Broadband weak vibration signal measuring method and system

Abstract

The invention provides a broadband weak vibration signal measurement method and system. The method comprises the following steps: collecting a broadband vibration signal based on a preset sensor system; performing signal preprocessing on the broadband vibration signal to obtain an enhanced signal of the broadband vibration signal; performing feature extraction on the enhanced signal of the broadband vibration signal to obtain instantaneous frequency and amplitude information of the broadband vibration signal; inputting the instantaneous frequency and amplitude information of the broadband vibration signal into a preset weak vibration signal measurement model to obtain a measurement result of the broadband weak vibration signal; the broadband vibration signals are preprocessed, so that the signal-to-noise ratio is improved; through feature extraction, on the premise that an original signal is not lost, the definition of the signal is improved, the measurement result of the weak vibration signal is obtained by comprehensively considering the instantaneous frequency and amplitude information features of the broadband vibration signal, the misjudgment condition caused by single feature judgment is avoided, the broadband weak vibration signal is measured on the whole, and the measurement accuracy is improved. And the reliability and comprehensiveness of the measurement result are improved.

Description

Technical Field

[0001] The present application relates to the technical field of weak signal measurement, and specifically relates to a method and system for measuring wide-band weak vibration signals. Background Art

[0002] Measuring wide-band weak vibration signals is a process focused on detecting and quantifying vibration signals with a wide frequency range and small amplitudes; its wide-band characteristic indicates that the signal frequency composition is complex, covering multiple frequency bands from low frequency to high frequency, possibly spanning from several hertz to several thousand hertz or even a wider frequency range; while the weak signals reveal that the amplitudes of these signals are extremely low, often approaching or below the background noise level of the sensor, especially in a complex background noise environment, where they are difficult to directly identify and accurately measure.

[0003] Currently, the research on wide-band weak vibration signals is still relatively scarce. Due to the small amplitudes of such signals, the sensor is required to have extremely high sensitivity to effectively capture the signals; however, high-sensitivity sensors not only have high costs but may also be accompanied by challenges in terms of stability and reliability; in addition, such sensors also have more stringent requirements for the measurement environment, for example, better isolation and shock absorption measures need to be taken, which undoubtedly increases the complexity and overall cost of measuring weak vibration signals. Therefore, the measurement of wide-band weak vibration signals faces a series of problems that need to be overcome urgently. Summary of the Invention

[0004] In order to overcome the above problems existing in the prior art, the present application provides a method and system for measuring wide-band weak vibration signals, and adopts the following technical solutions:

[0005] In a first aspect, the present application provides a method for measuring wide-band weak vibration signals, including:

[0006] Collecting wide-band vibration signals based on a preset sensor system, performing signal preprocessing on the wide-band vibration signals to obtain enhanced signals of the wide-band vibration signals;

[0007] Extracting features from the enhanced signals of the wide-band vibration signals to obtain the instantaneous frequency and amplitude information of the wide-band vibration signals;

[0008] Inputting the instantaneous frequency and amplitude information of the wide-band vibration signals into a preset weak vibration signal measurement model to obtain the measurement results of the wide-band weak vibration signals.

[0009] Further, the collecting wide-band vibration signals based on a preset sensor system includes:

[0010] Collecting wide-band vibration signals through a preset sensor system based on a preset sampling time and sampling frequency.

[0011] Furthermore, the signal preprocessing of the broadband vibration signal to obtain the enhanced signal of the broadband vibration signal specifically includes:

[0012] Removing non-target components from the broadband vibration signal to obtain an initial filtered vibration signal;

[0013] Inputting the initial filtered vibration signal into a preset artificial intelligence noise reduction model, automatically identifying and removing the noise components of the initial filtered vibration signal based on the noise and signal feature patterns learned by the artificial intelligence noise reduction model to obtain a noise-reduced signal;

[0014] Performing baseline correction on the noise-reduced signal to eliminate the DC component and obtain a baseline-corrected signal;

[0015] Performing feature enhancement processing on the key features of the baseline-corrected signal to obtain the enhanced signal of the broadband vibration signal.

[0016] Furthermore, the performing baseline correction on the noise-reduced signal to eliminate the DC component and obtain a baseline-corrected signal includes:

[0017] Assume that the noise-reduced signal is y(n), where n is the discrete time sequence number; then the polynomial fitting of the noise-reduced signal is p(n) = a 0 + a 1 n + a 2 n 2 , obtaining the polynomial coefficients a 0 , a 1 , a 2 through the data points of the noise-reduced signal y(n), making the error between the polynomial curve p(n) and the noise-reduced signal y(n) the smallest as a whole. After calculating the fitting polynomial, subtracting the polynomial curve p(n) from the noise-reduced signal y(n), that is, y corrected (n) = y(n) - p(n), to obtain the baseline-corrected signal y corrected (n).

[0018] Furthermore, the performing feature enhancement processing on the key features of the baseline-corrected signal to obtain the enhanced signal of the broadband vibration signal specifically includes:

[0019] Performing short-time Fourier transform on the baseline-corrected signal y corrected (n) to obtain the time-domain representation y(n, f), where n is the time index and f is the frequency index;

[0020] Based on the time-frequency region of the preset key features, marking the key feature region within a specific time range and frequency range;

[0021] Create a matrix \(M(n, f)\) with the same dimension as the time-domain representation \(y(n, f)\), and set all initial values to 1. Use the matrix \(M(n, f)\) as the time-frequency masking matrix.

[0022] Based on the time-frequency region corresponding to the key feature region, modify the element values at the corresponding positions in the matrix \(M(n, f)\) to the desired enhancement coefficient \(a\) (\(a>1\)).

[0023] Multiply the time-frequency mask \(M(n, f)\) and the original time-frequency representation \(y(n, f)\) element by element to obtain the enhanced time-frequency representation \(X\) enhanced (n, f), that is, \(X\) enhanced (n, f)=M(n, f)*y(n, f). At this time, the amplitude of the signal in the time-frequency region corresponding to the key feature region is enhanced according to the preset coefficient \(a\).

[0024] Based on the inverse short-time Fourier transform function, convert the enhanced time-frequency representation \(X\) enhanced (n, f) into a time-domain signal to obtain the enhanced time-domain signal, and the enhanced time-domain signal is the enhanced signal of the wide-band vibration signal.

[0025] Furthermore, performing feature extraction on the enhanced signal of the wide-band vibration signal to obtain the instantaneous frequency and amplitude information of the wide-band vibration signal, the specific content includes:

[0026] By finding the local maximum and minimum points of the enhanced signal of the wide-band vibration signal, constructing the upper and lower envelopes using cubic spline interpolation, calculating the local mean, and screening out the intrinsic mode functions according to the preset stopping criterion, and repeating the operation continuously until the remaining enhanced signal meets the corresponding stopping condition, finally obtaining several intrinsic mode functions and a trend term;

[0027] Taking each intrinsic mode function as a time-domain signal, performing a fast Fourier transform on the time-domain signal to obtain the frequency signal of each intrinsic mode function, processing the frequency signal based on a preset rule, and converting the frequency signal processed by the preset rule back to the time-domain through an inverse fast Fourier transform, constructing an analytic signal, obtaining the amplitude information by taking the amplitude of the analytic signal, and obtaining the instantaneous phase by the phase of the analytic signal;

[0028] Taking the time derivative of the instantaneous phase to obtain the instantaneous frequency.

[0029] In a second aspect, the present application also provides a wide-band weak vibration signal measurement system, including:

[0030] A weak vibration signal preprocessing module, configured to collect a wide-band vibration signal based on a preset sensor system, perform signal preprocessing on the wide-band vibration signal, and obtain the enhanced signal of the wide-band vibration signal;

[0031] A feature extraction module, configured to extract features from the enhanced signal of the broadband vibration signal, and obtain the instantaneous frequency and amplitude information of the broadband vibration signal;

[0032] A measurement result acquisition module, configured to input the instantaneous frequency and amplitude information of the broadband vibration signal into a preset weak vibration signal measurement model, and obtain the measurement result of the broadband weak vibration signal.

[0033] In a third aspect, the present application provides an electronic device, including:

[0034] One or more processors; a memory; and one or more computer programs, where the one or more computer programs are stored in the memory, and the one or more computer programs include instructions, when the instructions are executed by the device, enabling the device to execute the method described in the first aspect.

[0035] In a fourth aspect, the present application provides a computer-readable storage medium, in which a computer program is stored, and when it runs on a computer, enabling the computer to execute the method described in the first aspect.

[0036] In a fifth aspect, the present application provides a computer program, which is used to execute the method described in the first aspect when the computer program is executed by a computer.

[0037] In a possible design, the program in the fifth aspect can be stored in whole or in part on a storage medium packaged together with the processor, or can be stored in whole or in part on a memory not packaged together with the processor.

[0038] The present application has the following beneficial effects:

[0039] 1. The present application collects broadband vibration signals through a preset sensor system based on a preset sampling time and sampling frequency, and specifically obtains the required original vibration data, ensuring that the original vibration data covers the complete information of the target frequency band, which helps to improve the accuracy and effectiveness of weak vibration signal measurement.

[0040] 2. The present application first removes the non-target components in the broadband vibration signal, and then uses a preset artificial intelligence noise reduction model to automatically identify and remove the noise components of the initial filtered vibration signal based on the learned noise and signal feature patterns. Through double filtering processing, the present application purifies the signal to the greatest extent, reduces noise interference, can more accurately reflect the real vibration situation, and improves the reliability of the measurement result.

[0041] 3. This application eliminates the DC component and obtains the signal after baseline correction by fitting a polynomial and subtracting the polynomial curve from the denoised signal, which helps to remove the influence of baseline drift in the signal, avoid deviation caused by the DC component in the extraction of key vibration characteristics, etc., and further improve the measurement accuracy.

[0042] 4. This application enhances the key features by using the short-time Fourier transform combined with the time-frequency mask matrix, specifically highlighting the key feature regions of interest in the wide-band vibration signal, amplifying the important vibration information without changing the characteristics of other regions, which is beneficial to extracting the instantaneous frequency and amplitude information.

[0043] 5. This application filters out the intrinsic mode functions and trend terms by finding the local maximum and minimum points and constructing the upper and lower envelopes using cubic spline interpolation, which can adaptively decompose the complex vibration signal into multiple relatively simple and physically meaningful intrinsic mode functions. For wide-band and possibly complex weak vibration signals, it can better analyze the different frequency components and variation laws inside.

[0044] 6. This application obtains the instantaneous frequency and amplitude information by performing a fast Fourier transform on the decomposed intrinsic mode functions, accurately extracting the key characteristic parameters from the processed signal, laying a solid foundation for accurately measuring the wide-band weak vibration signal. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 FIG. is an exemplary system architecture diagram to which the embodiments of the present application can be applied;

[0046] Figure 2 FIG. is a flowchart of the method for measuring wide-band weak vibration signals according to the embodiments of the present application;

[0047] Figure 3 FIG. is a flowchart of obtaining the enhanced signal of the weak vibration signal according to the embodiments of the present application;

[0048] Figure 4 FIG. is a flowchart of extracting the features of the enhanced signal according to the embodiments of the present application;

[0049] Figure 5 FIG. is a system flowchart of the embodiments of the present application;

[0050] Figure 6 FIG. is a schematic diagram of a computer device according to the embodiments of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0051] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this application belongs; the terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above drawings are intended to cover non-exclusive inclusion. The terms "first", "second", etc. in the specification and claims of this application or the above drawings are used to distinguish different objects and not to describe a specific order.

[0052] Reference to "embodiment" herein means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of this application. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0053] In order to enable those skilled in the technical field to better understand the solution of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0054] As Figure 1 shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.

[0055] Users may use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications may be installed on the terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0056] The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, and desktop computers, etc.

[0057] Server 105 can be a server that provides various services, such as a background server that supports the pages displayed on the terminal devices 101, 102, and 103.

[0058] It should be noted that the broadband weak vibration signal measurement method provided by the embodiments of the present application is generally executed by a server / terminal device. Correspondingly, the broadband weak vibration signal measurement system is generally set in the server / terminal device.

[0059] It should be understood that Figure 1 the numbers of the terminal devices, networks, and servers in

[0060] This application is of great significance for equipment monitoring, fault diagnosis, and the formulation of equipment maintenance strategies in the industrial and engineering fields.

[0061] Continuing to refer to Figure 2 , the figure shows a flowchart of a broadband weak vibration signal measurement method of the present application. The method includes the following steps:

[0062] Step 201, collect a broadband vibration signal based on a preset sensor system, perform signal preprocessing on the broadband vibration signal, and obtain an enhanced signal of the broadband vibration signal.

[0063] In a possible implementation manner, a broadband vibration signal is collected based on a preset sampling time and sampling frequency through a preset sensor system.

[0064] For example, according to the measurement target and broadband requirements, the preset sensor system is composed of a combination of various types of sensors. For example, for low-frequency vibrations (such as below 1 Hz), an ultra-low-frequency seismometer can be selected; in the intermediate frequency range (1 Hz - 100 Hz), a MEMS accelerometer is used; for high-frequency vibrations (above 100 Hz), a piezoelectric accelerometer is used. These sensors are reasonably arranged at preset positions to ensure that different frequency vibration signals can be comprehensively sensed.

[0065] In a possible implementation manner, for the signal preprocessing of the broadband vibration signal to obtain the enhanced signal of the broadband vibration signal, please refer to Figure 3 , the specific content includes:

[0066] Step 31, remove non-target components from the broadband vibration signal to obtain an initial filtered vibration signal.

[0067] In a possible implementation manner, through a preset low-frequency cut-off frequency f L and a preset high-frequency cut-off frequency fH , remove the non-target frequency components of the broadband vibration signal to obtain an initial filtered vibration signal.

[0068] For example, according to the frequency range of the measured weak vibration signal, design a band-pass filter. Determine the low-frequency cut-off frequency f L and the high-frequency cut-off frequency f H . If the target signal of the weak vibration signal is mainly concentrated between 10 Hz and 150 Hz, f L can be set to 5 Hz, and f H can be set to 200 Hz to filter out low-frequency noise below 5 Hz (such as ultra-low-frequency interference in ground pulsation) and high-frequency noise above 200 Hz (such as high-frequency vibration caused by electromagnetic interference in the environment), highlighting the weak vibration signal in the target frequency band and improving the signal-to-noise ratio.

[0069] Step 32, input the initial filtered vibration signal into a preset artificial intelligence noise reduction model, and automatically identify and remove the noise components of the initial filtered vibration signal based on the noise and signal feature patterns learned by the artificial intelligence noise reduction model to obtain a noise-reduced signal.

[0070] In a possible implementation manner, use a marked training data set to train the artificial intelligence noise reduction model. The artificial intelligence model learns the feature patterns of noise and signals through training. After the artificial intelligence noise reduction model is trained, use the initial filtered vibration signal as the input of the artificial intelligence noise reduction model, extract the features helpful for noise reduction from the initial filtered vibration signal. These features include time-domain features, frequency-domain features, or time-frequency domain features. The artificial intelligence noise reduction model automatically identifies the noise components in the signal based on the features of the signal and removes the noise according to the learned feature patterns.

[0071] Step 33, perform baseline correction on the noise-reduced signal to eliminate the DC component and obtain a baseline-corrected signal.

[0072] In a possible implementation manner, assume that the noise-reduced signal is y(n), where n is the discrete time index; then the polynomial fitting of the noise-reduced signal is p(n) = a 0 + a 1 n + a 2 n 2 . Obtain the polynomial coefficients a 0 , a 1 , a 2 through the data points of the noise-reduced signal y(n), so that the error between the polynomial curve p(n) and the noise-reduced signal y(n) is minimized as a whole. After calculating the fitting polynomial, subtract the polynomial curve p(n) from the noise-reduced signal y(n), that is, y corrected(n) = y(n) - p(n), obtaining the signal y after baseline correction corrected (n).

[0073] Step 34, perform feature enhancement processing on the key features of the signal after baseline correction to obtain the enhanced signal of the broadband vibration signal.

[0074] In a possible implementation manner, the performing feature enhancement processing on the key features of the signal after baseline correction to obtain the enhanced signal of the broadband vibration signal specifically includes:

[0075] Perform short-time Fourier transform on the signal y corrected (n) after baseline correction to obtain the time-domain representation y(n, f), where n is the time index and f is the frequency index.

[0076] Based on the time-frequency region of the preset key features, mark the key feature region within a specific time range and frequency range.

[0077] Create a matrix M(n, f) with the same dimension as the time-domain representation y(n, f), and set all initial values to 1. Use the M(n, f) matrix as the time-frequency mask matrix.

[0078] Based on the time-frequency region corresponding to the key feature region, modify the element values to the desired enhancement coefficient a (a > 1) at the corresponding positions in the matrix M(n, f).

[0079] Multiply the time-frequency mask M(n, f) element-wise with the original time-frequency representation y(n, f) to obtain the enhanced time-frequency representation X enhanced (n, f), that is, X enhanced (n, f) = M(n, f) * y(n, f). At this time, the amplitude of the signal in the time-frequency region corresponding to the key feature region is enhanced according to the preset coefficient a.

[0080] Based on the inverse short-time Fourier transform function, convert the enhanced time-frequency representation X enhanced (n, f) into a time-domain signal to obtain the enhanced time-domain signal, and the enhanced time-domain signal is the enhanced signal of the broadband vibration signal.

[0081] Step 202, perform feature extraction on the enhanced signal of the broadband vibration signal to obtain the instantaneous frequency and amplitude information of the broadband vibration signal.

[0082] In a possible implementation manner, for the performing feature extraction on the enhanced signal of the broadband vibration signal to obtain the instantaneous frequency and amplitude information of the broadband vibration signal, please refer to Figure 4 , specifically includes:

[0083] Step 41: By finding the local maximum and minimum points of the enhanced signal of the broadband vibration signal, constructing the upper and lower envelopes using cubic spline interpolation, calculating the local mean, and screening out the intrinsic mode functions according to a preset stopping criterion, and continuously repeating the operation until the remaining enhanced signal meets the corresponding stopping condition, finally obtaining several intrinsic mode functions and a trend term; the preset stopping criterion can be that the standard deviation is less than a threshold value.

[0084] Step 42: Taking each intrinsic mode function as a time-domain signal, performing a fast Fourier transform on the time-domain signal to obtain the frequency signal of each intrinsic mode function, processing the frequency signal based on a preset rule, and converting the frequency signal processed by the preset rule back from the frequency domain to the time domain through an inverse fast Fourier transform, constructing an analytic signal, obtaining the amplitude information by taking the amplitude of the analytic signal, and obtaining the instantaneous phase by the phase of the analytic signal; the preset rule in the embodiment of the present application is multiplying the positive frequency by -j and multiplying the negative frequency by j.

[0085] Step 43: Taking the time derivative of the instantaneous phase to obtain the instantaneous frequency.

[0086] Step 203: Inputting the instantaneous frequency and amplitude information of the broadband vibration signal into a preset weak vibration signal measurement model to obtain the measurement result of the broadband weak vibration signal.

[0087] In a possible implementation manner, for the step of inputting the instantaneous frequency and amplitude information of the broadband vibration signal into a preset weak vibration signal measurement model to obtain the measurement result of the broadband weak vibration signal, the preset weak vibration signal measurement model can be a neural network model, a support vector machine model, etc. Based on the instantaneous frequency and amplitude information obtained from historical data as the input data of the preset weak vibration signal measurement model, according to the internal structure and parameters of the preset weak vibration signal measurement model, complex calculations and analyses are performed to automatically identify and extract the features and patterns related to the broadband weak vibration signal. After the preset weak vibration signal measurement model completes the measurement, the corresponding measurement result is output. The specific form and meaning of the measurement result depend on the design and training purpose of the preset weak vibration signal measurement model, and may be the category label of the weak vibration signal, the quantization value of the vibration intensity, the abnormal state judgment of the signal, etc. The user can further analyze and apply the measurement result according to actual needs.

[0088] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. This computer program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, an optical disc, a read-only memory (ROM), etc., or a random access memory (RAM), etc.

[0089] It should be understood that although the steps in the flowchart of the accompanying drawings are shown sequentially according to the indication of the arrows, these steps are not necessarily executed sequentially according to the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps has no strict order limit, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same moment, but can be executed at different moments. Their execution order is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or sub-steps or stages of other steps.

[0090] Continuing to refer to Figure 5 , the broadband weak vibration signal measurement system described in this embodiment includes:

[0091] A weak vibration signal preprocessing module 501, configured to collect a broadband vibration signal based on a preset sensor system, perform signal preprocessing on the broadband vibration signal, and obtain an enhanced signal of the broadband vibration signal;

[0092] A feature extraction module 502, configured to extract features from the enhanced signal of the broadband vibration signal, and obtain the instantaneous frequency and amplitude information of the broadband vibration signal;

[0093] A measurement result acquisition module 503, configured to input the instantaneous frequency and amplitude information of the broadband vibration signal into a preset weak vibration signal measurement model, and obtain the measurement result of the broadband weak vibration signal.

[0094] To solve the above technical problems, the embodiments of the present application also provide a computer device. Specifically, please refer to Figure 6 , Figure 6 which is the basic structural block diagram of the computer device in this embodiment.

[0095] The computer device 6 includes a memory 6a, a processor 6b, and a network interface 6c that are communicatively connected to each other via a system bus. It should be noted that only the computer device 6 with components 6a - 6c is shown in the figure, but it should be understood that it is not required to implement all the shown components, and more or fewer components can be implemented alternatively. Among them, those skilled in the art of this technology can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0096] The computer device can be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The computer device can interact with the user through means such as a keyboard, a mouse, a remote control, a touchpad, or a voice control device.

[0097] The memory 6a includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 6a can be an internal storage unit of the computer device 6, such as the hard disk or memory of the computer device 6. In other embodiments, the memory 6a can also be an external storage device of the computer device 6, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the computer device 6. Of course, the memory 6a can also include both the internal storage unit and the external storage device of the computer device 6. In this embodiment, the memory 6a is generally used to store the operating system and various application software installed on the computer device 6, such as the program code of the broadband weak vibration signal measurement method. In addition, the memory 6a can also be used to temporarily store various data that have been output or will be output.

[0098] In some embodiments, the processor 6b may be a Central Processing Unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips. The processor 6b is generally used to control the overall operation of the computer device 6. In this embodiment, the processor 6b is used to run the program code stored in the memory 6a or process data, such as running the program code of the broadband vibration signal measurement method.

[0099] The network interface 6c may include a wireless network interface or a wired network interface, and this network interface 6c is generally used to establish a communication connection between the computer device 6 and other electronic devices.

[0100] This application also provides another implementation manner, that is, to provide a non-volatile computer-readable storage medium storing a program of a broadband weak vibration signal measurement method, and the broadband vibration signal measurement can be executed by at least one processor, so that the at least one processor executes the steps of the broadband weak vibration signal measurement method as described above.

[0101] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-described embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation manner. Based on such an understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disc) and includes several instructions to enable a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in the various embodiments of this application.

[0102] Obviously, the above-described embodiments are only a part of the embodiments of this application, rather than all of the embodiments. The accompanying drawings show the preferred embodiments of this application, but do not limit the patent scope of this application. This application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosed content of this application more thorough and comprehensive. Although this application has been described in detail with reference to the foregoing embodiments, for those skilled in the art, they can still modify the technical solutions described in the foregoing specific embodiments, or perform equivalent replacements on some of the technical features. Any equivalent structure directly or indirectly using the content of the specification and drawings of this application in other related technical fields shall be within the scope of the patent protection of this application by the same token.

Claims

1. A method for measuring broadband weak vibration signals, characterized in that: include: Collecting a broadband vibration signal based on a preset sensor system, performing signal preprocessing on the broadband vibration signal, and obtaining an enhanced signal of the broadband vibration signal; Extracting features of the enhanced signal of the broadband vibration signal to obtain instantaneous frequency and amplitude information of the broadband vibration signal; The instantaneous frequency and amplitude information of the broadband vibration signal is input into a preset weak vibration signal measurement model to obtain a measurement result of the broadband weak vibration signal.

2. The method for measuring broadband weak vibration signals according to claim 1, characterized in that: The method of collecting a wide-band vibration signal based on a preset sensor system includes: The wide-band vibration signal is collected by a preset sensor system based on a preset sampling time and sampling frequency.

3. The method for measuring broadband weak vibration signals according to claim 1, characterized in that: The performing signal preprocessing on the broadband vibration signal to obtain an enhanced signal of the broadband vibration signal specifically includes: Removing non-target components from the broadband vibration signal to obtain an initial filtered vibration signal; Inputting the initial filtered vibration signal into a preset artificial intelligence noise reduction model, automatically identifying and removing the noise component of the initial filtered vibration signal based on the noise and signal characteristic patterns learned by the artificial intelligence noise reduction model, and obtaining a noise-reduced signal; Performing baseline correction on the noise-reduced signal to eliminate the DC component and obtain a baseline-corrected signal; The key features of the signal after baseline correction are subjected to feature enhancement processing to obtain an enhanced signal of the broadband vibration signal.

4. The method for measuring broadband weak vibration signals according to claim 3, characterized in that: The method of performing baseline correction on the noise-reduced signal to eliminate the DC component and obtain the baseline-corrected signal includes: Assume that the signal after noise reduction is y(n), where n is the discrete time sequence number; then the fitting polynomial of the signal after noise reduction is p(n)=a0+a1n+a2n 2 , obtain the polynomial coefficients a0, a1, and a2 through the data points of the denoised signal y(n), so that the error between the polynomial curve p(n) and the denoised signal y(n) is minimized as a whole. After calculating the fitting polynomial, subtract y(n) from the denoised signal, that is, y corrected (n) = y(n) - p(n), get the baseline corrected signal y corrected (n).

5. The method for measuring broadband weak vibration signals according to claim 3, characterized in that: The key features of the baseline-corrected signal are enhanced to obtain an enhanced signal of the broadband vibration signal, and the specific contents include: The baseline-corrected signal y corrected (n) Perform a short-time Fourier transform to obtain a time domain representation y(n,f), where n is the time index and f is the frequency index; Based on the time-frequency region of the preset key features, the key feature regions are marked in a specific time range and frequency range; Create a matrix M(n,f) with the same dimension as the time domain representation y(n,f), set all initial values ​​to 1, and use the M(n,f) matrix as the time-frequency mask matrix; Based on the time-frequency region corresponding to the key feature region, the element value at the corresponding position in the matrix M(n,f) is modified to the desired enhancement coefficient a (a>1); Multiply the time-frequency mask M(n,f) by the original time-frequency representation y(n,f) element by element to obtain the enhanced time-frequency representation X enhanced (n,f), that is, X enhanced (n,f)=M(n,f)*y(n,f), at this time, the amplitude of the time-frequency region signal corresponding to the key feature region is enhanced according to the preset coefficient a; Based on the inverse short-time Fourier transform function, the enhanced time-frequency representation X enhanced (n, f) is converted into a time domain signal to obtain an enhanced time domain signal, and the enhanced time domain signal is an enhanced signal of the wide-band vibration signal.

6. The method for measuring broadband weak vibration signals according to claim 1, characterized in that: The feature extraction of the enhanced signal of the broadband vibration signal to obtain the instantaneous frequency and amplitude information of the broadband vibration signal specifically includes: By finding the local maximum and minimum points of the enhanced signal of the broadband vibration signal, using cubic spline interpolation to construct upper and lower envelopes, calculating the local mean and screening out the intrinsic mode function according to a preset stop criterion, the operation is repeated until the remaining enhanced signal meets the corresponding stop condition, and finally a number of intrinsic mode functions and trend items are obtained; Taking each intrinsic mode function as a time domain signal, performing fast Fourier transform on the time domain signal to obtain the frequency signal of each intrinsic mode function, processing the frequency signal based on a preset rule, converting the frequency signal processed by the preset rule from the frequency domain back to the time domain through inverse fast Fourier transform, constructing an analytical signal, obtaining amplitude information by taking the amplitude of the analytical signal, and obtaining the instantaneous phase by taking the phase of the analytical signal; The instantaneous frequency is obtained by taking the time derivative of the instantaneous phase.

7. A broadband weak vibration signal measurement system, used to implement the broadband weak vibration signal measurement method of claims 1-6, characterized in that: include: A weak vibration signal preprocessing module is used to collect a broadband vibration signal based on a preset sensor system, perform signal preprocessing on the broadband vibration signal, and obtain an enhanced signal of the broadband vibration signal; A feature extraction module, used to extract features from the enhanced signal of the broadband vibration signal to obtain instantaneous frequency and amplitude information of the broadband vibration signal; The measurement result acquisition module is used to input the instantaneous frequency and amplitude information of the broadband vibration signal into a preset weak vibration signal measurement model to obtain the measurement result of the broadband weak vibration signal.

8. An electronic device, characterized in that: include: one or more processors; Memory; And one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions, which, when executed by the device, enable the device to perform the steps of the wide-band weak vibration signal measurement method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed on a computer, enables the computer to execute the steps of the method for measuring a wide-band weak vibration signal as described in any one of claims 1 to 6.

Images