59 results about "Vibration signal processing" patented technology

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 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 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 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 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 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.

The invention relates to the technical field of rotary mechanical vibration signal processing and fault diagnosis, and discloses a coal mine underground mechanical excitation identification method based on self-adaptive cepstrum exponential window filtering, which comprises the following steps: S1, preprocessing an original vibration signal; s2, constructing a band-pass filter to filter the preprocessed vibration signal; s3, performing equal-length segmentation on the vibration signal after band-pass filtering, and calculating a linear kurtosis value of each sub-segment; s4, obtaining an angle domain stable vibration signal; s5, adaptively determining a characteristic cepstrum boundary according to the cepstrum energy distribution; and S6, performing inversion on the cepstrum signal after cepstrum filtering to obtain a time domain forced excitation signal. The index window damping factor is automatically set by referring to the analytic relationship between the cepstrum delay and the suppression ratio, the limitation that a traditional cepstrum index window depends on empirical parameter estimation is overcome, cepstrum editing can adapt to different structures and working conditions, and the stability and effectiveness of system transfer characteristic suppression are guaranteed.

The utility model relates to the technical field of seat driving, and discloses a wireless somatosensory vibration system for a home theater, which comprises an audio signal processing end and a vibration driving end arranged in each seat of the home theater. The audio signal processing end comprises an audio signal processing module and a first Bluetooth module and is used for acquiring an audio signal output by a home theater sound system, quantizing the amplitude and frequency of the audio signal and then sending the audio signal; and the vibration driving end comprises a second Bluetooth module, a vibration signal processing module and a somatosensory vibrator, and is used for receiving the frequency and amplitude of the audio signal and generating a sine wave current signal to drive the somatosensory vibrator to vibrate. According to the utility model, the audio signal is analyzed to obtain the corresponding digital signal, so that the anti-interference performance of the signal is improved, and the signal is not easily interfered by the environment; and the Bluetooth module is used for broadcast transmission, so that the trouble of wiring is avoided, the cost is reduced, the quality and reliability of signal transmission are improved, and the film watching experience of a user is improved.

The embodiment of the invention discloses a hydroelectric generating set vibration signal processing method and a related device. The method comprises the steps of collecting a vibration signal of a hydroelectric generating set; taking the minimum information entropy as an optimization target function, and setting an optimization range of working parameters of a target decomposition algorithm according to the target function; according to a chaotic mapping mechanism, a sine and cosine optimization algorithm, a random walk perturbation algorithm and a t distribution variation strategy, an artificial chimpanzee army algorithm is improved; inputting the working parameters into an improved artificial chimpanzee army algorithm for iterative optimization, and outputting to obtain target working parameters; and inputting the target working parameter into a target decomposition algorithm, and performing modal decomposition of the vibration signal. Therefore, the decomposition precision of simulation signal analysis is improved, the noise reduction performance is optimized, noise suppression and effective information retention are realized, and a basis is provided for intelligent vibration monitoring and diagnosis of the hydroelectric generating set.

The application discloses a resonant gyroscope digital control system based on electromechanical synchronous sampling, which comprises a first preamplifier, a second preamplifier, a first A / D conversion unit, a second A / D conversion unit, a control unit, a D / A conversion unit and a low-pass filter. The control unit comprises a first demodulation unit, a second demodulation unit, a phase-locked loop and an automatic gain control unit and an NCO. The first preamplifier processes the vibration signal of a driving channel resonator, and the processed signal is converted into a digital signal by the first A / D conversion unit. The first demodulation unit demodulates the digital signal to obtain the phase and amplitude of the vibration signal. The phase-locked loop and the automatic gain control unit adjust the frequency increment of the NCO according to the phase and amplitude. The D / A conversion unit converts the driving signal into an analog signal. The low-pass filter filters the analog signal and outputs the filtered signal to the driving channel resonator. The second preamplifier processes the vibration signal of a detection channel resonator. The second A / D conversion unit converts the processed signal into a digital signal. The second demodulation unit demodulates the digital signal to obtain a rotation speed signal.

The invention provides an equipment vibration signal processing method and system suitable for a multi-noise condition, and the method comprises the steps: removing TF energy outside an IF ridge line track through the optimal fractional order wavelet transform FRWT of a signal, i.e., enabling the energy density on a time-frequency point to be represented by sharpening time frequency, and only carrying out the matching extraction of time frequency information in the IF track; the method has good performance for signals with energy concentrated in the direction of a time axis or a frequency axis in a time-frequency plane, can effectively solve the problem of signal interference under a multi-noise condition, and achieves the function of processing equipment vibration signals under the multi-noise condition. According to the invention, a self-matching extraction fractional order wavelet transform method SMEFRWT is adopted to accurately estimate and obtain a self-matching extraction operator which is used for matching a time-varying instantaneous frequency rule of a signal; an IF ridge line is accurately estimated by introducing a self-matching IF estimation operator; the method is suitable for high-resolution time-frequency analysis.

The embodiment of the application discloses a rotating equipment rotating speed estimation method based on hill peak identification and correlation analysis, belongs to the field of mechanical vibration signal processing, and comprises the following steps: collecting a vibration signal, using a Fourier transform method to calculate the frequency spectrum of the vibration signal, automatically identifying whether a hill peak exists in the frequency spectrum through a hill peak identification method, using a correlation analysis method to calculate the autocorrelation coefficient of an envelope signal or the vibration signal, using a smoothing filter to fit the autocorrelation coefficient to obtain a new autocorrelation coefficient, taking the two maximum value points in the new autocorrelation coefficient, obtaining two index position points corresponding to the two maximum value points, calculating the position difference of the two index position points, calculating the fundamental frequency according to the position difference, and calculating the rotating speed according to the fundamental frequency. The embodiment of the application can realize the rotating equipment rotating speed estimation based on the correlation analysis through the automatic identification of the modulation signal in the vibration signal waveform spectrum.

The invention discloses a vibration signal processing method, system and equipment of a tunnel boring machine. The vibration signal processing method of the tunnel boring machine comprises the following steps: obtaining tunneling parameters of the tunnel boring machine; judging whether the tunnel boring machine is in a tunneling state or not according to the tunneling parameters; if yes, original vibration signals of the tunnel boring machine in the tunneling process are collected; denoising the original vibration signal to obtain a target vibration signal; and identifying the surrounding rock category according to the target vibration signal. According to the embodiment of the invention, the vibration signal redundancy can be effectively reduced, the acquisition efficiency can be improved, the definition and the feature extraction effect of the vibration signal can be improved, and in addition, the vibration signal is utilized to perform real-time surrounding rock category identification, so that accurate classification of different surrounding rock categories can be realized.

The invention relates to a method for diagnosing deformation of a casing of an axial flow fan. The method comprises the following steps: (1) acquiring multi-source data; (2) vibration signal processing and spectrum analysis; (3) sound signal feature extraction: carrying out frequency domain analysis on the auscultation signal, extracting sound pressure level and frequency distribution features, judging a through-flow non-uniform region in combination with a vibration spectrum, and positioning a high-risk position of case deformation; (4) detecting the structure state of the casing; and (5) comprehensive diagnosis and fault positioning: if the following conditions are met at the same time, determining that the casing is deformed. The method has the advantages that (1) multi-dimensional fusion diagnosis: vibration, acoustics and structure detection data are combined, and the diagnosis accuracy is improved; and (2) quantitative analysis: realizing deformation degree grading and the like through quantitative indexes such as a frequency spectrum proportion and gap deviation.

The present invention relates to the technical field of transformer energy efficiency optimization, and discloses a method and system for dynamic energy efficiency optimization of transformers under multiple working conditions, including obtaining historical vibration signals of the transformer, and performing feature extraction and nonlinear analysis to obtain spectral characteristics and nonlinear characteristics; establishing a finite element model based on the change in the gap between core laminations according to the spectral characteristics and nonlinear characteristics; obtaining the real-time vibration signal of the transformer, and inputting the real-time vibration signal into the finite element model, calculating the gap data of the core laminations, and calculating the energy efficiency impact coefficient of the gap change on the transformer energy efficiency based on the gap data; and using an adaptive compensation mechanism to adjust the operating parameters of the transformer based on the energy efficiency impact coefficient. The present invention deeply combines vibration signal processing, nonlinear dynamics and energy efficiency optimization, effectively improving the evaluation accuracy and optimization effect of the transformer energy efficiency, providing an efficient solution for transformer operation and maintenance, and improving the operating efficiency and reliability of the transformer.

The application discloses an aero turboshaft engine fault diagnosis system and relates to the technical field of fault diagnosis. A collection module acquires horizontal, vertical and axial vibration signals; a processing module generates real-time characteristic vectors by introducing a dynamic short-time Fourier transform of a non-constant-width Gaussian window, a variational mode decomposition and a singular value decomposition; an incremental diagnosis module calculates the matching degree between real-time characteristic vectors or predicted characteristic vectors and known classes by a dynamic expansion network, determines whether to belong to the known classes or trigger an expansion mechanism according to an adaptive resonance theory, constructs a joint loss by using a Bayesian learning framework after expansion, and performs Gaussian process modeling, determines the loss by Bayesian optimization and updates network parameters; a prediction module generates predicted characteristic vectors when there is no fault; and a maintenance module sends or stores maintenance schemes as required, so that adaptive identification of the known classes and new fault classes is realized, the state can be predicted in advance, the operation safety of the engine is effectively ensured, and the maintenance cost is reduced.

The invention relates to the technical field of rotating machine vibration signal processing and fault early warning diagnosis, in particular to a rotating machine blade fault early warning method and device based on an auto-encoder and a medium. According to the method, the vibration acceleration sensor is installed on the equipment shell to collect signals, the sensor does not need to be directly installed on the blade, damage to the structure of the equipment shell due to punching is avoided, the integrity and stability of the overall structure of the rotating machine are guaranteed, and the accuracy and the reliability of the rotating machine are improved. Extra interference on equipment performance due to monitoring means is avoided, and the possibility that the blade fault risk is increased due to sensor installation is reduced.

The application provides a component abnormal sound diagnosis method based on a nonlinear dynamics neural network, and belongs to the technical field of acoustics, vibration signal processing and artificial intelligence, and comprises the following steps: constructing a multi-dimensional vibration-sound state feature vector according to collected three-axis acceleration of an excitation source and microphone sound pressure signals of a response source, and inputting the multi-dimensional vibration-sound state feature vector into a double-branch neural network, wherein the neural network comprises an abnormal sound mechanism classification branch neural network based on a deep nonlinear physical constraint loss function, which is used for analyzing the type of abnormal sound; and a material feature decoupling branch neural network based on fractional calculus, which is used for analyzing the material producing the abnormal sound.The application can solve the technical problem that the BSR abnormal sound AI automatic diagnosis scheme based on deep learning in the prior art has poor accuracy in abnormal sound identification and is difficult to guide component abnormal sound rectification work.