CN115389186A - Abnormal analysis method, device, terminal and storage medium - Google Patents

Abstract

The embodiment of the application discloses an anomaly analysis method, an anomaly analysis device, a terminal and a storage medium, which are applied to an airframe structure of an aircraft, wherein the method comprises the following steps: acquiring initial data of an engine body, wherein the initial data comprises noise data and vibration data of the engine body and is used as basic data for actively reducing noise of the engine body; storing the initial data; performing time-frequency analysis on the stored initial data to obtain time-frequency analysis data; processing the time-frequency analysis data to obtain advanced analysis data; and carrying out anomaly analysis on the organism according to the time-frequency analysis data and the advanced analysis data so as to determine the anomaly of the organism. The embodiment of the application can store the acquired initial data of the machine body in real time, effectively prevents the noise data and the vibration data from being lost and covered, and can apply the stored noise data and the stored vibration data to the abnormal analysis of the machine body, thereby improving the utilization rate of the noise data and the vibration data.

Description

Abnormal analysis method, device, terminal and storage medium

technical field

The present invention relates to the technical field of anomaly analysis, in particular to an anomaly analysis method, device, terminal and storage medium.

Background technique

At present, ANC (Active Noise Control) technology is mainly used for noise reduction in the aircraft cabin. By collecting the noise signal of the airframe in real time, it actively sends out the reverse sound wave corresponding to the noise signal, so as to achieve noise reduction in which the sound waves cancel each other out. Effect. However, when performing the above noise reduction operation, on the one hand, the noise signal will be updated in real time with the acquisition time; The real-time update of the acoustic signal, the historical data of the noise signal will be completely overwritten.

Since the noise signal is not only used to represent the noise level, but also to represent the state of the aircraft, for example, the abnormal diagnosis of the aircraft's body structure can be performed through the noise signal, so the historical data of the noise signal is covered, which also makes it unable to be applied to Abnormal state diagnosis and structural failure analysis of aircraft.

In view of this, it is necessary to develop an abnormal analysis method, device, terminal and storage medium to solve the above problems.

Contents of the invention

The embodiments of the present application provide an abnormality analysis method, device, terminal and storage medium, which can effectively prevent the noise data and vibration data of the body from being lost or overwritten, and can improve the utilization rate of the noise data and vibration data.

In order to solve the above technical problems, the embodiments of the application disclose the following technical solutions:

On the one hand, there is provided an anomaly analysis method applied to the body structure of an aircraft, the method comprising: acquiring initial data of the body, the initial data including noise data and vibration data of the body, and the initial data as a reference The basic data of active noise reduction of the body; storing the initial data; performing time-frequency analysis on the stored initial data to obtain time-frequency analysis data; processing the time-frequency analysis data to obtain further advanced analysis data; according to the time-frequency analysis data and the advanced analysis data, abnormality analysis is performed on the body to determine the abnormality of the body.

Optionally, before storing the initial data, the method further includes: performing split processing on the initial data to obtain split data of the initial data, and the split data is used to perform active noise reduction on the airframe.

Optionally, performing split processing on the initial data to obtain split data of the initial data includes: performing filtering processing on the initial data; copying the filtered initial data to obtain the Triage data for initial data.

Optionally, it further includes: uploading the offloaded data with a delay of a first preset duration, and storing the initial data after offloading processing with a delay of a second preset duration; wherein, the first A preset duration is shorter than the second preset duration.

Optionally, the advanced analysis data includes wavelet coefficients, Mel-frequency cepstral coefficients and spectral centroid features of the initial data, and the time-frequency analysis data is processed to obtain advanced analysis data, including: Wavelet analysis, Mel-frequency cepstral coefficient extraction and spectral centroid feature extraction are performed on the time-frequency analysis data.

Optionally, performing abnormal analysis on the body according to the time-frequency analysis data and the advanced analysis data includes: inputting the time-frequency analysis data and the advanced analysis data into a classifier, A classification result is obtained; and an abnormality of the body is determined according to a comparison result of the classification result with the historical abnormal data of the body.

Optionally, performing abnormal analysis on the body according to the time-frequency analysis data and the advanced analysis data includes: monitoring the body according to a comparison result between the time-frequency analysis data and a preset range status.

Optionally, the method further includes: performing spectrum analysis on the split data; generating a control signal according to the split data after spectrum analysis; sending the control signal to a noise reduction device, so that the noise reduction The device emits reverse sound waves for noise reduction.

Optionally, performing frequency spectrum analysis on the shunt data includes: acquiring vibration data and noise data in the shunt data; performing frequency spectrum analysis on the vibration data, and obtaining corresponding peak data from the vibration data ; Spectrum analysis is performed on the noise data to obtain the spectrum of the noise data; according to the spectrum of the peak data and the noise data, a reverse sound wave is generated, and the reverse sound wave is used to eliminate the peak data and the spectrum of the noise data the noise data.

In another aspect, a data processing device is provided, including: a data acquisition module, configured to acquire initial data of the body, the initial data includes noise data and vibration data of the body, and the initial data is used as a reference to the body Basic data for active noise reduction; a data storage module for storing the initial data; a time-frequency analysis module for performing time-frequency analysis on the stored initial data to obtain time-frequency analysis data; data processing A module for processing the time-frequency analysis data to obtain advanced analysis data; an abnormal analysis module for performing abnormal analysis on the body according to the time-frequency analysis data and the advanced analysis data to obtain An abnormality in the organism is determined.

Optionally, the device further includes a data splitting module, configured to: split the initial data to obtain split data of the initial data, and the split data is used to perform active noise reduction on the airframe.

Optionally, the data splitting module is further configured to: filter the initial data; copy the filtered initial data to obtain split data of the initial data.

Optionally, the data offloading module is further configured to: upload the offloaded data according to a first preset time delay, and store the offloaded initial data according to a second preset time delay ; Wherein, the first preset duration is shorter than the second preset duration.

Optionally, the advanced analysis data includes wavelet coefficients, Mel-frequency cepstral coefficients and spectral centroid features of the initial data, and the data processing module is further used to: perform wavelet analysis on the time-frequency analysis data, Mel frequency cepstral coefficient extraction and spectral centroid feature extraction.

Optionally, the abnormal analysis module is further configured to: input the time-frequency analysis data and the advanced analysis data into a classifier to obtain a classification result; The results are compared to determine the abnormality of the body.

Optionally, the abnormality analysis module is further configured to: monitor the state of the body according to a comparison result between the time-frequency analysis data and a preset range.

Optionally, the device further includes an active noise reduction module, configured to: perform spectrum analysis on the split data; generate a control signal according to the split data after spectrum analysis; send the control signal to the noise reduction device , so that the noise reduction device emits a reverse sound wave for noise reduction.

Optionally, the active noise reduction module is further configured to: acquire vibration data and noise data in the shunt data; perform frequency spectrum analysis on the vibration data, and acquire corresponding peak data from the vibration data; Spectrum analysis is performed on the noise data to obtain the spectrum of the noise data; according to the spectrum of the peak data and the noise data, a reverse sound wave is generated, and the reverse sound wave is used to eliminate the peak data and the noise data .

In yet another aspect, a terminal is provided, capable of performing the operations in the abnormality analysis method described above.

In yet another aspect, a storage medium is provided, the storage medium is used for storing a computer program, and the computer program is loaded by a processor to execute the abnormality analysis method as described above.

The above-mentioned technical solution has the following advantages or beneficial effects: by storing the collected initial data of the body including noise data and vibration data in real time, the initial data can be effectively prevented from being lost or overwritten, and the stored initial data can be applied to The abnormal analysis of the airframe improves the utilization rate of the initial data.

Description of drawings

In order to illustrate the technical solutions of the embodiments of the present invention more clearly, the accompanying drawings of the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description only relate to some embodiments of the present invention, rather than limiting the present invention. in:

FIG. 1 is an application scenario diagram of the abnormality analysis method provided by the embodiment of the present application;

Fig. 2 is a schematic flow chart of the abnormality analysis method provided by the embodiment of the present application;

FIG. 3 is a schematic flow chart of the abnormality analysis method provided by the embodiment of the present application;

FIG. 4 is a schematic flow chart of the abnormality analysis method provided by the embodiment of the present application;

FIG. 5 is a schematic flow chart of the abnormality analysis method provided by the embodiment of the present application;

FIG. 6 is a schematic structural diagram of an abnormality analysis device provided by an embodiment of the present application.

Detailed ways

The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the implementation methods in the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

In the drawings, the shapes and dimensions may be exaggerated for clarity, and the same reference numerals will be used throughout to designate the same or like parts.

Unless otherwise defined, the technical terms or scientific terms used herein shall have the usual meanings understood by those skilled in the art to which the present invention belongs. "First", "second" and similar words used in the patent application specification and claims of the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. Likewise, words like "a", "an" or "the" do not denote a limitation of quantity, but mean that there is at least one. Words such as "comprises" or "comprising" and similar terms mean that the elements or items listed before "comprising" or "comprising" include the elements or items listed after "comprising" or "comprising" and their equivalents, and do not exclude other component or object. "Up", "Down", "Left", "Right" and so on are only used to indicate the relative positional relationship. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

The aircraft in the embodiments of the present application may be various flight vehicles, such as airplanes, helicopters, unmanned aerial vehicles, space shuttles, rockets, etc., and the embodiments of the present application do not limit the types of aircraft.

Please refer to FIG. 1 , which is an application scenario diagram of the exception analysis method provided by the embodiment of the present application.

In this application scenario, it specifically includes a noise collection device 11 , a vibration collection device 12 , a data distribution device 13 , a memory 14 , a controller 15 , an abnormality analysis device 16 and a sounding device 17 .

Taking the flight scene of a civil aircraft as an example, the noise can refer to all the sounds produced by the aircraft during the flight, such as environmental sound, body structure sound, noise, etc., that is, the noise can be normal and not cause uncomfortable auditory effects on the human ear The normal sound can also be abnormal noise, howling and other noises that have an uncomfortable effect on human hearing. Correspondingly, the vibration can be the vibration frequency generated by the body mechanism of the aircraft, such as the vibration of the engine rotor of the aircraft, or it can be the abnormal vibration of the body structure, the vibration corresponding to the body structure that emits abnormal noise or howling. In the embodiment of the present application, the following initial data may include the above-mentioned noise data and vibration data.

The noise collection device 11 may be any device capable of collecting sound, such as an error microphone. In this application scenario, in order to ensure the comfort of passengers in the cabin, the noise collection device 11 may be installed in the seats of the cabin to collect various noise data in the cabin. In order to ensure the real-time collection effect of noise data, generally, two noise collection devices 11 can be installed at each seat.

The vibration collection device 12 may be any device capable of collecting vibration frequencies, such as an acceleration sensor, usually a three-phase vibration acceleration sensor. Generally, the vibration acquisition device 12 can be installed in a position with a higher vibration frequency of the aircraft, such as near the aircraft engine, on the wing skin of the aircraft, etc., to carry out real-time vibration acquisition in the above-mentioned frequently vibration-generating areas, There is generally no limit to the number of installations of the vibration collection devices 12 .

The data distribution device 13 may be any device capable of data distribution. In some embodiments, the data splitting device 13 may also have a filtering function to filter noises in the collected initial data, and split the initial data to ensure that at least one portion of the initial data will not be overwritten.

The storage 14 may be any device, terminal or server with a storage function. For example, databases, cloud storage servers, etc. The initial data after being distributed by the data distribution device 13 can be stored in the memory 14, so that the initial data in the memory 14 can be applied to abnormal analysis and status monitoring of the aircraft later.

The controller 15 may be any device, terminal or server with control functions. For example, actively control the server, actively control the terminal, and so on. The controller 15 can include components such as an integrated control chip, a signal conversion port, and an electrical conversion port. The controller 15 can generate a reverse sound wave according to the received initial data, and send a control command for sending the reverse sound wave to the sound generating device 17, For details about the reverse sound wave, please refer to the specific description below.

The anomaly analysis device 16 may be a device, a terminal, a server, etc. for performing anomaly analysis on an aircraft. In some embodiments, the anomaly analysis device 16 may output an anomaly analysis result for the aircraft according to the received initial data. For details about the abnormal analysis device 16 and the abnormal analysis results, please refer to the detailed description below.

The sound generating device 17 may be any device capable of emitting reverse sound waves, such as a secondary speaker. Generally, in order to ensure the effect of the sound generating device 17 emitting reverse sound waves, the sound generating device 17 can be integrated and installed in a box structure in the nacelle.

According to the above description, in the application scenario of the embodiment of the present application, the noise collection device 11 and the vibration collection device 12 can collect initial data including noise and vibration in real time, and perform data distribution processing through the data distribution device 13 . For the initial data after shunting processing, an initial data is stored in the memory 14, and the abnormal analysis of the state detection and the body structure of the aircraft by the abnormal analysis device 16; another initial data is sent to the controller 15, and the After processing, the reverse sound wave for active noise reduction is emitted by the sound generating device 17 .

It can be known from the above that the embodiment of the present application can store the initial data in real time to prevent the initial data from being overwritten during the process of collecting and using it for active noise reduction, resulting in loss of the initial data. In addition, by splitting the initial data, the initial data can be used for active noise reduction and anomaly analysis of the target aircraft, thereby effectively improving the utilization rate of the initial data.

It should be noted that the above application scenario diagram shown in FIG. 1 and its description content are provided for the purpose of illustration only, and are not intended to limit the scope of the present application. Those skilled in the art can make various modifications or changes based on the description of this application. For example, a database may also be included in the movie scene graph. For another example, one or more power supply modules for power supply, and other devices or modules may be added to the application scenario diagram. However, these changes and modifications do not depart from the scope of the present application.

Please refer to FIG. 2 , which is a schematic flowchart of an abnormality analysis method provided by an embodiment of the present application. The method provided in this embodiment can effectively prevent the initial data from being lost and overwritten, and can improve the utilization rate of the initial data. The method provided in this embodiment includes:

Step 210, acquiring initial data of the body.

The initial data refers to data related to sound, such as environmental sound, noise, noise, and generated vibration. In some embodiments, the initial data may include noise data and vibration data. The initial data can be used as basic data for active noise reduction of the airframe, for example, the initial data can be processed to generate reverse sound waves for active noise reduction.

In some embodiments, the initial data can be obtained through a sound collection device installed on the body. For example, the noise data can be acquired through the aforementioned noise acquisition device 11 (eg error microphone), and the vibration data can be acquired through the aforementioned vibration acquisition device 12 (eg vibration acceleration sensor).

Step 220, storing the initial data.

In some embodiments, the collected initial data can be stored in real time, for example, the initial data can be stored in an initial data database in real time, so that the initial data can be allocated and converted from the database later.

In some embodiments, before storing the initial data, the initial data may also be split to obtain split data of the initial data. For example, the aforementioned data splitting device 13 may be used to split the initial data. Among them, the shunt data can be used for active noise reduction on the body.

In some embodiments, the data distribution device 13 may have a filtering function. For example, the data distribution device 13 may perform filtering processing on the initial data to remove noise in the initial data, and the noise may refer to sounds that are not used in active noise reduction and abnormal analysis of the body. Specifically, the data distribution device 13 can attenuate the frequency components of the noise to an extremely low level according to the principle of band-pass filtering.

In some embodiments, the filtered initial data may be copied to obtain split data of the initial data. In this way, two copies of initial data can be simultaneously obtained through the data distribution device 13, so as to prevent the initial data from being overwritten due to real-time update.

The data distribution device 13 may also have a transmission function. In some embodiments, the split data may be uploaded with a delay of a first preset duration, and the initial data after split processing may be stored with a delay of a second preset duration. Wherein, the first preset duration may be shorter than the second preset duration. For example, the first preset duration can be 5ms, and the second preset duration can be 20ms, then the data distribution device 13 can upload the distribution data to the controller 15 with the first preset duration of low delay, and the same low delay The initial data is sent to the memory 14 for storage for a second preset duration. Since the abnormal analysis of the airframe is usually based on the flight period of the aircraft or a longer flight duration as the mission profile, active noise reduction is more real-time, so that the first preset duration can be shorter than the second preset duration.

Step 230, performing time-frequency analysis on the stored initial data to obtain time-frequency analysis data.

Time-frequency analysis refers to time-domain analysis and frequency-domain analysis. Time-domain analysis is to analyze the target signal in the time domain to analyze the stability, transient and steady-state performance of the target signal. For example, processing such as filtering, amplification, statistical feature calculation, and correlation analysis can be performed on the signal in the time domain. Taking the acquisition of the initial data of the battery of the aircraft as an example, time domain analysis can be used to obtain the moment or period when the battery howling occurs.

Frequency domain analysis refers to the analysis of the target signal in the frequency domain. Continue to take the analysis of the initial data of the aircraft battery as an example. By performing FFT transformation on the time domain signal after time domain analysis, the frequency domain signal that changes with frequency is obtained to obtain the peak frequency and frequency band of the initial data of the battery. .

Step 240, process the time-frequency analysis data to obtain advanced analysis data.

New time-frequency divided data can be obtained after time-frequency analysis is performed on the initial data. For example, the time-frequency analysis data can include time-domain signals, frequency signals, and analysis results of the initial data. In some embodiments, the advanced analysis data may include wavelet coefficients, Mel-frequency cepstral coefficients, and spectral centroid features of the original data. That is, based on the time-frequency analysis data, the initial data can be combined with relevant acoustic algorithms to further obtain advanced analysis data. For details about the advanced analysis data, please refer to the relevant description of step 250 .

Step 250: Perform abnormality analysis on the body according to the time-frequency analysis data and the advanced analysis data, so as to determine the abnormality of the body.

In some embodiments, wavelet analysis may be performed on the time-frequency analysis data. For example, fast Fourier transform (FFT) can be used to transform the time-frequency analysis data, and wavelet analysis can be performed on the signal of the initial data in the time domain and frequency domain. For example, the signal of noise data and vibration data can be analyzed by db3 wavelet The 5th layer decomposes and extracts relevant wavelet coefficients, such as extracting corresponding high-frequency coefficients.

Wavelet analysis can realize the subdivision of high-frequency signals and low-frequency signals, and obtain different analysis results. It can automatically adapt to the requirements of time-frequency signal analysis, so that it can focus on any details of the signal, and is especially suitable for non-linear applications in practical applications. Stable signals, such as transient signal mutation points, etc. For example, the position of the mutation point in the target signal can be extracted and its singularity can be judged by performing wavelet analysis on the target signal.

In some embodiments, Mel-frequency cepstral coefficient extraction can be performed on the time-frequency analysis data. Mel-frequency cepstral coefficients are used to calculate the spectral characteristics of a signal. Since the human ear has different auditory sensitivities to sound signals of different frequencies, the Mel-frequency cepstral coefficient can be used to reflect whether the target sound signal conforms to the auditory characteristics of the human ear.

In some embodiments, the power spectrum of the original data signal can be calculated by performing frame processing on the signal. Since the bass is easy to cover the treble, and the treble is difficult to cover the bass, the critical bandwidth of the sound masking at the low frequency is smaller than the high frequency, so the signal of the initial data can be filtered, and the energy of each signal in the filter can be calculated. It performs DCT transformation, calculates and extracts the corresponding Mel-frequency cepstral coefficients.

In some embodiments, spectral centroid feature extraction can be performed on the time-frequency analysis data.

Spectrum centroid feature is one of the important physical parameters to describe the properties of timbre. It is the center of gravity of the frequency component, and it is the frequency that is weighted and averaged by energy within a certain frequency range, and its unit is Hz. In the field of subjective perception, the spectral centroid feature can describe the brightness of the sound, and the material of the sounding object can be analyzed based on the brightness. In some embodiments, according to the frequency of the initial data and the time-frequency signal, the corresponding spectral centroid can be calculated based on the spectral centroid.

It can be seen from the above that after obtaining the time-frequency analysis data of the initial data, a variety of acoustic algorithm sets can be further combined to obtain more comprehensive and diverse advanced analysis data, so as to improve the efficiency and accuracy of subsequent abnormal analysis of the body sex.

Please refer to Figure 3, which is a schematic flowchart of the abnormality analysis method provided by the embodiment of the present application. The method provided by this embodiment includes:

Step 251: Input the time-frequency analysis data and the advanced analysis data into a classifier to obtain a classification result.

The classifier may be a device, device, terminal, or program for processing time-frequency analysis data and advanced analysis data. The classification result can be the type of abnormality corresponding to the body structure, for example, the classification result can be howling of the battery, unstable engine rotor, poor sealing of the hatch, etc.

Step 252: Determine the abnormality of the body according to the comparison result of the classification result and the historical abnormal data of the body.

In some embodiments, the classification results may be compared to the organism's historical abnormality data. For example, the classification result can be compared with the related analysis data of battery howling with the historical abnormal data corresponding to the abnormality, such as comparing the similarity in the wavelet analysis data of the two, or comparing the wavelet analysis data of the two, Mel The comprehensive similarity between the frequency cepstral coefficient and the spectral centroid feature determines whether the classification result is battery whine. Alternatively, the reliability of the classification result is determined, for example, the probability that the classification result is howling of the storage battery may be 80%.

In some embodiments, the classifier may be a machine learning model, such as a hidden Markov model. In some embodiments, the historical abnormal data can be used as training samples, and the abnormal classification results corresponding to the historical abnormal data can be used as labels to perform iterative training on the classifier, and update the parameters of the classifier to obtain a trained classifier to more accurately Obtain the classification results corresponding to the initial data.

In some embodiments, the state of the body can be monitored according to the comparison result between the time-frequency analysis data and the preset range. The preset range can be a reasonable range of the time-frequency signal corresponding to the sound emitted by the body under normal working conditions, that is, by comparing whether the time-frequency analysis data is within the preset range, the time period or frequency band in which the state of the body appears abnormal can be monitored. Thus, the utilization rate of the initial data is improved.

Please refer to Figure 4, which is a schematic flowchart of the abnormality analysis method provided by the embodiment of the present application. The method provided by this embodiment includes:

Step 410, performing frequency spectrum analysis on the split data.

In some embodiments, frequency spectrum analysis may be performed on the offload data to obtain subsequent data for active noise reduction. For details about performing frequency spectrum analysis on the offload data, reference may be made to FIG. 5 and its description.

Step 420: Generate a control signal according to the split data after spectrum analysis.

The control signal may include a control instruction to the noise reduction device, and the noise reduction device may be the aforementioned sound generating device 17, such as a secondary speaker. In some embodiments, the control signal may be to control the secondary speaker to emit sound waves for active noise reduction, so as to achieve the effect of active noise reduction on the body.

Step 430, sending the control signal to the noise reduction device, so that the noise reduction device emits a reverse sound wave for noise reduction.

The reverse sound wave refers to the sound wave with the same frequency as the noise and the opposite phase. The reverse sound wave can cancel the noise signal to achieve the effect of active noise reduction. In some embodiments, the noise reduction device can be controlled to emit reverse sound waves through a control signal.

It can be seen from the above that by applying the shunt data to the active noise reduction of the airframe, and applying the stored initial data to the abnormal analysis and status monitoring of the airframe, it can not only prevent the initial data from being overwritten and lost, but also effectively improve the accuracy of the initial data. Data utilization.

Please refer to Figure 5, which is a schematic flowchart of the abnormality analysis method provided by the embodiment of the present application. The method provided by this embodiment includes:

Step 411 , acquiring vibration data and noise data in the shunt data.

In some embodiments, the noise data can be acquired through the aforementioned noise acquisition device 11 , and the vibration data can be acquired through the aforementioned vibration acquisition device 12 , and the details of acquiring the initial data will not be repeated here.

Step 412 , performing frequency spectrum analysis on the vibration data, and obtaining corresponding peak data from the vibration data.

Peak data refers to frequency peaks that occur in vibration data. For example, frequency spectrum analysis can be performed on the vibration data of the engine rotor to obtain the first-order vibration peak value and the second-order vibration peak value of the engine.

Step 413 , perform spectrum analysis on the noise data, and obtain a spectrum of the noise data.

Spectrum refers to the abbreviation of frequency spectral density, which is the distribution curve of frequency. In some embodiments, spectrum analysis may be performed on the noise data to obtain a spectrum image, a spectrum curve, or related data values, etc. of the noise data.

Step 414: Generate a reverse sound wave according to the spectrum of the peak data and the noise data, and the reverse sound wave is used to eliminate the peak data and the noise data.

Because the initial data includes normal environmental sound, the working sound of the body, and also includes noise, abnormal sound caused by abnormal vibration, etc. In some embodiments, the peak data can be used as reference information, and the frequency spectrum of the noise data can be used as an offset value to generate a reverse sound wave corresponding to the peak data with the same frequency and opposite phase. Reference information refers to using the peak information as noise and abnormal noise to offset the peak data. The purpose is to eliminate the peak data as much as possible, so that the vibration frequency value corresponding to the peak data drops to the normal frequency range.

Please refer to FIG. 6 , which is a schematic structural diagram of an abnormality analysis device provided by an embodiment of the present application. Specifically, the apparatus may be integrated into network equipment, and the network equipment may be equipment such as a mobile terminal.

In some embodiments, the abnormal analysis device may include: a data acquisition module 61 , a data storage module 62 , a time-frequency analysis module 63 , a data processing module 64 , and an abnormal analysis module 65 .

In some embodiments, the data acquisition module 61 can be used to acquire initial data of the body, the initial data includes noise data and vibration data of the body, and the initial data is used as basic data for active noise reduction of the body The data storage module 62 can be used to store the initial data; the time-frequency analysis module 63 can be used to carry out time-frequency analysis to the stored initial data to obtain time-frequency analysis data; the data processing module 64 can be used for Process the time-frequency analysis data to obtain advanced analysis data; the abnormal analysis module 65 can be used to perform abnormal analysis on the body according to the time-frequency analysis data and the advanced analysis data to determine the Body abnormalities.

In some embodiments, the device further includes a data splitting module, configured to: split the initial data to obtain split data of the initial data, and the split data is used to perform active noise reduction on the body .

In some embodiments, the data splitting module is further configured to: filter the initial data; copy the filtered initial data to obtain split data of the initial data.

In some embodiments, the data offloading module is further configured to: upload the offloaded data according to a first preset time delay, and delay the offloaded initial data according to a second preset time length storing; wherein, the first preset duration is shorter than the second preset duration.

In some embodiments, the advanced analysis data includes wavelet coefficients, Mel-frequency cepstral coefficients and spectral centroid features of the initial data, and the data processing module is further used to: perform wavelet analysis on the time-frequency analysis data analysis, Mel frequency cepstral coefficient extraction and spectral centroid feature extraction.

In some embodiments, the abnormal analysis module 65 is further configured to: input the time-frequency analysis data and the advanced analysis data into a classifier to obtain a classification result; according to the classification result and the history of the body As a result of the comparison of the abnormality data, the abnormality of the organism is determined.

In some embodiments, the abnormality analysis module 65 is further configured to: monitor the state of the body according to a comparison result between the time-frequency analysis data and a preset range.

In some embodiments, the device further includes an active noise reduction module, configured to: perform spectrum analysis on the split data; generate a control signal according to the split data after spectrum analysis; send the control signal to the noise reduction the noise reduction device so that the noise reduction device emits a reverse sound wave for noise reduction.

In some embodiments, the active noise reduction module is further used to: acquire vibration data and noise data in the shunt data; perform frequency spectrum analysis on the vibration data, and acquire corresponding peak data from the vibration data; Spectrum analysis is performed on the noise data to obtain the spectrum of the noise data; according to the spectrum of the peak data and the noise data, a reverse sound wave is generated, and the reverse sound wave is used to eliminate the peak data and the frequency spectrum of the noise data. noisy data.

The number of devices and processing scales described here are used to simplify the description of the present invention. Applications, modifications and variations to the present invention will be apparent to those skilled in the art.

It can be understood that the method according to one or more embodiments of the present specification can be implemented by software, firmware or a combination thereof.

It should be understood that each embodiment in this specification is described in a progressive manner, the same or similar parts of each embodiment can be referred to each other, and each embodiment focuses on the difference from other embodiments . In particular, for the device and system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and for relevant parts, please refer to part of the description of the method embodiments. It should be understood that this specification discloses multiple embodiments, and the contents disclosed in these embodiments can be understood by referring to each other.

It should be understood that the foregoing describes specific embodiments of the present specification. Other implementations are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. Multitasking and parallel processing are also possible or may be advantageous in certain embodiments.

It should be understood that describing an element herein in the singular or showing only one in a drawing does not mean limiting the number of that element to one. Furthermore, modules or elements described or illustrated herein as separate may be combined into a single module or element, and modules or elements described or illustrated herein as a single may be split into a plurality of modules or elements.

It should also be understood that the terms and expressions used herein are for description only, and one or more embodiments of this specification should not be limited to these terms and expressions. The use of these terms and expressions does not mean to exclude any equivalent features shown and described (or parts thereof), and it should be recognized that various modifications may also be included within the scope of the claims. Other modifications, changes and substitutions may also exist. Accordingly, the claims should be read to cover all such equivalents.

Likewise, it should be pointed out that although the description has been made with reference to the current specific embodiments, those of ordinary skill in the art should recognize that the above embodiments are only used to illustrate one or more embodiments of this specification. Various equivalent changes or replacements can also be made without departing from the spirit of the present invention. Therefore, as long as the changes and modifications to the above-mentioned embodiments are within the scope of the spirit of the present invention, they will all fall within the claims of the present application. within the scope of the book.

It can be understood that the method according to one or more embodiments of the present specification can be implemented by software, firmware or a combination thereof.

It should be understood that each embodiment in this specification is described in a progressive manner, the same or similar parts of each embodiment can be referred to each other, and each embodiment focuses on the difference from other embodiments . In particular, for the device and system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and for relevant parts, please refer to part of the description of the method embodiments. It should be understood that this specification discloses multiple embodiments, and the contents disclosed in these embodiments can be understood by referring to each other.

It should be understood that the foregoing describes specific embodiments of the present specification. Other implementations are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. Multitasking and parallel processing are also possible or may be advantageous in certain embodiments.

It should be understood that describing an element herein in the singular or showing only one in a drawing does not mean limiting the number of that element to one. Furthermore, modules or elements described or illustrated herein as separate may be combined into a single module or element, and modules or elements described or illustrated herein as a single may be split into a plurality of modules or elements.

It should also be understood that the terms and expressions used herein are for description only, and one or more embodiments of this specification should not be limited to these terms and expressions. The use of these terms and expressions does not mean to exclude any equivalent features shown and described (or parts thereof), and it should be recognized that various modifications may also be included within the scope of the claims. Other modifications, changes and substitutions may also exist. Accordingly, the claims should be read to cover all such equivalents.

Likewise, it should be pointed out that although the description has been made with reference to the current specific embodiments, those of ordinary skill in the art should recognize that the above embodiments are only used to illustrate one or more embodiments of this specification. Various equivalent changes or replacements can also be made without departing from the spirit of the present invention. Therefore, as long as the changes and modifications to the above-mentioned embodiments are within the scope of the spirit of the present invention, they will all fall within the claims of the present application. within the scope of the book.

Claims (12)

1. An abnormal analysis method is characterized in that, being applied to the body structure of an aircraft, the method comprises: Acquire initial data of the body, the initial data includes noise data and vibration data of the body, and the initial data is used as basic data for active noise reduction of the body; storing the initial data; performing time-frequency analysis on the stored initial data to obtain time-frequency analysis data; Processing the time-frequency analysis data to obtain advanced analysis data; According to the time-frequency analysis data and the advanced analysis data, an abnormality analysis is performed on the body to determine the abnormality of the body. 2. The method according to claim 1, characterized in that, before storing the initial data, further comprising: performing split processing on the initial data to obtain split data of the initial data, the split data It is used to perform active noise reduction on the body. 3. The method according to claim 2, wherein said splitting said initial data to obtain split data of said initial data comprises: performing filtering processing on the initial data; The filtered initial data is copied to obtain split data of the initial data. 4. The method of claim 3, further comprising: uploading the offloaded data according to a first preset time delay, and storing the offloaded initial data according to a second preset time delay; Wherein, the first preset duration is shorter than the second preset duration. 5. The method according to claim 1, wherein said advanced analysis data comprises wavelet coefficients, Mel frequency cepstral coefficients and spectral centroid features of said initial data, said time-frequency analysis data Processing is performed to obtain advanced analysis data, including: performing wavelet analysis on the time-frequency analysis data, extracting Mel-frequency cepstral coefficients, and extracting spectral centroid features. 6. The method according to claim 1, wherein the abnormal analysis of the body according to the time-frequency analysis data and the advanced analysis data includes: Inputting the time-frequency analysis data and the advanced analysis data into a classifier to obtain a classification result; The abnormality of the body is determined according to the comparison result of the classification result and the historical abnormal data of the body. 7. The method according to claim 1, wherein the abnormal analysis of the body according to the time-frequency analysis data and the advanced analysis data includes: According to the comparison result of the time-frequency analysis data and the preset range, the state of the body is monitored. 8. The method according to any one of claims 2-4, further comprising: performing frequency spectrum analysis on the split data; generating a control signal according to the split data after spectrum analysis; The control signal is sent to the noise reduction device to cause the noise reduction device to emit a reverse sound wave for noise reduction. 9. The method according to claim 8, wherein said performing frequency spectrum analysis on said shunt data comprises: Obtain vibration data and noise data in the shunt data; performing frequency spectrum analysis on the vibration data, and obtaining corresponding peak data from the vibration data; performing frequency spectrum analysis on the noise data to obtain the frequency spectrum of the noise data; According to the spectrum of the peak data and the noise data, an inverse sound wave is generated, and the inverse sound wave is used to eliminate the peak data and the noise data. 10. An abnormal analysis device, characterized in that it comprises: A data acquisition module, configured to acquire initial data of the body, the initial data includes noise data and vibration data of the body, and the initial data is used as basic data for active noise reduction of the body; a data storage module, configured to store the initial data; A time-frequency analysis module, configured to perform time-frequency analysis on the stored initial data to obtain time-frequency analysis data; A data processing module, configured to process the time-frequency analysis data to obtain advanced analysis data; An anomaly analysis module, configured to perform an anomaly analysis on the body according to the time-frequency analysis data and the advanced analysis data, so as to determine the anomaly of the body. 11. A terminal, characterized in that it is capable of performing the operations in the abnormality analysis method according to any one of claims 1 to 9. 12. A storage medium, wherein the storage medium is used to store a computer program, and the computer program is loaded by a processor to execute the abnormality analysis method according to any one of claims 1 to 9.

Images