CN110108474A - A kind of rotating machinery operation stability on-line monitoring and appraisal procedure and system - Google Patents
A kind of rotating machinery operation stability on-line monitoring and appraisal procedure and system Download PDFInfo
- Publication number
- CN110108474A CN110108474A CN201910481631.2A CN201910481631A CN110108474A CN 110108474 A CN110108474 A CN 110108474A CN 201910481631 A CN201910481631 A CN 201910481631A CN 110108474 A CN110108474 A CN 110108474A
- Authority
- CN
- China
- Prior art keywords
- rotating machinery
- mechanical
- state
- abnormal
- unusual
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
Abstract
The present invention relates to a kind of rotating machinery operation stability on-line monitorings and appraisal procedure and system, utilize the mechanical signal that rotating machinery is monitored in sensor collection setting time；Singular value decomposition is carried out using mechanical signal of the singular value decomposition method to collection, the singular value that different time points mechanical signal obtains after singular value decomposition in setting time forms unusual value sequence, using the unusual value sequence state characteristic information current as monitored rotating machinery；The distance metric in timing is carried out to state characteristic information using statistical distance analysis, using the distance after measurement as abnormality degree score, multiple abnormality degree scores form abnormal degree series；Abnormal degree series are detected in real time using hypothesis testing, abnormal point appearance are judged whether there is, to determine whether occur abnormal state in rotating machinery operational process.The present invention can collect the mechanical signal of rotating machinery vibrating generation, and the operating status of mechanical movement is monitored after the mechanical signal of setting time is handled.
Description
Technical field
The invention belongs to system state machine monitoring technical fields, and in particular to a kind of rotating machinery operation stability is online
Monitoring and evaluation method and system.
Background technique
With the rapid development of Mechanical Industry Technology, modern mechanical equipment is towards high speed, high-precision, high efficiency and height
The direction of automation is developed, and for the health operation for guaranteeing these mechanical equipments, avoids occurring key components and parts in use
The situations such as mechanical breakdown caused by unstability, failure, equipment failure；Mechanical equipment shutdown maintenance is avoided, a large amount of warp is generated
Ji loss or even serious industrial production accident；It needs in real time to assess the operation stability of mechanical equipment, detects machine
The abnormality that tool equipment occurs in the process of running, it is possible to the early stage sign point of the mechanical equipment failure of appearance, by its table
Sign is the abnormality of mechanical movement, reminds operator to take and timely handles.
Inventor thinks: the method that the monitoring of rotating machinery operation stability mainly uses frequency-domain analysis at present, due to
Its calculation amount is bigger, and substantially offline mode, while the result diagnosed is also required to professional's analysis, so that
Current method is unable to the monitoring of real-time online and analyzes the operation stability of rotating machinery.
Summary of the invention
It is online the purpose of the present invention is to overcome above-mentioned the deficiencies in the prior art, providing a kind of rotating machinery operation stability
Monitoring and evaluation method and system.This method is capable of the monitoring of the completion mechanical movement stability of real-time online, while realizing needle
The completion STABILITY MONITORING and assessment adaptive to different conditions.
The first object of the present invention is to provide a kind of rotating machinery operation stability on-line monitoring and appraisal procedure, Neng Goushi
When collect the mechanical signal that monitored rotating machinery vibrating generates, monitored after the mechanical signal of setting time length is handled
Mechanical movement whether there is abnormality.
The second object of the present invention is to provide a kind of rotating machinery operation stability on-line monitoring and assessment system, based on upper
The rotating machinery operation stability on-line monitoring and appraisal procedure stated, realize the real-time monitoring of running state of rotating machine, in time
It was found that the exception of running state of rotating machine.
To achieve the above object, the present invention adopts the following technical solutions:
A kind of rotating machinery operation stability on-line monitoring and appraisal procedure, comprising the following steps:
Step 1, the mechanical letter that rotating machinery is monitored in setting time is collected with the sample frequency set using sensor
Number；The sensor includes vibrating sensor, and the mechanical signal includes vibration signal.
Step 2, singular value decomposition, machinery in setting time are carried out using mechanical signal of the singular value decomposition method to collection
The singular value that signal obtains after singular value decomposition forms unusual value sequence, works as unusual value sequence as monitored rotating machinery
Preceding state characteristic information.Unusual value sequence contains all information of the fragment signal data, while the sequence also being capable of table
The substantive characteristics of the fragment signal Mechanical Running Condition is levied out, these unusual value sequences are able to reflect out machinery in time series
Operating status situation of change.The extraction singular value as characteristic information in signal method in bearing failure diagnosis
Using.
Step 3, the distance metric carried out in timing to state characteristic information is analyzed using statistical distance, by after measurement away from
From as abnormality degree score, multiple abnormality degree scores form abnormal degree series.Statistical distance analysis can quickly quantify unusual
Similarity between different value sequence, and then can be realized real-time accurate effect.Than being reduced greatly using the method for neural network
The historical signal data learning training stage of amount, and complicated computational discrimination process.Statistical distance is analyzed in speech recognition, text
It has been applied in this identification or video Activity recognition.
Step 4, abnormal degree series are detected using hypothesis testing in real time, judges whether there is abnormal point appearance, with
Determine whether occur abnormal state in rotating machinery operational process.Hypothesis testing is very common inspection in statistical analysis
Proved recipe method, it is able to achieve adaptive stability analysis under different working condition, and then improves the application scenarios of this method, increases
Add practical ability.
A kind of rotating machinery operation stability on-line monitoring and assessment system, including state acquisition module, state feature mention
Modulus block, abnormal state degree metric module, state change moment determining module.
State acquisition module is used to acquire the mechanical signal of monitored rotating machinery；
State characteristic extracting module is connect with state acquisition module, and state characteristic extracting module is used to utilize singular value decomposition
Method extracts the state characteristic information that mechanical movement is characterized in mechanical signal；
State acquisition module is connect with abnormal state degree metric module, and abnormal state degree metric module is used for assay measures machine
Abnormality degree between the state characteristic information of tool operation；
The connection of abnormal state degree metric module is connect with state change moment determining module, state change moment determining module
For being detected using hypothesis testing abnormality degree, mechanical movement stability is assessed, and then determine that Mechanical Running Condition becomes
At the time of change.
Beneficial effects of the present invention:
1) present invention acquires the vibration signal in running state of rotating machine using sensor in real time, and utilizes singular value
Decomposition technique obtains state characteristic information of the unusual value sequence in setting time as mechanical movement in the time slice, relatively
For other signal processing modes, the characterization of operating status characteristic information is more accurate.
2) the abnormality degree score of the unusual value sequence of two neighboring time span is obtained by the way of statistical distance analysis,
And multiple abnormality degree scores are formed into abnormal degree series, data basis is provided for subsequent abnormal judgement；While abnormality degree
Calculating can be completed in the very short time, be capable of the monitoring mechanical signal of real-time online and assessed Mechanical Running Condition.
3) inspection that abnormal point in abnormal degree series can be easily realized using hypothesis testing, unusual condition is mentioned in time
Operator is supplied, avoids mechanical breakdown caused by running state of rotating machine exception, the problem of equipment failure.
Detailed description of the invention
The accompanying drawings constituting a part of this application is used to provide further understanding of the present application, and the application's shows
Meaning property embodiment and its explanation do not constitute the restriction to the application for explaining the application.
Fig. 1 is the flow chart of monitoring method in the embodiment of the present invention 1；
Fig. 2 is the unusual value sequence of setting time length in the embodiment of the present invention 1；
Fig. 3 is the exception that the mechanical signal of setting time length in the embodiment of the present invention 1 is obtained according to statistical analysis measurement
Degree series figure；
Fig. 4 is overall structure diagram in the embodiment of the present invention 2；
Fig. 5 is the data analysis chart that specific experiment obtains in the embodiment of the present invention 1.
Specific embodiment
It is noted that following detailed description is all illustrative, it is intended to provide further instruction to the application.Unless another
It indicates, all technical and scientific terms used herein has usual with the application person of an ordinary skill in the technical field
The identical meanings of understanding.
It should be noted that term used herein above is merely to describe specific embodiment, and be not intended to restricted root
According to the illustrative embodiments of the application.As used herein, unless the context clearly indicates otherwise, otherwise singular
Also it is intended to include plural form, additionally, it should be understood that, when in the present specification using term "comprising" and/or " packet
Include " when, indicate existing characteristics, step, operation, device, component and/or their combination.
Embodiment 1
As shown in Figs. 1-5, a kind of rotating machinery operation stability on-line monitoring and appraisal procedure, including following step are provided
It is rapid:
Step 1, the mechanical signal that rotating machinery is monitored in setting time is collected with the frequency set using sensor；Institute
Stating sensor includes vibrating sensor, and the mechanical signal includes vibration signal.
Step 2, singular value decomposition, difference in setting time are carried out using mechanical signal of the singular value decomposition method to collection
The singular value that the mechanical signal at time point obtains after singular value decomposition forms unusual value sequence, using unusual value sequence as being supervised
Survey the current state characteristic information of rotating machinery.
Specifically, the mechanical signal of sensor collection is x in moment t(t), take the mechanical signal that wherein a segment length is T
XT=(x1,…,xT), XTEach time point mechanical signal is arranged the sequence to be formed, x sequentially in time by expression1, x2Deng expression sequence
Object in column, index number indicate its location in the sequence.
It is translated into the time series Y an of multidimensional1,…,YKWherein Yi=(xi,…,xi+L-1)TFor one-dimensional column to
Amount, L are the length of sliding window, and the range of selection is 2≤L≤T/2, and in actual application, L is taken as the one third length of T
It and is integer.The time series of multidimensional is also known as Hankel matrix Y:
Wherein, L, K representing matrix Y have L row, K column；The numerical value of K is determined by L.yijThe member that the i-th row jth arranges in representing matrix Y
Element.
Singular value decomposition is carried out to matrix Y, matrix Y can be decomposed into the product of three matrixes:
Y=U Σ VT
Wherein, U is the orthogonal matrix of L × L, and V is the orthogonal matrix of K × K, and Σ is that the matrix of L × K is also referred to as the unusual of Y
It is worth value matrix；
Element in ΣReferred to as singular value, because the energy that partial value includes before unusual value sequence occupies
Entire unusual value sequence, therefore we take the unusual value sequence of preceding d=a × L length as the feature extracted, wherein a be than
Example coefficient, value range be (0 ..., 1].Therefore a data slot XT=(x1,…,xT) extract unusual value sequenceData distribution architecture be used to reflect the current state feature of mechanical movement,The as state characteristic information of Current mechanical operation.
As shown in Fig. 2, being the unusual value sequence of the mechanical signal extraction of a setting time length of the present embodiment, that is, mention
The characteristic sequence figure taken.
Step 3, the distance metric carried out in timing to state characteristic information is analyzed using statistical distance, by after measurement away from
From as abnormality degree score, multiple abnormality degree scores form abnormal degree series；
Specifically, two groups of unusual value sequences of the mechanical signal of the continuous two setting time length obtained by step 2 areWithWherein n indicates a unusual value sequence qiThe location of between multiple unusual value sequences,
I.e. n-th unusual value sequence qi.Using symmetrical KL divergence (Symmetric Kullback-Leibler Divergence) come real
Now to two groups of unusual value sequencesWithBetween measurement:
Calculating firstly for the probability function f (q) of the unusual value sequence of a time span is as follows:
It is by unusual value sequenceProbability function be expressed as f1 (q) again, for unusual value sequenceProbability letter
Number is expressed as f2 (q) again；
For between two sequence data group distributions probability function f1 (q) of symmetrical KL divergence metric calculation and f2 (q)
Distance D (f1 | | f2) and D (f2 | | f1):
The metric range of final symmetrical KL divergence calculates as follows:
Abnormality degree between the characteristic sequence of two signal segments continuously monitored is sn。
Fig. 3 is the abnormal degree series that one section of signal comprising state change of the invention is obtained according to statistical analysis measurement
Figure.
Step 4, abnormal degree series are detected using hypothesis testing in real time, judges whether there is abnormal point appearance, with
Determine whether occur abnormal state in rotating machinery operational process.
It is specific: abnormal degree series to be detected using 3 σ control figures of hypothesis testing, if having the sign of abnormality
1000000 points of appearance, hypothesis testing model are as follows:
Wherein H0For acceptance region, H1For region of rejection.Work as H0It is true, i.e. H1When being rejected, the signal of current time segment is indicated
In there is no abnormal state；
Work as H0It is rejected, i.e. H1When being true, indicates there is abnormal state in the signal of current time segment, simultaneously should
The abnormality degree at moment is the abnormal point in abnormal degree series；
And σnThe respectively sample average and sample variance of Gaussian Profile, calculation are as follows:
Embodiment 2
A kind of rotating machinery operation stability on-line monitoring and assessment system, including state acquisition module, state feature mention
Modulus block, abnormal state degree metric module, state change moment determining module.
State acquisition module is used to acquire the mechanical signal of monitored rotating machinery.
State characteristic extracting module is connect with state acquisition module, and state characteristic extracting module is used to utilize singular value decomposition
Method extracts the state characteristic information that mechanical movement is characterized in mechanical signal；The state characteristic extracting module can be from acquisition
The mechanical signal that setting time length is extracted in mechanical signal constructs Hankel matrix, carries out singular value point to the matrix of generation
Solution, the state characteristic information for the Current mechanical operation that obtained unusual value sequence is extracted as the setting time length.
State acquisition module is connect with abnormal state degree metric module, and abnormal state degree metric module is used for assay measures machine
Abnormality degree between the state characteristic information of tool operation；The abnormal state degree metric module: symmetrical KL divergence measurement side is utilized
Method calculates the unusual value sequence of continuous two setting time length signals, i.e. the symmetrical KL of the calculating unusual value sequence of two adjacent groups dissipates
Distance is spent, the abnormality degree score by symmetrical KL divergence distance as state change in mechanical movement.
The connection of abnormal state degree metric module is connect with state change moment determining module, state change moment determining module
For being detected using hypothesis testing abnormality degree, mechanical movement stability is assessed, and then determine that Mechanical Running Condition becomes
At the time of change.
The state change moment determining module can examine abnormal degree series using 3 σ control figures of hypothesis testing
It surveys, at the time of judging with the presence or absence of abnormality in mechanical movement, and determine that abnormality changes.
Above-mentioned, although the foregoing specific embodiments of the present invention is described with reference to the accompanying drawings, not protects model to the present invention
The limitation enclosed, those skilled in the art should understand that, based on the technical solutions of the present invention, those skilled in the art are not
Need to make the creative labor the various modifications or changes that can be made still within protection scope of the present invention.
Claims (9)
1. a kind of rotating machinery operation stability on-line monitoring and appraisal procedure, which comprises the following steps:
Step 1, the mechanical signal that rotating machinery is monitored in setting time is collected with the frequency set using sensor；
Step 2, singular value decomposition, different time in setting time are carried out using mechanical signal of the singular value decomposition method to collection
The singular value that point mechanical signal obtains after singular value decomposition forms unusual value sequence, using unusual value sequence as monitored rotation
Mechanical current state characteristic information；
Step 3, the distance metric carried out in timing to state characteristic information is analyzed using statistical distance, and the distance after measurement is made
For abnormality degree score, multiple abnormality degree scores form abnormal degree series；
Step 4, abnormal degree series are detected using hypothesis testing in real time, abnormal point appearance is judged whether there is, with determination
Whether abnormal state is occurred in rotating machinery operational process.
2. a kind of rotating machinery operation stability on-line monitoring according to claim 1 and appraisal procedure, which is characterized in that
The sensor includes vibrating sensor, and the mechanical signal includes vibration signal.
3. a kind of rotating machinery operation stability on-line monitoring according to claim 1 and appraisal procedure, which is characterized in that
Specific mode in the step 2 are as follows:
The mechanical signal of sensor collection is x in moment t(t), take the mechanical signal X that wherein a period of time length is TT=
(x1,…,xT), it is translated into the time series of a multidimensional, that is, is converted into Hankel matrix Y, is indicated are as follows:
XTEach time point mechanical signal is arranged the sequence to be formed, x sequentially in time by expression1, x2Deng pair indicated in sequence
As index number indicates its location in the sequence；L, K representing matrix Y has L row, K column；The numerical value of K determines by L, yij
The element that the i-th row jth arranges in representing matrix Y；
Singular value decomposition is carried out to matrix Y, matrix Y can be decomposed into the product of three matrixes:
Y=U Σ VT
Wherein, U is the orthogonal matrix of L × L, and V is the orthogonal matrix of K × K, and Σ is that the matrix of L × K is also referred to as the singular value square of Y
Battle array；
Diagonal element in ΣReferred to as singular value, because the energy that partial value includes before unusual value sequence accounts for
According to entire unusual value sequence, take the unusual value sequence of preceding d=a × L length as the feature extracted, wherein a is proportionality coefficient,
The value range of a be (0 ..., 1]；
One data slot XT=(x1,…,xT) extract unusual value sequenceData distribution architecture use
In reflection mechanical movement current state feature,The as state characteristic information of Current mechanical operation.
4. a kind of rotating machinery operation stability on-line monitoring according to claim 3 and appraisal procedure, which is characterized in that
Specific steps in the step 3 are as follows:
Two groups of unusual value sequences of the mechanical signal of the continuous two setting time length obtained by step 2 areWithWherein n indicates a unusual value sequence qiThe location of between multiple unusual value sequences, i.e., the
N unusual value sequence qi, realized using symmetrical KL divergence to two groups of unusual value sequencesWithBetween measurement,
Calculating firstly for the probability function f (q) of the unusual value sequence of a time span is as follows:
It is by unusual value sequenceProbability function be expressed as f1 (q) again, for unusual value sequenceProbability function weight
Newly it is expressed as f2 (q)；
With symmetrical KL divergence metric calculation two sequence data groups distribution the distance between probability function f1 (q) and f2 (q) D (f1 |
| f2) and D (f2 | | f1):
The metric range of final symmetrical KL divergence calculates as follows:
Abnormality degree between the characteristic sequence of two signal segments continuously monitored is sn。
5. a kind of rotating machinery operation stability on-line monitoring according to claim 4 and appraisal procedure, which is characterized in that
Specific steps in the step 4 are as follows: abnormal degree series are detected using 3 σ control figures of hypothesis testing, if having abnormal shape
The sign point of state occurs, and hypothesis testing model is as follows:
Wherein H0For acceptance region, H1For region of rejection, work as H0It is true, i.e. H1When being rejected, indicate do not have in the signal of current time segment
There is abnormal state；
Work as H0It is rejected, i.e. H1When being true, indicate there is abnormal state, while the moment in the signal of current time segment
Abnormality degree be abnormal point in abnormal degree series；
And σnThe respectively sample average and sample variance of Gaussian Profile, calculation are as follows:
6. a kind of rotating machinery operation stability on-line monitoring and assessment system, are utilized any one of claim 1-5 institute
The rotating machinery operation stability on-line monitoring and appraisal procedure stated characterized by comprising
State acquisition module, for acquiring the mechanical signal of monitored rotating machinery；
State characteristic extracting module, for extracting the state spy for characterizing mechanical movement in mechanical signal by singular value decomposition method
Reference breath；
Abnormal state degree metric module, for the abnormality degree between the state characteristic information of assay measures mechanical movement；
State change moment determining module is used to be detected using hypothesis testing abnormality degree, assesses mechanical movement stability,
And then at the time of determining that Mechanical Running Condition changes.
7. a kind of rotating machinery operation stability on-line monitoring according to claim 6 and appraisal procedure, which is characterized in that
The state characteristic extracting module can extract the mechanical signal building Hunk of setting time length from the mechanical signal of acquisition
Obtained unusual value sequence is extracted the matrix progress singular value decomposition of generation matrix by you as the setting time length
The state characteristic information of Current mechanical operation.
8. a kind of rotating machinery operation stability on-line monitoring according to claim 6 and appraisal procedure, which is characterized in that
The abnormal state degree metric module can calculate continuous two setting time length signals using symmetrical KL divergence measure
Unusual value sequence, the abnormality degree score by symmetrical KL divergence distance as state change in mechanical movement.
9. a kind of rotating machinery operation stability on-line monitoring according to claim 6 and appraisal procedure, which is characterized in that
The state change moment determining module can detect abnormal degree series using 3 σ control figures of hypothesis testing, judge
At the time of whether there is abnormality in mechanical movement, and determine that abnormality changes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910481631.2A CN110108474B (en) | 2019-06-04 | 2019-06-04 | Online monitoring and evaluating method and system for operation stability of rotary machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910481631.2A CN110108474B (en) | 2019-06-04 | 2019-06-04 | Online monitoring and evaluating method and system for operation stability of rotary machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110108474A true CN110108474A (en) | 2019-08-09 |
| CN110108474B CN110108474B (en) | 2020-05-15 |
Family
ID=67493748
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910481631.2A Active CN110108474B (en) | 2019-06-04 | 2019-06-04 | Online monitoring and evaluating method and system for operation stability of rotary machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110108474B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111144267A (en) * | 2019-12-23 | 2020-05-12 | 上海联影智能医疗科技有限公司 | Equipment operation state detection method and device, storage medium and computer equipment |
| CN114414227A (en) * | 2021-12-29 | 2022-04-29 | 华电电力科学研究院有限公司 | Equipment collision sensing method, device, equipment and storage medium |
| CN115309090A (en) * | 2022-09-28 | 2022-11-08 | 深圳市世坤科技实业有限公司 | Mechanical equipment working state control system and method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020178193A1 (en) * | 1997-11-18 | 2002-11-28 | Samsung Electronics Co., Ltd. | Method for filtering signals from nonlinear dynamical systems |
| CN103743563A (en) * | 2013-08-13 | 2014-04-23 | 华北电力大学（保定） | Fan gear box space failure predicating method based on temperature data |
| CN106650696A (en) * | 2016-12-30 | 2017-05-10 | 山东大学 | Handwritten electrical element identification method based on singular value decomposition |
| CN106959400A (en) * | 2017-02-28 | 2017-07-18 | 中国南方电网有限责任公司 | It is a kind of that the secondary device hidden failure diagnostic method analyzed with big data is monitored based on abnormity point |
| CN108444712A (en) * | 2018-05-07 | 2018-08-24 | 东南大学 | Based on the wind-powered electricity generation transmission system base bearing analysis of vibration signal method for improving HHT and fuzzy entropy |
| CN109583386A (en) * | 2018-11-30 | 2019-04-05 | 中南大学 | A kind of intelligent rotating mechanical breakdown depth network characterization discrimination method |
-
2019
- 2019-06-04 CN CN201910481631.2A patent/CN110108474B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020178193A1 (en) * | 1997-11-18 | 2002-11-28 | Samsung Electronics Co., Ltd. | Method for filtering signals from nonlinear dynamical systems |
| CN103743563A (en) * | 2013-08-13 | 2014-04-23 | 华北电力大学（保定） | Fan gear box space failure predicating method based on temperature data |
| CN106650696A (en) * | 2016-12-30 | 2017-05-10 | 山东大学 | Handwritten electrical element identification method based on singular value decomposition |
| CN106959400A (en) * | 2017-02-28 | 2017-07-18 | 中国南方电网有限责任公司 | It is a kind of that the secondary device hidden failure diagnostic method analyzed with big data is monitored based on abnormity point |
| CN108444712A (en) * | 2018-05-07 | 2018-08-24 | 东南大学 | Based on the wind-powered electricity generation transmission system base bearing analysis of vibration signal method for improving HHT and fuzzy entropy |
| CN109583386A (en) * | 2018-11-30 | 2019-04-05 | 中南大学 | A kind of intelligent rotating mechanical breakdown depth network characterization discrimination method |
Non-Patent Citations (1)
| Title |
|---|
| 于萍等: "基于奇异谱相对熵与灰色绝对关联度的监测数据特征分析", 《噪声与振动控制》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111144267A (en) * | 2019-12-23 | 2020-05-12 | 上海联影智能医疗科技有限公司 | Equipment operation state detection method and device, storage medium and computer equipment |
| CN111144267B (en) * | 2019-12-23 | 2023-09-26 | 上海联影智能医疗科技有限公司 | Equipment running state detection method and device, storage medium and computer equipment |
| CN114414227A (en) * | 2021-12-29 | 2022-04-29 | 华电电力科学研究院有限公司 | Equipment collision sensing method, device, equipment and storage medium |
| CN114414227B (en) * | 2021-12-29 | 2023-05-26 | 华电电力科学研究院有限公司 | Equipment collision sensing method, device, equipment and storage medium |
| CN115309090A (en) * | 2022-09-28 | 2022-11-08 | 深圳市世坤科技实业有限公司 | Mechanical equipment working state control system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110108474B (en) | 2020-05-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104712542B (en) | A kind of reciprocating compressor sensitive features based on Internet of Things are extracted and method for diagnosing faults | |
| CN109858104B (en) | Rolling bearing health assessment and fault diagnosis method and monitoring system | |
| US6804563B1 (en) | Multidimensional method and system for statistical process control | |
| CN110108474A (en) | A kind of rotating machinery operation stability on-line monitoring and appraisal procedure and system | |
| CN113834657B (en) | Bearing fault early warning and diagnosis method based on improved MSET and frequency spectrum characteristics | |
| CN106404441B (en) | A kind of failure modes diagnostic method based on non-linear similarity index | |
| CN113838054B (en) | Mechanical part surface damage detection method based on artificial intelligence | |
| WO2016004749A1 (en) | Method for recognizing tool abrasion degree of large numerical control milling machine | |
| CN111678699B (en) | Early fault monitoring and diagnosing method and system for rolling bearing | |
| CN112393906B (en) | Method for diagnosing, classifying and evaluating health of weak signal fault of bogie bearing of metro vehicle | |
| CN111721834A (en) | Cable partial discharge online monitoring defect identification method | |
| CN116070527B (en) | Milling cutter residual life prediction method based on degradation model | |
| CN109298633A (en) | Chemical production process fault monitoring method based on adaptive piecemeal Non-negative Matrix Factorization | |
| CN104102726A (en) | Modified K-means clustering algorithm based on hierarchical clustering | |
| CN109061387A (en) | A kind of power grid abnormality method of discrimination based on annulus theorem | |
| CN111504647A (en) | AR-MSET-based performance degradation evaluation method for rolling bearing | |
| CN111913443A (en) | Industrial equipment fault early warning method based on similarity | |
| CN104880217A (en) | Fault sensor information reconstruction method based on measured value association degree | |
| CN109434562A (en) | Milling cutter state of wear recognition methods based on partition clustering | |
| US20190122131A1 (en) | An anomaly identification method for structural monitoring data considering spatial-temporal correlation | |
| CN112947649B (en) | Multivariate process monitoring method based on mutual information matrix projection | |
| CN107330264B (en) | Method for verifying reliability of bridge monitoring data | |
| CN110057588B (en) | Bearing early fault detection and diagnosis method and system based on fusion of singular value and graph theory characteristics | |
| CN106250937B (en) | A kind of failure modes diagnostic method based on non-index of similarity | |
| CN116720073A (en) | Abnormality detection extraction method and system based on classifier |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |