CN117743836B - Abnormal vibration monitoring method for bearing - Google Patents
Abnormal vibration monitoring method for bearing Download PDFInfo
- Publication number
- CN117743836B CN117743836B CN202410190095.1A CN202410190095A CN117743836B CN 117743836 B CN117743836 B CN 117743836B CN 202410190095 A CN202410190095 A CN 202410190095A CN 117743836 B CN117743836 B CN 117743836B
- Authority
- CN
- China
- Prior art keywords
- vibration
- period
- horizontal
- sequence
- bearing
- 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
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 134
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000012544 monitoring process Methods 0.000 title claims abstract description 22
- 230000009466 transformation Effects 0.000 claims abstract description 18
- 230000005856 abnormality Effects 0.000 claims abstract description 15
- 238000001514 detection method Methods 0.000 claims abstract description 12
- 230000000737 periodic effect Effects 0.000 claims abstract description 11
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 4
- 230000008859 change Effects 0.000 description 4
- 238000000354 decomposition reaction Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000007789 sealing Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/70—Wind energy
- Y02E10/72—Wind turbines with rotation axis in wind direction
Abstract
The invention relates to the technical field of electric digital data processing, in particular to a bearing abnormal vibration monitoring method, which comprises the following steps: amplitude signals of the bearings of each period in the horizontal direction and the vertical direction are collected, and a horizontal period amplitude sequence is obtained; performing wavelet transformation on the horizontal periodic amplitude sequence to obtain a horizontal vibration denoising sequence; obtaining a weight coefficient according to the difference between corresponding elements in the horizontal vibration denoising sequence of adjacent periods; acquiring a continuous amplitude difference index according to the horizontal vibration denoising sequence and the weight coefficient; obtaining the bearing horizontal abnormal vibration confidence coefficient according to the horizontal vibration denoising sequence and the difference between the continuous amplitude difference indexes, and simultaneously obtaining the bearing vertical abnormal vibration confidence coefficient so as to obtain an abnormal vibration confidence point; and obtaining a vibration abnormality detection result of the period in which the current moment is located according to the abnormal vibration confidence point. The invention can realize the implementation monitoring of the abnormal vibration of the bearing and improve the accuracy of the monitoring.
Description
Technical Field
The application relates to the technical field of brain signal data optimization processing, in particular to a bearing abnormal vibration monitoring method.
Background
With the gradual improvement of industrialization in China, the mechanical device becomes an indispensable component in the production process. Wherein the bearing is an important component in the machine for reducing friction between machine parts. Bearings are generally composed of an inner ring, an outer ring, rolling bodies, a cage and a sealing device, and are widely used in various machines due to their functions of reducing friction, bearing weight and protecting a rotation supporting portion.
When the bearing runs, regular reciprocating motion can be carried out near the balance position of the bearing, and abnormal vibration conditions can influence the service life of the bearing and even further influence the normal operation of a mechanical system. Therefore, the abnormal vibration of the bearing is monitored, and the method has important significance for normal operation and safety of a mechanical system. In the prior art, the characteristics of the vibration data of the bearing are few, and the amplitude of the vibration of the bearing is usually used for detecting the abnormal vibration of the bearing, but when the surrounding environment changes, the vibration sensor is abnormal, so that the amplitude can also change. Therefore, the accuracy of detecting abnormal vibration of the bearing depending only on the bearing vibration amplitude is not high.
Disclosure of Invention
In order to solve the technical problems, the invention provides a method for monitoring abnormal vibration of a bearing so as to solve the existing problems.
The invention relates to a method for monitoring abnormal vibration of a bearing, which adopts the following technical scheme:
one embodiment of the invention provides a method for monitoring abnormal vibration of a bearing, which comprises the following steps:
collecting amplitude signals of the bearing at each moment in each period in the horizontal direction and the vertical direction; obtaining a horizontal period amplitude sequence according to the amplitude signals of the bearing at each moment in the horizontal direction;
Decomposing the horizontal periodic amplitude sequence by using a wavelet function, and decomposing the horizontal periodic amplitude sequence into detail coefficient sequences of all scales; performing threshold processing on detail coefficients in the detail coefficient sequences of each scale, and performing wavelet transformation on the detail coefficients subjected to the threshold processing to obtain a horizontal vibration denoising sequence; obtaining a horizontal vibration differential sequence of the period of each moment according to all elements in the horizontal vibration denoising sequence of the period of each moment; obtaining a weight coefficient according to the difference between corresponding elements in the horizontal vibration denoising sequence of adjacent periods; acquiring a continuous amplitude difference index according to the horizontal vibration denoising sequence, the horizontal vibration difference sequence and the weight coefficient of the adjacent period; obtaining vibration abnormal characteristic differences according to differences between horizontal vibration denoising sequences of each period and other periods and continuous amplitude difference indexes; obtaining bearing horizontal abnormal vibration confidence coefficient of each period according to the difference between the vibration abnormal characteristic differences of the adjacent periods; for the amplitude signal of the bearing at each moment in each period in the vertical direction, the same acquisition method as the bearing horizontal abnormal vibration confidence is adopted to obtain the bearing vertical abnormal vibration confidence of each period; acquiring abnormal vibration confidence points according to the bearing horizontal abnormal vibration confidence degrees and the bearing vertical abnormal vibration confidence degrees of each period;
and obtaining a vibration abnormality detection result of the period in which the current moment is located according to the abnormal vibration confidence point.
Further, the obtaining a horizontal periodic amplitude sequence according to the amplitude signal of the bearing at each moment in the horizontal direction includes:
the sequence of amplitude signals of the period at each time in the horizontal direction is recorded as a horizontal period amplitude sequence of the period at each time.
Further, the thresholding is performed on the detail coefficients in the detail coefficient sequence of each scale, and wavelet transformation is performed on the detail coefficients after thresholding to obtain a horizontal vibration denoising sequence, which comprises the following steps:
For each detail coefficient in the detail coefficient sequence of each scale, when the absolute value of the detail coefficient is larger than or equal to a preset detail coefficient threshold value, directly taking the detail coefficient as the detail coefficient after threshold processing; otherwise, calculating the tangent value of the detail coefficient, and taking the product of a preset denoising factor and the tangent value as the detail coefficient after threshold processing; and obtaining the horizontal vibration denoising sequence of the period of each moment by inverse transformation in wavelet transformation for all the thresholded detail coefficients.
Further, the obtaining the horizontal vibration differential sequence of the period of each moment according to all the elements in the horizontal vibration denoising sequence of the period of each moment includes:
and taking the first-order differential sequence of the horizontal vibration denoising sequence of the period of each moment as the horizontal vibration differential sequence of the period of each moment.
Further, the obtaining the weight coefficient according to the difference between the corresponding elements in the horizontal vibration denoising sequence of the adjacent period includes:
The ith amplitude signal in the horizontal vibration denoising sequence of the period where the moment t is located is recorded as a first amplitude signal; the ith amplitude signal in the horizontal vibration denoising sequence of the period before the period where the t moment is positioned is recorded as a second amplitude signal; obtaining a maximum value between the absolute value of the first amplitude signal and the absolute value of the second amplitude signal, calculating the opposite number of the maximum value, obtaining an exponential function taking the opposite number as an index, wherein the natural constant is taken as a base number; and taking the difference value between 1 and the calculation result of the exponential function as a weight coefficient of an ith amplitude signal in the horizontal vibration denoising sequence of the period where the moment t is located.
Further, the continuous amplitude difference index is obtained according to the horizontal vibration denoising sequence, the horizontal vibration difference sequence and the weight coefficient of the adjacent period, and the expression is:
in the method, in the process of the invention, Horizontal vibration denoising sequence/>, representing period where time t is locatedContinuous amplitude difference index,/>Representing the number of amplitude signals acquired in one period,/>Horizontal vibration denoising sequence/>, which is period where time t is locatedWeight coefficient of i-th amplitude signal,/>Is a natural constant,/>Horizontal vibration differential sequence/>, which represents period where time t is locatedI-th element of (a)/>)Differential sequence of horizontal vibration representing the period preceding the period in which the moment t is located/>I-th element of (a)/>)Represent horizontal vibration denoising sequence/>Zero crossing rate of all amplitude signals in (1)/(Represent horizontal vibration denoising sequence/>Zero crossing rate of all amplitude signals in the system.
Further, the obtaining the vibration abnormal characteristic difference according to the difference between the horizontal vibration denoising sequence and the continuous amplitude difference index of each period and other periods includes:
Recording any period as a period to be analyzed, calculating cosine similarity between the period to be analyzed and a horizontal vibration denoising sequence among other periods, and obtaining a sum of 1 and the cosine similarity; obtaining the maximum value between the sum and a preset limiting factor; and taking the ratio of the continuous amplitude difference index of the horizontal vibration denoising sequence of the period to be analyzed to the maximum value as the vibration abnormal characteristic difference between the period to be analyzed and other periods.
Further, the obtaining the bearing horizontal abnormal vibration confidence of each period according to the difference between the vibration abnormal characteristic differences of the adjacent periods includes:
Marking any period as a period to be analyzed, and taking a preset number of periods before the period to be analyzed as a neighborhood period of the period to be analyzed; obtaining the sum value and the maximum value of the vibration abnormal characteristic differences between the period to be analyzed and all the neighborhood periods; calculating the difference between the sum and the maximum value, and recording the difference as a first difference; and calculating the difference value between the number of the neighborhood periods of the period to be analyzed and 1, recording the difference value as a second difference value, and taking the ratio of the first difference value to the second difference value as the bearing horizontal abnormal vibration confidence coefficient of the period to be analyzed.
Further, the obtaining the abnormal vibration confidence point according to the bearing horizontal abnormal vibration confidence and the bearing vertical abnormal vibration confidence of each period includes:
and taking the bearing horizontal abnormal vibration confidence coefficient as an abscissa and the bearing vertical abnormal vibration confidence coefficient as an ordinate, and marking a coordinate point formed by the bearing horizontal abnormal vibration confidence coefficient and the bearing vertical abnormal vibration confidence coefficient of each period as an abnormal vibration confidence point corresponding to each period.
Further, the obtaining the vibration abnormality detection result of the period in which the current moment is located according to the abnormal vibration confidence point includes:
performing anomaly detection on the anomaly vibration confidence points of all periods by using an LOF anomaly detection algorithm to obtain LOF outlier factors of each anomaly vibration confidence point;
If the LOF outlier factor of the abnormal vibration confidence point corresponding to the period of the current moment is greater than 1, the vibration of the bearing at the current moment is abnormal.
The invention has at least the following beneficial effects:
According to the method, when the bearing runs, abnormal conditions of vibration signals are analyzed, firstly, a threshold processing function in wavelet transformation is modified, and bearing amplitude signals acquired by using a vibration sensor are denoised so as to accurately remove noise interference; further, a continuous amplitude difference index is constructed by using a horizontal vibration denoising sequence, so that the difference between amplitude signals of the continuous bearing is accurately reflected, further, a vibration abnormal characteristic difference is constructed according to the continuous amplitude difference index, and the difference degree of the vibration abnormal characteristic between different periods is reflected, so that the abnormality of the vibration sensor and the interference of environmental factors are eliminated. According to the vibration abnormal characteristic differences between adjacent periods, the bearing horizontal abnormal vibration confidence coefficient is constructed, the bearing abnormal vibration of each period is detected by combining the bearing vertical abnormal vibration confidence coefficient, whether the bearing is abnormal or not is judged through the outlier degree of the two abnormal vibration confidence coefficients of the period where the current moment is located, and therefore the robustness of the vibration abnormal characteristic is higher. The method combines the characteristics of the amplitude signals, and effectively improves the accuracy of abnormal monitoring of the bearing abnormal amplitude signals.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of steps of a method for monitoring abnormal vibration of a bearing according to the present invention;
Fig. 2 is a flowchart for obtaining the confidence of the horizontal abnormal vibration of the bearing.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description is given below of a bearing abnormal vibration monitoring method according to the invention, which is specific to the implementation, structure, characteristics and effects thereof, with reference to the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of the method for monitoring abnormal vibration of a bearing provided by the invention with reference to the accompanying drawings.
The method for monitoring abnormal vibration of a bearing provided by an embodiment of the present invention, specifically, provides a method for monitoring abnormal vibration of a bearing, referring to fig. 1, the method includes the following steps:
and S001, acquiring amplitude signals of the bearing in the horizontal direction and the vertical direction.
Vibration sensors are arranged in the horizontal direction and the vertical direction of the bearing, and vibration conditions of the bearing in the two directions are continuously monitored. The amplitude signal exhibits a certain periodicity due to the operating characteristics of the bearing. The rotation speed of the bearing is obtained to be n circles per second, and the time for the bearing to rotate for one circle isIn seconds, the time of one revolution of the bearing is taken as one period, and zn data are acquired by the vibration sensor in one period. The amplitude signal of the bearing in the horizontal direction is denoted as X, and the amplitude signal in the vertical direction is denoted as Y. The sequence consisting of the amplitude signals of the period at the time t in the horizontal direction is recorded as a horizontal period amplitude sequence/>The sequence of amplitude signals of the period at the moment t in the vertical direction is denoted as vertical period amplitude sequence/>。
To this end, a horizontal periodic amplitude sequence of the bearing in the horizontal direction and a vertical periodic amplitude sequence in the vertical direction at each timing are obtained.
Step S002, denoising the horizontal periodic amplitude sequence to obtain a horizontal vibration denoising sequence; obtaining a continuous amplitude difference index according to the difference between corresponding elements in the horizontal vibration denoising sequence of adjacent periods; and obtaining the bearing horizontal abnormal vibration confidence coefficient of each period according to the horizontal vibration denoising sequence and the difference between the continuous amplitude difference indexes, and obtaining the abnormal vibration confidence coefficient by combining the vertical period amplitude sequence in the vertical direction.
The bearing has strong practicability as a key mechanical component. The bearing amplitude signal is used as information data representing the running state of the bearing, which implies that the mechanical component is key information of normal running. The embodiment aims to acquire the bearing horizontal abnormal vibration confidence according to the characteristic difference of the amplitude signals between adjacent periods, judge the abnormal condition of the bearing, and the specific flow is shown in fig. 2. Under normal conditions, the trend of the amplitude signal is the same in each period. In order to accurately reflect the trend characteristics of the amplitude signals, the wavelet transformation is used for removing noise in the original vibration data, is an analysis signal decomposition method, and overcomes the defect that the Fourier transformation has weak capability on local analysis and non-stationary signals. Due to the characteristic of cyclic repetition of vibration of the bearing, morlet wavelet function is used in wavelet transformation, and horizontal period amplitude sequence of the wavelet transformation to the period at the moment t is usedDenoising mainly comprises three steps of signal decomposition, thresholding and signal reconstruction. The wavelet change decomposes the amplitude signal into sub-data of a plurality of scales, the invention carries out 3-layer wavelet decomposition to obtain a detail coefficient sequence of three scales after decomposition，/>，/>. Defining a threshold selection function:
In the above-mentioned method, the step of, Representation/>The detail coefficient after threshold processing, Q represents a threshold selection function,/>For the detail coefficient threshold, the embodiment is set to 1.5, a is the denoising factor, and the embodiment is set to 0.07,/>For a sequence of detail coefficientsThe ith detail coefficient of (a); /(I)As a tangent function.
The wavelet transformation is used for the horizontal periodic amplitude sequence, and the phenomenon of poor reconstruction of the denoising sequence caused by the step change of the threshold value point is avoided through a selection function of a semi-soft threshold value. The bearing amplitude signal acquired by the vibration sensor is the sum of a real amplitude signal and noise, the detail coefficient corresponding to the effective vibration signal on the wavelet domain is larger, and the detail coefficient corresponding to the noise high-frequency signal is smaller, so that the high-frequency noise in the bearing amplitude signal is removed through a threshold selection function.
The detail coefficient of each detail coefficient sequence after threshold processing is subjected to inverse transformation in wavelet transformation to obtain a horizontal vibration denoising sequence of the period where the moment t is located。
For a bearing that is operating properly, the denoising sequence trend of its amplitude signal is similar, i.e., the up-down vibration of the bearing occurs at the same time in the cycle. The traditional Euclidean distance does not consider the characteristics of amplitude signals and the change of trend, can not accurately reflect the similarity condition of bearing amplitude signals, and carries out horizontal vibration denoising sequence of the period where the moment t isThe first-order differential sequence of (a) is used as a horizontal vibration differential sequence/>, of a period where the moment t is locatedThereby defining a continuous amplitude difference index:
in the method, in the process of the invention, Horizontal vibration denoising sequence/>, representing period where time t is locatedContinuous amplitude difference index,/>Representing the number of amplitude signals in a cycle,/>Horizontal vibration denoising sequence for period where t moment is locatedThe weight coefficient of the i-th amplitude signal in (a), e is a natural constant,/>Represents an exponential function with a base of a natural constant,Expressed as maximum value,/>An i-th amplitude signal in the horizontal vibration denoising sequence representing the period in which the time t is located,An i-th amplitude signal in a horizontal vibration denoising sequence representing the period preceding the period in which the time t is located,/>Horizontal vibration differential sequence/>, which represents period where time t is locatedThe i element in (1) reflects the variation trend of the i amplitude signal in the horizontal vibration denoising sequence,/>Differential sequence of horizontal vibration representing the period preceding the period in which the moment t is located/>I-th element of (a)/>)The zero crossing rate of all amplitude signals in the horizontal vibration denoising sequence of the period where the time t is located is shown, and the calculation of the zero crossing rate is a known technology and is not repeated.
The amplitude signal is given to the bearing vibration denoising sequence by the amplitude signal, so that the distance of the bearing amplitude signal is calculated according to the trend and the numerical value of the vibration. Because the bearing vibration denoising sequence shows the characteristics of up-and-down vibration, the data when vibration is generated is more focused, and the weight coefficient in the above formulaThe data points with larger vibration have larger weight coefficients, and the amplitude signals with smoother positions near the zero point have smaller weight coefficients. When vibration denoising sequenceThe difference value is small when the vibration trends are consistent, such as/>, when the vibration trends are inconsistentIs positive and/>A negative value indicates that the direction of vibration at the same position in the cycle is different, and the error at this time is unacceptable, and the error in this case is increased by the operation of squaring. When the amplitude signals are similar, the transformation trends are the same, so that the difference value of the amplitude signals is smaller, the zero crossing rate is similar to the denominator and is approximately 1, and the integral continuous amplitude difference index is smaller. In summary, the smaller the continuous amplitude difference index cdis between the two periods, the more similar the amplitude signal, and the less the probability of abnormal vibration of the bearing.
In order to monitor the vibration abnormality of the bearing conveniently, vibration abnormality characteristic differences are further constructed according to continuous amplitude difference indexes:
In the above-mentioned method, the step of, Representing vibration anomaly characteristic differences between period u and period v,/>Horizontal vibration denoising sequence representing period u,/>Horizontal vibration denoising sequence representing period v,/>Represent horizontal vibration denoising sequence/>And/>A continuous amplitude difference index between them,/(I)As cosine similarity function,/>The limiting factor is set to 0.1, which is the maximum value of the limiting denominator.
The vibration abnormal characteristic difference is constructed by further combining cosine similarity according to the continuous amplitude difference index, and the value domain of the cosine similarity is mapped between [0,2] by adding 1 to the cosine similarity. When the period u is similar to the amplitude signal in the horizontal direction of the adjacent period, the continuous amplitude difference indexThe cosine similarity of the vibration denoising sequence of two periods is close to 1, and the abnormal characteristics/>The denominator of (2) is close to 2, which means that the more similar the abnormal conditions of the period v and the period u are, the less the vibration abnormal characteristics of the whole body are. At the same time, in order to prevent the two vibration denoising sequences from being extremely dissimilar, thereby leading to the situation that the cosine similarity is approximate to-1 and the abnormal characteristic is infinite caused by the fact that the denominator is close to zero, the maximum value and the limiting factor/>, are adoptedTo limit the minimum of the outlier denominator.
The vibration abnormal characteristics of the bearing in one vibration period are calculated by comparing the current horizontal vibration denoising sequence with the previous horizontal vibration denoising sequence, however, in actual situations, the vibration abnormal of the bearing in one period may be caused by occasional abnormality of the vibration sensor instead of abnormality of the bearing. When there are a plurality of vibration abnormality characteristics that differ greatly in succession, the abnormal vibration of the bearing is only the abnormal vibration of the bearing. Therefore, it is necessary to determine the degree of abnormality according to the vibration abnormality characteristics of a plurality of vibration periods, record u periods before the period where the t moment is located as the neighborhood period of the period where the t moment is located, in this embodiment, u is 3 periods, and construct the bearing horizontal abnormal vibration confidence level：
In the above-mentioned method, the step of,The bearing horizontal abnormal vibration confidence coefficient of the period where the t moment is located is represented, u represents the number of neighborhood periods, and is expressed by the number of the neighborhood periodsRepresenting the vibration abnormality characteristic difference between the period at the time t and the first i periods of the period at the time t,/>Representing a function taking the maximum value.
The abnormal vibration confidence avoids the phenomenon that a single larger abnormal vibration characteristic is monitored due to occasional anomalies of the vibration sensor by removing the difference of the largest abnormal vibration characteristic. When the abnormal vibration characteristics between the period of the moment t and a certain period are larger, the maximum abnormal characteristics are subtracted from the denominator in the abnormal vibration confidence coefficient possibly caused by the abnormal vibration of the vibration sensor, and the average value is obtained, so that the relative stability of the abnormal vibration confidence coefficient is maintained, and the robustness is higher.
So far, according to the amplitude signal of the bearing in the horizontal direction, the bearing horizontal abnormal vibration confidence coefficient of each period is obtained, and similarly, according to the amplitude signal of the bearing in the vertical direction, the bearing vertical abnormal vibration confidence coefficient is obtained through calculation, and the method for obtaining the bearing vertical abnormal vibration confidence coefficient is the same as the method for obtaining the bearing horizontal abnormal vibration confidence coefficient. The bearing horizontal abnormal vibration confidence coefficient is taken as an abscissa, the bearing vertical abnormal vibration confidence coefficient is taken as an ordinate, and the two abnormal vibration confidence coefficients of each period are mapped into a two-dimensional plane, wherein the bearing horizontal abnormal vibration confidence coefficient of the period where the moment t is locatedConfidence of abnormal vibration perpendicular to bearing/>Constituted coordinate points/>The abnormal vibration confidence point corresponding to the period where the moment t is located is called.
Step S003, obtaining vibration abnormality detection results of the period where the current moment is located according to the abnormal vibration confidence points of all the periods.
Under the condition that the bearing normally operates, obtaining continuously detected abnormal vibration confidence points of all periods, carrying out abnormal detection on the abnormal vibration confidence points of all periods by using an LOF algorithm, and if the outlier factor of the abnormal vibration confidence point corresponding to the period where the current moment is located is larger than 1, considering that the vibration of the bearing is abnormal. The specific flow of the LOF anomaly detection algorithm is a well-known technique and will not be described in detail.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and the same or similar parts of each embodiment are referred to each other, and each embodiment mainly describes differences from other embodiments.
The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; the technical solutions described in the foregoing embodiments are modified or some of the technical features are replaced equivalently, so that the essence of the corresponding technical solutions does not deviate from the scope of the technical solutions of the embodiments of the present application, and all the technical solutions are included in the protection scope of the present application.
Claims (7)
1. A method for monitoring abnormal vibration of a bearing, the method comprising the steps of:
collecting amplitude signals of the bearing at each moment in each period in the horizontal direction and the vertical direction; obtaining a horizontal period amplitude sequence according to the amplitude signals of the bearing at each moment in the horizontal direction;
Decomposing the horizontal periodic amplitude sequence by using a wavelet function, and decomposing the horizontal periodic amplitude sequence into detail coefficient sequences of all scales; performing threshold processing on detail coefficients in the detail coefficient sequences of each scale, and performing wavelet transformation on the detail coefficients subjected to the threshold processing to obtain a horizontal vibration denoising sequence; obtaining a horizontal vibration differential sequence of the period of each moment according to all elements in the horizontal vibration denoising sequence of the period of each moment; obtaining a weight coefficient according to the difference between corresponding elements in the horizontal vibration denoising sequence of adjacent periods; acquiring a continuous amplitude difference index according to the horizontal vibration denoising sequence, the horizontal vibration difference sequence and the weight coefficient of the adjacent period; obtaining vibration abnormal characteristic differences according to differences between horizontal vibration denoising sequences of each period and other periods and continuous amplitude difference indexes; obtaining bearing horizontal abnormal vibration confidence coefficient of each period according to the difference between the vibration abnormal characteristic differences of the adjacent periods; for the amplitude signal of the bearing at each moment in each period in the vertical direction, the same acquisition method as the bearing horizontal abnormal vibration confidence is adopted to obtain the bearing vertical abnormal vibration confidence of each period; acquiring abnormal vibration confidence points according to the bearing horizontal abnormal vibration confidence degrees and the bearing vertical abnormal vibration confidence degrees of each period;
Obtaining a vibration abnormality detection result of the period in which the current moment is located according to the abnormal vibration confidence point;
The obtaining the weight coefficient according to the difference between the corresponding elements in the horizontal vibration denoising sequence of the adjacent period comprises the following steps:
The ith amplitude signal in the horizontal vibration denoising sequence of the period where the moment t is located is recorded as a first amplitude signal; the ith amplitude signal in the horizontal vibration denoising sequence of the period before the period where the t moment is positioned is recorded as a second amplitude signal; obtaining a maximum value between the absolute value of the first amplitude signal and the absolute value of the second amplitude signal, calculating the opposite number of the maximum value, obtaining an exponential function taking the opposite number as an index, wherein the natural constant is taken as a base number; taking the difference between 1 and the calculation result of the exponential function as a weight coefficient of an ith amplitude signal in a horizontal vibration denoising sequence of the period where the moment t is located;
the continuous amplitude difference index is obtained according to the horizontal vibration denoising sequence, the horizontal vibration difference sequence and the weight coefficient of the adjacent period, and the expression is as follows:
in the method, in the process of the invention, Horizontal vibration denoising sequence/>, representing period where time t is locatedIs a continuous amplitude difference index of (c),Representing the number of amplitude signals acquired in one period,/>Horizontal vibration denoising sequence for period where t moment is locatedWeight coefficient of i-th amplitude signal,/>Is a natural constant,/>Horizontal vibration differential sequence/>, which represents period where time t is locatedI-th element of (a)/>)Differential sequence of horizontal vibration representing the period preceding the period in which the moment t is located/>I-th element of (a)/>)Represent horizontal vibration denoising sequence/>Zero crossing rate of all amplitude signals in (1)/(Represent horizontal vibration denoising sequence/>Zero crossing rate of all amplitude signals in the system;
the vibration abnormal characteristic difference is obtained according to the difference between the horizontal vibration denoising sequence and the continuous amplitude difference index of each period and other periods, and the method comprises the following steps:
Recording any period as a period to be analyzed, calculating cosine similarity between the period to be analyzed and a horizontal vibration denoising sequence between other periods, and obtaining a sum value of the cosine similarity and 1; obtaining the maximum value between the sum and a preset limiting factor; and taking the ratio of the continuous amplitude difference index of the horizontal vibration denoising sequence of the period to be analyzed to the maximum value as the vibration abnormal characteristic difference between the period to be analyzed and other periods.
2. The method for monitoring abnormal vibration of a bearing according to claim 1, wherein the step of obtaining a horizontal periodic amplitude sequence from the amplitude signal of the bearing in the horizontal direction at each time comprises:
the sequence of amplitude signals of the period at each time in the horizontal direction is recorded as a horizontal period amplitude sequence of the period at each time.
3. The method for monitoring abnormal vibration of a bearing according to claim 1, wherein the thresholding of the detail coefficients in the detail coefficient sequence of each scale, and the wavelet transformation of the thresholded detail coefficients to obtain the horizontal vibration denoising sequence, comprises:
For each detail coefficient in the detail coefficient sequence of each scale, when the absolute value of the detail coefficient is larger than or equal to a preset detail coefficient threshold value, directly taking the detail coefficient as the detail coefficient after threshold processing; otherwise, calculating the tangent value of the detail coefficient, and taking the product of a preset denoising factor and the tangent value as the detail coefficient after threshold processing; and obtaining the horizontal vibration denoising sequence of the period of each moment by inverse transformation in wavelet transformation for all the thresholded detail coefficients.
4. The method for monitoring abnormal vibration of a bearing according to claim 1, wherein the step of obtaining the differential sequence of horizontal vibration in the period of each moment from all elements in the denoising sequence of horizontal vibration in the period of each moment comprises:
and taking the first-order differential sequence of the horizontal vibration denoising sequence of the period of each moment as the horizontal vibration differential sequence of the period of each moment.
5. The method for monitoring abnormal vibration of bearings according to claim 1, wherein said obtaining the confidence of abnormal vibration of the bearing level for each period based on the difference between the differences of the abnormal vibration characteristics of adjacent periods comprises:
Marking any period as a period to be analyzed, and taking a preset number of periods before the period to be analyzed as a neighborhood period of the period to be analyzed; obtaining the sum value and the maximum value of the vibration abnormal characteristic differences between the period to be analyzed and all the neighborhood periods; calculating the difference between the sum and the maximum value, and recording the difference as a first difference; and calculating the difference value between the number of the neighborhood periods of the period to be analyzed and 1, recording the difference value as a second difference value, and taking the ratio of the first difference value to the second difference value as the bearing horizontal abnormal vibration confidence coefficient of the period to be analyzed.
6. The method for monitoring abnormal vibration of a bearing according to claim 1, wherein the obtaining the abnormal vibration confidence point according to the bearing horizontal abnormal vibration confidence and the bearing vertical abnormal vibration confidence of each period comprises:
and taking the bearing horizontal abnormal vibration confidence coefficient as an abscissa and the bearing vertical abnormal vibration confidence coefficient as an ordinate, and marking a coordinate point formed by the bearing horizontal abnormal vibration confidence coefficient and the bearing vertical abnormal vibration confidence coefficient of each period as an abnormal vibration confidence point corresponding to each period.
7. The method for monitoring abnormal vibration of a bearing according to claim 1, wherein the step of obtaining the vibration abnormality detection result of the cycle at the current time according to the abnormal vibration confidence point comprises the steps of:
performing anomaly detection on the anomaly vibration confidence points of all periods by using an LOF anomaly detection algorithm to obtain LOF outlier factors of each anomaly vibration confidence point;
If the LOF outlier factor of the abnormal vibration confidence point corresponding to the period of the current moment is greater than 1, the vibration of the bearing at the current moment is abnormal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410190095.1A CN117743836B (en) | 2024-02-21 | 2024-02-21 | Abnormal vibration monitoring method for bearing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410190095.1A CN117743836B (en) | 2024-02-21 | 2024-02-21 | Abnormal vibration monitoring method for bearing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117743836A CN117743836A (en) | 2024-03-22 |
| CN117743836B true CN117743836B (en) | 2024-05-03 |
Family
ID=90259544
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410190095.1A Active CN117743836B (en) | 2024-02-21 | 2024-02-21 | Abnormal vibration monitoring method for bearing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117743836B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07218334A (en) * | 1994-02-07 | 1995-08-18 | Nippon Steel Corp | Method and device for diagnosing bearing |
| CN1677111A (en) * | 2004-03-19 | 2005-10-05 | 株式会社电装 | Vibration type angular velocity sensor |
| CN105241660A (en) * | 2015-11-09 | 2016-01-13 | 西南交通大学 | High-speed rail large-scale bridge performance evaluation method based on health monitoring data |
| CN105973621A (en) * | 2016-05-02 | 2016-09-28 | 国家电网公司 | Abnormal vibration analysis-based GIS (gas insulated switchgear) mechanical fault diagnosis method and system |
| CN108414240A (en) * | 2018-03-15 | 2018-08-17 | 广东工业大学 | A kind of method and apparatus of detection machine abnormal vibrations |
| CN112459971A (en) * | 2020-11-30 | 2021-03-09 | 吉电(滁州)章广风力发电有限公司 | Abnormal vibration detection method for tower of wind generating set |
| WO2021164267A1 (en) * | 2020-02-21 | 2021-08-26 | 平安科技（深圳）有限公司 | Anomaly detection method and apparatus, and terminal device and storage medium |
| CN115184016A (en) * | 2022-09-06 | 2022-10-14 | 江苏东控自动化科技有限公司 | Elevator bearing fault detection method |
| CN115935286A (en) * | 2022-11-29 | 2023-04-07 | 石家庄铁道大学 | Abnormal point detection method, device and terminal for railway bearing state monitoring data |
| CN116383750A (en) * | 2023-04-11 | 2023-07-04 | 大连理工大学 | Rolling bearing early-stage abnormality detection method based on windowed differential health index |
| CN116486146A (en) * | 2023-03-31 | 2023-07-25 | 华电电力科学研究院有限公司 | Fault detection method, system, device and medium for rotary mechanical equipment |
| CN116842348A (en) * | 2023-08-31 | 2023-10-03 | 安徽省云鹏工程项目管理有限公司 | Bridge health monitoring system based on artificial intelligence |
| CN117031277A (en) * | 2023-09-29 | 2023-11-10 | 苏州保邦电气有限公司 | Intelligent monitoring method for motor running state |
| CN117077064A (en) * | 2023-10-13 | 2023-11-17 | 云南滇能智慧能源有限公司 | Fault detection method, device and equipment for wind power equipment and storage medium |
| KR102608613B1 (en) * | 2023-06-07 | 2023-12-01 | 주식회사 성원 | Apparatus and method for ditecting equipment abnormality based on sensing data |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6879430B2 (en) * | 2018-03-23 | 2021-06-02 | 日本電気株式会社 | Abnormality diagnosis device, abnormality diagnosis method, and program |
-
2024
- 2024-02-21 CN CN202410190095.1A patent/CN117743836B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07218334A (en) * | 1994-02-07 | 1995-08-18 | Nippon Steel Corp | Method and device for diagnosing bearing |
| CN1677111A (en) * | 2004-03-19 | 2005-10-05 | 株式会社电装 | Vibration type angular velocity sensor |
| CN105241660A (en) * | 2015-11-09 | 2016-01-13 | 西南交通大学 | High-speed rail large-scale bridge performance evaluation method based on health monitoring data |
| CN105973621A (en) * | 2016-05-02 | 2016-09-28 | 国家电网公司 | Abnormal vibration analysis-based GIS (gas insulated switchgear) mechanical fault diagnosis method and system |
| CN108414240A (en) * | 2018-03-15 | 2018-08-17 | 广东工业大学 | A kind of method and apparatus of detection machine abnormal vibrations |
| WO2021164267A1 (en) * | 2020-02-21 | 2021-08-26 | 平安科技（深圳）有限公司 | Anomaly detection method and apparatus, and terminal device and storage medium |
| CN112459971A (en) * | 2020-11-30 | 2021-03-09 | 吉电(滁州)章广风力发电有限公司 | Abnormal vibration detection method for tower of wind generating set |
| CN115184016A (en) * | 2022-09-06 | 2022-10-14 | 江苏东控自动化科技有限公司 | Elevator bearing fault detection method |
| CN115935286A (en) * | 2022-11-29 | 2023-04-07 | 石家庄铁道大学 | Abnormal point detection method, device and terminal for railway bearing state monitoring data |
| CN116486146A (en) * | 2023-03-31 | 2023-07-25 | 华电电力科学研究院有限公司 | Fault detection method, system, device and medium for rotary mechanical equipment |
| CN116383750A (en) * | 2023-04-11 | 2023-07-04 | 大连理工大学 | Rolling bearing early-stage abnormality detection method based on windowed differential health index |
| KR102608613B1 (en) * | 2023-06-07 | 2023-12-01 | 주식회사 성원 | Apparatus and method for ditecting equipment abnormality based on sensing data |
| CN116842348A (en) * | 2023-08-31 | 2023-10-03 | 安徽省云鹏工程项目管理有限公司 | Bridge health monitoring system based on artificial intelligence |
| CN117031277A (en) * | 2023-09-29 | 2023-11-10 | 苏州保邦电气有限公司 | Intelligent monitoring method for motor running state |
| CN117077064A (en) * | 2023-10-13 | 2023-11-17 | 云南滇能智慧能源有限公司 | Fault detection method, device and equipment for wind power equipment and storage medium |
Non-Patent Citations (6)
| Title |
|---|
| Vehicle Bearing Fault Signal Detection Method Based on Long-Short-Term Memory Network;Pin Xia;AIAM2021: 2021 3rd International Conference on Artificial Intelligence and Advanced Manufacture;20220314;全文 * |
| 冯辅周 ; 司爱威 ; 饶国强 ; 江鹏程 ; .基于小波相关排列熵的轴承早期故障诊断技术.机械工程学报.2012,(第13期),全文. * |
| 周洪煜 ; 封帆帆 ; .基于小波分析的转炉轴承在线振动故障诊断系统.电气传动.2007,(第06期),全文. * |
| 李建国 等.电子式滚动轴承寿命强化试验机的研制.内燃机与配件.2019,(第第4期期),全文. * |
| 杨帆 ; 丁常富 ; 夏褚芮 ; 郭泰成 ; .风力发电机组轴承振动信号去噪方法分析研究.可再生能源.2014,(第12期),全文. * |
| 肖良瑜 ; 李建伟 ; 宋大凤 ; 曾小华 ; .立式屏蔽电机半速涡动异常振动试验分析.振动.测试与诊断.2015,(第02期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117743836A (en) | 2024-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Sun et al. | Bearing fault diagnosis based on EMD and improved Chebyshev distance in SDP image | |
| Jiao et al. | Deep coupled dense convolutional network with complementary data for intelligent fault diagnosis | |
| CN111353482B (en) | LSTM-based fatigue factor recessive anomaly detection and fault diagnosis method | |
| Zhao et al. | Convolution wavelet packet transform and its applications to signal processing | |
| CN111089726A (en) | Rolling bearing fault diagnosis method based on optimal dimension singular spectrum decomposition | |
| CN110989005B (en) | Weak magnetic anomaly self-adaptive real-time detection method based on scalar magnetometer array | |
| CN112559598B (en) | Telemetry time series data abnormity detection method and system based on graph neural network | |
| CN111678698A (en) | Rolling bearing fault detection method based on sound and vibration signal fusion | |
| CN113607415A (en) | Bearing fault diagnosis method based on short-time stochastic resonance under variable rotating speed | |
| CN112801497A (en) | Anomaly detection method and device | |
| CN113239970A (en) | Model training method, equipment vibration abnormity detection method and device | |
| CN117743836B (en) | Abnormal vibration monitoring method for bearing | |
| CN117093857B (en) | Rapid processing method for intelligent ring test data | |
| CN112648220A (en) | Fan fault diagnosis method based on wavelet-approximate entropy | |
| CN116933059A (en) | Fault identification method fusing variance and 1D-LBP | |
| CN112033656A (en) | Mechanical system fault detection method based on broadband spectrum processing | |
| CN116501183A (en) | Mouse displacement regulation and control method and system based on multi-sensor fusion | |
| CN110702786A (en) | Beam structure damage identification method based on multi-scale singular attractor prediction error | |
| CN113758708B (en) | Rolling bearing signal frequency domain fault diagnosis method based on L1 norm and group norm constraint | |
| CN114463258B (en) | Rolling stock brake pad abrasion detection method based on deep learning technology | |
| CN112683533A (en) | Signal enhancement method and system for bearing fault diagnosis | |
| CN105787444B (en) | Signal denoising method based on V system | |
| CN114705427A (en) | Rolling bearing intelligent fault diagnosis method under strong noise environment | |
| CN114090949A (en) | Robust vibration signal characteristic value calculation method | |
| KR20230100999A (en) | Method for determining dominant frequency of rotating machinery facilities, and computing system performing the same |
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 |