CN116299705A - Vibration detection method and system - Google Patents
Vibration detection method and system Download PDFInfo
- Publication number
- CN116299705A CN116299705A CN202310280217.1A CN202310280217A CN116299705A CN 116299705 A CN116299705 A CN 116299705A CN 202310280217 A CN202310280217 A CN 202310280217A CN 116299705 A CN116299705 A CN 116299705A
- Authority
- CN
- China
- Prior art keywords
- signal
- wavelet
- vibration
- analysis
- coefficient
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 40
- 238000004458 analytical method Methods 0.000 claims abstract description 52
- 238000000034 method Methods 0.000 claims abstract description 35
- 238000012545 processing Methods 0.000 claims abstract description 31
- 230000033001 locomotion Effects 0.000 claims abstract description 29
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 28
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 26
- 230000003321 amplification Effects 0.000 claims abstract description 25
- 238000003199 nucleic acid amplification method Methods 0.000 claims abstract description 25
- 238000000605 extraction Methods 0.000 claims abstract description 13
- 230000009466 transformation Effects 0.000 claims description 13
- 230000002068 genetic effect Effects 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 9
- 238000013528 artificial neural network Methods 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 3
- 230000035939 shock Effects 0.000 claims 4
- 238000001228 spectrum Methods 0.000 abstract description 13
- 230000009467 reduction Effects 0.000 abstract description 8
- 238000013473 artificial intelligence Methods 0.000 abstract description 5
- 238000005457 optimization Methods 0.000 abstract description 3
- 230000000737 periodic effect Effects 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 17
- 238000003860 storage Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000011218 segmentation Effects 0.000 description 5
- 230000015654 memory Effects 0.000 description 4
- 238000005070 sampling Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 230000001668 ameliorated effect Effects 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000012248 genetic selection Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000002028 premature Effects 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 238000004611 spectroscopical analysis Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
- G01V1/28—Processing seismic data, e.g. for interpretation or for event detection
- G01V1/30—Analysis
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
- G01V1/28—Processing seismic data, e.g. for interpretation or for event detection
- G01V1/282—Application of seismic models, synthetic seismograms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Remote Sensing (AREA)
- General Physics & Mathematics (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geophysics (AREA)
- Geology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Environmental & Geological Engineering (AREA)
- Acoustics & Sound (AREA)
- Theoretical Computer Science (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Genetics & Genomics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Physiology (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention discloses a vibration detection method and a system, wherein the method comprises the steps of obtaining a vibration signal; performing wavelet analysis processing on the collected earthquake motion signals; carrying out signal modulation and amplification treatment on the earthquake motion signal after wavelet analysis treatment; and carrying out feature extraction and vibration signal analysis on the earthquake vibration signals subjected to signal modulation and amplification. According to the invention, wavelet decomposition and noise reduction are carried out on the acquired signals, then zero crossing count identification of the target signals in the time domain and the frequency domain and an improved periodic chart power spectrum estimation analysis identification method are judged, so that effective identification of vibration detection targets is realized, the capability of a vibration sensor for effectively identifying massive acquired signals and improving the resolution of characteristic information is changed, false alarms and false alarms are reduced through optimization of a background artificial intelligence algorithm, and the detection capability requirement of special application scenes on specific targets is fully met.
Description
Technical Field
The invention relates to the technical field of vibration detection, in particular to a vibration detection method and a vibration detection system.
Background
The vibration detection system adopts a traditional artificial neural network algorithm, namely a method of calculating the minimum value of the objective function by taking the square of network error as the objective function and adopting a gradient descent method, and the defects of the method include that the learning speed is low, the learning times of vibration signals can be converged only by hundreds of times or even thousands of times of learning, and the vibration detection system is easy to fall into local minimum values, and aims at the conditions of identifying effective vibration signals and early warning, and rapidly learning and effectively filtering irrelevant vibration such as vibration generated by non-personnel (animals), vibration generated by nature such as wind, rain, trees, stones and the like, and reducing false alarm and false alarm rate of the vibration signals. The vibration sensor is required to detect the vibration generated by specific targets such as people, vehicles, underground excavation and the like in a targeted manner by optimizing an algorithm mode and combining an artificial intelligence technology, so that the vibration sensor is supported for application in specific scenes.
The foregoing is provided merely for the purpose of facilitating understanding of the technical solutions of the present invention and is not intended to represent an admission that the foregoing is prior art.
Disclosure of Invention
The invention mainly aims to provide a vibration detection method and a vibration detection system, and aims to solve the technical problems of false alarm and high false alarm rate of the current vibration detection.
To achieve the above object, the present invention provides a vibration detection method comprising the steps of:
s1: obtaining a seismic signal;
s2: performing wavelet analysis processing on the collected earthquake motion signals;
s3: carrying out signal modulation and amplification treatment on the earthquake motion signal after wavelet analysis treatment;
s4: and carrying out feature extraction and vibration signal analysis on the earthquake vibration signals subjected to signal modulation and amplification.
Optionally, in the step S1, the obtaining a seismic signal specifically includes: and collecting a ground vibration signal caused by the ground target movement through a vibration sensor.
Optionally, in the step S2, the wavelet filtering process specifically includes:
s21: performing wavelet decomposition on the collected earthquake motion signals, and determining a threshold value of a wavelet coefficient;
s22: updating the coefficient of the earthquake motion signal after wavelet classification according to the threshold value of the wavelet coefficient;
s23: and performing wavelet inverse transformation, and reconstructing the wavelet coefficient subjected to threshold processing to obtain a restored original signal.
Optionally, the updating step of the coefficient of the seismic signal after wavelet classification specifically includes: when the coefficient of the local vibration signal after wavelet decomposition is larger than the threshold value of the wavelet coefficient, the original coefficient value is reserved; otherwise the coefficient is set to zero.
Optionally, in the step of performing wavelet decomposition on the collected seismic signals, the method specifically includes:
s211: selecting any wavelet decomposition layer number K and a basis function, and carrying out wavelet decomposition on the collected earthquake motion signals to K layers to obtain a required wavelet decomposition coefficient;
s212: processing the obtained wavelet decomposition coefficient by a soft limiting function;
s213: reconstructing the wavelet coefficient subjected to threshold processing to obtain an estimated value of an original signal;
s214: changing the wavelet and repeating the steps to determine the wavelet base;
s215: after the wavelet base is determined, the wavelet decomposition layer number K is changed, and the wavelet decomposition layer number is obtained by repeating the steps.
Optionally, the signal modulation and amplification circuit includes a first stage amplification circuit formed by two symmetrical in-phase amplifiers and a second stage amplification circuit formed by a differential amplifier.
Optionally, in the step of extracting the characteristics of the seismic signals after the signal modulation and amplification, the characteristic extraction includes extracting one or more of time domain characteristics, frequency domain characteristics, parameterized model characteristics, gao Jiepu analysis, and nonlinear characteristics.
Optionally, the vibration signal analysis includes a signal zero crossing analysis and a welch algorithm analysis.
Optionally, after the steps of feature extraction and vibration signal analysis are performed on the seismic vibration signal after the signal modulation and amplification, the method further includes: and training a target recognition model by adopting the self-adaptive genetic algorithm model and the neural network.
In addition, in order to achieve the above object, the present invention also provides a vibration detection system including:
the signal acquisition module is used for acquiring the earthquake motion signal;
the wavelet analysis module is used for carrying out wavelet analysis processing on the collected earthquake motion signals;
the signal processing module is used for carrying out signal modulation and amplification processing on the earthquake motion signal after wavelet analysis processing;
and the signal analysis module is used for carrying out feature extraction and vibration signal analysis on the earthquake vibration signals subjected to signal modulation and amplification.
The embodiment of the invention provides a vibration detection method and a vibration detection system, wherein the method comprises the steps of obtaining a seismic vibration signal; performing wavelet analysis processing on the collected earthquake motion signals; carrying out signal modulation and amplification treatment on the earthquake motion signal after wavelet analysis treatment; and carrying out feature extraction and vibration signal analysis on the earthquake vibration signals subjected to signal modulation and amplification. According to the invention, wavelet decomposition and noise reduction are carried out on the acquired signals, then zero crossing count identification of the target signals in the time domain and the frequency domain and an improved periodic chart power spectrum estimation analysis identification method are judged, so that effective identification of vibration detection targets is realized, the capability of a vibration sensor for effectively identifying massive acquired signals and improving the resolution of characteristic information is changed, false alarms and false alarms are reduced through optimization of a background artificial intelligence algorithm, and the detection capability requirement of special application scenes on specific targets is fully met.
Drawings
FIG. 1 is a flow chart of a vibration detection method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of an amplifying circuit according to the present invention;
FIG. 3 is a schematic diagram of a wavelet noise reduction framework of the present invention;
FIG. 4 is a model diagram of the adaptive genetic algorithm of the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
An embodiment of the present invention provides a vibration detection method, referring to fig. 1, fig. 1 is a schematic flow chart of an embodiment of the vibration detection method of the present invention.
In this embodiment, the vibration detection method includes the steps of:
s1: obtaining a seismic signal;
s2: performing wavelet analysis processing on the collected earthquake motion signals;
s3: carrying out signal modulation and amplification treatment on the earthquake motion signal after wavelet analysis treatment;
s4: and carrying out feature extraction and vibration signal analysis on the earthquake vibration signals subjected to signal modulation and amplification.
Specifically, in the present embodiment, the means for performing vibration detection mainly includes a sensor for acquiring seismic information, a modulating circuit section for modulating a sensing signal, a seismic signal acquisition and signal processing section, a seismic signal feature extraction section, and the like.
1. The vibration sensor detects a signal generated by the ground vibration caused by the movement of a ground target, generates an electric signal of the target through a modulation circuit, and outputs and transmits the electric signal.
2. The continuous wavelet transformation has the characteristics of linearity, translational invariance, telescopic invariance, redundancy and the like. In the process of preprocessing the signals, after the target signals are processed through wavelet transformation, the characteristic information of the target signals can be reserved, meanwhile, the noise of the signals can be reduced, the signal-to-noise ratio of the collected signals is improved, and therefore the characteristic information in the collected signals can be effectively extracted. Wavelet transformation is a multi-resolution analysis method with time and scale as parameters. Different resolutions are provided at different positions of the time and scale planes, and short-time high frequency in the signal can be analyzed and low frequency in the signal can be estimated through enough time resolution. Through verification, the wavelet transformation is utilized to reduce noise of non-stationary signals (such as time-varying signals and abrupt signals), so that the signal noise can be reduced, the signal to noise ratio can be improved, and the original characteristic information of the signal can be reserved, thereby playing a key role.
The signal receiving and transmitting part mainly comprises a signal modulation and amplification circuit, and the target signal which can be detected by the vibration detector is weak, and sometimes the signal can only have tens of microvolts, and the signal needs to be amplified and preprocessed by the front end, so that the system can work for a long time under the condition of limited battery power supply, and the amplification circuit is designed by high input impedance, high common mode rejection ratio and adjustable zero position. The amplifying circuit adopts a three-operational-amplifier in-phase parallel structure and consists of two stages: two symmetrical in-phase amplifiers form a first stage, and the second stage is a differential amplifier.
In order to improve the common-mode interference resistance and inhibit drift of the circuit, the design of the circuit strictly selects resistors according to the principle of up-down symmetry, and the closed-loop amplification multiple of the whole amplifier is ensured.
3. Target characteristic analysis of vibration signals
The target characteristic analysis of the vibration signal requires the establishment of a database containing all possible target identity information, the comparison by means of matching, and the classification of the target by means of a classification algorithm. The extractable features include mainly, for a particular signal, for example, time domain features, frequency domain features, parametric model features, gao Jiepu analysis, non-linear features and other features. The vibration signal denoised by wavelet is analyzed by time domain and frequency domain, and the characteristics of the vibration target are extracted by artificial intelligence technology. Further classification of the discrimination targets is achieved by formulating a target recognition strategy, such as zero crossing analysis by time domain, and Welch power spectroscopy in frequency domain.
The zero crossing number analysis of the signal is to compare the amplitude of the time domain signal in a determined time period with a set threshold value, and count the number of times that the signal positively crosses or negatively crosses the threshold value. The difficulty of the zero-crossing analysis recognition method is that the zero-crossing threshold value is set, and the setting of the threshold value cannot be a fixed value but can correspondingly float along with the amplitude value of the signal.
The welch algorithm analyzes the spectrum estimation variance, the windowing type, the data segmentation length and the segmentation overlapping degree to realize sampling of the signal according to the required sampling frequency, form an observation sequence, segment the observation sequence, perform windowing processing on each segment of data without repetition or repetition between segments, calculate the power spectrum of each segment by using a periodogram method, perform normalization processing, average the calculation result of each segment, and obtain the power spectrum estimation value of the signal. The welch algorithm uses a dynamic segmentation method to perform dimension reduction processing, extracts characteristics from the energy distribution of a target signal in a frequency domain, and has a good recognition effect even if stronger background noise exists or multiple targets are simultaneously present.
For the amplifying circuit part, as shown in fig. 2, two symmetrical in-phase amplifiers constitute a first stage, and a second stage is a differential amplifier. The resistors are chosen strictly according to the principle of up-down symmetry, ensuring r3=r4, r6=r5, r1=r2.
It should be noted that, in the preferred embodiment:
1. wavelet analysis and wavelet construction applied to irregular sets, and non-stationary, non-uniform, time-varying signal processing, nonlinear scale methods, and the like are widely applied. The wavelet transformation takes the wavelet as the basis function and the Fourier transformation takes the sine wave as the basis function because the basis functions used when the wavelet transformation and the Fourier transformation decompose the signals are different, so that the wavelet transformation has the time-frequency localization capability. The wavelet transformation has better time resolution at high frequency and better frequency resolution at low frequency, and is just in line with the characteristics of low-frequency signals and high-frequency signals, namely, the low-frequency signals change slowly and the high-frequency signals change rapidly.
The wavelet filtering process includes the steps of performing wavelet decomposition on the acquired signals, determining a threshold value of wavelet coefficients, and retaining original coefficient values when the coefficients of the signals after wavelet decomposition are larger than the threshold value; otherwise the coefficient is set to zero. And then carrying out wavelet inverse transformation, and reconstructing the wavelet coefficient subjected to threshold processing to obtain a restored original signal. The wavelet noise reduction process frame diagram is shown in fig. 3:
in the wavelet noise reduction implementation process, firstly, the wavelet base and the wavelet decomposition layer number are selected; and secondly, selecting a threshold value and a threshold function.
(l) And selecting a certain wavelet decomposition layer number K and a basis function, and carrying out wavelet decomposition on the acquired signals to K layers, so that the required wavelet decomposition coefficients can be obtained.
(2) The wavelet coefficients obtained before are processed using a soft clipping function.
(3) And reconstructing the wavelet coefficient subjected to threshold processing to obtain an estimated value x-A of the original signal.
(4) Finally, the wavelet is changed and the three steps are repeated, so that a proper wavelet base can be determined.
After the proper wavelet base is determined, the wavelet decomposition layer number K is changed, and the three steps are repeated, so that the wavelet decomposition layer number can be finally determined.
2. The Welch algorithm perfects the periodogram method by segmenting, partially overlapping, and using different window functions on the data.
(1) Generating a signal X (t) to be detected, and setting the frequency component and the signal-to-noise ratio of the signal;
(2) Sampling X (t) according to the requirement (the sampling theorem is required to be satisfied) and intercepting to obtain a limited-length observation sequence X [ n ];
(3) Setting Welch power spectrum estimation related parameters including FFT point number, data weight length and the like:
(4) Windowing is carried out on each segment of data;
(5) And performing power spectrum calculation on each piece of data, and averaging each piece of results to obtain a signal power spectrum of the blessing.
The new sequence after the Welch algorithm segmentation is independent of each other, so that the estimated mean value is unchanged, and the variance is 1/L of the original value, and therefore, a better variance characteristic can be achieved. However, the more segments must result in a reduction in spectral resolution, so the segment length needs to be carefully selected, and the problem of reduction in spectral resolution can be ameliorated by increasing the overlap between the segments of data. Meanwhile, the selection of window functions also affects the effect of power spectrum estimation, different window functions lead to different spectrum estimation resolutions, and sidelobe attenuation also has larger difference. When the proper window function, the number of segments and the number of overlapping points are selected, a better power spectrum estimation characteristic can be achieved, thereby facilitating signal detection.
3. The background adopts an artificial neural network algorithm which is suitable for describing the nonlinear relation between the target and the characteristics under the complex condition, can rapidly process a large amount of data, simultaneously superimpose the self-adaptive genetic algorithm, can effectively reduce the defect of converging to the global minimum point, and simultaneously increases the recognition rate and reduces the conditions of false alarm and high false alarm rate.
An adaptive genetic algorithm model diagram, as shown in fig. 4:
the self-adaptive genetic algorithm is a calculation model for simulating the biological evolution process of genetic selection and natural elimination, has good global optimization performance, can change crossover and mutation probability in a self-adaptive manner in the evolution process, and solves the problems of premature convergence and low searching efficiency in the later period of evolution, so that the self-adaptive genetic algorithm is combined with an artificial neural network algorithm. During training, the weight of the neural network is searched by using a genetic algorithm, the searching range is reduced, then the artificial neural network algorithm is used for accurately solving, the purposes of global searching, rapidness and high efficiency can be achieved, and the problem of local minima can be avoided.
In the embodiment, a vibration detection method is provided, wavelet decomposition and noise reduction are carried out on collected signals, then zero crossing count identification of target signals in time domain and frequency domain and an improved periodic chart power spectrum estimation analysis identification method are judged, and effective identification of vibration detection targets is realized; by adopting the artificial intelligence method of the Welch algorithm, the performance such as spectrum estimation resolution, variance and the like of the Welch algorithm is simulated and analyzed by means of the signal processing and numerical analysis capability of MATLAB, and the better resolution capability is obtained in the signal characteristic recognition of a vibration detection system due to the reasonable introduction of data segmentation and window functions of the Welch algorithm; the background adopts a self-adaptive genetic algorithm to overlap an artificial neural network algorithm, so that the recognition rate of the acquired signals is improved, and the false alarm rate are reduced.
The embodiment also provides a vibration detection system, the vibration detection system includes:
the signal acquisition module is used for acquiring the earthquake motion signal;
the wavelet analysis module is used for carrying out wavelet analysis processing on the collected earthquake motion signals;
the signal processing module is used for carrying out signal modulation and amplification processing on the earthquake motion signal after wavelet analysis processing;
and the signal analysis module is used for carrying out feature extraction and vibration signal analysis on the earthquake vibration signals subjected to signal modulation and amplification.
Other embodiments or specific implementations of the vibration detection system of the present invention may refer to the above-mentioned method embodiments, and are not described herein.
In addition, the embodiment of the invention also provides a storage medium, wherein a vibration detection program is stored on the storage medium, and the vibration detection program realizes the steps of the vibration detection method when being executed by a processor. Therefore, a detailed description will not be given here. In addition, the description of the beneficial effects of the same method is omitted. For technical details not disclosed in the embodiments of the computer-readable storage medium according to the present application, please refer to the description of the method embodiments of the present application. As an example, the program instructions may be deployed to be executed on one computing device or on multiple computing devices at one site or distributed across multiple sites and interconnected by a communication network.
Those skilled in the art will appreciate that implementing all or part of the above-described methods may be accomplished by way of computer programs, which may be stored on a computer-readable storage medium, and which, when executed, may comprise the steps of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), or the like.
It should be further noted that the above-described apparatus embodiments are merely illustrative, and that the units described as separate units may or may not be physically separate, and that units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the drawings of the embodiment of the device provided by the invention, the connection relation between the modules represents that the modules have communication connection, and can be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the present invention may be implemented by means of software plus necessary general purpose hardware, or of course by means of special purpose hardware including application specific integrated circuits, special purpose CPUs, special purpose memories, special purpose components, etc. Generally, functions performed by computer programs can be easily implemented by corresponding hardware, and specific hardware structures for implementing the same functions can be varied, such as analog circuits, digital circuits, or dedicated circuits. However, a software program implementation is a preferred embodiment for many more of the cases of the present invention. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a readable storage medium, such as a floppy disk, a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random-access Memory (RAM, random Access Memory), a magnetic disk or an optical disk of a computer, etc., including several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to execute the method according to the embodiments of the present invention.
Claims (10)
1. A method of vibration detection, the method comprising the steps of:
s1: obtaining a seismic signal;
s2: performing wavelet analysis processing on the collected earthquake motion signals;
s3: carrying out signal modulation and amplification treatment on the earthquake motion signal after wavelet analysis treatment;
s4: and carrying out feature extraction and vibration signal analysis on the earthquake vibration signals subjected to signal modulation and amplification.
2. The vibration detection method according to claim 1, wherein in the step S1, the seismic vibration signal is acquired, specifically: and collecting a ground vibration signal caused by the ground target movement through a vibration sensor.
3. The vibration detection method according to claim 1, wherein in the step S2, the wavelet filtering process specifically includes:
s21: performing wavelet decomposition on the collected earthquake motion signals, and determining a threshold value of a wavelet coefficient;
s22: updating the coefficient of the earthquake motion signal after wavelet classification according to the threshold value of the wavelet coefficient;
s23: and performing wavelet inverse transformation, and reconstructing the wavelet coefficient subjected to threshold processing to obtain a restored original signal.
4. A vibration detecting method according to claim 3, wherein the updating step of the coefficient of the vibration signal subjected to the wavelet classification comprises: when the coefficient of the local vibration signal after wavelet decomposition is larger than the threshold value of the wavelet coefficient, the original coefficient value is reserved; otherwise the coefficient is set to zero.
5. A shock detection method as claimed in claim 3, wherein the step of wavelet decomposing the collected seismic signals comprises:
s211: selecting any wavelet decomposition layer number K and a basis function, and carrying out wavelet decomposition on the collected earthquake motion signals to K layers to obtain a required wavelet decomposition coefficient;
s212: processing the obtained wavelet decomposition coefficient by a soft limiting function;
s213: reconstructing the wavelet coefficient subjected to threshold processing to obtain an estimated value of an original signal;
s214: changing the wavelet and repeating the steps to determine the wavelet base;
s215: after the wavelet base is determined, the wavelet decomposition layer number K is changed, and the wavelet decomposition layer number is obtained by repeating the steps.
6. The vibration detecting method of claim 1, wherein the signal modulating and amplifying circuit includes a first stage amplifying circuit formed of two symmetrical in-phase amplifiers and a second stage amplifying circuit formed of a differential amplifier.
7. The shock detection method of claim 1 wherein in the step of extracting features from the modulated and amplified seismic signal, the feature extraction comprises extracting one or more of time domain features, frequency domain features, parametric model features, gao Jiepu analysis, or nonlinear features.
8. The shock detection method of claim 1 wherein shock signal analysis comprises signal zero crossing analysis and welch algorithm analysis.
9. The vibration detection method according to claim 1, wherein after the step of feature extraction and vibration signal analysis of the earthquake motion signal after the signal modulation and amplification process, the method further comprises: and training a target recognition model by adopting the self-adaptive genetic algorithm model and the neural network.
10. A vibration detection system, the system comprising:
the signal acquisition module is used for acquiring the earthquake motion signal;
the wavelet analysis module is used for carrying out wavelet analysis processing on the collected earthquake motion signals;
the signal processing module is used for carrying out signal modulation and amplification processing on the earthquake motion signal after wavelet analysis processing;
and the signal analysis module is used for carrying out feature extraction and vibration signal analysis on the earthquake vibration signals subjected to signal modulation and amplification.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310280217.1A CN116299705A (en) | 2023-03-21 | 2023-03-21 | Vibration detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310280217.1A CN116299705A (en) | 2023-03-21 | 2023-03-21 | Vibration detection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116299705A true CN116299705A (en) | 2023-06-23 |
Family
ID=86802878
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310280217.1A Pending CN116299705A (en) | 2023-03-21 | 2023-03-21 | Vibration detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116299705A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6728645B1 (en) * | 2003-01-07 | 2004-04-27 | Electro-Optics Research & Development Ltd. | Method and system for automatic identification of objects type according to their characteristic spectrum of vibration frequencies |
| CN101575970A (en) * | 2008-05-09 | 2009-11-11 | 高岩 | Lithology while drilling and reservoir characteristics recognizing method |
| CN107356962A (en) * | 2017-07-14 | 2017-11-17 | 北京知觉科技有限公司 | Micro-seismic Signals localization method and device based on fibre optical sensor |
| US20210333425A1 (en) * | 2020-04-28 | 2021-10-28 | Xi'an Jiaotong University | Seismic Time-Frequency Analysis Method Based on Generalized Chirplet Transform with Time-Synchronized Extraction |
| CN115438765A (en) * | 2022-09-06 | 2022-12-06 | 中国人民解放军国防科技大学 | Moving target identification method, device and equipment based on evolutionary neural network |
-
2023
- 2023-03-21 CN CN202310280217.1A patent/CN116299705A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6728645B1 (en) * | 2003-01-07 | 2004-04-27 | Electro-Optics Research & Development Ltd. | Method and system for automatic identification of objects type according to their characteristic spectrum of vibration frequencies |
| CN101575970A (en) * | 2008-05-09 | 2009-11-11 | 高岩 | Lithology while drilling and reservoir characteristics recognizing method |
| CN107356962A (en) * | 2017-07-14 | 2017-11-17 | 北京知觉科技有限公司 | Micro-seismic Signals localization method and device based on fibre optical sensor |
| US20210333425A1 (en) * | 2020-04-28 | 2021-10-28 | Xi'an Jiaotong University | Seismic Time-Frequency Analysis Method Based on Generalized Chirplet Transform with Time-Synchronized Extraction |
| CN115438765A (en) * | 2022-09-06 | 2022-12-06 | 中国人民解放军国防科技大学 | Moving target identification method, device and equipment based on evolutionary neural network |
Non-Patent Citations (3)
| Title |
|---|
| 徐照胜: "地震动传感器的目标检测和识别算法研究", 中国优秀硕士学位论文全文数据库 信息科技辑, no. 11, pages 263 - 264 * |
| 陈亚亚: "基于地震动的地面移动目标识别研究", 中国优秀硕士学位论文全文数据库 信息科技辑, no. 11, pages 4 - 32 * |
| 龙礼 等: "基于GA-BP神经网络的目标识别方法", 传感器与微系统, vol. 38, no. 10, pages 48 - 49 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Sun et al. | Fault diagnosis of rolling bearing based on empirical mode decomposition and improved manhattan distance in symmetrized dot pattern image | |
| CN108680796B (en) | Electromagnetic information leakage detection system and method for computer display | |
| CN109827776B (en) | Bearing fault detection method and system | |
| CN108710777B (en) | Diversified anomaly detection identification method based on multi-convolution self-coding neural network | |
| CN103824302B (en) | The SAR image change detection merged based on direction wave area image | |
| CN113094993B (en) | Modulation signal denoising method based on self-coding neural network | |
| CN107392123B (en) | Radio frequency fingerprint feature extraction and identification method based on coherent accumulation noise elimination | |
| CN110133643B (en) | Plant root system detection method and device | |
| CN106886044A (en) | A kind of microseism first break pickup method based on shearing wave Yu Akaike's Information Criterion | |
| CN114595732B (en) | Radar radiation source sorting method based on depth clustering | |
| CN115640506B (en) | Magnetic particle distribution model reconstruction method and system based on time-frequency spectrum signal enhancement | |
| CN102800057A (en) | Image denoising method based on phase equalization for magnetic resonance imaging | |
| CN108961181A (en) | A kind of ground penetrating radar image denoising method based on shearlet transformation | |
| CN116153329A (en) | CWT-LBP-based sound signal time-frequency texture feature extraction method | |
| CN109409216B (en) | Speed self-adaptive indoor human body detection method based on subcarrier dynamic selection | |
| Li et al. | Magnetotelluric signal-noise separation method based on SVM–CEEMDWT | |
| CN106338651A (en) | Particle filter analysis method applied to lower frequency oscillation mode identification of power system | |
| CN117633588A (en) | Pipeline leakage positioning method based on spectrum weighting and residual convolution neural network | |
| CN116299705A (en) | Vibration detection method and system | |
| CN117473414A (en) | Bearing fault position identification method based on low-noise time-frequency image | |
| CN108197651A (en) | A kind of vehicle identification method based on vibrating sensor | |
| CN104200472A (en) | Non-local wavelet information based remote sensing image change detection method | |
| Orlic et al. | Earthquake—explosion discrimination using genetic algorithm-based boosting approach | |
| CN116910648A (en) | GIS equipment partial discharge spectrum analysis method, system and medium | |
| CN109002798B (en) | Single-lead visual evoked potential extraction method based on convolutional neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |