CN115130064A - Vibration data anomaly detection method, device, equipment and storage medium - Google Patents
Vibration data anomaly detection method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN115130064A CN115130064A CN202210874037.1A CN202210874037A CN115130064A CN 115130064 A CN115130064 A CN 115130064A CN 202210874037 A CN202210874037 A CN 202210874037A CN 115130064 A CN115130064 A CN 115130064A
- Authority
- CN
- China
- Prior art keywords
- vibration data
- target
- historical
- probability distribution
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Mathematical Analysis (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The application provides a method, a device, equipment and a storage medium for detecting abnormal vibration data, wherein the method comprises the following steps: acquiring target vibration data to be detected, acquisition time of the target vibration data and a historical vibration data sequence corresponding to the target vibration data; generating a probability distribution function corresponding to the acquisition time according to each historical vibration data in the historical vibration data sequence; obtaining a confidence interval based on the probability distribution function and the statistical characteristics corresponding to the probability distribution function; and carrying out abnormity detection on the target vibration data based on the confidence interval. The confidence interval for judging the target vibration data to be detected is determined for the historical targeted data, and the abnormity of the target vibration data to be detected is judged through the confidence interval, so that the accuracy of the judgment result is ensured.
Description
Technical Field
The application relates to the technical field of vibration data processing, in particular to a vibration data abnormity detection method, device, equipment and storage medium.
Background
As industrial production gradually enters the mechanical era, mechanical equipment used for production in industry and manufacturing industry is continuously developing towards large-scale, precise and automatic, and in order to ensure safe and normal operation of the machinery and avoid serious economic and property loss caused by faults such as equipment deterioration and damage, fault diagnosis of the mechanical equipment is increasingly regarded by people.
Since the vibration signal of the mechanical equipment contains a large amount of information of the working process of the equipment, the fault diagnosis of the mechanical equipment is generally performed by detecting the abnormality of the vibration signal. In the related technology, the vibration data is mainly judged through experience accumulation of workers, and the judgment accuracy of abnormal vibration data is low due to certain subjectivity and experience limitation.
Disclosure of Invention
The application provides a vibration data abnormity detection method, a device, equipment and a storage medium, wherein a confidence interval for judging target vibration data to be detected is determined for historical targeted data, and abnormity judgment is carried out on the target vibration data to be detected through the confidence interval, so that the accuracy of a judgment result is ensured.
In a first aspect, the present application provides a method for detecting an abnormality in vibration data, including:
acquiring target vibration data to be detected, acquisition time of the target vibration data and a historical vibration data sequence corresponding to the target vibration data;
generating a probability distribution function corresponding to the acquisition time according to each historical vibration data in the historical vibration data sequence;
obtaining a confidence interval based on the probability distribution function and the statistical characteristics corresponding to the probability distribution function;
and carrying out abnormity detection on the target vibration data based on the confidence interval.
In a possible implementation manner of the present application, obtaining a confidence interval based on the probability distribution function and a statistical characteristic corresponding to the probability distribution function includes:
obtaining statistical characteristics of the random vibration data according to the probability value of the random vibration data of the probability distribution function corresponding to the acquisition time, wherein the statistical characteristics comprise at least one of a mean value and a variance;
and performing standard deviation processing on the statistical characteristics based on a preset vibration data interval generation rule to obtain a confidence interval.
In one possible implementation manner of the present application, after the detecting the abnormality of the target vibration data based on the confidence interval, the method further includes:
if the target vibration data are abnormal vibration data, determining standard vibration data according to the statistical characteristics corresponding to the probability distribution function;
and adding the standard vibration data into a historical vibration data sequence, and updating the historical vibration data sequence.
In a possible implementation manner of the present application, the generating a probability distribution function corresponding to the collection time according to each historical vibration data in the historical vibration data sequence includes:
inputting historical vibration data in the historical vibration data sequence into a preset Gaussian distribution model to obtain a Gaussian model core function, wherein the Gaussian distribution model is a vibration data statistical model formed by inputting Gaussian white noise hypothesis under a Bayesian framework;
acquiring a function type of the Gaussian model core function, and acquiring a log-likelihood function corresponding to the index type if the function type is the index type;
and solving a vibration calculation parameter corresponding to the log-likelihood function according to the historical vibration data sequence, and generating a probability distribution function corresponding to the acquisition time according to the vibration calculation parameter.
In a possible implementation manner of the present application, the solving a vibration calculation parameter corresponding to the log likelihood function according to the historical vibration data sequence, and generating a probability distribution function corresponding to the acquisition time according to the vibration calculation parameter includes:
determining a kernel function matrix corresponding to the historical vibration data sequence according to the historical vibration data sequence and the Gaussian model kernel function;
solving the vibration calculation parameters corresponding to the log likelihood function according to the historical vibration data sequence and the kernel function matrix;
and generating a probability distribution function corresponding to the acquisition time according to a preset posterior distribution function and the vibration calculation parameters.
In one possible implementation manner of the present application, after performing anomaly detection on the target vibration data based on the confidence interval, the method includes:
when the target vibration data are detected to be abnormal vibration data, accumulating the target vibration data to an abnormal vibration data set;
if the quantity of abnormal vibration data in an abnormal vibration data set exceeds a preset quantity threshold, counting target data change information of each abnormal vibration data in the abnormal vibration data set;
determining target exception handling information corresponding to the target data change information based on a preset mapping relation between the exception handling information and the data change information;
and generating and feeding back vibration data abnormal information based on the target abnormal processing information and the target data change information.
In one possible implementation manner of the present application, the performing abnormality detection on the target vibration data based on the confidence interval includes:
if the target vibration data are located in the confidence interval, judging that the target vibration data are normal vibration data;
and if the target vibration data is located outside the confidence interval, judging that the target vibration data is abnormal vibration data.
In a second aspect, the present application provides a vibration data abnormality detection apparatus that detects abnormality in vibration data
An acquisition module: the system comprises a data acquisition module, a data acquisition module and a data acquisition module, wherein the data acquisition module is used for acquiring target vibration data to be detected, acquisition time of the target vibration data and a historical vibration data sequence corresponding to the target vibration data;
a determination module: the probability distribution function corresponding to the acquisition time is generated according to each historical vibration data in the historical vibration data sequence;
an interval determination module: the device is used for obtaining a confidence interval based on the probability distribution function and the statistical characteristics corresponding to the probability distribution function;
a detection module: and the target vibration data is subjected to abnormity detection based on the confidence interval.
In a third aspect, the present application provides a vibration data abnormality detection apparatus including:
one or more processors;
a memory; and
one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the processor to implement any of the vibration data anomaly detection methods.
In a fourth aspect, the present application provides a computer readable storage medium having a computer program stored thereon, the computer program being loaded by a processor to perform the steps of any of the vibration data abnormality detection methods.
According to the method, the device, the equipment and the storage medium for detecting the abnormal vibration data, the target vibration data to be detected, the acquisition time of the target vibration data and a historical vibration data sequence corresponding to the target vibration data are obtained; then generating a probability distribution function corresponding to the acquisition time according to each historical vibration data in the historical vibration data sequence; then, based on the probability distribution function and the statistical characteristics corresponding to the probability distribution function, a confidence interval is obtained; and performing anomaly detection on the target vibration data based on the confidence interval. The probability distribution function of the acquisition time is determined through the historical vibration data sequence and the probability distribution function corresponding to the historical vibration data sequence, namely, the probability distribution function of the vibration data which possibly appears and corresponds to the acquisition time is determined according to the historical vibration data sequence, the diversity of the data and the relevance of the time between corresponding data are ensured, then a confidence interval for judging whether the target vibration data to be detected is abnormal or not is obtained according to the probability distribution function and the statistical characteristics corresponding to the probability distribution function, the limitation that prediction is directly carried out through a preset value is avoided, and the accuracy of the data is ensured.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic view of a scene of a data anomaly detection method provided in an embodiment of the present application;
FIG. 2 is a schematic flow chart diagram illustrating one embodiment of a data anomaly detection method provided in an embodiment of the present application;
FIG. 3 is a schematic flow chart illustrating an embodiment of determining a probability distribution function in the vibration data anomaly detection method provided herein;
FIG. 4 is a schematic flow chart diagram illustrating one embodiment of confidence interval determination in a vibration data anomaly detection method provided herein;
FIG. 5 is a schematic flow chart diagram illustrating a data anomaly detection method provided in an embodiment of the present application;
FIG. 6 is a schematic flow chart diagram illustrating a method for detecting data anomalies according to yet another embodiment of the present disclosure;
FIG. 7 is a schematic structural diagram of an embodiment of a data anomaly detection device provided in an embodiment of the present application;
fig. 8 is a schematic structural diagram of an embodiment of the data anomaly detection device provided in the embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the description of the present invention, it is to be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. indicate orientations or positional relationships based on those shown in the drawings, merely for convenience of description and simplicity of description, and do not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, are not to be construed as limiting the present invention. Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, features defined as "first", "second", may explicitly or implicitly include one or more of the described features. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
In this application, the word "exemplary" is used to mean "serving as an example, instance, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments. The following description is presented to enable any person skilled in the art to make and use the invention. In the following description, details are set forth for the purpose of explanation. It will be apparent to one of ordinary skill in the art that the present invention may be practiced without these specific details. In other instances, well-known structures and processes are not shown in detail to avoid obscuring the description of the invention with unnecessary detail. Thus, the present invention is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.
Embodiments of the present application provide a method, an apparatus, a device and a computer readable storage medium for detecting an abnormality of vibration data, which are described in detail below.
The vibration data abnormity detection method is applied to a vibration data abnormity detection device, the vibration data abnormity detection device is arranged on vibration data abnormity detection equipment, one or more processors, a memory and one or more application programs are arranged in the vibration data abnormity detection equipment, and the one or more application programs are stored in the memory and configured to be executed by the processor to realize the vibration data abnormity detection method; the vibration data abnormality detection device may be a terminal, such as a mobile phone or a tablet computer, and may also be a server or a service cluster formed by multiple servers.
As shown in fig. 1, fig. 1 is a schematic view of a scenario of a vibration data anomaly detection method according to an embodiment of the present application, where the vibration data anomaly detection scenario includes a vibration data anomaly detection device 100 (a vibration data anomaly detection apparatus is integrated in the vibration data anomaly detection device 100), and a computer-readable storage medium corresponding to the vibration data anomaly detection is run in the vibration data anomaly detection device 100 to perform a step of vibration data anomaly detection.
It should be understood that the vibration data anomaly detection device in the scenario of the vibration data anomaly detection method shown in fig. 1, or the apparatuses included in the vibration data anomaly detection device, do not limit the embodiment of the present invention, that is, the number of apparatuses and the types of apparatuses included in the scenario of the vibration data anomaly detection method, or the number of apparatuses and the types of apparatuses included in each apparatus do not affect the overall implementation of the technical solution in the embodiment of the present invention, and all the apparatuses can be calculated as equivalent replacements or derivatives of the technical solution claimed in the embodiment of the present invention.
The vibration data abnormality detection apparatus 100 according to the embodiment of the present invention is mainly configured to: acquiring target vibration data to be detected, acquisition time of the target vibration data and a historical vibration data sequence corresponding to the target vibration data; generating a probability distribution function corresponding to the acquisition time according to each historical vibration data in the historical vibration data sequence; obtaining a confidence interval based on the probability distribution function and the statistical characteristics corresponding to the probability distribution function; and carrying out abnormity detection on the target vibration data based on the confidence interval.
The vibration data anomaly detection device 100 in the embodiment of the present invention may be an independent vibration data anomaly detection device, or may be a vibration data anomaly detection device network or a vibration data anomaly detection device cluster composed of vibration data anomaly detection devices, for example, the vibration data anomaly detection device 100 described in the embodiment of the present invention includes, but is not limited to, a computer, a network host, a single network vibration data anomaly detection device, a plurality of network vibration data anomaly detection device sets, or a cloud vibration data anomaly detection device composed of a plurality of vibration data anomaly detection devices. Wherein the cloud vibration data abnormality detection device is constituted by a large number of computers based on cloud computing (cloud computing) or a network vibration data abnormality detection device.
Those skilled in the art can understand that the application environment shown in fig. 1 is only one application scenario related to the present application scheme, and does not constitute a limitation on the application scenario of the present application scheme, and that other application environments may further include more or less vibration data anomaly detection devices than those shown in fig. 1, or a network connection relationship of the vibration data anomaly detection devices, for example, only 1 vibration data anomaly detection device is shown in fig. 1, and it can be understood that the scenario of the vibration data anomaly detection method may further include one or more other vibration data anomaly detection devices, which is not limited herein specifically; the vibration data abnormality detection apparatus 100 may further include a memory therein, and may be configured to store the vibration data.
In addition, in the scene of the vibration data abnormality detection method, the vibration data abnormality detection device 100 may be provided with a display device, or the vibration data abnormality detection device 100 is not provided with a display device in communication connection with an external display device 200, and the display device 200 is used for outputting a result executed by the vibration data abnormality detection method in the vibration data abnormality detection device. The vibration data anomaly detection device 100 may access the background vibration database 300 (the background vibration database may be in a local memory of the vibration data anomaly detection device, and may also be set in the cloud), and information related to the vibration data anomaly detection is stored in the background vibration database 300, for example, a historical vibration data sequence, or a preset calculation function, a calculation model, and the like may be stored in the background vibration database 300.
It should be noted that the scene schematic diagram of the vibration data anomaly detection method shown in fig. 1 is only an example, and the scene of the vibration data anomaly detection method described in the embodiment of the present invention is for more clearly explaining the technical solution of the embodiment of the present invention, and does not constitute a limitation on the technical solution provided in the embodiment of the present invention.
Based on the scene of the vibration data anomaly detection method, an embodiment of the vibration data anomaly detection method is provided.
As shown in fig. 2, which is a schematic flowchart of an embodiment of a method for detecting an abnormality in vibration data according to an embodiment of the present application, the method for detecting an abnormality in vibration data includes steps S201 to S204:
s201, target vibration data to be detected, acquisition time of the target vibration data and a historical vibration data sequence corresponding to the target vibration data are acquired.
The vibration data is the vibration data to be detected collected at any moment, and it can be understood that the vibration data may be the vibration data collected at the current moment or the vibration data to be detected collected at the previous collection moment. It will be appreciated that the vibration data may be collected by a vibration data collection device mounted on the vibration generating apparatus, such as by a vibration sensor.
It can be understood that the collection time is the collection time of the target vibration data, the target vibration data may be any one of the continuously collected vibration data, or the target vibration data collected by the vibration data collection device according to the preset vibration data collection frequency,
the target vibration data is a historical vibration data sequence corresponding to the target vibration data, that is, historical vibration data within a preset time period before the acquisition time of the target vibration data, for example, the target vibration data is y t With a time t of acquisition, i.e. the historical vibration data sequence comprises Y train ＝[y t-k ，y t-k+1 ，...，y t-1 ](ii) a Wherein k is a preset time duration, it can be understood that each of the historical vibration data corresponds to a second acquisition time, it can be understood that the second has no practical meaning, and only in order to distinguish the acquisition times, it can be understood that y is t And y t-1 With an acquisition period therebetween, which may be one second, one hour, etc.
It is understood that the data in the historical vibration sequence are arranged in a time sequence, that is, the historical vibration sequence is a time sequence matrix corresponding to the historical vibration data, and the historical vibration data sequence changes corresponding to the change of the target vibration data.
S202, generating a probability distribution function corresponding to the acquisition time according to each historical vibration data in the historical vibration data sequence.
The probability distribution function of the acquisition time is a prediction function of occurrence probability of all possible vibration data of the acquisition time, and it can be understood that the possible vibration data at the position is prediction number vibration data, and the preset vibration data can be predicted according to a historical vibration data sequence and a preset calculation model or a preset calculation formula.
Specifically, referring to fig. 3, fig. 3 is an embodiment of implementing probability distribution function determination in the vibration data anomaly detection method provided by the present application, and includes steps S301 to S303:
s301, inputting the historical vibration data in the historical vibration data sequence into a preset Gaussian distribution model to obtain a Gaussian model core function, wherein the Gaussian distribution model is a vibration data statistical model formed by inputting Gaussian white noise hypothesis under a Bayesian framework.
S302, obtaining a function type of the Gaussian model core function, and if the function type is an exponential type, obtaining a log-likelihood function corresponding to the exponential type.
S303, solving a vibration calculation parameter corresponding to the log likelihood function according to the historical vibration data sequence, and generating a probability distribution function corresponding to the acquisition time according to the vibration calculation parameter.
Specifically, the core function of the gaussian model is as follows:
wherein, the Gaussian model kernel function comprises a parameter sigma to be optimized c L has an initial value, wherein, in one embodiment of the present application, said (t) is i -t j ) 2 The acquisition time t corresponding to any two historical vibration data in the corresponding historical vibration data sequence can be i And t j The variance value therebetween.
Further, the log-likelihood function is as follows:
wherein, L is a preset log-likelihood function, and p (Y) train |X train ，σ z ) A likelihood function calculated from the historical training data sequence, the likelihood function conforming to a white Gaussian noise distribution, Y train Is a historical vibration data sequence (which is a matrix including a plurality of historical vibration data distributed according to the acquisition time), wherein t is the acquisition time, and sigma is z For the parameter to be optimized, C is a kernel function matrix, and it can be understood that the kernel function matrix can be obtained by calculation according to a kernel matrix function.
In the embodiments of the present application, said x train According to a preset system error, the vibration data of the historical vibration data sequence is corrected to obtainThe historical vibration data sequence of arrival. The calculation method for correcting the vibration data of the historical vibration data sequence according to the system error is not specifically limited in the present application, and in the embodiment of the present application, a formula for correcting the vibration data of the historical vibration data sequence according to the system error is shown in the following:
Y＝X+Z
wherein Y is any historical vibration data in the historical vibration sequence data, Z is a preset system error, and X is any historical vibration data corrected corresponding to Y in the historical vibration sequence data.
Specifically, solving the vibration calculation parameter corresponding to the log-likelihood function according to the historical vibration data sequence includes:
(1) determining a kernel function matrix corresponding to the historical vibration data sequence according to the historical vibration data sequence and the Gaussian model kernel function;
(2) solving the vibration calculation parameters corresponding to the log likelihood function according to the historical vibration data sequence and the kernel function matrix;
(3) and generating a probability distribution function corresponding to the acquisition time according to a preset posterior distribution function and the vibration calculation parameters.
Specifically, the historical vibration data sequence is obtained by modifying the historical vibration data in the historical vibration data sequence, the data in the modified historical vibration sequence is substituted into a Gaussian model kernel function to obtain a kernel function matrix, then the historical vibration data sequence and the kernel function matrix are substituted into a log-likelihood function, a conjugate gradient method is used for solving the partial derivative of the log-likelihood function, and the locally optimal sigma conforming to the local optimum is obtained z 、σ c And l to obtain a vibration calculation parameter theta, wherein the vibration calculation parameter theta is { sigma ═ sigma c ，l，σ z And the Gaussian model kernel function includes a parameter sigma to be optimized according to the vibration calculation parameter c And l, updating to obtain an updated Gaussian model core function.
Then, a probability distribution function corresponding to the acquisition time is generated based on the preset posterior distribution function and the vibration calculation parameter, specifically, the preset posterior distribution function is as follows:
wherein, Y * |Y train The symbol-is proportional to the posterior probability distribution, i.e., the probability distribution function of the acquisition time; c * Cross kernel function matrix, C, for training and test sets ** Is a kernel function matrix of the test set. Specifically, the kernel function matrix is calculated according to the updated gaussian model kernel function (kernel matrix function).
Specifically, the updated Gaussian model kernel function can obtain C at the future time and the past time * Matrix, same principle C ** It is a matrix of all future moments, C is a matrix related to the past time (training) only, that is, it can be understood that C can be calculated by substituting the acquisition time in the historical vibration data sequence into the updated gaussian model kernel function, and C can be obtained by substituting the acquisition time in the historical vibration data sequence and the acquisition time of the target vibration data into the updated gaussian model kernel function * And substituting the acquisition time of the target vibration data into the updated Gaussian model kernel function to obtain C ** 。
And S203, obtaining a confidence interval based on the probability distribution function and the statistical characteristics corresponding to the probability distribution function.
Specifically, referring to fig. 4, the statistical characteristics, that is, data such as variance and mean corresponding to the probability distribution function, in fig. 4, an embodiment of determining a confidence interval in the vibration data abnormality detection method provided by the present application includes steps S401 to S402:
s401, obtaining statistical characteristics of the random vibration data according to probability values of the random vibration data of the acquisition time corresponding to the probability distribution function, wherein the statistical characteristics comprise at least one of mean values and variances.
S402, based on a preset vibration data interval generation rule, standard deviation processing is conducted on the statistical characteristics to obtain a confidence interval.
Specifically, in the embodiment of the present application, the statistical characteristics include a mean and a standard deviation, wherein the mean and the standard deviation are the probability distribution function
Mean value of
And standard deviation of
That is, for example, through the obtained probability distribution function, an accumulated probability density function may be calculated for acquiring a mean value and a standard deviation corresponding to vibration data that may occur in time, and when the value of the accumulated probability density function is 0.5, a corresponding point is a mean value, and a corresponding standard deviation is calculated according to the mean value and the vibration data that may occur in time.
Specifically, the preset vibration data interval generation rule is a three-sigma principle, and in the embodiment of the application, the confidence interval I belongs to [ I ∈ ], [ I ] low ，I up ]See the formula for generation of:
specifically, the vibration data confidence interval corresponding to the acquisition time is determined through a calculation formula, and the mean value and the variance.
And S204, carrying out abnormity detection on the target vibration data based on the confidence interval.
Specifically, after a confidence interval is obtained, the target vibration data is compared with the confidence interval, and if the target vibration data is located in the confidence interval, the target vibration data is judged to be normal vibration data; and if the target vibration data is located outside the confidence interval, judging that the target vibration data is abnormal vibration data.
Further, on the basis of any one of the above embodiments, referring to fig. 5, after performing abnormality detection on the target vibration data, the method further includes steps S501 to S502:
s501, if the target vibration data are abnormal vibration data, determining standard vibration data corresponding to the target vibration data according to statistical characteristics corresponding to the probability distribution function;
s502, adding the standard vibration data into the historical vibration data sequence, and updating the historical vibration data sequence.
Specifically, after the target vibration data is subjected to the abnormal detection, if the target vibration data is abnormal vibration data, standard vibration data is determined according to statistical characteristics corresponding to the probability distribution function, specifically, the standard vibration data replaces the abnormal vibration data to form a historical data set, specifically, the standard vibration data is mean data in the statistical characteristics, and it can be understood that in some other embodiments of the present application, the standard vibration data may also be a preset value. The present application is not specifically limited. Namely, the standard vibration data is added into a historical vibration data sequence, the historical vibration data sequence is updated, and the target vibration data corresponding to the next acquisition time is subjected to abnormality detection based on the updated historical vibration data sequence.
Further, on the basis of any one of the above embodiments, referring to fig. 6, after performing abnormality detection on the target vibration data, the method further includes steps S601-S605:
s601, when the target vibration data are detected to be abnormal vibration data, accumulating the target vibration data to an abnormal vibration data set.
The abnormal data included in the abnormal vibration data set can be abnormal data of at least one vibration data acquisition cycle at intervals, and it can be understood that the preset time can be preset according to different vibration working conditions, for example, the vibration data acquisition cycle is compared with the end, the preset time can be set to be shorter, the vibration data acquisition cycle is longer, the preset time can be set to be longer, and the abnormal vibration data in the preset time is accumulated to avoid the limitation of single abnormal judgment.
S602, if the number of abnormal vibration data in an abnormal vibration data set exceeds a preset number threshold, counting target data change information of each abnormal vibration data in the abnormal vibration data set.
Specifically, if the number of the abnormal vibration data accumulated by the abnormal vibration data set reaches a preset accumulated number, it is indicated that the vibration equipment corresponding to the vibration data may actually fail, and the situation of misjudgment of the vibration data is reduced, and then target data change information between the abnormal vibration data is determined according to the magnitude relation of the vibration data between the abnormal vibration data in the abnormal vibration data set, for example, according to a vibration data error mean value, an error standard deviation and the like between the abnormal vibration data in the abnormal vibration data set.
S603, determining target abnormal processing information corresponding to the target data change information based on a preset mapping relation between the abnormal processing information and the data change information.
And S604, generating and feeding back vibration data abnormal information based on the target abnormal processing information and the target data change information.
Specifically, the target abnormal processing information may be historical operation information or historical failure cause corresponding to target data change information, and the vibration data abnormal information is generated based on the target abnormal processing information and the target data change information, that is, the processing operation and/or failure cause condition corresponding to abnormal data is fed back according to historical data while the abnormal data judgment gives a result.
It can be understood that the vibration data anomaly detection method is applied to vibration data anomaly detection equipment, and the vibration data anomaly detection equipment can feed back a feedback result to a display end communicating with the vibration data anomaly detection equipment, such as a display screen of the vibration equipment corresponding to the vibration data, or generate a voice broadcast instruction for corresponding feedback.
In the embodiment, by providing a vibration data anomaly detection method, target vibration data to be detected, acquisition time of the target vibration data and a historical vibration data sequence corresponding to the target vibration data are acquired; then generating a probability distribution function corresponding to the acquisition time according to each historical vibration data in the historical vibration data sequence; then obtaining a confidence interval based on the probability distribution function and the statistical characteristics corresponding to the probability distribution function; and performing anomaly detection on the target vibration data based on the confidence interval. The probability distribution function of the acquisition time is determined through the historical vibration data sequence and the probability distribution function corresponding to the historical vibration data sequence, namely, the probability distribution function of the vibration data which possibly appears and corresponds to the acquisition time is determined according to the historical vibration data sequence, the diversity of the data and the relevance of the time between corresponding data are ensured, then a confidence interval for judging whether the target vibration data to be detected is abnormal or not is obtained according to the probability distribution function and the statistical characteristics corresponding to the probability distribution function, the limitation that prediction is directly carried out through a preset value is avoided, and the accuracy of the data is ensured.
In order to better implement the abnormal detection method of the vibration data in the embodiment of the present application, on the basis of the abnormal detection method of the vibration data, the embodiment of the present application further provides an abnormal detection device of the vibration data, as shown in fig. 7, the abnormal detection device of the vibration data includes 701-704:
an acquisition module 701: the system comprises a data acquisition unit, a data storage unit and a data processing unit, wherein the data acquisition unit is used for acquiring target vibration data to be detected, acquisition time of the target vibration data and a historical vibration data sequence corresponding to the target vibration data;
the determination module 702: the probability distribution function corresponding to the acquisition time is generated according to each historical vibration data in the historical vibration data sequence;
the interval determination module 703: the device is used for obtaining a confidence interval based on the probability distribution function and the statistical characteristics corresponding to the probability distribution function;
the detection module 704: and the target vibration data is subjected to abnormity detection based on the confidence interval.
In some embodiments of the present application, the interval determining module 703: the method is used for obtaining a confidence interval based on the probability distribution function and the statistical characteristics corresponding to the probability distribution function, and specifically includes the following steps:
obtaining statistical characteristics of the random vibration data according to probability values of the random vibration data of the probability distribution function corresponding to the acquisition time, wherein the statistical characteristics comprise at least one of mean values and variances;
and performing standard deviation processing on the statistical characteristics based on a preset vibration data interval generation rule to obtain a confidence interval.
In some embodiments of the present application, the apparatus for detecting an abnormality of vibration data further includes a data sequence updating module, configured to, after performing an abnormality detection on the target vibration data based on the confidence interval:
if the target vibration data are abnormal vibration data, determining standard vibration data corresponding to the target vibration data according to the statistical characteristics corresponding to the probability distribution function;
and adding the standard vibration data into the historical vibration data sequence, and updating the historical vibration data sequence.
In some embodiments of the present application, the determining module 702: the method is used for generating a probability distribution function corresponding to the acquisition time according to each historical vibration data in the historical vibration data sequence, and specifically includes the following steps:
inputting historical vibration data in the historical vibration data sequence into a preset Gaussian distribution model to obtain a Gaussian model core function, wherein the Gaussian distribution model is a vibration data statistical model formed by inputting Gaussian white noise hypothesis under a Bayesian framework;
acquiring a function type of the Gaussian model core function, and if the function type is an index type, acquiring a log-likelihood function corresponding to the index type;
and solving a vibration calculation parameter corresponding to the log-likelihood function according to the historical vibration data sequence, and generating a probability distribution function corresponding to the acquisition time according to the vibration calculation parameter.
In some embodiments of the present application, the determining module 702 further comprises: solving a vibration calculation parameter corresponding to the log-likelihood function according to the historical vibration data sequence, and generating a probability distribution function corresponding to the acquisition time according to the vibration calculation parameter, wherein the method specifically comprises the following steps:
determining a kernel function matrix corresponding to the historical vibration data sequence according to the historical vibration data sequence and the Gaussian model kernel function;
solving the vibration calculation parameters corresponding to the log likelihood function according to the historical vibration data sequence and the kernel function matrix;
and generating a probability distribution function corresponding to the acquisition time according to a preset posterior distribution function and the vibration calculation parameters.
In some embodiments of the present application, the vibration data anomaly detection apparatus further comprises a feedback module configured to:
after abnormality detection of the target vibration data based on the confidence interval,
when the target vibration data are detected to be abnormal vibration data, accumulating the target vibration data to an abnormal vibration data set;
if the quantity of abnormal vibration data in an abnormal vibration data set exceeds a preset quantity threshold, counting target data change information of each abnormal vibration data in the abnormal vibration data set;
determining target exception handling information corresponding to the target data change information based on a preset mapping relation between the exception handling information and the data change information;
and generating and feeding back vibration data abnormal information based on the target abnormal processing information and the target data change information.
In some embodiments of the present application, the detection module 704: the method is used for carrying out abnormity detection on the target vibration data based on the confidence interval, and specifically comprises the following steps:
if the target vibration data are located in the confidence interval, judging that the target vibration data are normal vibration data;
and if the target vibration data is located outside the confidence interval, judging that the target vibration data is abnormal vibration data.
In the embodiment, by providing a vibration data anomaly detection device, target vibration data to be detected, acquisition time of the target vibration data and a historical vibration data sequence corresponding to the target vibration data are acquired; then generating a probability distribution function corresponding to the acquisition time according to each historical vibration data in the historical vibration data sequence; then obtaining a confidence interval based on the probability distribution function and the statistical characteristics corresponding to the probability distribution function; and performing anomaly detection on the target vibration data based on the confidence interval. The probability distribution function of the acquisition time is determined through the historical vibration data sequence and the probability distribution function corresponding to the historical vibration data sequence, namely, the probability distribution function of the vibration data which possibly appears and corresponds to the acquisition time is determined according to the historical vibration data sequence, the diversity of the data and the relevance of the time between corresponding data are ensured, then a confidence interval for judging whether the target vibration data to be detected is abnormal or not is obtained according to the probability distribution function and the statistical characteristics corresponding to the probability distribution function, the limitation that prediction is directly carried out through a preset value is avoided, and the accuracy of the data is ensured.
An embodiment of the present invention further provides a device for detecting an abnormality in vibration data, as shown in fig. 8, where fig. 8 is a schematic structural diagram of an embodiment of the device for detecting an abnormality in vibration data provided in an embodiment of the present application.
The vibration data abnormality detection device integrates any one of the vibration data abnormality detection apparatuses provided by the embodiments of the present invention, and includes:
one or more processors;
a memory; and
one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the processor for performing the steps of the vibration data abnormality detection method described in any of the above embodiments of the vibration data abnormality detection method.
Specifically, the method comprises the following steps: the vibration data abnormality detection apparatus may include components such as a processor 801 of one or more processing cores, a memory 802 of one or more computer-readable storage media, a power supply 803, and an input unit 804. It will be understood by those skilled in the art that the configuration of the vibration data abnormality detection apparatus shown in fig. 8 does not constitute a limitation of the vibration data abnormality detection apparatus, and may include more or less components than those shown, or some components may be combined, or a different arrangement of components may be provided. Wherein:
the processor 801 is a control center of the vibration data abnormality detection apparatus, connects various parts of the entire vibration data abnormality detection apparatus by using various interfaces and lines, and executes various functions and processing data of the vibration data abnormality detection apparatus by running or executing software programs and/or modules stored in the memory 802 and calling data stored in the memory 802, thereby performing overall monitoring of the vibration data abnormality detection apparatus. Alternatively, processor 801 may include one or more processing cores; preferably, the processor 801 may integrate an application processor, which mainly handles operating systems, user interfaces, application programs, etc., and a modem processor, which mainly handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 801.
The memory 802 may be used to store software programs and modules, and the processor 801 executes various functional applications and data processing by operating the software programs and modules stored in the memory 802. The memory 802 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data created according to use of the vibration data abnormality detection apparatus, and the like. Further, the memory 802 may include high speed random access memory and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, the memory 802 may also include a memory controller to provide the processor 801 access to the memory 802.
The apparatus for detecting abnormality of vibration data further includes a power source 803 for supplying power to each component, and preferably, the power source 803 may be logically connected to the processor 801 through a power management system, so that functions of managing charging, discharging, and power consumption are implemented through the power management system. The power supply 803 may also include one or more dc or ac power sources, recharging systems, power failure detection circuitry, power converters or inverters, power status indicators, and any like components.
The vibration data abnormality detection apparatus may further include an input unit 804, and the input unit 804 may be used to receive input numeric or character information and generate a keyboard, mouse, joystick, optical or trackball signal input in relation to user settings and function control.
Although not shown, the vibration data abnormality detecting apparatus may further include a display unit or the like, which will not be described in detail herein. Specifically, in this embodiment, the processor 801 in the vibration data abnormality detection apparatus loads an executable file corresponding to one or more processes of an application program into the memory 802 according to the following instructions, and the processor 801 runs the application program stored in the memory 802, thereby implementing various functions as follows:
acquiring target vibration data to be detected, acquisition time of the target vibration data and a historical vibration data sequence corresponding to the target vibration data;
generating a probability distribution function corresponding to the acquisition time according to each historical vibration data in the historical vibration data sequence;
obtaining a confidence interval based on the probability distribution function and the statistical characteristics corresponding to the probability distribution function;
and carrying out abnormity detection on the target vibration data based on the confidence interval.
It will be understood by those skilled in the art that all or part of the steps of the methods of the above embodiments may be performed by instructions or by associated hardware controlled by the instructions, which may be stored in a computer readable storage medium and loaded and executed by a processor.
To this end, an embodiment of the present invention provides a computer-readable storage medium, which may include: a Read Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and the like. The computer program is loaded by a processor to execute the steps of any vibration data abnormality detection method provided by the embodiment of the invention. For example, the computer program may be loaded by a processor to perform the steps of:
acquiring target vibration data to be detected, acquisition time of the target vibration data and a historical vibration data sequence corresponding to the target vibration data;
generating a probability distribution function corresponding to the acquisition time according to each historical vibration data in the historical vibration data sequence;
obtaining a confidence interval based on the probability distribution function and the statistical characteristics corresponding to the probability distribution function;
and carrying out abnormity detection on the target vibration data based on the confidence interval.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and parts that are not described in detail in a certain embodiment may refer to the above detailed descriptions of other embodiments, and are not described herein again.
In specific implementation, each unit or structure may be implemented as an independent entity, or may be combined arbitrarily to be implemented as the same entity or several entities, and specific implementation of each unit or structure may refer to the foregoing method embodiment, which is not described herein again.
The above operations can be implemented in the foregoing embodiments, and are not described in detail herein.
The method, apparatus, device and storage medium for detecting vibration data anomaly provided in the embodiments of the present application are described in detail above, and specific examples are applied herein to explain the principles and embodiments of the present invention, and the description of the embodiments is only used to help understanding the method and its core ideas of the present invention; meanwhile, for those skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (10)
1. A vibration data abnormality detection method characterized by comprising:
acquiring target vibration data to be detected, acquisition time of the target vibration data and a historical vibration data sequence corresponding to the target vibration data;
generating a probability distribution function corresponding to the acquisition time according to each historical vibration data in the historical vibration data sequence;
obtaining a confidence interval based on the probability distribution function and the statistical characteristics corresponding to the probability distribution function;
and carrying out abnormity detection on the target vibration data based on the confidence interval.
2. The method for detecting the abnormality of the vibration data according to claim 1, wherein obtaining a confidence interval based on the probability distribution function and a statistical characteristic corresponding to the probability distribution function includes:
obtaining statistical characteristics of the random vibration data according to probability values of the random vibration data of the probability distribution function corresponding to the acquisition time, wherein the statistical characteristics comprise at least one of mean values and variances;
and performing standard deviation processing on the statistical characteristics based on a preset vibration data interval generation rule to obtain a confidence interval.
3. The vibration data abnormality detection method according to claim 1, further comprising, after abnormality detection of the target vibration data based on the confidence interval:
if the target vibration data are abnormal vibration data, determining standard vibration data corresponding to the target vibration data according to the statistical characteristics corresponding to the probability distribution function;
and adding the standard vibration data into the historical vibration data sequence, and updating the historical vibration data sequence.
4. The method for detecting the abnormality of the vibration data according to claim 1, wherein the generating a probability distribution function corresponding to the collection time based on each historical vibration data in the historical vibration data sequence includes:
inputting historical vibration data in the historical vibration data sequence into a preset Gaussian distribution model to obtain a Gaussian model core function, wherein the Gaussian distribution model is a vibration data statistical model formed by inputting Gaussian white noise hypothesis under a Bayesian framework;
acquiring a function type of the Gaussian model core function, and acquiring a log-likelihood function corresponding to the index type if the function type is the index type;
and solving a vibration calculation parameter corresponding to the log-likelihood function according to the historical vibration data sequence, and generating a probability distribution function corresponding to the acquisition time according to the vibration calculation parameter.
5. The method for detecting the abnormal vibration data according to claim 4, wherein the solving of the corresponding vibration calculation parameters of the log likelihood function according to the historical vibration data sequence and the generation of the probability distribution function corresponding to the collection time according to the vibration calculation parameters comprises:
determining a kernel function matrix corresponding to the historical vibration data sequence according to the historical vibration data sequence and the Gaussian model kernel function;
solving the vibration calculation parameters corresponding to the log likelihood function according to the historical vibration data sequence and the kernel function matrix;
and generating a probability distribution function corresponding to the acquisition time according to a preset posterior distribution function and the vibration calculation parameters.
6. The vibration data abnormality detection method according to claim 1, wherein after abnormality detection of the target vibration data based on the confidence interval, the method includes:
when the target vibration data are detected to be abnormal vibration data, accumulating the target vibration data to an abnormal vibration data set;
if the quantity of the abnormal vibration data in the abnormal vibration data set exceeds a preset quantity threshold value, counting target data change information of each abnormal vibration data in the abnormal vibration data set;
determining target exception handling information corresponding to the target data change information based on a preset mapping relation between the exception handling information and the data change information;
and generating and feeding back vibration data abnormal information based on the target abnormal processing information and the target data change information.
7. The vibration data abnormality detection method according to claim 1, wherein the abnormality detection of the target vibration data based on the confidence interval includes:
if the target vibration data are located in the confidence interval, judging that the target vibration data are normal vibration data;
and if the target vibration data is located outside the confidence interval, judging that the target vibration data is abnormal vibration data.
8. A vibration data abnormality detection apparatus, characterized by comprising:
an acquisition module: the system comprises a data acquisition module, a data acquisition module and a data acquisition module, wherein the data acquisition module is used for acquiring target vibration data to be detected, acquisition time of the target vibration data and a historical vibration data sequence corresponding to the target vibration data;
a determination module: the probability distribution function corresponding to the acquisition time is generated according to each historical vibration data in the historical vibration data sequence;
an interval determination module: the device is used for obtaining a confidence interval based on the probability distribution function and the statistical characteristics corresponding to the probability distribution function;
a detection module: and the target vibration data is subjected to abnormity detection based on the confidence interval.
9. A vibration data abnormality detection apparatus characterized by comprising:
one or more processors;
a memory; and
one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the processor to implement the vibration data anomaly detection method of any one of claims 1-7.
10. A computer-readable storage medium, having stored thereon a computer program which is loaded by a processor to perform the steps in the vibration data abnormality detection method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210874037.1A CN115130064A (en) | 2022-07-21 | 2022-07-21 | Vibration data anomaly detection method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210874037.1A CN115130064A (en) | 2022-07-21 | 2022-07-21 | Vibration data anomaly detection method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115130064A true CN115130064A (en) | 2022-09-30 |
Family
ID=83383456
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210874037.1A Pending CN115130064A (en) | 2022-07-21 | 2022-07-21 | Vibration data anomaly detection method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115130064A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117518939A (en) * | 2023-12-06 | 2024-02-06 | 广州市顺风船舶服务有限公司 | Industrial control system based on big data |
-
2022
- 2022-07-21 CN CN202210874037.1A patent/CN115130064A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117518939A (en) * | 2023-12-06 | 2024-02-06 | 广州市顺风船舶服务有限公司 | Industrial control system based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11746753B2 (en) | Method and apparatus for detecting fault, method and apparatus for training model, and device and storage medium | |
| WO2022068645A1 (en) | Database fault discovery method, apparatus, electronic device, and storage medium | |
| CN110516971B (en) | Anomaly detection method, device, medium and computing equipment | |
| JP2021121956A (en) | Failure prediction method, device, electronic facility, storage media and program | |
| CN108919935A (en) | Monitoring method, device and equipment for power supply on server mainboard | |
| US20170372212A1 (en) | Model based root cause analysis | |
| CN107391335B (en) | Method and equipment for checking health state of cluster | |
| CN110178121A (en) | A kind of detection method and its terminal of database | |
| US11762448B1 (en) | Method for troubleshooting abnormal sensor in energy-storage apparatus, terminal device, and storage medium | |
| JPWO2013088565A1 (en) | Detection device, detection program, and detection method | |
| CN115130064A (en) | Vibration data anomaly detection method, device, equipment and storage medium | |
| CN112583610B (en) | System state prediction method, system state prediction device, server and storage medium | |
| CN110417751B (en) | Network security early warning method, device and storage medium | |
| WO2018154845A1 (en) | Management device, management method, and program | |
| CN111400114A (en) | Deep recursion network-based big data computer system fault detection method and system | |
| US20190362262A1 (en) | Information processing device, non-transitory storage medium and information processing method | |
| JP2015185120A (en) | Information processing equipment, information processing method, and program | |
| CN112463883A (en) | Reliability monitoring method, device and equipment based on big data synchronization platform | |
| CN115774208A (en) | Battery unit abnormity monitoring method and device, electronic equipment and medium | |
| CN115643163A (en) | Fault equipment positioning method, device, equipment and storage medium | |
| CN115643158A (en) | Equipment cluster repairing method, device, equipment and storage medium | |
| WO2024046470A1 (en) | Weighing abnormality detection method and apparatus, and related apparatus | |
| US20230367932A1 (en) | Adaptive density estimation with multi-layered histograms | |
| CN112162528A (en) | Fault diagnosis method, device, equipment and storage medium of numerical control machine tool | |
| CN117055718B (en) | System, method, device, equipment and storage medium for detecting power consumption of server |
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 |