CN110108474B - Online monitoring and evaluating method and system for operation stability of rotary machine - Google Patents

Online monitoring and evaluating method and system for operation stability of rotary machine Download PDF

Info

Publication number
CN110108474B
CN110108474B CN201910481631.2A CN201910481631A CN110108474B CN 110108474 B CN110108474 B CN 110108474B CN 201910481631 A CN201910481631 A CN 201910481631A CN 110108474 B CN110108474 B CN 110108474B
Authority
CN
China
Prior art keywords
sequence
singular value
mechanical
state
abnormal
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201910481631.2A
Other languages
Chinese (zh)
Other versions
CN110108474A (en
Inventor
卢国梁
文新
闫鹏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shandong University
Original Assignee
Shandong University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shandong University filed Critical Shandong University
Priority to CN201910481631.2A priority Critical patent/CN110108474B/en
Publication of CN110108474A publication Critical patent/CN110108474A/en
Application granted granted Critical
Publication of CN110108474B publication Critical patent/CN110108474B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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 invention relates to a method and a system for monitoring and evaluating the running stability of a rotary machine on line, wherein a sensor is used for collecting mechanical signals of the monitored rotary machine within a set time; performing singular value decomposition on the collected mechanical signals by using a singular value decomposition method, forming a singular value sequence by using singular values obtained after the mechanical signals at different time points in set time are subjected to the singular value decomposition, and taking the singular value sequence as the current state characteristic information of the monitored rotary machine; performing time-series distance measurement on the state characteristic information by utilizing statistical distance analysis, taking the measured distance as an abnormal degree score, and forming an abnormal degree sequence by using a plurality of abnormal degree scores; and detecting the abnormal degree sequence in real time by using hypothesis test, and judging whether abnormal points appear or not so as to determine whether abnormal states appear or not in the running process of the rotary mechanical equipment. The invention can collect mechanical signals generated by the vibration of the rotary machine, process the mechanical signals of set time and monitor the running state of mechanical motion.

Description

Online monitoring and evaluating method and system for operation stability of rotary machine
Technical Field
The invention belongs to the technical field of mechanical system state monitoring, and particularly relates to a method and a system for online monitoring and evaluating the operation stability of a rotary machine.
Background
With the rapid development of the mechanical industrial technology, modern mechanical equipment develops towards the directions of high speed, high precision, high efficiency and high automation, so that the conditions of instability of key parts and mechanical failure, equipment failure and the like caused by failure are avoided in the use process in order to ensure the healthy operation of the mechanical equipment; the machine avoids the shutdown maintenance of mechanical equipment, generates a large amount of economic loss and even serious industrial production accidents; the operation stability of the mechanical equipment needs to be evaluated in real time, abnormal states of the mechanical equipment in the operation process are monitored, namely early signs of mechanical equipment failure which can occur are characterized as abnormal states of mechanical operation, and operators are reminded to take timely treatment.
The inventor thinks that: at present, the operation stability of the rotary machine is mainly monitored by adopting a frequency domain analysis method, and because the calculated amount is large and the method is basically in an off-line mode, and meanwhile, the diagnosis result also needs to be analyzed by a professional, the operation stability of the rotary machine cannot be monitored and analyzed in real time in an on-line manner by the existing method.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a method and a system for online monitoring and evaluating the operation stability of a rotary machine. The method can complete the monitoring of the mechanical operation stability on line in real time, and meanwhile, the self-adaptive stability monitoring and evaluation aiming at different states are realized.
The first purpose of the present invention is to provide an online monitoring and evaluating method for the operation stability of a rotating machine, which can collect a mechanical signal generated by the vibration of the monitored rotating machine in real time, process the mechanical signal with a set time length, and monitor whether the mechanical motion is in an abnormal state.
The second purpose of the present invention is to provide an online monitoring and evaluating system for the operation stability of a rotary machine, which is based on the online monitoring and evaluating method for the operation stability of a rotary machine, so as to realize real-time monitoring of the operation state of the rotary machine and timely find the abnormality of the operation state of the rotary machine.
In order to achieve the purpose, the invention adopts the following technical scheme:
an online monitoring and evaluating method for the operation stability of a rotating machine comprises the following steps:
step 1, collecting mechanical signals of a monitored rotating machine within set time by using a sensor at a set sampling frequency; the sensor comprises a vibration sensor and the mechanical signal comprises a vibration signal.
And 2, performing singular value decomposition on the collected mechanical signals by using a singular value decomposition method, forming a singular value sequence by using singular values obtained after the singular value decomposition of the mechanical signals in set time, and taking the singular value sequence as the current state characteristic information of the monitored rotating machinery. The singular value sequence contains all information of the segment signal data, and simultaneously the sequence can also represent essential characteristics of the mechanical operating state of the segment signal, and the singular value sequences can reflect the mechanical operating state change situation on the time sequence. The method for extracting singular values as characteristic information in signals is already applied to bearing fault diagnosis.
And 3, performing time-series distance measurement on the state characteristic information by utilizing statistical distance analysis, taking the measured distance as an abnormal degree score, and forming an abnormal degree sequence by using a plurality of abnormal degree scores. The statistical distance analysis can rapidly quantify the similarity between the singular value sequences, and further can realize the real-time and accurate effect. Compared with a method adopting a neural network, a large number of historical signal data learning and training stages and complex calculation and discrimination processes are reduced. Statistical distance analysis has been applied to speech recognition, text recognition, or video behavior recognition.
And 4, detecting the abnormal degree sequence in real time by using hypothesis testing, and judging whether abnormal points appear or not so as to determine whether the abnormal state appears in the running process of the rotary mechanical equipment or not. The hypothesis test is a very common test method in statistical analysis, and can realize self-adaptive stability analysis under different working states, thereby improving the application scene of the method and increasing the practical capability.
An online monitoring and evaluating system for the running stability of a rotary machine comprises a state acquisition module, a state feature extraction module, a state abnormality degree measurement module and a state change moment determination module.
The state acquisition module is used for acquiring mechanical signals of the monitored rotating machinery;
the state feature extraction module is connected with the state acquisition module and is used for extracting state feature information representing mechanical operation in the mechanical signal by using a singular value decomposition method;
the state anomaly degree measurement module is used for analyzing and measuring the anomaly degree between state characteristic information of the operation of the machine;
the state anomaly degree measurement module is connected with the state change time determination module, and the state change time determination module is used for detecting by using the hypothesis test anomaly degree, evaluating the mechanical operation stability and further determining the time when the mechanical operation state changes.
The invention has the beneficial effects that:
1) the method adopts the sensor to collect the vibration signal in the running state of the rotary machine in real time, obtains the singular value sequence in the set time by utilizing the singular value decomposition technology as the state characteristic information of the machine running in the time segment, and has more accurate representation of the running state characteristic information compared with other signal processing modes.
2) Obtaining the abnormal degree scores of the singular value sequences of two adjacent time lengths by adopting a statistical distance analysis mode, and forming the abnormal degree scores into an abnormal degree sequence so as to provide a data basis for subsequent abnormal judgment; meanwhile, the calculation of the abnormal degree can be completed in a short time, and the mechanical signal can be monitored and the mechanical running state can be evaluated in real time in an online manner.
3) The detection of abnormal points in an abnormal degree sequence can be conveniently realized by adopting hypothesis detection, the abnormal conditions are timely provided for operators, and the problems of mechanical failure and equipment failure caused by abnormal running state of the rotary machine are avoided.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application.
FIG. 1 is a flowchart of a monitoring method in embodiment 1 of the present invention;
FIG. 2 is a sequence of singular values for which a time length is set in embodiment 1 of the present invention;
FIG. 3 is a sequence diagram of the degree of abnormality of a mechanical signal of a set time length measured by statistical analysis according to example 1 of the present invention;
FIG. 4 is a schematic view of the overall structure in embodiment 2 of the present invention;
FIG. 5 is a graph showing an analysis of data obtained in a specific experiment in example 1 of the present invention.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
Example 1
As shown in fig. 1 to 5, an online monitoring and evaluating method for the operation stability of a rotating machine is provided, which comprises the following steps:
step 1, collecting mechanical signals of a monitored rotating machine within set time by using a sensor at a set frequency; the sensor comprises a vibration sensor and the mechanical signal comprises a vibration signal.
And 2, performing singular value decomposition on the collected mechanical signals by using a singular value decomposition method, forming a singular value sequence by using singular values obtained after the singular value decomposition is performed on the mechanical signals at different time points in set time, and taking the singular value sequence as the current state characteristic information of the monitored rotating machinery.
Specifically, the mechanical signal collected by the sensor is x at time t(t)Taking one section of mechanical signal X with length TT＝(x1,…,xT)，XTRepresenting a sequence of mechanical signals arranged in time order at time points, x1，x2Etc. denote objects in the sequence, with subscript numbers denoting their position in the sequence.
Convert it into a multidimensional time sequence Y1,…,YKWherein Y isi＝(xi,…,xi+L-1)TThe method is a one-dimensional column vector, L is the length of a sliding window, the selected range is that L is more than or equal to 2 and less than or equal to T/2, and in practical application, L is one third of the length of T and is an integer. The multidimensional time series is also called hankel matrix Y:
Figure BDA0002084039380000051
l, K list of themThe matrix Y has L rows and K columns; the value of K is determined by L. y isijRepresenting the element in row i and column j of matrix Y.
Singular value decomposition is performed on the matrix Y, which can be decomposed as the product of three matrices:
Y＝UΣVT
wherein, U is an L × L orthogonal matrix, V is a K × K orthogonal matrix, and a matrix Σ of L × K is also referred to as a singular value matrix of Y;
elements in sigma
Figure BDA0002084039380000052
Called singular value, because the energy contained in the front scores of the singular value sequence occupies the whole singular value sequence, we take the singular value sequence with the length of a × L as the extracted feature, wherein a is a proportionality coefficient and the value range is (0.. multidot.1.)]. Thus a data fragment XT＝(x1,…,xT) Sequence of extracted singular values
Figure BDA0002084039380000061
Is used to reflect the current state characteristics of machine operation,
Figure BDA0002084039380000062
i.e. the status characteristic information of the current machine operation.
As shown in fig. 2, the sequence of singular values extracted from a mechanical signal with a set time length, i.e. the extracted feature sequence diagram, is shown in this embodiment.
Step 3, performing time-series distance measurement on the state characteristic information by utilizing statistical distance analysis, taking the measured distance as an abnormal degree score, and forming an abnormal degree sequence by a plurality of abnormal degree scores;
specifically, the two sets of singular value sequences of the mechanical signals of two continuous set time lengths obtained in the step 2 are
Figure BDA0002084039380000063
And
Figure BDA0002084039380000064
wherein n represents a sequence of singular values qiAt positions between the plurality of singular value sequences, i.e. the nth singular value sequence qi. Symmetric KL Divergence (symmetry Kullback-Leibler Divergence) is adopted to realize the sequence of two groups of singular values
Figure BDA0002084039380000065
And
Figure BDA0002084039380000066
the measure in between:
first, the probability function f (q) for a time-length singular value sequence is calculated as follows:
Figure BDA0002084039380000067
sequence the singular values into
Figure BDA0002084039380000068
Is re-expressed as f1(q) for the sequence of singular values
Figure BDA0002084039380000069
Is re-expressed as f2 (q);
for the computation of distances D (f1| | f2) and D (f2| | f1) between two sequence data set distribution probability functions f1(q) and f2(q) with a symmetric KL divergence metric:
Figure BDA00020840393800000610
Figure BDA00020840393800000611
the metric distance of the final symmetric KL divergence is calculated as follows:
Figure BDA00020840393800000612
the degree of abnormality between the signature sequences of two successively monitored signal segments is sn。
FIG. 3 is a sequence of anomaly metrics from statistical analysis of a signal containing a change in state according to the present invention.
And 4, detecting the abnormal degree sequence in real time by using hypothesis testing, and judging whether abnormal points appear or not so as to determine whether the abnormal state appears in the running process of the rotary mechanical equipment or not.
Specifically, the method comprises the following steps: and (3) detecting the abnormal degree sequence by using a 3 sigma control chart of hypothesis test, and judging whether a symptom point of an abnormal state appears or not, wherein a hypothesis test model is as follows:
Figure BDA0002084039380000071
Figure BDA0002084039380000072
wherein H0To accept domain, H1Is the reject field. When H is present0Is true, i.e. H1When the signal is rejected, the signal of the current time segment has no abnormal state;
when H is present0Is rejected, i.e. H1When the current time segment is true, the abnormal state occurs in the signal of the current time segment, and the abnormal degree at the time is an abnormal point in the abnormal degree sequence;
Figure BDA0002084039380000073
and σnThe mean value and variance of the samples are respectively Gaussian distribution, and the calculation mode is as follows:
Figure BDA0002084039380000074
Figure BDA0002084039380000075
example 2
An online monitoring and evaluating system for the running stability of a rotary machine comprises a state acquisition module, a state feature extraction module, a state abnormality degree measurement module and a state change moment determination module.
The state acquisition module is used for acquiring mechanical signals of the monitored rotating machinery.
The state feature extraction module is connected with the state acquisition module and is used for extracting state feature information representing mechanical operation in the mechanical signal by using a singular value decomposition method; the state feature extraction module can extract mechanical signals with set time length from the collected mechanical signals to construct a Hankel matrix, perform singular value decomposition on the generated matrix, and take the obtained singular value sequence as the state feature information of the current mechanical operation extracted by the set time length.
The state anomaly degree measurement module is used for analyzing and measuring the anomaly degree between state characteristic information of the operation of the machine; the state anomaly metric module: and calculating singular value sequences of two continuous signals with set time length by using a symmetrical KL divergence measurement method, namely calculating symmetrical KL divergence distances of two adjacent groups of singular value sequences, and taking the symmetrical KL divergence distances as abnormal degree scores of state change in mechanical operation.
The state anomaly degree measurement module is connected with the state change time determination module, and the state change time determination module is used for detecting by using the hypothesis test anomaly degree, evaluating the mechanical operation stability and further determining the time when the mechanical operation state changes.
The state change time determining module can detect an abnormal degree sequence by using a 3 sigma control chart of hypothesis test, judge whether an abnormal state exists in the operation of the machine and determine the time when the abnormal state changes.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present invention, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive efforts by those skilled in the art based on the technical solution of the present invention.

Claims (7)

1. An online monitoring and evaluating method for the operation stability of a rotating machine is characterized by comprising the following steps:
step 1, collecting mechanical signals of a monitored rotating machine within set time by using a sensor at a set frequency;
step 2, carrying out singular value decomposition on the collected mechanical signals by using a singular value decomposition method, forming a singular value sequence by using singular values obtained after singular value decomposition on the mechanical signals at different time points in set time, and taking the singular value sequence as the current state characteristic information of the monitored rotating machinery;
step 3, performing time-series distance measurement on the state characteristic information by utilizing statistical distance analysis, taking the measured distance as an abnormal degree score, and forming an abnormal degree sequence by a plurality of abnormal degree scores;
the specific steps in the step 3 are as follows:
the two groups of singular value sequences of the mechanical signals with two continuous set time lengths obtained in the step 2 are
Figure FDA0002432798100000011
And
Figure FDA0002432798100000012
wherein n represents a sequence of singular values qiAt positions between the plurality of singular value sequences, i.e. the nth singular value sequence qiSymmetric KL divergence is adopted to realize the two groups of singular value sequences
Figure FDA0002432798100000013
And
Figure FDA0002432798100000014
the measure of the amount of the difference between,
first, the probability function f (q) for a time-length singular value sequence is calculated as follows:
Figure FDA0002432798100000015
sequence the singular values into
Figure FDA0002432798100000016
Is re-expressed as f1(q) for the sequence of singular values
Figure FDA0002432798100000017
Is re-expressed as f2 (q);
the distances D (f1| | | f2) and D (f2| | f1) between the two sequence data set probability functions f1(q) and f2(q) are calculated using a symmetric KL divergence metric:
Figure FDA0002432798100000018
Figure FDA0002432798100000021
the metric distance of the final symmetric KL divergence is calculated as follows:
Figure FDA0002432798100000022
the degree of abnormality between the signature sequences of two successively monitored signal segments is sn；
And 4, detecting the abnormal degree sequence in real time by using hypothesis testing, and judging whether abnormal points appear or not so as to determine whether the abnormal state appears in the running process of the rotary mechanical equipment or not.
2. The method of claim 1, wherein the sensor comprises a vibration sensor and the mechanical signal comprises a vibration signal.
3. The method for on-line monitoring and evaluating the operation stability of the rotating machine according to claim 1, wherein the specific manner in the step 2 is as follows:
the mechanical signal collected by the sensor is x at the time t(t)Taking one of the mechanical signals X with a time length of TT＝(x1,…,xT) It is converted into a multidimensional time series, i.e. into a hankel matrix Y, expressed as:
Figure FDA0002432798100000023
XTrepresenting a sequence of mechanical signals arranged in time order at time points, x1To xTRepresenting an object in the sequence with subscript numbers indicating its position in the sequence; l, K shows matrix Y has L rows, K columns; the value of K is determined by L, yijAn element representing the ith row and the jth column in the matrix Y;
singular value decomposition is performed on the matrix Y, which can be decomposed as the product of three matrices:
Y＝UΣVT
wherein, U is an L × L orthogonal matrix, V is a K × K orthogonal matrix, and a matrix Σ of L × K is also referred to as a singular value matrix of Y;
diagonal elements in sigma
Figure FDA0002432798100000031
The singular values are called, because the energy contained in the front scores of the singular value sequence occupies the whole singular value sequence, the singular value sequence with the length of a multiplied by L before d is taken as the extracted characteristic, wherein a is the value range of a proportionality coefficient (0.. multidot.1.)](ii) a Thus a data fragment XT＝(x1,…,xT) Sequence of extracted singular values
Figure FDA0002432798100000032
Is used to reflect the current state characteristics of machine operation,
Figure FDA0002432798100000033
i.e. the status characteristic information of the current machine operation.
4. The method for on-line monitoring and evaluating the operation stability of the rotating machine according to claim 1, wherein the specific steps in the step 4 are as follows: and (3) detecting the abnormal degree sequence by using a 3 sigma control chart of hypothesis test, and judging whether a symptom point of an abnormal state appears or not, wherein a hypothesis test model is as follows:
H0:
Figure FDA0002432798100000034
H1:
Figure FDA0002432798100000035
wherein H0To accept domain, H1Is a rejection area; when H is present0Is true, i.e. H1When the signal is rejected, the signal of the current time segment has no abnormal state;
when H is present0Is rejected, i.e. H1When the current time segment is true, the abnormal state occurs in the signal of the current time segment, and the abnormal degree at the time is an abnormal point in the abnormal degree sequence;
Figure FDA0002432798100000036
and σnThe mean value and variance of the samples are respectively Gaussian distribution, and the calculation mode is as follows:
Figure FDA0002432798100000037
Figure FDA0002432798100000038
5. an online monitoring and evaluating system for the operation stability of a rotating machine, which utilizes the online monitoring and evaluating method for the operation stability of a rotating machine as claimed in any one of claims 1 to 4, and is characterized by comprising:
the state acquisition module is used for acquiring mechanical signals of the monitored rotating machinery;
the state feature extraction module is used for extracting state feature information representing mechanical operation in the mechanical signal by a singular value decomposition method;
the state anomaly degree measurement module is used for analyzing the anomaly degree among state characteristic information for measuring the operation of the machine; the state anomaly degree measurement module can calculate singular value sequences of two continuous signals with set time length by using a symmetrical KL divergence degree measurement method, and the symmetrical KL divergence degree distance is used as the anomaly degree of state change in mechanical operation;
and the state change time determining module is used for detecting by using the hypothesis test abnormality degree, evaluating the mechanical operation stability and further determining the time when the mechanical operation state changes.
6. The system of claim 5, wherein the state feature extraction module is configured to extract mechanical signals of a set time length from the collected mechanical signals to construct a Hankel matrix, perform singular value decomposition on the generated matrix, and use an obtained singular value sequence as the state feature information of the current mechanical operation extracted by the set time length.
7. The system of claim 5, wherein the state change timing determination module is capable of detecting the abnormality degree sequence by using a 3 σ control chart of hypothesis testing, determining whether an abnormal state exists in the operation of the machine, and determining the timing of the abnormal state change.
CN201910481631.2A 2019-06-04 2019-06-04 Online monitoring and evaluating method and system for operation stability of rotary machine Active CN110108474B (en)

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 CN110108474A (en) 2019-08-09
CN110108474B true 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)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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
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

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100268455B1 (en) * 1997-11-18 2000-10-16 윤종용 Filtering method of non-linear dynamics signal
CN103743563B (en) * 2013-08-13 2016-01-06 华北电力大学（保定） A kind of gear case of blower subspace failure prediction method based on temperature data
CN106650696B (en) * 2016-12-30 2019-12-10 山东大学 method for identifying handwritten electrical element symbol based on singular value decomposition
CN106959400B (en) * 2017-02-28 2020-03-31 中国南方电网有限责任公司 Secondary equipment hidden danger fault diagnosis method based on abnormal point monitoring and big data analysis
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
CN109583386B (en) * 2018-11-30 2020-08-25 中南大学 Intelligent rotating machinery fault depth network feature identification method

Also Published As

Publication number Publication date
CN110108474A (en) 2019-08-09

Similar Documents

Publication Publication Date Title
CN110108474B (en) Online monitoring and evaluating method and system for operation stability of rotary machine
CN113834657B (en) Bearing fault early warning and diagnosis method based on improved MSET and frequency spectrum characteristics
CN110110768B (en) Rolling bearing fault diagnosis method based on parallel feature learning and multiple classifiers
CN111353482A (en) LSTM-based fatigue factor recessive anomaly detection and fault diagnosis method
CN112257530B (en) Rolling bearing fault diagnosis method based on blind signal separation and support vector machine
CN113838054B (en) Mechanical part surface damage detection method based on artificial intelligence
CN111678699B (en) Early fault monitoring and diagnosing method and system for rolling bearing
CN105241680A (en) Health state assessment method for rotary machine based on probability density function
CN108956111B (en) Abnormal state detection method and detection system for mechanical part
CN111964909A (en) Rolling bearing operation state detection method, fault diagnosis method and system
CN115409131B (en) Production line abnormity detection method based on SPC process control system
CN111368428B (en) Sensor precision degradation fault detection method based on monitoring second-order statistics
CN111504647A (en) AR-MSET-based performance degradation evaluation method for rolling bearing
CN111861272A (en) Multi-source data-based complex electromechanical system abnormal state detection method
CN112304611A (en) Deep learning-based bearing fault diagnosis method
CN112000081B (en) Fault monitoring method and system based on multi-block information extraction and Mahalanobis distance
CN114118219A (en) Data-driven real-time abnormal detection method for health state of long-term power-on equipment
CN115758200A (en) Vibration signal fault identification method and system based on similarity measurement
CN108955855B (en) Vibration signal feature extraction method, monitoring method and device for rotary machine
CN110057588B (en) Bearing early fault detection and diagnosis method and system based on fusion of singular value and graph theory characteristics
CN110160781B (en) Test set reconstruction and prediction method for rotary machine fault classification
CN115034094B (en) Prediction method and system for operation state of metal processing machine tool
Song et al. Fault diagnosis and process monitoring using a statistical pattern framework based on a self-organizing map
CN115659271A (en) Sensor abnormality detection method, model training method, system, device, and medium
CN112069621B (en) Method for predicting residual service life of rolling bearing based on linear reliability index

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