CN110133500A - Motor on-line monitoring and failure omen diagnostic system and method based on multi-layer framework - Google Patents
Motor on-line monitoring and failure omen diagnostic system and method based on multi-layer framework Download PDFInfo
- Publication number
- CN110133500A CN110133500A CN201910395820.8A CN201910395820A CN110133500A CN 110133500 A CN110133500 A CN 110133500A CN 201910395820 A CN201910395820 A CN 201910395820A CN 110133500 A CN110133500 A CN 110133500A
- Authority
- CN
- China
- Prior art keywords
- layer
- data center
- cloud data
- failure
- motor
- 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
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/34—Testing dynamo-electric machines
- G01R31/343—Testing dynamo-electric machines in operation
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a kind of, and the motor based on multi-layer framework is monitored on-line and failure omen diagnostic system and method.Motor on-line monitoring and failure omen diagnostic system and method based on multi-layer framework of the invention, by constructing multilevel diagnostic service layer, by hierarchical screening, step-by-step analysis diagnose in the way of to motor operating state carry out failure omen sentence knowledge, with the continuous raising of framework level, used diagnosis algorithm is also more advanced, and database more enriches complete, and diagnostic result accuracy rate is higher, while ensuring accuracy rate of diagnosis, diagnosis efficiency is greatly improved.Also, user can also comprehensively consider diagnosis efficiency and accuracy rate of diagnosis, select suitable diagnosis framework to carry out electrical fault omen diagnostic analysis, applicability is stronger.
Description
Technical field
The present invention relates to motor diagnostic technical fields, particularly, are related to a kind of motor on-line monitoring based on multi-layer framework
With failure omen diagnostic system and method.
Background technique
With the progress of science and technology and the continuous development of social economy, motor plays more in production and daily life
Carry out heavier effect.Motor produces most important motive power and driving device as modernization industry, once catastrophic failure occurs,
The interruption and weight huge economic loss of production procedure are not only resulted in, and it is also possible to causes casualties.Many important
Application aspect loses the value for being often significantly larger than motor itself caused by unplanned parking caused by one electrical fault.
The existing processing mode diagnosed to motor is all by data in local computer completion diagnostic analysis, or
Data are uploaded to Cloud Server and carry out unified diagnostic analysis.But existing local diagnostic analysis mode is all that will diagnose calculation
In local data layer, the key of Diagnosing Faults of Electrical is that diagnostic analysis algorithm and database compare for method and data store administration, by
Data volume in local machine database is limited, causes the accuracy rate of local diagnostic analysis mode very low.Existing cloud clothes
Business device diagnostic mode is to be unified in concentrate in Cloud Server to be analyzed and processed data, cloud server data database storing
To measure larger, comparing is cumbersome, if diagnostic service is all compared using comprehensive diagnostic analysis and complete database each time,
It is lower then to will lead to analyzing and diagnosing analysis efficiency.Therefore, existing motor diagnostic processing mode cannot be considered in terms of diagnosis efficiency and examine
The problem of disconnected accuracy rate.
Summary of the invention
Motor on-line monitoring and failure omen diagnostic system and the method that the present invention provides a kind of based on multi-layer framework, with
Solve the technical issues of cannot be considered in terms of diagnosis efficiency and accuracy rate of diagnosis existing for existing motor diagnostic processing mode.
According to an aspect of the present invention, provide it is a kind of based on multi-layer framework motor on-line monitoring with failure omen diagnose
System, including data acquisition equipment layer, local data acquisition layer, plant area's cloud data center's layer, region cloud data center's layer
With central cloud data center's layer, the local data acquisition layer respectively with data acquisition equipment layer and cloud data center, plant area
Layer connection, region cloud data center's layer connect with plant area's cloud data center's layer and central cloud data center's layer respectively
It connects；
The data acquisition equipment layer is used to acquire the original waveform data of motor；
The local data acquisition layer is used to obtain the original waveform data of motor and carries out to motor operating state primary
Failure sentences knowledge, and original waveform data and primary fault are sentenced and know obtained primary features data, failure omen warning information uploads
To plant area's cloud data center's layer；
The intermediate failure that plant area cloud data center's layer is used to carry out motor operating state sentences knowledge, and by suspicious waveform
Data and intermediate failure sentence mid-level features data, the failure omen warning information known and obtained and are uploaded to region cloud data center
Layer；
The suspicious Wave data that region cloud data center's layer is used to upload based on plant area's cloud data center's layer into
The middle-and-high-ranking failure of row motor operating state sentences knowledge, and suspicious Wave data and middle-and-high-ranking failure are sentenced to the middle-and-high-ranking spy for knowing and obtaining
Sign data, failure omen warning information are uploaded to central cloud data center's layer；
The suspicious Wave data that the center cloud data center's layer is used to upload based on region cloud data center's layer into
The High Fault of row motor operating state sentences knowledge.
Further, the local data acquisition layer passes through the analysis of temporal signatures value, historical data trend analysis and history
Comparing analysis carries out primary fault to motor operating state and sentences knowledge.
Further, plant area cloud data center's layer passes through fast Fourier analysis, frequency analysis and spectral trends
The intermediate failure for changing analysis progress motor operating state sentences knowledge.
Further, region cloud data center's layer first improves the signal-to-noise ratio of signal, then passes through multi-faceted diagnosis point
Analysis carries out middle-and-high-ranking failure to motor operating state and sentences knowledge.
Further, region cloud data center's layer passes through digital signal pre-treatment, digital signal filter and small echo
The signal-to-noise ratio of threshold denoising raising signal.
Further, the digital signal pre-treatment is by going DC terms, nonlinear trend item being gone to eliminate sensor drift
And measurement interference, the digital signal filter and wavelet threshold denoising are for eliminating low frequency or high-frequency interferencing signal and noise
Signal.
Further, region cloud data center's layer passes through fast Fourier analysis, frequency analysis, cepstrum point
Analysis, power spectrumanalysis, waterfall map analysis, resonance and demodulation analysis and the multi-faceted diagnostic analysis of wavelet analysis realization.
Further, the central cloud data center's layer includes the human-computer interaction mould for sentence for expert's intervention knowledge
Block.
Further, plant area cloud data center's layer, region cloud data center's layer and central cloud data center
Layer is also used to issue failure omen warning information by Web server.
Motor on-line monitoring and the failure omen diagnostic method that the present invention also provides a kind of based on multi-layer framework, using as above
The motor on-line monitoring and failure omen diagnostic system, comprising the following steps:
Step S1: the original waveform data of motor is acquired by data acquisition equipment layer；
Step S2: the original waveform data of motor is obtained using local data acquisition layer and motor operating state is carried out just
Grade failure sentences knowledges, and original waveform data and primary fault are sentenced primary features data that knowledge obtains, in failure omen warning information
Reach plant area's cloud data center's layer；
Step S3: intermediate failure is carried out to motor operating state using plant area's cloud data center's layer and sentences knowledge, and will be suspicious
Wave data and intermediate failure are sentenced mid-level features data, the failure omen warning information known and obtained and are uploaded in the data of region cloud
Central layer；
Step S4: the suspicious Wave data uploaded using region cloud data center's layer based on plant area's cloud data center's layer
Middle-and-high-ranking failure is carried out to motor operating state and sentences knowledges, and he suspicious Wave data and middle-and-high-ranking failure is sentenced know obtain it is middle-and-high-ranking
Characteristic, failure omen warning information are uploaded to central cloud data center's layer；
Step S5: the suspicious Wave data uploaded using central cloud data center's layer based on region cloud data center's layer
High Fault is carried out to motor operating state and sentences knowledge.
The invention has the following advantages:
Motor on-line monitoring and failure omen diagnostic system based on multi-layer framework of the invention, by constructing local data
Acquisition layer, plant area's cloud data center's layer, region cloud data center's layer and central cloud data center's layer carry out layering diagnosis,
By hierarchical screening, step-by-step analysis diagnose in the way of to motor operating state carry out failure omen sentence knowledge, with framework level
Constantly increasing, used diagnosis algorithm is also more advanced, and the database the abundant complete, and diagnostic result accuracy rate is higher, and
In view of the diagnosis algorithm that local data acquisition layer uses is relatively simple, primary fault identifying result accuracy rate may be lower, because
This uploads original waveform data between local data acquisition layer and plant area's cloud data center's layer, utilizes plant area's cloud data
More advanced algorithm carries out analyzing and diagnosing to original waveform data again in central core, improves the accuracy rate that knowledge is sentenced in diagnosis,
And in order to improve diagnosis efficiency, the suspicious Wave data that region cloud data center's layer only uploads plant area's cloud data center's layer
It is analyzed, the suspicious Wave data that central cloud data center's layer only uploads region cloud data center's layer is analyzed,
While ensuring accuracy rate of diagnosis, diagnosis efficiency is greatly improved.Also, user can also comprehensively consider diagnosis efficiency and
Accuracy rate of diagnosis selects suitable diagnosis framework to carry out electrical fault omen diagnostic analysis, and applicability is stronger.Base of the invention
System high efficiency is guaranteed by the diagnostic analysis of low-level in the motor on-line monitoring and failure omen diagnostic system of multi-layer framework
Operation, when that can not make a definite diagnosis, upper layer grade requests higher primary diagnosis service, guarantees diagnostic analysis accuracy.
In addition, it is of the invention based on multi-layer framework motor on-line monitoring it is same as failure omen diagnostic method have it is above-mentioned
Advantage.
Other than objects, features and advantages described above, there are also other objects, features and advantages by the present invention.
Below with reference to figure, the present invention is described in further detail.
Detailed description of the invention
The attached drawing constituted part of this application is used to provide further understanding of the present invention, schematic reality of the invention
It applies example and its explanation is used to explain the present invention, do not constitute improper limitations of the present invention.In the accompanying drawings:
Fig. 1 is the motor on-line monitoring and failure omen diagnostic system based on multi-layer framework of the preferred embodiment of the present invention
Structural schematic diagram.
Fig. 2 is the motor on-line monitoring and failure omen diagnostic method based on multi-layer framework of another embodiment of the present invention
Flow diagram.
Description of symbols
11, data acquisition equipment layer；12, local data acquisition layer；13, plant area cloud data center's layer；14, region cloud
Data center's layer；15, central cloud data center's layer；151, human-computer interaction module；20, motor device layer.
Specific embodiment
The embodiment of the present invention is described in detail below in conjunction with attached drawing, but the present invention can be limited by following and
The multitude of different ways of covering is implemented.
As shown in Figure 1, the preferred embodiment of the present invention provides a kind of motor on-line monitoring and failure based on multi-layer framework
Omen diagnostic system, by construct multilevel diagnostic service layer, by hierarchical screening, step-by-step analysis diagnose in the way of to motor operation
State carries out failure omen and sentences knowledge, has very high diagnosis efficiency and accuracy rate of diagnosis.The motor based on multi-layer framework exists
Line monitoring and failure omen diagnostic system include data acquisition equipment layer 11, local data acquisition layer 12, in plant area's cloud data
Central layer 13, region cloud data center's layer 14 and central cloud data center's layer 15, the local data acquisition layer 12 respectively with
Data acquisition equipment layer 11 and plant area's cloud data center's layer 13 connect, region cloud data center's layer 14 respectively with plant area
Cloud data center's layer 13 and central cloud data center's layer 15 connect.It is appreciated that the data acquisition equipment layer 11 and electricity
Machine equipment layer 20 connects, and the data acquisition equipment layer 11 is used to acquire the real-time running state data of motor device, and motor is set
Standby real-time running state data are the original waveform data of motor, and specifically, the data acquisition equipment layer 11 includes more
A data collection station, data collection station acquires the real-time running state data of motor device by sensor, i.e., by motor
The analog signals of equipment are converted to digital quantity signal, such as electricity data, vibration data, temperature data etc., one or more
The on-line operation data acquisition of the corresponding motor device of data collection station.
The native processor of the local data acquisition layer 12 and the data collection station of data acquisition equipment layer 11 communicate
Connection, the local data acquisition layer 12 is for the original waveform data of acquisition motor in real time and saves to local data base, this
Ground processor analyzes original waveform data by local computer failure omen diagnosis algorithm, in conjunction in local data base
Original data carry out primary fault to motor operating state and sentence knowledge to obtain diagnosis report.It is appreciated that the diagnosis report
In include is the electrical fault omen warning information being had determined by local computer failure omen diagnosis algorithm, and/or
The corresponding fault signature data of failure omen warning information.Know in addition, the local data acquisition layer 12 sentences primary fault
To primary features data and failure omen warning information and original waveform data be transmitted to plant area's cloud data center's layer 13
It is further analyzed.Specifically, the local data acquisition layer 12 carries out preliminary screening to original waveform data, when passing through
The analysis of characteristic of field value, historical data trend analysis and historical data compare analysis and sentence to motor operating state progress primary fault
Know, the analysis of temporal signatures value specifically includes the temporal signatures values such as virtual value, amplitude, peak value, the form factor for extracting signal, goes forward side by side
Row real-time monitoring judges motor status exception when being more than the threshold values of setting；Historical data trend analysis includes to motor characteristic
Value Data carries out trending analysis, when data variation trend is more than the threshold values of setting, judges motor status exception.It can manage
Solution, the primary features data that the local data acquisition layer 12 uploads are temporal signatures Value Data.It is appreciated that the local
After data collection layer 12 sentences knowledge to motor operating state completion primary fault, to the database and knowledge base of local computer
It is updated, include in knowledge base is the electrical fault omen determined based on local computer failure omen diagnosis algorithm
The corresponding temporal signatures Value Data of warning information.Local computer failure omen diagnosis algorithm follows and would rather make a false report, can not fail to report
Principle carry out fault pre-alarming, fault diagnosis threshold value is relatively large, sentences and knows accuracy rate and tell somebody what one's real intentions are, therefore original waveform data is uploaded
Higher level-one analysis is carried out to plant area's cloud data center's layer 13, sentences knowledge accuracy rate to improve.
Plant area cloud data center's layer 13 and local data acquisition layer 12 pass through plant area's LAN connection, the local
The native processor of data collection layer 12 is uploaded by plant area's local area network to the server of plant area's cloud data center's layer 13 primary
Characteristic, original waveform data and failure omen warning information, plant area cloud data center's layer 13 are serviced by plant area
Device failure omen diagnosis algorithm analyzes original waveform data, thus to motor operating state carry out intermediate failure sentence knowledge with
Obtain diagnosis report.It is appreciated that include in the diagnosis report be by plant area's server failure omen diagnosis algorithm
Through determining electrical fault omen warning information and/or the corresponding fault signature data of failure omen warning information.It can manage
Solution, after plant area cloud data center's layer 13 sentences knowledge to the intermediate failure of motor operating state completion, to the number of plant area's server
It is updated according to library and knowledge base, include in the knowledge base is calculated based on the diagnosis of plant area's server failure omen
The corresponding fault signature data of electrical fault omen warning information that method determines.It is appreciated that plant area's server failure omen is examined
Disconnected algorithm not only includes local computer failure omen diagnosis algorithm, i.e., comprising the analysis of temporal signatures value, historical data trend point
Analysis and historical data compare analysis, and also pass through the technologies pair such as fast Fourier analysis, frequency analysis, spectral trendsization analysis
Received suspicious Wave data is further analyzed, to complete to sentence knowledge to the intermediate failure of motor operating state.Wherein, quickly
Fourier analysis, which is specifically included, carries out Fast Fourier Transform (FFT) to signal, then extracts electrical fault feature letter by spectrum analysis
Number；Frequency analysis specifically include to stator current signal carry out frequency analysis, by detection electric current in harmonic components, amplitude,
And its variation tendency, failure omen is carried out to motor and sentences knowledge；Spectral trendsization analysis is specifically included is extracted instead by spectrum analysis
The characteristic frequency ingredient of motor operating state is answered, and trending analysis is carried out to it, when spectral change trend is more than the threshold of setting
When value, motor abnormality is determined.It is appreciated that plant area cloud data center's layer 13 is also by mid-level features data, suspicious waveform
Data and failure omen warning information are uploaded to region cloud data center's layer 14 and are further analyzed, wherein described
Mid-level features data refer to that plant area cloud data center's layer 13 is become by fast Fourier analysis, frequency analysis, frequency spectrum
Harmonic components and amplitude, characteristic frequency in the characteristic that gesture is analyzed, such as electrical fault characteristic signal, electric current etc.
Data, the suspicious Wave data that plant area cloud data center's layer 13 uploads refers to be diagnosed by plant area's server failure omen
Algorithm can not accurately determine the Wave data of electrical fault omen warning information, what plant area cloud data center's layer 13 uploaded
Failure omen warning information includes that plant area cloud data center's layer 13 itself is calculated by the diagnosis of plant area's server failure omen
The failure omen warning information that method determines can also include the failure omen warning information that local data acquisition layer 12 uploads.It can
The historical data of all motor devices of plant area and the fault signature data of most common failure are stored to understand, in plant area's server, are led to
Comparing is crossed, intermediate failure is carried out to motor operating state data and sentences knowledge.The data volume of plant area's server compares local data base
In data volume will it is more, parser is also more advanced, and therefore, the failure of plant area cloud data center's layer 13 sentences knowledge ability ratio
Local data acquisition layer 12 is stronger, and it is higher to sentence knowledge accuracy rate.
In addition, plant area cloud data center's layer 13 issues failure omen warning information by Web server, arbitrarily award
The plant area user of power accesses Web service address by browser, can inquire the real-time running state data and event of motor device
Hinder omen and diagnoses warning information.For example, local data acquisition layer 12 requests diagnostic service, factory to plant area's cloud data center's layer 13
The data that area cloud data center's layer 13 uploads local data acquisition layer 12 are analyzed, if plant area's cloud data center's layer
13 it can be concluded that accurate diagnosis, plant area's cloud data center's layer 13 can will reach local data acquisition under diagnostic message
Layer 12 can pass through the Web for accessing plant area cloud data center's layer 13 with its Web server, local data acquisition layer 12 is uploaded to
Server checks diagnostic message；If plant area's cloud data center's layer 13 can not obtain accurate diagnosis, again by data
The secondary region cloud data center's layer 14 that is uploaded to is analyzed.
Region cloud data center's layer 14 is connect with plant area cloud data center's layer 13 by Internet network, institute
The server of plant area's cloud data center's layer 13 is stated by the original waveform data of the motor of all monitorings of on-site, suspicious waveform number
According to and failure omen warning information be uploaded to the server of region cloud data center's layer 14.Region cloud data center's layer
14 analyze suspicious Wave data based on region server failure omen diagnosis algorithm, to complete motor operating state
It is middle-and-high-ranking to sentence knowledge to generate diagnosis report.It is appreciated that include in the diagnosis report is by before region server failure
The corresponding failure of the electrical fault omen warning information and/or the failure omen warning information that million diagnosis algorithms have determined is special
Levy data.Specifically, the server of region cloud data center's layer 14 is not only integrated with plant area's server failure omen and examines
Disconnected algorithm, is also integrated with more advanced algorithm, filters especially by digital signal pre-treatment, signal, wavelet threshold denoising etc. is calculated
Method improves Signal-to-Noise, then passes through fast Fourier analysis, frequency analysis, cepstrum analysis, power spectrumanalysis, waterfall
The advanced analysis algorithms such as map analysis, resonance and demodulation analysis, wavelet analysis carry out data analysis.Data pre-processing, which specifically includes, to be passed through
It goes DC terms, the technologies such as nonlinear trend item is gone to eliminate sensor drift and measurement interference, digital signal filter and small echo
The technologies such as threshold denoising can eliminate low frequency or high-frequency interferencing signal and noise signal, improve the signal-to-noise ratio of signal.Relative to
Plant area's server failure omen diagnosis algorithm, region server failure omen diagnosis algorithm are also integrated with resonance and demodulation and analyze, is small
The advanced analysis algorithm such as wave analysis has better effect for extracting faint fault-signal, and increases cepstrum, power
The maps such as spectrum, Waterfall plot, carry out multi-faceted diagnostic analysis, and diagnostic analysis result is more acurrate.Region cloud data center's layer
14 database has historical data base abundant and fault signature database, and High Fault omen diagnostic analysis is combined to calculate
There is method stronger failure to sentence knowledge ability.The failure omen accuracy rate of diagnosis of region cloud data center's layer 14 is higher, leads to
Equipment O&M can be instructed in normal situation.In addition, region cloud data center's layer 14 is also by middle-and-high-ranking characteristic, suspicious
Wave data and failure omen warning information are uploaded to central cloud data center's layer 15 and are further analyzed, wherein
The middle-and-high-ranking characteristic refers to through region server failure omen diagnosis algorithm in plant area's cloud data center's layer 13
The characteristic obtained after the suspicious Wave data analysis passed, such as the data analyzed by resonance and demodulation, pass through small echo
Obtained data etc. are analyzed, the suspicious Wave data that region cloud data center's layer 14 uploads refers to through region server failure
The suspicious Wave data that omen diagnosis algorithm uploads plant area's cloud data center's layer 13 is analyzed and can not accurately determine electricity
The Wave data of machine failure omen warning information, the failure omen warning information packet that region cloud data center's layer 14 uploads
It is pre- to include the failure omen that region cloud data center's layer 14 itself is determined by region server failure omen diagnosis algorithm
Alert information can also include the failure omen warning information that plant area cloud data center's layer 13 uploads.It is appreciated that the region
After cloud data center's layer 14 sentences knowledge to the middle-and-high-ranking failure of motor operating state completion, database and knowledge base are carried out more
Newly, include in knowledge base is the electrical fault omen early warning letter determined based on region server failure omen diagnosis algorithm
Cease corresponding middle-and-high-ranking characteristic data value.
In addition, region cloud data center's layer 14 also issues failure omen warning information by Web server, arbitrarily
The zone user of authorization can access Web service address by browser, inquire the real-time running state data and event of motor device
Hinder omen and diagnoses warning information.For example, plant area's cloud data center's layer 13 requests diagnosis to take to region cloud data center's layer 14
Business, the data that region cloud data center's layer 14 uploads plant area's cloud data center's layer 13 are analyzed, if region cloud
Data center's layer 14 is it can be concluded that accurate diagnosis, region cloud data center's layer 14 can will reach factory under diagnostic message
Area cloud data center's layer 13 and it is uploaded to its Web server, plant area's cloud data center's layer 13 can pass through access region cloud
The Web server of end data central core 14 checks diagnostic message；If region cloud data center's layer 14 can not obtain accurately
Data are then uploaded to central cloud data center's layer 15 again and analyzed by diagnosis.
Center cloud data center's layer 15 is connect by Internet network with region cloud data center's layer 14, institute
The server for stating region cloud data center's layer 14 passes through Internet network for the original of the motor device of monitorings all in region
Beginning Wave data, suspicious Wave data and failure omen warning information are uploaded to the server of central cloud data center's layer 15.
Center cloud data center's layer 15 analyzes suspicious Wave data based on central server failure omen diagnosis algorithm,
Knowledge is sentenced to complete the High Fault of motor operating state.After completing High Fault and sentencing knowledge, the center cloud data center
The database and knowledge base of 15 pairs of layer itself are updated.It is appreciated that the central server failure omen diagnosis is calculated
Method is roughly the same with region server failure omen diagnosis algorithm, but the database of central cloud data center's layer 15 is than region cloud
The database of end data central core 14 is more complete, even if by identical diagnosis algorithm, center cloud data center's layer
15 diagnostic result is also more more acurrate than region cloud data center's layer 14.Also, center cloud data center's layer 15 is also wrapped
A personal-machine interactive module 151 is included, the human-computer interaction module 151 is used to carry out sentencing knowledge for expert's intervention, for only a few area
Domain cloud data center's layer 14 can not accurately sentence the suspicious Wave data of knowledge, can carry out sentencing knowledge by expert's intervention, to mention
Height sentences knowledge accuracy.
In addition, center cloud data center's layer 15 also issues failure omen warning information by Web server, arbitrarily
The central user of authorization can access Web service address by browser, inquire the real-time running state data and event of motor device
Hinder omen and diagnoses warning information.For example, region cloud data center's layer 14 requests diagnosis to take to central cloud data center's layer 15
Business, the data that central cloud data center's layer 15 uploads region cloud data center's layer 14 are analyzed, central cloud data
Central core 15 obtains accurate diagnosis, and central cloud data center's layer 15 can will reach region cloud number under diagnostic message
According to central core 14 and it is uploaded to its Web server, region cloud data center's layer 14 can be by accessing in the data of central cloud
The Web server of central layer 15 checks diagnostic message.
It is appreciated that being used as a kind of selection, the data acquisition equipment layer 11 and plant area's cloud data center's layer 13 are distinguished
It is connect with mobile terminal, user can use mobile terminal and carry out motor Daily Round Check, and the APP on mobile terminal can be from data
It acquires mechanical floor 11 and obtains motor operating state data, check motor operating state, and motor operating state data can be passed
Plant area's cloud data center's layer 13 is transported to, in addition, user can also be accessed in the data of plant area cloud by the APP on mobile terminal
The server of the server of central layer 13, the server of region cloud data center's layer 14 and central cloud data center's layer 15, is looked into
Electrical fault omen diagnostic result is seen, to realize transfer point inspection and diagnosis inquiry.
Motor on-line monitoring and failure omen diagnostic system based on multi-layer framework of the invention, by constructing multilevel diagnostic
Service layer, by hierarchical screening, step-by-step analysis diagnose in the way of to motor operating state carry out failure omen sentence knowledge, with framework
The continuous raising of level, used diagnosis algorithm is also more advanced, and diagnostic result accuracy rate is higher, and in view of local number
The diagnosis algorithm used according to acquisition layer 12 is relatively simple, and primary fault identifying result accuracy rate may tell somebody what one's real intentions are, therefore in local number
Original waveform data is uploaded according between acquisition layer 12 and plant area's cloud data center's layer 13, utilizes plant area's cloud data center's layer
More advanced algorithm carries out analyzing and diagnosing to original waveform data again in 13, improves diagnosis and sentences the accuracy rate of knowledge, and is
Raising diagnosis efficiency, the suspicious Wave data that region cloud data center's layer 14 only uploads plant area's cloud data center's layer 13
It is analyzed, the suspicious Wave data that central cloud data center's layer 15 only uploads region cloud data center's layer 14 divides
Analysis, while ensuring accuracy rate of diagnosis, is greatly improved diagnosis efficiency.Also, user can also comprehensively consider diagnosis effect
Rate and accuracy rate of diagnosis select suitable diagnosis framework to carry out electrical fault omen diagnostic analysis, and applicability is stronger.
It is appreciated that as shown in Fig. 2, another embodiment of the present invention also to provide a kind of motor based on multi-layer framework online
Monitoring and failure omen diagnostic method, it is described to be based on using motor as described above on-line monitoring and failure omen diagnostic system
Multi-layer framework motor on-line monitoring with failure omen diagnostic method the following steps are included:
Step S1: the original waveform data of motor is acquired by data acquisition equipment layer；
Step S2: the original waveform data of motor is obtained using local data acquisition layer and motor operating state is carried out just
Grade failure sentences knowledges, and original waveform data and primary fault are sentenced primary features data that knowledge obtains, in failure omen warning information
Reach plant area's cloud data center's layer；
Step S3: intermediate failure is carried out to motor operating state using plant area's cloud data center's layer and sentences knowledge, and will be suspicious
Wave data and intermediate failure are sentenced mid-level features data, the failure omen warning information known and obtained and are uploaded in the data of region cloud
Central layer；
Step S4: the suspicious Wave data uploaded using region cloud data center's layer based on plant area's cloud data center's layer
Middle-and-high-ranking failure is carried out to motor operating state and sentences knowledges, and he suspicious Wave data and middle-and-high-ranking failure is sentenced know obtain it is middle-and-high-ranking
Characteristic, failure omen warning information are uploaded to central cloud data center's layer；
Step S5: the suspicious Wave data uploaded using central cloud data center's layer based on region cloud data center's layer
High Fault is carried out to motor operating state and sentences knowledge.
Motor on-line monitoring and failure omen diagnostic method based on multi-layer framework of the invention, by constructing multilevel diagnostic
Service layer, by hierarchical screening, step-by-step analysis diagnose in the way of to motor operating state carry out failure omen sentence knowledge, with framework
The continuous raising of level, used diagnosis algorithm is also more advanced, and diagnostic result accuracy rate is higher, and in view of local number
The diagnosis algorithm used according to acquisition layer is relatively simple, and primary fault identifying result accuracy rate may tell somebody what one's real intentions are, therefore in local data
Upload original waveform data between acquisition layer and plant area's cloud data center's layer, using in plant area's cloud data center's layer more
Advanced algorithm carries out analyzing and diagnosing to original waveform data again, improves diagnosis and sentences the accuracy rate of knowledge, and examines to improve
Disconnected efficiency, the suspicious Wave data that region cloud data center's layer only uploads plant area's cloud data center's layer are analyzed, in
The suspicious Wave data that centre cloud data center's layer only uploads region cloud data center's layer is analyzed, quasi- ensuring to diagnose
While true rate, diagnosis efficiency is greatly improved.Also, user can also comprehensively consider diagnosis efficiency and accuracy rate of diagnosis,
Selection is suitable to diagnose framework to carry out electrical fault omen diagnostic analysis, and applicability is stronger.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of motor on-line monitoring and failure omen diagnostic system based on multi-layer framework, which is characterized in that
Including data acquisition equipment layer (11), local data acquisition layer (12), plant area's cloud data center's layer (13), region cloud
Data center's layer (14) and central cloud data center's layer (15), the local data acquisition layer (12) set with data acquisition respectively
Standby layer (11) and plant area's cloud data center's layer (13) connection, region cloud data center's layer (14) respectively with plant area cloud
Data center's layer (13) and central cloud data center's layer (15) connect；
The data acquisition equipment layer (11) is used to acquire the original waveform data of motor；
The local data acquisition layer (12) is used to obtain the original waveform data of motor and carries out to motor operating state primary
Failure sentences knowledge, and original waveform data and primary fault are sentenced and know obtained primary features data, failure omen warning information uploads
To plant area's cloud data center's layer (13)；
The intermediate failure that plant area cloud data center's layer (13) is used to carry out motor operating state sentences knowledge, and by suspicious waveform
Data and intermediate failure sentence mid-level features data, the failure omen warning information known and obtained and are uploaded to region cloud data center's layer
(14)；
Region cloud data center's layer (14) is used for the suspicious waveform number uploaded based on plant area cloud data center's layer (13)
Knowledge is sentenced according to the middle-and-high-ranking failure for carrying out motor operating state, and suspicious Wave data and middle-and-high-ranking failure are sentenced to the middle height known and obtained
Grade characteristic, failure omen warning information are uploaded to central cloud data center's layer (15)；
The suspicious waveform number that the center cloud data center's layer (15) is used to upload based on region cloud data center's layer (14)
Knowledge is sentenced according to the High Fault for carrying out motor operating state.
2. motor on-line monitoring as described in claim 1 and failure omen diagnostic system, which is characterized in that
The local data acquisition layer (12) is compared by the analysis of temporal signatures value, historical data trend analysis and historical data
Analysis carries out primary fault to motor operating state and sentences knowledge.
3. motor on-line monitoring as described in claim 1 and failure omen diagnostic system, which is characterized in that
Plant area cloud data center's layer (13) is carried out by fast Fourier analysis, frequency analysis and spectral trendsization analysis
The intermediate failure of motor operating state sentences knowledge.
4. motor on-line monitoring as described in claim 1 and failure omen diagnostic system, which is characterized in that
Region cloud data center's layer (14) first improves the signal-to-noise ratio of signal, then is transported by multi-faceted diagnostic analysis to motor
Row state carries out middle-and-high-ranking failure and sentences knowledge.
5. motor on-line monitoring as claimed in claim 4 and failure omen diagnostic system, which is characterized in that
Region cloud data center's layer (14) is mentioned by digital signal pre-treatment, digital signal filter and wavelet threshold denoising
The signal-to-noise ratio of high RST.
6. motor on-line monitoring as claimed in claim 5 and failure omen diagnostic system, which is characterized in that
The digital signal pre-treatment is interfered by going DC terms, nonlinear trend item being gone to eliminate sensor drift and measure,
The digital signal filter and wavelet threshold denoising are for eliminating low frequency or high-frequency interferencing signal and noise signal.
7. motor on-line monitoring as claimed in claim 4 and failure omen diagnostic system, which is characterized in that
Region cloud data center's layer (14) passes through fast Fourier analysis, frequency analysis, cepstrum analysis, power spectrum point
Analysis, waterfall map analysis, resonance and demodulation analysis and the multi-faceted diagnostic analysis of wavelet analysis realization.
8. motor on-line monitoring as described in claim 1 and failure omen diagnostic system, which is characterized in that
The center cloud data center's layer (15) includes the human-computer interaction module (151) for sentence for expert's intervention knowledge.
9. motor on-line monitoring as described in claim 1 and failure omen diagnostic system, which is characterized in that
Plant area cloud data center's layer (13), region cloud data center's layer (14) and central cloud data center's layer (15)
It is also used to issue failure omen warning information by Web server.
10. a kind of motor on-line monitoring and failure omen diagnostic method based on multi-layer framework, any using such as claim 1-9
Motor on-line monitoring and failure omen diagnostic system described in, which is characterized in that
The following steps are included:
Step S1: the original waveform data of motor is acquired by data acquisition equipment layer；
Step S2: the original waveform data of motor is obtained using local data acquisition layer and primary event is carried out to motor operating state
Barrier sentences knowledge, and original waveform data and primary fault are sentenced primary features data, the failure omen warning information known and obtained and are uploaded to
Plant area's cloud data center's layer；
Step S3: carrying out intermediate failure to motor operating state using plant area's cloud data center's layer and sentence knowledge, and by suspicious waveform
Data and intermediate failure sentence mid-level features data, the failure omen warning information known and obtained and are uploaded to region cloud data center
Layer；
Step S4: the suspicious Wave data uploaded using region cloud data center's layer based on plant area's cloud data center's layer is to electricity
Machine operating status carries out middle-and-high-ranking failure and sentences knowledge, and suspicious Wave data and middle-and-high-ranking failure are sentenced to the middle-and-high-ranking feature known and obtained
Data, failure omen warning information are uploaded to central cloud data center's layer；
Step S5: the suspicious Wave data uploaded using central cloud data center's layer based on region cloud data center's layer is to electricity
Machine operating status carries out High Fault and sentences knowledge.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910395820.8A CN110133500B (en) | 2019-05-13 | 2019-05-13 | Motor online monitoring and fault precursor diagnosis system and method based on multi-layer architecture |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910395820.8A CN110133500B (en) | 2019-05-13 | 2019-05-13 | Motor online monitoring and fault precursor diagnosis system and method based on multi-layer architecture |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110133500A true CN110133500A (en) | 2019-08-16 |
| CN110133500B CN110133500B (en) | 2021-08-20 |
Family
ID=67573767
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910395820.8A Active CN110133500B (en) | 2019-05-13 | 2019-05-13 | Motor online monitoring and fault precursor diagnosis system and method based on multi-layer architecture |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110133500B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110597144A (en) * | 2019-09-30 | 2019-12-20 | 鞍钢集团自动化有限公司 | Motor sensor data acquisition unit and data acquisition method |
| CN110597145A (en) * | 2019-09-30 | 2019-12-20 | 鞍钢集团自动化有限公司 | Full life cycle management data acquisition system of electrical equipment |
| CN111444169A (en) * | 2020-03-30 | 2020-07-24 | 国网江苏省电力有限公司连云港市赣榆区供电分公司 | Transformer substation electrical equipment state monitoring and diagnosis system and method |
| CN112763908A (en) * | 2020-12-25 | 2021-05-07 | 中国机械设备工程股份有限公司 | Motor health index evaluation system based on multi-fault feature combination |
| CN114647234A (en) * | 2022-05-23 | 2022-06-21 | 医链数科医疗科技(江苏)有限公司 | Medical equipment monitoring method and device based on Internet of things and storage medium |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103161681B (en) * | 2011-12-13 | 2016-10-05 | 湘潭大学 | A kind of wind power generating set based on multilevel diagnostic safeguards system |
| CN102730571B (en) * | 2012-06-01 | 2014-10-29 | 华中科技大学 | Online monitoring and fault diagnosing system for crane |
| CN102840101A (en) * | 2012-09-13 | 2012-12-26 | 成都阜特科技股份有限公司 | Distributed condition monitoring system |
| CN203552245U (en) * | 2013-07-18 | 2014-04-16 | 国家电网公司 | Online monitoring system for energy efficiency of fan and water pump |
| CN103746829B (en) * | 2013-12-20 | 2017-04-05 | 中国科学院计算技术研究所 | A kind of failure sensory perceptual system and its method based on cluster |
| CN107884679B (en) * | 2017-10-27 | 2019-11-19 | 山东理工大学 | Small current Earth design method based on transient zero-sequence current signal characteristic |
| CN109585013A (en) * | 2018-11-30 | 2019-04-05 | 武汉兰丁医学高科技有限公司 | A kind of distributed medical diagnostic analysis method and system |
-
2019
- 2019-05-13 CN CN201910395820.8A patent/CN110133500B/en active Active
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110597144A (en) * | 2019-09-30 | 2019-12-20 | 鞍钢集团自动化有限公司 | Motor sensor data acquisition unit and data acquisition method |
| CN110597145A (en) * | 2019-09-30 | 2019-12-20 | 鞍钢集团自动化有限公司 | Full life cycle management data acquisition system of electrical equipment |
| CN111444169A (en) * | 2020-03-30 | 2020-07-24 | 国网江苏省电力有限公司连云港市赣榆区供电分公司 | Transformer substation electrical equipment state monitoring and diagnosis system and method |
| CN112763908A (en) * | 2020-12-25 | 2021-05-07 | 中国机械设备工程股份有限公司 | Motor health index evaluation system based on multi-fault feature combination |
| CN112763908B (en) * | 2020-12-25 | 2023-09-12 | 中国机械设备工程股份有限公司 | Motor health index evaluation system based on multi-fault feature combination |
| CN114647234A (en) * | 2022-05-23 | 2022-06-21 | 医链数科医疗科技(江苏)有限公司 | Medical equipment monitoring method and device based on Internet of things and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110133500B (en) | 2021-08-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110133500A (en) | Motor on-line monitoring and failure omen diagnostic system and method based on multi-layer framework | |
| Helmi et al. | Rolling bearing fault detection of electric motor using time domain and frequency domain features extraction and ANFIS | |
| Sadoughi et al. | Physics-based convolutional neural network for fault diagnosis of rolling element bearings | |
| Zhao et al. | Fault diagnosis of wind turbine bearing based on variational mode decomposition and Teager energy operator | |
| CN105424395B (en) | Method and device for determining equipment fault | |
| CN106769052B (en) | A kind of mechanical system rolling bearing intelligent failure diagnosis method based on clustering | |
| CN106006344B (en) | Staircase On-line Fault early warning system and method for diagnosing faults | |
| Su et al. | Induction machine condition monitoring using neural network modeling | |
| Lee et al. | New fault diagnosis of circuit breakers | |
| Wang et al. | Fault diagnosis and health assessment for bearings using the Mahalanobis–Taguchi system based on EMD-SVD | |
| CN105626502B (en) | Plunger pump health evaluating method based on wavelet packet and laplacian eigenmaps | |
| KR101625087B1 (en) | A electrical equipment fault diagnostic apparatus according to harmonic analysis | |
| Gougam et al. | Bearing faults classification under various operation modes using time domain features, singular value decomposition, and fuzzy logic system | |
| CN103616187A (en) | Fault diagnosis method based on multi-dimension information fusion | |
| CN110008350A (en) | A kind of pump Ankang knowledge base lookup method based on Bayesian inference | |
| Amezquita-Sanchez et al. | Fractal dimension-based approach for detection of multiple combined faults on induction motors | |
| CN107473036A (en) | Elevator traction machine remote online detects and diagnostic system and its checkout and diagnosis method | |
| Li et al. | Fuzzy determination of informative frequency band for bearing fault detection | |
| CN110398647A (en) | Transformer state monitoring method | |
| Qin et al. | Remaining useful life prediction for rotating machinery based on optimal degradation indicator | |
| Abolghasemi et al. | Recursive singular spectrum analysis for induction machines unbalanced rotor fault diagnosis | |
| Liu et al. | A Rolling Bearing Fault Diagnosis‐Optimized Scale‐Space Representation for the Empirical Wavelet Transform | |
| Ambika et al. | Vibration signal based condition monitoring of mechanical equipment with scattering transform | |
| Wang et al. | Rotating machine fault detection based on HOS and artificial neural networks | |
| Lopez-Gutierrez et al. | Induction machine bearing fault detection using empirical wavelet transform |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200715 Address after: 100055 Guang'an Menwai Street 178, Xicheng District, Beijing Applicant after: CHINA MACHINERY ENGINEERING Corp. Applicant after: CHINA MACHINERY INTERNATIONAL ENGINEERING DESIGN & RESEARCH INSTITUTE Co.,Ltd. Address before: 410007, No. 18 middle Shaoshan Road, Yuhua District, Hunan, Changsha Applicant before: CHINA MACHINERY INTERNATIONAL ENGINEERING DESIGN & RESEARCH INSTITUTE Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |