CN117609743B - 3D vision-based equipment data supervision method and system - Google Patents
3D vision-based equipment data supervision method and system Download PDFInfo
- Publication number
- CN117609743B CN117609743B CN202410098867.9A CN202410098867A CN117609743B CN 117609743 B CN117609743 B CN 117609743B CN 202410098867 A CN202410098867 A CN 202410098867A CN 117609743 B CN117609743 B CN 117609743B
- Authority
- CN
- China
- Prior art keywords
- signal
- vibration
- vibration signal
- characteristic analysis
- fluctuation
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 64
- 238000012545 processing Methods 0.000 claims abstract description 12
- 238000013507 mapping Methods 0.000 claims description 18
- 238000010606 normalization Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 3
- 238000007906 compression Methods 0.000 abstract description 6
- 230000006835 compression Effects 0.000 abstract description 6
- 230000006870 function Effects 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000033001 locomotion Effects 0.000 description 3
- 238000012216 screening Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013144 data compression Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
- G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
- G06F2218/04—Denoising
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to a device data supervision method and system based on 3D vision, wherein the method acquires a vibration signal of 3D vision equipment in a preset period, and acquires the signal fluctuation complexity and component characteristic analysis index of the vibration signal; according to the signal fluctuation complexity and the component characteristic analysis index of the vibration signal, a stopping criterion when the vibration signal is subjected to EMD decomposition is obtained, the vibration signal is subjected to EMD decomposition based on the stopping criterion, a corresponding decomposition result is obtained, supervision and storage are carried out on the decomposition result, and the number of IMFs generated after the vibration signal is subjected to EMD decomposition is reduced to the greatest extent by carrying out self-adaptive adjustment on the stopping criterion when the vibration signal is subjected to EMD decomposition, so that the positive influence of the follow-up compression storage and supervision treatment on the vibration signal is promoted.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a device data supervision method and system based on 3D vision.
Background
In the fields of robotics, unmanned automobiles, virtual reality, and augmented reality, 3D vision-based device data are of great value, including but not limited to depth images, point cloud data, and various other types of information collected by 3D cameras or laser radar (LiDAR). Meanwhile, a great amount of important vibration signal data exist in the working and running process of the 3D visual equipment, and the vibration signal data can intuitively reflect the physical motion state and the working performance of the equipment, for example: vibration signals of the equipment, such as vibration signals caused by mechanical movements such as lens rotation or sensor movement in the equipment, can be generated during operation of a laser radar or a stereo camera; or vibration signals caused by external environments such as an unmanned aerial vehicle or an unmanned aerial vehicle dynamic platform.
Since vibration signal data needs to be acquired at a high frequency by a corresponding sensor, a large amount of vibration signal data can be generated, so that great pressure is brought to storage, transmission and supervision of the large amount of vibration signal data, in the prior art, signal decomposition and compression processing are generally carried out on the vibration signal data by using EMD decomposition, and the EMD decomposition principle is that preprocessed target data is divided into a limited number of eigen mode functions (INTRINSIC MODE FUNCTIONS, IMF) by using EMD decomposition (empirical mode decomposition), abnormal detection is carried out by analyzing component change characteristics of each IMF, and IMFs with larger energy or more important information contribution are reserved to realize better data compression storage.
However, due to the diversity and complexity of the vibration signal data, the stability of the vibration signal compression and decomposition effects of the traditional EMD decomposition algorithm aiming at different characteristics is low, namely the vibration characteristics of the original vibration signal are very dependent, so that how to improve the positive influence of the IMF fluctuation obtained by decomposition on the vibration data storage supervision while guaranteeing the characteristics of the original vibration signal data becomes a problem to be solved.
Disclosure of Invention
In view of this, the embodiment of the invention provides a device data supervision method based on 3D vision, so as to solve the problem of how to improve the positive influence of IMF fluctuation obtained by decomposition on vibration data storage supervision while guaranteeing the data characteristics of original vibration signals.
In a first aspect, an embodiment of the present invention provides a device data supervision method based on 3D vision, where the device data supervision method includes the following steps:
Acquiring a vibration signal of the 3D vision equipment in a preset period to construct a vibration signal fluctuation curve of the vibration signal;
obtaining extreme points on the vibration signal fluctuation curve, and obtaining the signal fluctuation complexity of the vibration signal according to the number of the extreme points and the difference between the vibration amplitudes of all data points on the vibration signal fluctuation curve;
Acquiring a signal-to-noise ratio of the vibration signal according to the vibration amplitude of each data point on the vibration signal fluctuation curve, acquiring a maximum vibration amplitude on the vibration signal fluctuation curve, and acquiring a component characteristic analysis index of the vibration signal according to the signal-to-noise ratio, the number of the maximum vibration amplitudes and the number of the extreme points;
And acquiring a stopping criterion when the vibration signal is subjected to EMD decomposition according to the signal fluctuation complexity degree and the component characteristic analysis index of the vibration signal, performing EMD decomposition on the vibration signal based on the stopping criterion to obtain a corresponding decomposition result, and performing supervision and storage on the decomposition result.
Further, the obtaining the signal fluctuation complexity of the vibration signal according to the number of the extreme points and the difference between the vibration magnitudes of the data points on the vibration signal fluctuation curve includes:
acquiring the number of data points of zero crossing points on the vibration signal fluctuation curve, calculating the absolute value of the difference between the number of data points and the number of extreme points, and carrying out normalization processing on the absolute value of the difference to obtain a corresponding first normalization value;
According to the vibration amplitude of each data point on the vibration signal fluctuation curve, calculating to obtain a vibration amplitude variance, and carrying out normalization processing on the vibration amplitude variance to obtain a corresponding second normalization value;
and carrying out weighted summation on the first normalized value and the second normalized value, wherein the obtained weighted summation result is used as the signal fluctuation complexity of the vibration signal.
Further, the obtaining the signal-to-noise ratio of the vibration signal according to the vibration amplitude of each data point on the vibration signal fluctuation curve includes:
noise filtering is carried out on the vibration signals to obtain filtered vibration signals, and noise data points on a vibration signal fluctuation curve are obtained according to differences between the filtered vibration signals and the vibration signals;
And obtaining the signal to noise ratio of the vibration signal according to the vibration amplitude values of the noise data points and the non-noise data points on the vibration signal fluctuation curve.
Further, the obtaining the component characteristic analysis index of the vibration signal according to the signal-to-noise ratio, the number of the maximum vibration amplitude values and the number of the extreme points includes:
acquiring a normalized value of the maximum vibration amplitude, calculating a ratio between the number of the maximum vibration amplitude and the number of the extreme points, and carrying out weighted summation on the ratio and the normalized value of the maximum vibration amplitude to obtain a corresponding summation result;
And carrying out negative mapping on the signal to noise ratio to obtain a corresponding first mapping value, carrying out negative mapping on the summation result to obtain a corresponding second mapping value, and taking the result of weighted summation of the first mapping value and the second mapping value as a component characteristic analysis index of the vibration signal.
Further, the obtaining a stopping criterion when performing EMD decomposition on the vibration signal according to the signal fluctuation complexity and the component characteristic analysis index of the vibration signal includes:
And determining the signal category to which the vibration signal belongs according to the signal fluctuation complexity degree and the component characteristic analysis index of the vibration signal, and determining a stopping criterion when EMD decomposition is carried out on the vibration signal according to the signal category to which the vibration signal belongs.
Further, the determining, according to the signal fluctuation complexity and the component characteristic analysis index of the vibration signal, the signal class to which the vibration signal belongs includes:
acquiring a signal fluctuation complexity threshold and a component characteristic analysis index threshold;
if the signal fluctuation complexity of the vibration signal is greater than the signal fluctuation complexity threshold and the component characteristic analysis index is smaller than the component characteristic analysis index threshold, the signal class to which the vibration signal belongs is a first signal class;
If the signal fluctuation complexity of the vibration signal is smaller than or equal to the signal fluctuation complexity threshold, and the component characteristic analysis index is smaller than the component characteristic analysis index threshold, the signal class to which the vibration signal belongs is a second signal class;
If the signal fluctuation complexity of the vibration signal is greater than the signal fluctuation complexity threshold and the component characteristic analysis index is greater than or equal to the component characteristic analysis index threshold, the signal class to which the vibration signal belongs is a third signal class;
and if the signal fluctuation complexity of the vibration signal is smaller than or equal to the signal fluctuation complexity threshold and the component characteristic analysis index is larger than or equal to the component characteristic analysis index threshold, the signal class to which the vibration signal belongs is a fourth signal class.
Further, the stopping criterion during the EMD decomposition includes a standard deviation threshold, and the standard deviation threshold of the first signal class is smaller than the standard deviation threshold of the second signal class, the standard deviation threshold of the second signal class is smaller than the standard deviation threshold of the third signal class, and the standard deviation threshold of the third signal class is smaller than the standard deviation threshold of the fourth signal class.
In a second aspect, an embodiment of the present invention further provides a device data supervision system based on 3D vision, including a memory, a processor, and a computer program stored in the memory and running on the processor, where the processor implements the device data supervision method according to the first aspect when executing the computer program.
Compared with the prior art, the embodiment of the invention has the beneficial effects that:
The method comprises the steps of obtaining a vibration signal of the 3D vision equipment in a preset period to construct a vibration signal fluctuation curve of the vibration signal; obtaining extreme points on the vibration signal fluctuation curve, and obtaining the signal fluctuation complexity of the vibration signal according to the number of the extreme points and the difference between the vibration amplitudes of all data points on the vibration signal fluctuation curve; acquiring a signal-to-noise ratio of the vibration signal according to the vibration amplitude of each data point on the vibration signal fluctuation curve, acquiring a maximum vibration amplitude on the vibration signal fluctuation curve, and acquiring a component characteristic analysis index of the vibration signal according to the signal-to-noise ratio, the number of the maximum vibration amplitudes and the number of the extreme points; and acquiring a stopping criterion when the vibration signal is subjected to EMD decomposition according to the signal fluctuation complexity degree and the component characteristic analysis index of the vibration signal, performing EMD decomposition on the vibration signal based on the stopping criterion to obtain a corresponding decomposition result, and performing supervision and storage on the decomposition result. The vibration signal fluctuation curve of the 3D visual equipment is used for analyzing fluctuation characteristics and information components of the vibration signal in a preset period, so that the stopping criterion when the vibration signal is subjected to EMD decomposition is adaptively adjusted according to the analysis result, the number of IMFs generated after the vibration signal is decomposed by the EMD is reduced to the greatest extent on the premise that the decomposition result and the supervision effect of the vibration signal are not affected, and meanwhile, the decomposed IMFs are smoother, so that the positive influence of the follow-up compression storage and supervision processing of the vibration signal is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a method for supervising device data based on 3D vision according to an embodiment of the present invention.
Detailed Description
Embodiments of the present disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and intended for the purpose of explaining the present disclosure and are not to be construed as limiting the present disclosure.
It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the foregoing figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the disclosure described herein may be capable of operation in sequences other than those illustrated or described herein. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present disclosure as detailed in the accompanying claims.
The technical scheme of the application obtains, stores, uses, processes and the like the data, which all meet the relevant regulations of national laws and regulations. In order to illustrate the technical scheme of the application, the following description is made by specific examples.
Referring to fig. 1, a method flowchart of a device data supervision method based on 3D vision according to an embodiment of the present invention is shown in fig. 1, where the device data supervision method may include:
Step S101, acquiring a vibration signal of the 3D vision apparatus within a preset period to construct a vibration signal fluctuation curve of the vibration signal.
In the embodiment of the invention, according to the type of the 3D vision equipment, a corresponding sensor is selected to acquire vibration signal data of the 3D vision equipment, wherein the sensor comprises, but is not limited to, an accelerometer, a gyroscope and the like. Therefore, the vibration signal of the 3D vision equipment in a preset period (1 hour or one day) can be acquired, the vibration signal is transmitted to the computer through the wireless gateway, the computer guides the vibration signal into signal processing analysis software such as a MATLAB platform and Python software, and a vibration signal fluctuation curve of the vibration signal is drawn, and the vibration signal fluctuation curve can directly show the fluctuation mode of the vibration signal.
Step S102, extreme points on the vibration signal fluctuation curve are obtained, and the signal fluctuation complexity of the vibration signal is obtained according to the number of the extreme points and the difference between the vibration amplitudes of all the data points on the vibration signal fluctuation curve.
Since the stopping criteria of the EMD decomposition algorithm determines the number of execution of one eigenmode function (IMF) screening process, the screening process is typically performed based on the standard deviation (Standard Deviation, SD) between the current IMF and the IMF obtained in the last iteration, i.e., if the standard deviation is less than a preset standard deviation threshold, the screening process is stopped and the next IMF is started to be acquired.
The higher standard deviation threshold in the stopping criterion of the EMD decomposition algorithm can affect the number of IMFs obtained by EMD decomposition and the smoothness of the IMFs, and can lead the EMD decomposition to stop iterating earlier and start extracting the next IMF, so the higher standard deviation threshold can reduce the number of generated IMFs as a whole, and the higher standard deviation threshold means that larger differences are allowed, the obtained IMFs can be smoother globally, and the standard deviation threshold in the stopping criterion of the EMD decomposition algorithm can be heightened, although the decomposition process can be simplified to a certain extent and compression supervision results are optimized, the loss of certain details or characteristic information in data is caused, so the standard deviation threshold in the stopping criterion when the EMD decomposition is carried out on the vibration signal is adaptively set by carrying out feature analysis on the vibration signal fluctuation curve of the vibration signal.
Firstly, obtaining extreme points on a vibration signal fluctuation curve by using a first derivative, and then obtaining the signal fluctuation complexity of the vibration signal according to the number of the extreme points and the difference between the vibration amplitudes of all data points on the vibration signal fluctuation curve, wherein the specific obtaining method of the signal fluctuation complexity is as follows:
acquiring the number of data points of zero crossing points on the vibration signal fluctuation curve, calculating the absolute value of the difference between the number of data points and the number of extreme points, and carrying out normalization processing on the absolute value of the difference to obtain a corresponding first normalization value;
According to the vibration amplitude of each data point on the vibration signal fluctuation curve, calculating to obtain a vibration amplitude variance, and carrying out normalization processing on the vibration amplitude variance to obtain a corresponding second normalization value;
and carrying out weighted summation on the first normalized value and the second normalized value, wherein the obtained weighted summation result is used as the signal fluctuation complexity of the vibration signal.
In one embodiment, the computational expression of the signal fluctuation complexity of the vibration signal is:
Wherein represents the signal fluctuation complexity of the vibration signal,/> represents the first weight,/> represents the normalization function,/> represents the vibration amplitude of the ith data point on the vibration signal fluctuation curve,/> represents the mean value of the vibration amplitudes of all data points on the vibration signal fluctuation curve, N represents the total number of data points on the vibration signal fluctuation curve,/> represents the second weight,/> represents the number of extreme points on the vibration signal fluctuation curve,/> represents the zero crossing point on the vibration signal fluctuation curve (the data point with the vibration amplitude of 0 on the vibration signal fluctuation curve),/> represents the number of data points with zero crossing points on the vibration signal fluctuation curve, |represents the absolute sign,/> represents the vibration amplitude variance.
Preferably, in the embodiment of the present invention, if the first weight and the second weight are set to experience values, , the present invention is not limited, and may be set according to the scene.
It should be noted that, the vibration amplitude variance of all data points on the vibration signal fluctuation curve is calculated and used for representing the fluctuation degree of the vibration signal in the preset period, the smaller the vibration amplitude variance is, the more stable and concentrated the vibration signal fluctuation in the preset period is, the larger vibration amplitude or intense vibration is not generated by the 3D vision equipment, the smaller the signal fluctuation complexity of the corresponding vibration signal is, otherwise, the larger the vibration amplitude variance is, the more complex or intense fluctuation characteristics exist in the 3D vision equipment, and the larger the signal fluctuation complexity of the corresponding vibration signal is; meanwhile, the more the number of data points of the zero crossing points is, the more stable the vibration signal is, the more the number of extreme points is, and the more intense the fluctuation of the vibration signal is, so that the larger the difference/> between the number of data points of the zero crossing points and the number of the extreme points is, the worse the fluctuation stability of the vibration signal is, and the greater the signal fluctuation complexity of the corresponding vibration signal is.
Step S103, according to the vibration amplitude of each data point on the vibration signal fluctuation curve, obtaining the signal-to-noise ratio of the vibration signal, obtaining the maximum vibration amplitude on the vibration signal fluctuation curve, and according to the signal-to-noise ratio, the number of the maximum vibration amplitudes and the number of extreme points, obtaining the component characteristic analysis index of the vibration signal.
In the embodiment of the invention, after the signal fluctuation complexity of the vibration signal is obtained, the characteristic analysis of the information components contained in the vibration signal is carried out according to the fluctuation curve of the vibration signal so as to detect the noise degree and the high-frequency information content in the vibration signal. Firstly, according to the vibration amplitude of each data point on the vibration signal fluctuation curve, the signal-to-noise ratio of the vibration signal is obtained, and the specific obtaining method of the signal-to-noise ratio of the vibration signal is as follows: noise filtering is carried out on the vibration signals to obtain filtered vibration signals, and noise data points on a vibration signal fluctuation curve are obtained according to differences between the filtered vibration signals and the vibration signals; and obtaining the signal to noise ratio of the vibration signal according to the vibration amplitude values of the noise data points and the non-noise data points on the vibration signal fluctuation curve.
In one embodiment, first, according to an effective frequency range of the vibration signal, a band-pass filter is used to filter noise of other frequencies to obtain a filtered vibration signal, and then, by subtracting the original vibration signal from the filtered vibration signal, noise data points on a vibration signal fluctuation curve can be obtained. Counting the number of non-noise data points (signal data points) on a vibration signal fluctuation curve, namely , and the number of noise data points, namely/> , and acquiring the signal-to-noise ratio of the vibration signal according to the number of the non-noise data points and the vibration amplitude thereof, wherein the calculation expression of the signal-to-noise ratio of the vibration signal is as follows:
Where denotes the signal-to-noise ratio of the vibration signal,/> denotes a logarithmic function based on a constant of 10,/> denotes the vibration amplitude of the ith non-noise data point,/> denotes the vibration amplitude of the ith noise data point,/> denotes the number of non-noise data points, and/> denotes the number of noise data points.
It should be noted that, the signal-to-noise ratio is a common indicator for measuring the signal quality, and the higher the signal-to-noise ratio, the lower the noise level in the vibration signal.
Further, analyzing high-frequency information contained in the vibration signal, acquiring a maximum vibration amplitude according to the vibration amplitude of each data point on the vibration signal fluctuation curve, counting the number of the maximum vibration amplitudes, and further acquiring a component characteristic analysis index of the vibration signal according to the signal-to-noise ratio, the number of the maximum vibration amplitudes and the number of extreme points on the vibration signal fluctuation curve, wherein the acquisition method of the component characteristic analysis index of the vibration signal is as follows:
acquiring a normalized value of the maximum vibration amplitude, calculating a ratio between the number of the maximum vibration amplitude and the number of the extreme points, and carrying out weighted summation on the ratio and the normalized value of the maximum vibration amplitude to obtain a corresponding summation result;
And carrying out negative mapping on the signal to noise ratio to obtain a corresponding first mapping value, carrying out negative mapping on the summation result to obtain a corresponding second mapping value, and taking the result of weighted summation of the first mapping value and the second mapping value as a component characteristic analysis index of the vibration signal.
In one embodiment, the calculation expression of the component characteristic analysis index of the vibration signal is:
Wherein denotes a component characteristic analysis index of the vibration signal,/> denotes a third weight,/> denotes an exponential function based on a natural constant e,/> denotes a signal-to-noise ratio of the vibration signal,/> denotes a fourth weight,/> denotes a normalization function,/> denotes a maximum vibration amplitude on the vibration signal fluctuation curve,/> denotes a number of maximum vibration amplitudes on the vibration signal fluctuation curve,/> denotes a number of extreme points on the vibration signal fluctuation curve,/> denotes a first weight coefficient, and/> denotes a second weight coefficient.
Preferably, in the embodiment of the present invention, an empirical value , is given, which is not limited, and may be set according to the scene.
The higher the signal-to-noise ratio is, the lower the noise level in the vibration signal is, and the smaller the component characteristic analysis index of the corresponding vibration signal is; the maximum vibration amplitude represents high-frequency information in the vibration signal, the more the number of the maximum vibration amplitudes on the vibration signal fluctuation curve is, the more the high-frequency information in the corresponding vibration signal is, the vibration amplitude corresponding to the extreme point on the vibration signal fluctuation curve comprises the minimum vibration amplitude and the maximum vibration amplitude of the vibration signal, therefore, the larger the ratio/> between the number of the maximum vibration amplitude and the number of the extreme point is, the more the high-frequency information in the vibration signal is, the smaller the component characteristic analysis index of the corresponding vibration signal is, and the inaccuracy is obtained by subsequently heightening the standard deviation threshold value when the EMD is decomposed.
Step S104, according to the signal fluctuation complexity and the component characteristic analysis index of the vibration signal, a stopping criterion when the vibration signal is subjected to EMD decomposition is obtained, the vibration signal is subjected to EMD decomposition based on the stopping criterion, a corresponding decomposition result is obtained, and the decomposition result is subjected to supervision and storage.
In the embodiment of the invention, the analysis of the complexity of signal fluctuation of the vibration signal is considered to be an important reference for the standard deviation threshold value in the stopping criterion when the EMD decomposition is adjustable, and the standard deviation threshold value is adjusted to be higher for the vibration signal with simple relative fluctuation and severe fluctuation, so that important characteristics are not lost; secondly, it is considered that if the noise level of the vibration signal is higher, the higher the standard deviation threshold can be better to help suppress the influence of noise, the higher the necessary degree corresponding to the higher standard deviation threshold is, and if the intensity of the high-frequency information contained in the vibration signal is lower or occupies less, the vibration signal is more suitable for the standard deviation threshold of the heightening stop criterion, thereby reducing the influence of the component. Therefore, according to the signal fluctuation complexity and the component characteristic analysis index of the vibration signal, a stopping criterion when the vibration signal is subjected to EMD decomposition is obtained, specifically:
And determining the signal category to which the vibration signal belongs according to the signal fluctuation complexity degree and the component characteristic analysis index of the vibration signal, and determining a stopping criterion when EMD decomposition is carried out on the vibration signal according to the signal category to which the vibration signal belongs.
Preferably, determining the signal category to which the vibration signal belongs according to the signal fluctuation complexity and the component characteristic analysis index of the vibration signal includes:
acquiring a signal fluctuation complexity threshold and a component characteristic analysis index threshold;
if the signal fluctuation complexity of the vibration signal is greater than the signal fluctuation complexity threshold and the component characteristic analysis index is smaller than the component characteristic analysis index threshold, the signal class to which the vibration signal belongs is a first signal class;
If the signal fluctuation complexity of the vibration signal is smaller than or equal to the signal fluctuation complexity threshold, and the component characteristic analysis index is smaller than the component characteristic analysis index threshold, the signal class to which the vibration signal belongs is a second signal class;
If the signal fluctuation complexity of the vibration signal is greater than the signal fluctuation complexity threshold and the component characteristic analysis index is greater than or equal to the component characteristic analysis index threshold, the signal class to which the vibration signal belongs is a third signal class;
and if the signal fluctuation complexity of the vibration signal is smaller than or equal to the signal fluctuation complexity threshold and the component characteristic analysis index is larger than or equal to the component characteristic analysis index threshold, the signal class to which the vibration signal belongs is a fourth signal class.
In one embodiment, the expression for determining the signal class to which the vibration signal belongs according to the signal fluctuation complexity and the component characteristic analysis index is:
wherein denotes a signal fluctuation complexity threshold, and/() denotes a component characteristic analysis index threshold.
Preferably, in the embodiment of the present invention, and this is not a limitation, and the implementer may set itself according to the implementation scenario.
In the embodiment of the invention, the first signal category means that the signal fluctuation complexity is higher and the component characteristics are lower, so that the necessity of the adjustment of the standard deviation threshold value of the vibration signal is lower, and the standard deviation threshold value of the vibration signal during EMD decomposition can not be adjusted so as not to lose more important data; the second signal class refers to a signal with lower complexity but lower component characteristics; the standard deviation threshold value of the vibration signals can be finely adjusted when EMD decomposition is carried out; the third signal class refers to that the signal fluctuation complexity is higher but the component characteristics are higher, so that the necessity of raising the standard deviation threshold value of the vibration signal in EMD decomposition is slightly larger than that of the second signal class; the fourth signal class means that not only the signal fluctuation complexity is low, but also the component characteristics are high, and the necessity of heightening the standard deviation threshold value of the vibration signal class is maximum when the EMD decomposition is performed, so that the standard deviation threshold value of the first signal class is smaller than the standard deviation threshold value of the second signal class, the standard deviation threshold value of the second signal class is smaller than the standard deviation threshold value of the third signal class, and the standard deviation threshold value of the third signal class is smaller than the standard deviation threshold value of the fourth signal class. Further, after determining the signal type to which the vibration signal belongs, the standard deviation threshold of the signal type can be used as a stopping criterion when the vibration signal is subjected to EMD decomposition.
In one embodiment, considering that in Empirical Mode Decomposition (EMD), the standard stopping criterion is typically calculated based on the local mean of the signal, and the conventional standard deviation threshold range is [0.2,0.3], taking 0.3 as an example, the standard deviation threshold of the first signal class is set to 0.3, the standard deviation threshold of the second signal class is set to 0.5, the standard deviation threshold of the third signal class is set to 0.7, and the standard deviation threshold of the fourth signal class is set to 1.
It should be noted that, in the embodiment of the present invention, the setting of the standard deviation threshold values of the first signal category, the second signal category, the third signal category and the fourth signal category is not limited.
Further, after the standard deviation threshold in the stop criterion when the vibration signal is subjected to EMD decomposition is obtained, the vibration signal is subjected to EMD decomposition, thereby obtaining a plurality of IMFs. After a plurality of IMFs are obtained, the IMFs can be stored in a compressed mode, and vibration data of the 3D visual equipment can be monitored. It should be noted that, the EMD decomposition of the signal belongs to the prior art, and is not described herein; how to perform supervision and storage on the IMF obtained by performing EMD decomposition on the vibration signal does not belong to the key point of the present invention, and is not described here again.
In summary, the vibration signal of the 3D vision device in the preset period is obtained, so as to construct a vibration signal fluctuation curve of the vibration signal; obtaining extreme points on a vibration signal fluctuation curve, and obtaining the signal fluctuation complexity of the vibration signal according to the number of the extreme points and the difference between the vibration amplitudes of all the data points on the vibration signal fluctuation curve; acquiring a signal-to-noise ratio of the vibration signal according to the vibration amplitude of each data point on the vibration signal fluctuation curve, acquiring the maximum vibration amplitude on the vibration signal fluctuation curve, and acquiring a component characteristic analysis index of the vibration signal according to the signal-to-noise ratio, the number of the maximum vibration amplitudes and the number of extreme points; according to the signal fluctuation complexity and the component characteristic analysis index of the vibration signal, a stopping criterion when the vibration signal is subjected to EMD decomposition is obtained, the vibration signal is subjected to EMD decomposition based on the stopping criterion, a corresponding decomposition result is obtained, and the decomposition result is subjected to supervision and storage. The vibration signal fluctuation curve of the 3D visual equipment is used for analyzing fluctuation characteristics and information components of the vibration signal in a preset period, so that the stopping criterion when the vibration signal is subjected to EMD decomposition is adaptively adjusted according to the analysis result, the number of IMFs generated after the vibration signal is decomposed by the EMD is reduced to the greatest extent on the premise that the decomposition result and the supervision effect of the vibration signal are not affected, and meanwhile, the decomposed IMFs are smoother, so that the positive influence of the follow-up compression storage and supervision processing of the vibration signal is improved.
Based on the same inventive concept as the above method, the embodiment of the invention further provides a 3D vision-based device data supervision system, which comprises a memory, a processor and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of any one of the above 3D vision-based device data supervision methods when executing the computer program.
The above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention.
Claims (7)
1. The 3D vision-based equipment data supervision method is characterized by comprising the following steps of:
Acquiring a vibration signal of the 3D vision equipment in a preset period to construct a vibration signal fluctuation curve of the vibration signal;
obtaining extreme points on the vibration signal fluctuation curve, and obtaining the signal fluctuation complexity of the vibration signal according to the number of the extreme points and the difference between the vibration amplitudes of all data points on the vibration signal fluctuation curve;
Acquiring a signal-to-noise ratio of the vibration signal according to the vibration amplitude of each data point on the vibration signal fluctuation curve, acquiring a maximum vibration amplitude on the vibration signal fluctuation curve, and acquiring a component characteristic analysis index of the vibration signal according to the signal-to-noise ratio, the number of the maximum vibration amplitudes and the number of the extreme points;
Acquiring a stopping criterion when the vibration signal is subjected to EMD decomposition according to the signal fluctuation complexity degree and the component characteristic analysis index of the vibration signal, performing EMD decomposition on the vibration signal based on the stopping criterion to obtain a corresponding decomposition result, and performing supervision and storage on the decomposition result;
the obtaining the signal fluctuation complexity of the vibration signal according to the number of the extreme points and the difference between the vibration amplitudes of the data points on the vibration signal fluctuation curve comprises the following steps:
acquiring the number of data points of zero crossing points on the vibration signal fluctuation curve, calculating the absolute value of the difference between the number of data points and the number of extreme points, and carrying out normalization processing on the absolute value of the difference to obtain a corresponding first normalization value;
According to the vibration amplitude of each data point on the vibration signal fluctuation curve, calculating to obtain a vibration amplitude variance, and carrying out normalization processing on the vibration amplitude variance to obtain a corresponding second normalization value;
and carrying out weighted summation on the first normalized value and the second normalized value, wherein the obtained weighted summation result is used as the signal fluctuation complexity of the vibration signal.
2. The 3D vision-based device data supervision method according to claim 1, wherein the obtaining the signal-to-noise ratio of the vibration signal according to the vibration amplitude of each data point on the vibration signal fluctuation curve includes:
noise filtering is carried out on the vibration signals to obtain filtered vibration signals, and noise data points on a vibration signal fluctuation curve are obtained according to differences between the filtered vibration signals and the vibration signals;
And obtaining the signal to noise ratio of the vibration signal according to the vibration amplitude values of the noise data points and the non-noise data points on the vibration signal fluctuation curve.
3. The 3D vision-based device data supervision method according to claim 1, wherein the obtaining the component characteristic analysis index of the vibration signal according to the signal-to-noise ratio, the number of the maximum vibration amplitudes, and the number of the extreme points includes:
acquiring a normalized value of the maximum vibration amplitude, calculating a ratio between the number of the maximum vibration amplitude and the number of the extreme points, and carrying out weighted summation on the ratio and the normalized value of the maximum vibration amplitude to obtain a corresponding summation result;
And carrying out negative mapping on the signal to noise ratio to obtain a corresponding first mapping value, carrying out negative mapping on the summation result to obtain a corresponding second mapping value, and taking the result of weighted summation of the first mapping value and the second mapping value as a component characteristic analysis index of the vibration signal.
4. The 3D vision-based device data supervision method according to claim 1, wherein the obtaining a stopping criterion when performing EMD decomposition on the vibration signal according to the signal fluctuation complexity and the component characteristic analysis index of the vibration signal includes:
And determining the signal category to which the vibration signal belongs according to the signal fluctuation complexity degree and the component characteristic analysis index of the vibration signal, and determining a stopping criterion when EMD decomposition is carried out on the vibration signal according to the signal category to which the vibration signal belongs.
5. The 3D vision-based device data supervision method according to claim 4, wherein the determining the signal category to which the vibration signal belongs according to the signal fluctuation complexity and the component characteristic analysis index of the vibration signal includes:
acquiring a signal fluctuation complexity threshold and a component characteristic analysis index threshold;
if the signal fluctuation complexity of the vibration signal is greater than the signal fluctuation complexity threshold and the component characteristic analysis index is smaller than the component characteristic analysis index threshold, the signal class to which the vibration signal belongs is a first signal class;
If the signal fluctuation complexity of the vibration signal is smaller than or equal to the signal fluctuation complexity threshold, and the component characteristic analysis index is smaller than the component characteristic analysis index threshold, the signal class to which the vibration signal belongs is a second signal class;
If the signal fluctuation complexity of the vibration signal is greater than the signal fluctuation complexity threshold and the component characteristic analysis index is greater than or equal to the component characteristic analysis index threshold, the signal class to which the vibration signal belongs is a third signal class;
and if the signal fluctuation complexity of the vibration signal is smaller than or equal to the signal fluctuation complexity threshold and the component characteristic analysis index is larger than or equal to the component characteristic analysis index threshold, the signal class to which the vibration signal belongs is a fourth signal class.
6. The 3D vision-based device data supervision method according to claim 5, wherein the stopping criteria when the EMD is decomposed includes a standard deviation threshold, and the standard deviation threshold of the first signal class is smaller than the standard deviation threshold of the second signal class, and the standard deviation threshold of the second signal class is smaller than the standard deviation threshold of the third signal class, and the standard deviation threshold of the third signal class is smaller than the standard deviation threshold of the fourth signal class.
7. A 3D vision-based device data supervision system comprising a memory, a processor and a computer program stored in the memory and running on the processor, characterized in that the processor implements the steps of a 3D vision-based device data supervision method according to any one of the claims 1 to 6 when the computer program is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410098867.9A CN117609743B (en) | 2024-01-24 | 2024-01-24 | 3D vision-based equipment data supervision method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410098867.9A CN117609743B (en) | 2024-01-24 | 2024-01-24 | 3D vision-based equipment data supervision method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117609743A CN117609743A (en) | 2024-02-27 |
| CN117609743B true CN117609743B (en) | 2024-04-16 |
Family
ID=89944749
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410098867.9A Active CN117609743B (en) | 2024-01-24 | 2024-01-24 | 3D vision-based equipment data supervision method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117609743B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109341848A (en) * | 2018-09-26 | 2019-02-15 | 东莞青柳新材料有限公司 | A kind of safety monitoring system of tunnel operation stage |
| CN110068388A (en) * | 2019-03-29 | 2019-07-30 | 南京航空航天大学 | A kind of method for detecting vibration of view-based access control model and blind source separating |
| DE102022203238A1 (en) * | 2022-04-01 | 2023-10-05 | Robert Bosch Gesellschaft mit beschränkter Haftung | Method for classifying operating points using sound signals |
-
2024
- 2024-01-24 CN CN202410098867.9A patent/CN117609743B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109341848A (en) * | 2018-09-26 | 2019-02-15 | 东莞青柳新材料有限公司 | A kind of safety monitoring system of tunnel operation stage |
| CN110068388A (en) * | 2019-03-29 | 2019-07-30 | 南京航空航天大学 | A kind of method for detecting vibration of view-based access control model and blind source separating |
| DE102022203238A1 (en) * | 2022-04-01 | 2023-10-05 | Robert Bosch Gesellschaft mit beschränkter Haftung | Method for classifying operating points using sound signals |
Non-Patent Citations (2)
| Title |
|---|
| Video-Based Vibration Measurement Using an Unmanned Aerial Vehicle: An Anti-Disturbance Algorithm for the Shaking of Airborne Cameras;Zongdi Zang等;《IEEE Transactions on Instrumentation and Measurement》;20230818;第72卷;全文 * |
| 风电机组振动监测与故障预测***;赵洪山;徐樊浩;徐文岐;高夺;;陕西电力;20160720(07);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117609743A (en) | 2024-02-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111582054B (en) | Point cloud data processing method and device and obstacle detection method and device | |
| CN116309757B (en) | Binocular stereo matching method based on machine vision | |
| CN109640224B (en) | Pickup method and device | |
| CN111624567A (en) | Constant false alarm detection method and device | |
| CN117272210A (en) | Method and system for detecting abnormal hidden danger data of building construction | |
| CN117454085B (en) | Vehicle online monitoring method and system | |
| CN116955938A (en) | Dry-type waste gas treatment equipment monitoring method and system based on data analysis | |
| CN111369458A (en) | Infrared dim target background suppression method based on multi-scale rolling guide filtering smoothing | |
| CN114862828A (en) | Light spot searching method and device, computer readable medium and electronic equipment | |
| CN117609743B (en) | 3D vision-based equipment data supervision method and system | |
| CN118015808A (en) | Intelligent security monitoring method and system | |
| CN111126456B (en) | Neural network model processing method, device, equipment and storage medium | |
| CN113486861A (en) | Moire pattern picture generation method and device | |
| CN117934897A (en) | Equipment abnormality detection method, device, equipment and storage medium | |
| CN113259589A (en) | Binocular camera intelligent sensing method with base line self-adaptive adjustment and device thereof | |
| CN112420066A (en) | Noise reduction method, noise reduction device, computer equipment and computer readable storage medium | |
| CN111580049A (en) | Dynamic target sound source tracking and monitoring method and terminal equipment | |
| CN114972950A (en) | Multi-target detection method, device, equipment, medium and product | |
| CN113920273A (en) | Image processing method, image processing device, electronic equipment and storage medium | |
| CN114387324A (en) | Depth imaging method, depth imaging device, electronic equipment and computer readable storage medium | |
| CN110135305B (en) | Method, apparatus, device and medium for fatigue detection | |
| CN113920023A (en) | Image processing method and device, computer readable medium and electronic device | |
| CN111190169A (en) | Radar data filtering method and device, electronic device and storage medium | |
| CN112578909B (en) | Method and device for equipment interaction | |
| CN117351470B (en) | Operator fatigue detection method based on space-time characteristics |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |