a rotor rub-impact identification method and system based on cyclic spectrum eigen orthogonal decomposition, and the method comprises the steps: continuously collecting vibration signals of a continuously operating gas turbine and a combined cycle unit support bearing at equal intervals and equal length, and carrying out the preprocessing; a cyclic spectrum correlation mapping graph of the preprocessed vibration signals of the equal-length supporting bearing is obtained, a two-dimensional cyclic spectrum correlation mapping graph is obtained through amplitude normalization, and discrete estimation is carried out; constructing a snapshot matrix and performing intrinsic orthogonal decomposition; and determining the number of reconstructed modes according to the change condition of the modal energy ratio of each order, reconstructing an intrinsic orthogonal decomposition result, carrying out full-band integration along the spectral frequency direction to obtain a fault mode demodulation spectrum, and analyzing the correlation between the fault mode demodulation spectrum and the two-dimensional cyclic spectrum coherence mapping graph to determine the fault occurrence time. According to the method, the fault mode can be accurately extracted, the fault occurrence time can be identified, and the industrial field requirement of unit vibration monitoring in a continuous monitoring scene is met.