CN110377001A - Industrial equipment intelligent Fault Diagnose Systems and method based on data fusion - Google Patents
Industrial equipment intelligent Fault Diagnose Systems and method based on data fusion Download PDFInfo
- Publication number
- CN110377001A CN110377001A CN201910481502.3A CN201910481502A CN110377001A CN 110377001 A CN110377001 A CN 110377001A CN 201910481502 A CN201910481502 A CN 201910481502A CN 110377001 A CN110377001 A CN 110377001A
- Authority
- CN
- China
- Prior art keywords
- industrial equipment
- diagnosis
- fuzzy
- failure
- equipment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0224—Process history based detection method, e.g. whereby history implies the availability of large amounts of data
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24065—Real time diagnostics
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of industrial equipment intelligent Fault Diagnose Systems and method based on data fusion, wherein in fault diagnosis system, factory's client is used to obtain and show the equipment account information of the industrial equipment of equipment account database purchase, and factory's client, which is used to obtain, patrols patrolling for inspection task standard database storage and examine a mission bit stream；Point inspection equipments are patrolled in industry and on-line monitoring equipment is used to be acquired the different types of operating parameter of industrial equipment, collected operating parameter is sent in device history data library, fuzzy diagnosis logical data base is used to carry out pattern-recognition according to the fuzzy diagnosis rule combination fuzzy relation matrix based on subordinating degree function, obtains the confidence level of failure cause.According to the technical solution of the present invention, the failure menace level of each component of industrial equipment is provided in time, and then the health status of unit is assessed, to give industrial equipment operation and maintenance suggestion.
Description
Technical field
The present invention relates to fault diagnosis technology field more particularly to a kind of industrial equipment intelligent troubles based on data fusion
Diagnostic system and a kind of industrial equipment intelligent failure diagnosis method based on data fusion.
Background technique
Gas turbine generator have the advantages that it is compact-sized, run smoothly, securely and reliably, quick start on-load, be one
The novel power-equipment of kind, the important role played in modern industrial production.Gas turbine is as gas turbine generator set
Power-equipment, influenced easily to exist by many factors such as harsh environments, peak regulation needs, service wears in the process of running
Potential faults.Gas turbine fault diagnosis architecture is improved, the fault diagnosis of gas turbine is carried out in time, is conducive to exclude hidden
Suffer from, reduce accident rate, improve safety, is unit safety operation, increasing economic efficiency provides theoretical foundation.Therefore, it fires
The research of gas-turbine method for diagnosing faults to reliability service, safety guarantee, prolongs the service life, the side such as scientific management and maintenance
The work in face has very strong practical significance.
Data fusion is to analyze the observation information from multiple sensors or multi-source using computer technology, integrate
Processing, to obtain decision and estimate the treatment process of the information of required by task.Data fusion center is to from multiple sensors
Information merged, can also by the observational facts of information and man-machine interface from multiple sensors carry out information fusion
(this fusion is usually decision level fusion), extracts prognostic information, under inference machine effect, by the knowledge in sign and knowledge base
Matching, makes Fault Tree Diagnosis Decision, is supplied to user.Self study can be added in the fault diagnosis system merged based on information
Module, failure decision feeds back to knowledge base through self-learning module, and modifies to corresponding confidence factor, more new knowledge
Library.Meanwhile self-learning module can according in knowledge base knowledge and user the dynamic response that system is putd question to is made inferences, to obtain
New knowledge is obtained, summarizes new experience, constantly expand knowledge library, realizes the self-learning function of expert system.
Summary of the invention
At least one of regarding to the issue above, the industrial equipment intelligence event based on data fusion that the present invention provides a kind of
Hinder diagnostic system and method, the operating standard based on Gas Generator Set, and combines online monitoring data, the real-time SIS data of production, point
It examines data and accurate diagnosis off-line data carries out data fusion, using the judgment threshold of fault signature and based on subordinating degree function
Fuzzy diagnosis rule provides the failure menace level of each component of industrial equipment in time, and then carries out to the health status of unit
Assessment, to give industrial equipment operation and maintenance suggestion.
To achieve the above object, the present invention provides a kind of industrial equipment intelligent trouble diagnosis system based on data fusion
System, comprising: point inspection equipments, on-line monitoring equipment, accurate diagnosis model database, device history data library, factory visitor are patrolled in industry
Family end, data fusion model and fuzzy diagnosis logical data base；Factory's client is for obtaining and showing equipment account number
According to the equipment account information of the industrial equipment of library storage, factory's client patrols an inspection task normal data for obtaining
An inspection mission bit stream is patrolled in library storage, and the inspection mission bit stream that patrols is sent to patrol officer to patrol a little using the industry
Inspection equipment carries out the industrial equipment to patrol an inspection；Point inspection equipments are patrolled in the industry and the on-line monitoring equipment is used to work
The different types of operating parameter of industry equipment is acquired, and the industry patrols point inspection equipments for industrial equipment described in collection in worksite
Operating parameter, the on-line monitoring equipment is for online or obtain the operating parameter of the industrial equipment offline, the industry
It patrols point inspection equipments and the collected operating parameter of the on-line monitoring equipment is sent in the device history data library, the essence
Close diagnostic model database is used to acquire and store the accurate diagnosis data of the industrial equipment；The data fusion model obtains
The operating parameter of the industrial equipment stored in the device history data library carries out the operating parameter of the industrial equipment
Data fusion, to extract the breakdown judge data of typical fault mode character pair；The fuzzy diagnosis logical data base is used for
The fuzzy relation matrix of failure cause Yu failure symptom relationship is established according to the breakdown judge data, and according to based on degree of membership
The fuzzy diagnosis rule of function carries out pattern-recognition in conjunction with the fuzzy relation matrix, obtains the confidence level of failure cause, and root
The fault diagnosis result of the industrial equipment is exported according to the confidence level.
In the above-mentioned technical solutions, it is preferable that the industrial equipment intelligent Fault Diagnose Systems based on data fusion further include
Remote terminal and expert's remote diagnosis database, the Remote terminal obtains to be stored in the device history data library
The industrial equipment operating parameter, diagnostic result is sent to expert's remote diagnosis data by the Remote terminal
The diagnostic result is sent to factory's client by library, expert's remote diagnosis database.
In the above-mentioned technical solutions, it is preferable that expert's remote diagnosis database is non-exception in the diagnostic result
When, the diagnostic result is sent to factory's client, when the diagnostic result is abnormal, obtains the accurate diagnosis
The accurate diagnosis Data Concurrent of model database is sent to the Remote terminal.
In the above-mentioned technical solutions, it is preferable that the industrial equipment intelligent Fault Diagnose Systems based on data fusion further include
An inspection task assessment models database is patrolled, the inspection task assessment models database that patrols is for right according to preset assessment rule
It is described to patrol the push period for inspection task of patrolling stored in inspection task standard database and adjusted, it is patrolled to realize to described
The dynamic adjustment of point inspection task, and dynamic adjusted is patrolled into an inspection task and is sent to factory's client, the factory visitor
The dynamic is patrolled an inspection task and is sent to patrol officer to patrol point inspection equipments to the industrial equipment using the industry by family end
It carries out patrolling an inspection.
In the above-mentioned technical solutions, it is preferable that the point inspection equipments that patrol include logging, point inspection instrument, inspection instrument, vibration prison
Instrument, infrared thermal imager, ultrasonic detection equipment, current spectrum instrument, oil liquid ferrograph analyzer, oil liquid laser granulometry is controlled to count
One of instrument, laser tachometer and spot dynamic balance instrument are a variety of；Equipment account letter in the equipment account database
Breath includes industrial equipment type, number of units, model and one of structure and parameter or a variety of.
The present invention also proposes a kind of industrial equipment intelligent failure diagnosis method based on data fusion, comprising: using industry
It patrols point inspection equipments or on-line monitoring equipment acquires the operating parameter of the industrial equipment；To the operating parameter of the industrial equipment into
It is associated with failure symptom that row data fusion to obtain breakdown judge data, according to the breakdown judge data establishes failure cause
Fuzzy relation matrix；The fuzzy diagnosis rule based on subordinating degree function is established according to the feature of the breakdown judge data；With
The fuzzy diagnosis rule is that decision logic carries out pattern-recognition to the fuzzy relation matrix, obtains the credible of failure cause
It spends, and obtains the fault diagnosis result of the industrial equipment according to the confidence level.
In the above-mentioned technical solutions, it is preferable that the industrial equipment intelligent failure diagnosis method based on data fusion further include:
According to the fault diagnosis result in conjunction with the typical fault mode of the industrial equipment, the event of the component of the industrial equipment is determined
Hinder menace level；In conjunction with field practice experience and the failure menace level, the maintenance decision for the component is obtained.
In the above-mentioned technical solutions, it is preferable that the industrial equipment intelligent failure diagnosis method based on data fusion further include:
The fault diagnosis result and the maintenance decision are sent to factory's client.
In the above-mentioned technical solutions, it is preferable that described to establish failure cause fuzzy relation square associated with failure symptom
Battle array specifically includes: establishing failure symptom si(i ∈ (1,2,3, m)), n kind failure cause fj(j∈(1,2,
3, n) fuzzy sign vector), is indicated using S, indicates fuzzy reason vector using F, then
WhereinIndicate failure to the degree of membership of sign,Indicate failure to reason fjDegree of membership, then S and F have fuzzy relation:Wherein R is fuzzy relation matrix,
Wherein, rijIndicate si、fjBetween relationship strength, rijCodomain is [0,1].
In the above-mentioned technical solutions, it is preferable that the form of the Failure Diagnostic Code based on subordinating degree function are as follows: IF E
THEN H (CF, λ), wherein E is the hazy condition that fuzzy proposition indicates, H is the fuzzy conclusion that fuzzy proposition indicates, CF is mould
The confidence factor of rule is pasted, λ is the threshold value of fuzzy rule；
The subordinating degree function includes the subordinating degree function of characteristic frequency:
The subordinating degree function in precession direction:
And the subordinating degree function of direction of vibration:
Wherein, independent variable x is axially or radially to vibrate passband amplitude；A, b, c are real constant, for " direction of vibration is diameter
To " from " direction of vibration be axial " take different values；The meaning of real constant c refers to passband amplitude x greatly to c it is assumed that for the direction
The confidence level of vibration is 100%.
Compared with prior art, the invention has the benefit that the operating standard based on Gas Generator Set, and online prison is combined
Measured data, the real-time SIS data of production, point inspection data and accurate diagnosis off-line data carry out data fusion, utilize fault signature
Judgment threshold and fuzzy diagnosis rule based on subordinating degree function, the failure for providing each component of industrial equipment in time are serious etc.
Grade, and then the health status of unit is assessed, to give industrial equipment operation and maintenance suggestion.
Detailed description of the invention
Fig. 1 is the original of the industrial equipment intelligent Fault Diagnose Systems based on data fusion disclosed in an embodiment of the present invention
Manage schematic diagram；
Fig. 2 is the stream of the industrial equipment intelligent failure diagnosis method based on data fusion disclosed in an embodiment of the present invention
Journey schematic block diagram.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiments of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill people
Member's every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
The present invention is described in further detail with reference to the accompanying drawing:
As depicted in figs. 1 and 2, a kind of industrial equipment intelligent trouble diagnosis based on data fusion provided according to the present invention
System, comprising: point inspection equipments, on-line monitoring equipment, accurate diagnosis model database, device history data library, factory are patrolled in industry
Client, data fusion model and fuzzy diagnosis logical data base；Factory's client is for obtaining and showing equipment account data
The equipment account information of the industrial equipment of library storage, factory's client, which is used to obtain, patrols patrolling for an inspection task standard database storage
Point inspection mission bit stream, and will patrol an inspection mission bit stream be sent to patrol officer with using industry patrol point inspection equipments to industrial equipment into
Row patrols an inspection；Point inspection equipments are patrolled in industry and on-line monitoring equipment is used to carry out the different types of operating parameter of industrial equipment
Operating parameter of the point inspection equipments for collection in worksite industrial equipment is patrolled in acquisition, industry, and on-line monitoring equipment is for online or offline
The operating parameter of industrial equipment is obtained, point inspection equipments are patrolled in industry and the collected operating parameter of on-line monitoring equipment is sent to equipment
In historical data base, accurate diagnosis model database is used to acquire and the accurate diagnosis data of storage industry equipment；Data fusion
Model obtains the operating parameter of the industrial equipment stored in device history data library, carries out data to the operating parameter of industrial equipment
Fusion, to extract the breakdown judge data of typical fault mode character pair；Fuzzy diagnosis logical data base is used for according to failure
Judge that data establish the fuzzy relation matrix of failure cause Yu failure symptom relationship, and is examined according to fuzzy based on subordinating degree function
Disconnected rule combines fuzzy relation matrix to carry out pattern-recognition, obtains the confidence level of failure cause, and export industry according to confidence level
The fault diagnosis result of equipment.
In the above embodiment, it is preferable that the industrial equipment intelligent Fault Diagnose Systems based on data fusion further include remote
Journey expert terminals and expert's remote diagnosis database, Remote terminal obtain the industrial equipment stored in device history data library
Operating parameter, diagnostic result is sent to expert's remote diagnosis database, expert's remote diagnosis database by Remote terminal
Diagnostic result is sent to factory's client.
In the above embodiment, it is preferable that expert's remote diagnosis database ties diagnosis when diagnostic result is non-abnormal
Fruit is sent to factory's client, when diagnostic result is abnormal, obtains the accurate diagnosis data of accurate diagnosis model database simultaneously
It is sent to Remote terminal.
In the above embodiment, it is preferable that the industrial equipment intelligent Fault Diagnose Systems based on data fusion further include patrolling
Point inspection task assessment models database patrols an inspection task assessment models database and is used to be examined according to preset assessment rule to patrolling
The push period for patrolling inspection task stored in task standard database is adjusted, to realize to patrolling a dynamic for inspection task
Adjustment, and dynamic adjusted is patrolled into an inspection task and is sent to factory's client, factory's client will dynamically patrol an inspection task hair
It send to patrol officer and industrial equipment is carried out to patrol an inspection to patrol point inspection equipments using industry.
In the above embodiment, it is preferable that patrol point inspection equipments include logging, point inspection instrument, inspection instrument, vibration monitoring instrument,
Infrared thermal imager, ultrasonic detection equipment, current spectrum instrument, oil liquid ferrograph analyzer, oil liquid laser granulometry calculating instrument, laser
One of tachometer and spot dynamic balance instrument are a variety of；Equipment account information in equipment account database is set including industry
Make preparations for sowing class, number of units, model and one of structure and parameter or a variety of.
According to above-described embodiment propose the industrial equipment intelligent Fault Diagnose Systems based on data fusion, including:
Equipment account database, industrial equipment is static and multidate information for recording, and carries out KKS coding, receive factory its
The calling of his system realizes that account data is shared and uniformly；
An inspection task standard database is patrolled, for establishing and storing each position patrol inspection Standard Task, point inspection Standard Task, essence
It is close point inspection Standard Task, make an inspection tour Standard Task, to grease standard task, rotate at regular intervals and testing standard task, four keep
Point inspection equipments calling is patrolled in technical standards, the receiving such as Standard Task, point inspection estimation standard；
Online detection instrument runs obtained industrial equipment for offline and online acquisition field equipment state data
Parameter state data are sent to industrial equipment historical data base；
Point inspection equipments collection in worksite operating parameter status data is patrolled corresponding to industry for storing in device history data library
As a result, according to from industry patrol the received industrial equipment operating parameter status data of point inspection equipments carry out defect analysis, deterioration analysis,
Task statistics, performance statistics, can also be pushed to factory's other systems by open intermediate database and carry out data sharing；
Expert's remote diagnosis database, for storing the industrial equipment diagnosis knot for corresponding to industrial equipment accurate diagnosis data
Fruit determines corresponding industrial equipment diagnostic result according to from the received industrial equipment accurate diagnosis data of accurate diagnosis equipment, hair
Give plant terminal；Or accurate diagnosis model will be sent to from the received industrial equipment accurate diagnosis data of accurate diagnosis equipment
Database is sent to expert terminals, will be sent to factory's client from the received maintenance information of Remote terminal；
Accurate diagnosis model database, for acquiring and storing the accurate diagnosis data and its maintenance letter of corresponding industrial equipment
Breath obtains corresponding maintenance after receiving the industrial equipment accurate diagnosis data that industrial equipment expert remote diagnosis database is sent
Information is sent to factory's client；
An inspection task assessment models database is patrolled, according to assessment rule, is appointed for adjusting the standard that every is patrolled point inspection equipments
The business push period so that an inspection task is patrolled in dynamic adjustment, and is sent to factory's client；
Factory's client, for according to the industrial equipment account information from equipment account data base call, determination will to be patrolled a little
The industrial equipment of inspection or diagnosis；According to the industrial equipment diagnostic result or maintenance received from industrial equipment remote diagnosis database
Information is supplied to maintenance personnel, refers to industrial equipment diagnostic result, or instruction maintenance personnel according to maintenance information for maintenance personnel
Industrial equipment is safeguarded；Or an inspection task is patrolled from a dynamic for inspection task assessment models database is patrolled according to reception,
Instruction patrols check staff and carries out equipment state acquisition to scene；
Remote terminal, for receiving the industrial equipment diagnostic data of industrial equipment remote diagnosis database transmission, into
After row remote diagnosis, it is maintained information, is sent to factory's client；
Workflow engine defines role, application flow controller realizes factory's operation flow by establishing Work flow model
Control；
Communication interface, industry patrol point inspection equipments by interface routines such as 4G/WIF/USB and patrol an inspection historical data base progress
Data transmission.
The present invention also proposes a kind of industrial equipment intelligent failure diagnosis method based on data fusion, comprising: using industry
Patrol the operating parameter of point inspection equipments or on-line monitoring equipment acquisition industrial equipment；Data are carried out to the operating parameter of industrial equipment to melt
It closes to obtain breakdown judge data, establishes failure cause fuzzy relation square associated with failure symptom according to breakdown judge data
Battle array；The fuzzy diagnosis rule based on subordinating degree function is established according to the feature of breakdown judge data；It is to sentence with fuzzy diagnosis rule
Disconnected logic carries out pattern-recognition to fuzzy relation matrix, obtains the confidence level of failure cause, and show that industry is set according to confidence level
Standby fault diagnosis result.
In the above embodiment, it is preferable that the industrial equipment intelligent failure diagnosis method based on data fusion further include: root
According to the typical fault mode of fault diagnosis result combination industrial equipment, the failure menace level of the component of industrial equipment is determined；Knot
Field practice experience and failure menace level are closed, obtains the maintenance decision for the component.
In the above embodiment, it is preferable that the industrial equipment intelligent failure diagnosis method based on data fusion further include: will
Fault diagnosis result and maintenance decision are sent to factory's client.
In the above embodiment, it is preferable that it is specific to establish failure cause fuzzy relation matrix associated with failure symptom
It include: to establish failure symptom si(i ∈ (1,2,3, m)), n kind failure cause fj(j ∈ (1,2,3, n)),
Fuzzy sign vector is indicated using S, indicates fuzzy reason vector using F, then
WhereinIndicate failure to the degree of membership of sign,Indicate failure to reason fjDegree of membership, then S and F have fuzzy relation:Wherein R is fuzzy relation matrix,
Wherein, rijIndicate si、fjBetween relationship strength, rijCodomain is [0,1].rijBigger, relationship is closer, smaller pass
System is more become estranged；The each element of fuzzy relation matrix a line indicates that the relationship between a certain failure symptom and various failure causes is strong
Degree, each element of a certain column indicate the relationship strength between various failure symptoms and a certain failure cause.rijIt is confirmed that no conjunction
Reason directly affects the accuracy of diagnostic result.
In the above embodiment, it is preferable that the form of the Failure Diagnostic Code based on subordinating degree function are as follows: IF E THEN
H (CF, λ), wherein E is the hazy condition that fuzzy proposition indicates, H is the fuzzy conclusion that fuzzy proposition indicates, CF is fuzzy rule
Confidence factor, λ is the threshold value of fuzzy rule, for pointing out the limitation that can be used of rule.
Specifically, being determined according to the property of parameter itself for rotating machinery vibrating failure diagnosis, such as feature frequency
Rate uses numeric form；Precession direction is boolean value；Axis uses up track, time domain waveform, phase property, stability of vibration are converted to
Other numerical value confirm degree of membership.
Wherein, subordinating degree function includes the subordinating degree function of characteristic frequency, wherein independent variable after characteristic spectra most substantially
Value；K, a, β are real constant, and different values is taken for different characteristic spectras；The meaning of real constant a refers to when characteristic spectra maximum
Amplitude x assert that this feature frequency range 100% is not present when being less than a；
The subordinating degree function in precession direction:
And the subordinating degree function of direction of vibration:
Wherein, independent variable x is axially or radially to vibrate passband amplitude；A, b, c are real constant, for " direction of vibration is diameter
To " from " direction of vibration be axial " take different values；The meaning of real constant c refers to passband amplitude x greatly to c it is assumed that for the direction
The confidence level of vibration is 100%.
Specifically, decision logic are as follows:
Single failure:
IF si THEN fj(rij)
Wherein, siIt is i-th kind of failure symptom；fjIt is jth kind failure cause；riiFor the Rules control factor.
Multiple faults:
IF s1(μs1, ω1j)AND s2(μs2, ω2j)AND … si(μsi, ωij) … AND … sm(μsm, ωmj)
THEN fi(CF, λj), wherein m is to support failure cause fjSign number；siIt is to support fjA sign；μsiIt is sign
Million siDegree of membership, ωijIt is measurement sign siTo failure cause fjThe numerical value of contribution；CF is the confidence level of rule, λjFor rule
The threshold value then set up.
Reason vector can must be obscured in conjunction with above-mentioned diagnostic logicIt is logical
Often use following moving model according to failure symptom: fault diagnosis model forAnd in single event
Barrier and multiple failure symptoms judge that pairing is distinguished when failure carries out following calculating at the confidence level of precondition and rule:
Single failure:
CFSynthesis=CFPrecondition×CFRule
CFSynthesis=min { CFPrecondition, CFRule}
CFSynthesis=min { 0, CFPrecondition+CFRule-1}
The Credibility judgement of same conclusion is supported from a rule:
CF (H)=max { CF1(H), CF2(H) ..., CFn(H)}
CF (H) represents total confidence level of conclusion；N represents the general rule number for supporting conclusion H；CFi(H) it represents according to the i-th rules and regulations
The decision confidence being then calculated.
The diagnostic logic of final mode identification, provides the failure menace level of each component of gas turbine, and then to unit
Health status assessed.
During concrete practice, Jiangsu power plant in 2016, one kind that 2 F grades of gas turbine application this method provide
Since intelligent failure diagnosis method based on data fusion, on-line monitoring, off-line monitoring data, SIS data, DCS number have been got through
According to equal information islands；Equipment fault knowledge base, repair history account, maintenance are established, it is bad to carry out foreseeability to Gas Generator Set equipment
Change analysis and fault diagnosis, timely and effective progress equipment health state evaluation, life appraisal, risk assessment are accurate to formulate maintenance
Period, maintenance mode, repair quality, maintenance rank, overhauling project are optimized, reduce the cost of overhaul, avoided repairing and
It owes to repair, explore scheduled overhaul, periodic inspection.It is standby in spare unit by rising to 98% from original 85% in terms of accuracy rate of diagnosis
The Kucheng of part will control aspect and save more than 50 ten thousand yuan.
Fault mode and shadow are established according to gas turbine group design feature, working principle and fault characteristic by this method
Analytical database is rung, realizes the theoretical basis of gas turbine typical fault mechanism identification.Establish gas turbine group fault mode with
The standardized analysis process of impact analysis, to the potential fault mode of identifying system in each stage, failure cause and its to being
The influence of performance of uniting and unit safety.Data fusion is carried out by Real-time process parameter, offline and online data, is passed through in conjunction with expert
It tests and algorithm model, foundation automatically generates diagnosis based on fuzzy diagnosis logic.By combining expertise and algorithm mould
Type obtains the inputs of the information as BP neural network such as fault signature, each layer setting unit number；Using verifying diagnosis into
Row training, adjusts numerical value, threshold value, until anticipation error carries out self study to reasonable range, to the historical empirical data of equipment.
Maintenance strategy is proposed for the typical fault mode of gas turbine, realizes and status, repair history are run according to electric power factory equipment
Information, maintenance interval facilities, determine the grade of maintenance of equipment, to time between overhauls(TBO), maintenance mode, repair quality, maintenance grade
, overhauling project is not optimized, reduce the cost of overhaul, avoided repairing and owe to repair, explore scheduled overhaul, periodic inspection,
The human relations overhauling system of repair based on condition of component and trouble hunting various ways one.It according to the method for the present invention, can early detection combustion gas wheel
The defect and hidden trouble of equipment of unit reduce standby redundancy consumption, and reduction is non-to stop number, prevents serious accident, improve equipment
Reliability, Optimal Maintenance project and period effectively evade maintenance brought by conservative periodic inspection excessively and set to health
Standby the problem of destroying, utilization rate of equipment and installations can be improved, reduce the cost of overhaul, Scientific evaluation equipment Risk extends gas turbine group
Equipment life.
During being managed to equipment, in order to which traditional section being transitioned into based on pipe based on repairing is studied the science
It reads it is necessary to do based on maintenance not in harmony, supplemented by scheduled overhaul.Using advanced monitoring technology to the operation data of equipment into
Row monitoring analysis, compares device history log and device characteristics, confirms the health status of equipment, then carries out synthesis and comment
Estimate.The decision of maintenance plan is established on the basis of grasping equipment and carrying out technology analysis, preventative inspection is purposefully carried out
It repairs.
These are only the preferred embodiment of the present invention, is not intended to restrict the invention, for those skilled in the art
For member, the invention may be variously modified and varied.All within the spirits and principles of the present invention, it is made it is any modification,
Equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of industrial equipment intelligent Fault Diagnose Systems based on data fusion characterized by comprising industry is patrolled an inspection and set
Standby, on-line monitoring equipment, accurate diagnosis model database, device history data library, factory's client, data fusion model and mould
Paste diagnostic logic database；
Factory's client is used to obtain and show the equipment account letter of the industrial equipment of equipment account database purchase
Breath, factory's client, which is used to obtain, patrols patrolling for inspection task standard database storage and examines a mission bit stream, and patrols described
Point inspection mission bit stream is sent to patrol officer and carries out patrolling an inspection to the industrial equipment to patrol point inspection equipments using the industry；
Point inspection equipments are patrolled in the industry and the on-line monitoring equipment is used to the different types of operating parameter to industrial equipment
It is acquired, operating parameter of the point inspection equipments for industrial equipment described in collection in worksite is patrolled in the industry, and the on-line monitoring is set
It is ready for use on operating parameter that is online or obtaining the industrial equipment offline, point inspection equipments are patrolled in the industry and the on-line monitoring is set
Standby collected operating parameter is sent in the device history data library, and the accurate diagnosis model database is for acquiring simultaneously
Store the accurate diagnosis data of the industrial equipment；
The data fusion model obtains the operating parameter of the industrial equipment stored in the device history data library, to institute
The operating parameter for stating industrial equipment carries out data fusion, to extract the breakdown judge data of typical fault mode character pair；
The fuzzy diagnosis logical data base is used to establish failure cause and failure symptom relationship according to the breakdown judge data
Fuzzy relation matrix, and according to the fuzzy diagnosis rule based on subordinating degree function in conjunction with the fuzzy relation matrix carry out mode
Identification, obtains the confidence level of failure cause, and the fault diagnosis result of the industrial equipment is exported according to the confidence level.
2. the industrial equipment intelligent Fault Diagnose Systems according to claim 1 based on data fusion, which is characterized in that also
Including Remote terminal and expert's remote diagnosis database,
The Remote terminal obtains the operating parameter of the industrial equipment stored in the device history data library, described
Diagnostic result is sent to expert's remote diagnosis database by Remote terminal, and expert's remote diagnosis database is by institute
It states diagnostic result and is sent to factory's client.
3. the industrial equipment intelligent Fault Diagnose Systems according to claim 2 based on data fusion, which is characterized in that institute
Expert's remote diagnosis database is stated when the diagnostic result is non-abnormal, the diagnostic result is sent to the factory client
End, when the diagnostic result is abnormal, the accurate diagnosis Data Concurrent for obtaining the accurate diagnosis model database is sent to institute
State Remote terminal.
4. the industrial equipment intelligent Fault Diagnose Systems according to claim 1 based on data fusion, which is characterized in that also
Including patrolling an inspection task assessment models database, the inspection task assessment models database that patrols is used to be advised according to preset assessment
It then patrols the push period for inspection task of patrolling stored in inspection task standard database to described and adjusts, to realize to institute
The dynamic adjustment for patrolling an inspection task is stated, and dynamic adjusted is patrolled into an inspection task and is sent to factory's client, the work
The dynamic is patrolled an inspection task and is sent to patrol officer to patrol point inspection equipments to the industry using the industry by factory's client
Equipment carries out patrolling an inspection.
5. the industrial equipment intelligent Fault Diagnose Systems according to claim 1 based on data fusion, which is characterized in that institute
Stating and patrolling point inspection equipments includes logging, point inspection instrument, inspection instrument, vibration monitoring instrument, infrared thermal imager, ultrasonic detection equipment, electricity
Flow one in frequency spectrograph, oil liquid ferrograph analyzer, oil liquid laser granulometry calculating instrument, laser tachometer and spot dynamic balance instrument
Kind is a variety of；Equipment account information in the equipment account database include industrial equipment type, number of units, model and structure and
One of parameter is a variety of.
6. a kind of industrial equipment intelligent failure diagnosis method based on data fusion characterized by comprising
Point inspection equipments are patrolled using industry or on-line monitoring equipment acquires the operating parameter of the industrial equipment；
Data fusion is carried out to obtain breakdown judge data, according to the breakdown judge number to the operating parameter of the industrial equipment
According to establishing failure cause fuzzy relation matrix associated with failure symptom；
The fuzzy diagnosis rule based on subordinating degree function is established according to the feature of the breakdown judge data；
Pattern-recognition is carried out to the fuzzy relation matrix using the fuzzy diagnosis rule as decision logic, obtains failure cause
Confidence level, and obtain according to the confidence level fault diagnosis result of the industrial equipment.
7. the industrial equipment intelligent failure diagnosis method according to claim 6 based on data fusion, which is characterized in that also
Include:
According to the fault diagnosis result in conjunction with the typical fault mode of the industrial equipment, the component of the industrial equipment is determined
Failure menace level；
In conjunction with field practice experience and the failure menace level, the maintenance decision for the component is obtained.
8. the industrial equipment intelligent failure diagnosis method according to claim 7 based on data fusion, which is characterized in that also
It include: that the fault diagnosis result and the maintenance decision are sent to factory's client.
9. the industrial equipment intelligent failure diagnosis method according to claim 6 based on data fusion, which is characterized in that institute
It states and establishes failure cause fuzzy relation matrix associated with failure symptom and specifically include:
Establish failure symptom si(i ∈ (1,2,3, m)), n kind failure cause fj(j ∈ (1,2,3, n)),
Fuzzy sign vector is indicated using S, indicates fuzzy reason vector using F, then
WhereinIndicate failure to the degree of membership of sign,Indicate failure to reason fjDegree of membership, then S and F have fuzzy relation:Wherein R is fuzzy relation matrix,
Wherein, rijIndicate si、fjBetween relationship strength, rijCodomain is [0,1].
10. the industrial equipment intelligent failure diagnosis method according to claim 6 based on data fusion, which is characterized in that
The form of the Failure Diagnostic Code based on subordinating degree function are as follows:
IF E THEN H (CF, λ), wherein E is the hazy condition that fuzzy proposition indicates, H is the fuzzy knot that fuzzy proposition indicates
By CF is the confidence factor of fuzzy rule, and λ is the threshold value of fuzzy rule；
The subordinating degree function includes the subordinating degree function of characteristic frequency:
The subordinating degree function in precession direction:
And the subordinating degree function of direction of vibration:
Wherein, independent variable x is axially or radially to vibrate passband amplitude；A, b, c are real constant, for " direction of vibration be radial " with
" direction of vibration is axial " takes different values；The meaning of real constant c refers to passband amplitude x greatly to c it is assumed that vibrating for the direction
Confidence level be 100%.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910481502.3A CN110377001A (en) | 2019-06-04 | 2019-06-04 | Industrial equipment intelligent Fault Diagnose Systems and method based on data fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910481502.3A CN110377001A (en) | 2019-06-04 | 2019-06-04 | Industrial equipment intelligent Fault Diagnose Systems and method based on data fusion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110377001A true CN110377001A (en) | 2019-10-25 |
Family
ID=68249718
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910481502.3A Pending CN110377001A (en) | 2019-06-04 | 2019-06-04 | Industrial equipment intelligent Fault Diagnose Systems and method based on data fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110377001A (en) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110794799A (en) * | 2019-11-28 | 2020-02-14 | 桂林电子科技大学 | Big data system with fault diagnosis function applied to industrial production |
| CN110879586A (en) * | 2019-12-04 | 2020-03-13 | 江苏方天电力技术有限公司 | Phase modulator fault diagnosis and state monitoring method and system |
| CN110906152A (en) * | 2019-12-04 | 2020-03-24 | 江苏方天电力技术有限公司 | An online safety warning system for camera oil system |
| CN111044570A (en) * | 2019-12-28 | 2020-04-21 | 广东电网有限责任公司 | Defect identification and early warning method and device for power equipment and computer equipment |
| CN111061191A (en) * | 2019-12-24 | 2020-04-24 | 泉州装备制造研究所 | A distributed oil and gas storage tank remote operation and maintenance system and method |
| CN111221320A (en) * | 2019-12-27 | 2020-06-02 | 北京航天测控技术有限公司 | Data interpretation method and device, terminal and computer readable medium |
| CN111612337A (en) * | 2020-05-21 | 2020-09-01 | 杭州英集动力科技有限公司 | Automatic issuing method and automatic issuing system for heat supply network scheduling |
| CN111736545A (en) * | 2020-05-20 | 2020-10-02 | 国网河北省电力有限公司电力科学研究院 | System and method for data fusion, error correction and analysis of power unit |
| CN112464565A (en) * | 2020-12-01 | 2021-03-09 | 国网江苏省电力有限公司 | Equipment fault early warning method, system and storage medium integrating intelligent modeling and fuzzy rule |
| CN112731903A (en) * | 2020-11-27 | 2021-04-30 | 成都飞机工业（集团）有限责任公司 | Diagnosis system and method for all-electric transmission flight control fault |
| CN112947177A (en) * | 2021-02-04 | 2021-06-11 | 中国神华能源股份有限公司国华电力分公司 | Equipment point inspection system, method, device and storage medium |
| CN113240140A (en) * | 2021-06-04 | 2021-08-10 | 海尔数字科技(青岛)有限公司 | Fault detection method, device, equipment and storage medium of physical equipment |
| CN113655774A (en) * | 2021-07-21 | 2021-11-16 | 大唐互联科技(武汉)有限公司 | Machine tool remote diagnosis method and system based on industrial internet big data |
| CN113726583A (en) * | 2021-09-24 | 2021-11-30 | 贵州电网有限责任公司 | Remote control unit communication state judgment method based on FSM model |
| CN114154662A (en) * | 2021-12-13 | 2022-03-08 | 龙岩烟草工业有限责任公司 | Fault diagnosis method and device for operating system, computer equipment and storage medium |
| CN114760332A (en) * | 2020-12-29 | 2022-07-15 | 江苏金恒信息科技股份有限公司 | Efficient equipment monitoring and analyzing method |
| CN115469643A (en) * | 2022-09-15 | 2022-12-13 | 中国核动力研究设计院 | A method, system and medium for health management of nuclear power plant rotating machinery |
| CN115616997A (en) * | 2022-10-17 | 2023-01-17 | 华能威海发电有限责任公司 | Thermal control state monitoring and knowledge base fusion method and system |
| CN117193273A (en) * | 2023-11-07 | 2023-12-08 | 广东鑫钻节能科技股份有限公司 | Positioning and tracing system and method for digital energy air compression station |
| CN118194152A (en) * | 2024-05-16 | 2024-06-14 | 苏州顶裕节能环保有限公司 | Dynamic balance instrument data processing method, device and equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005309616A (en) * | 2004-04-19 | 2005-11-04 | Mitsubishi Electric Corp | Facility equipment failure diagnosis system and failure diagnostic rule creation method |
| CN101135601A (en) * | 2007-10-18 | 2008-03-05 | 北京英华达电力电子工程科技有限公司 | Rotating machinery vibrating failure diagnosis device and method |
| CN103091112A (en) * | 2013-01-31 | 2013-05-08 | 林惠堂 | Method and device of car emission fault detection and diagnosis based on fuzzy reasoning and self-learning |
| CN105181338A (en) * | 2015-09-08 | 2015-12-23 | 广西大学 | Engine state monitoring and fault diagnosis method based on vibration and fluid information |
| CN105590146A (en) * | 2016-02-29 | 2016-05-18 | 上海带来科技有限公司 | Power plant device intelligent prediction overhaul method and power plant device intelligent prediction overhaul system based on big data |
| CN108287529A (en) * | 2017-12-28 | 2018-07-17 | 北京必可测科技股份有限公司 | Inspection, long-range accurate diagnosis and maintenance system and a method are patrolled in integration |
-
2019
- 2019-06-04 CN CN201910481502.3A patent/CN110377001A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005309616A (en) * | 2004-04-19 | 2005-11-04 | Mitsubishi Electric Corp | Facility equipment failure diagnosis system and failure diagnostic rule creation method |
| CN101135601A (en) * | 2007-10-18 | 2008-03-05 | 北京英华达电力电子工程科技有限公司 | Rotating machinery vibrating failure diagnosis device and method |
| CN103091112A (en) * | 2013-01-31 | 2013-05-08 | 林惠堂 | Method and device of car emission fault detection and diagnosis based on fuzzy reasoning and self-learning |
| CN105181338A (en) * | 2015-09-08 | 2015-12-23 | 广西大学 | Engine state monitoring and fault diagnosis method based on vibration and fluid information |
| CN105590146A (en) * | 2016-02-29 | 2016-05-18 | 上海带来科技有限公司 | Power plant device intelligent prediction overhaul method and power plant device intelligent prediction overhaul system based on big data |
| CN108287529A (en) * | 2017-12-28 | 2018-07-17 | 北京必可测科技股份有限公司 | Inspection, long-range accurate diagnosis and maintenance system and a method are patrolled in integration |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110794799A (en) * | 2019-11-28 | 2020-02-14 | 桂林电子科技大学 | Big data system with fault diagnosis function applied to industrial production |
| CN110906152B (en) * | 2019-12-04 | 2021-05-18 | 江苏方天电力技术有限公司 | An online safety warning system for camera oil system |
| CN110879586A (en) * | 2019-12-04 | 2020-03-13 | 江苏方天电力技术有限公司 | Phase modulator fault diagnosis and state monitoring method and system |
| CN110906152A (en) * | 2019-12-04 | 2020-03-24 | 江苏方天电力技术有限公司 | An online safety warning system for camera oil system |
| CN111061191A (en) * | 2019-12-24 | 2020-04-24 | 泉州装备制造研究所 | A distributed oil and gas storage tank remote operation and maintenance system and method |
| CN111061191B (en) * | 2019-12-24 | 2022-06-14 | 泉州装备制造研究所 | Distributed oil-gas storage tank remote operation and maintenance method |
| CN111221320A (en) * | 2019-12-27 | 2020-06-02 | 北京航天测控技术有限公司 | Data interpretation method and device, terminal and computer readable medium |
| CN111221320B (en) * | 2019-12-27 | 2021-08-10 | 北京航天测控技术有限公司 | Data interpretation method and device, terminal and computer readable medium |
| CN111044570A (en) * | 2019-12-28 | 2020-04-21 | 广东电网有限责任公司 | Defect identification and early warning method and device for power equipment and computer equipment |
| CN111736545A (en) * | 2020-05-20 | 2020-10-02 | 国网河北省电力有限公司电力科学研究院 | System and method for data fusion, error correction and analysis of power unit |
| CN111612337A (en) * | 2020-05-21 | 2020-09-01 | 杭州英集动力科技有限公司 | Automatic issuing method and automatic issuing system for heat supply network scheduling |
| CN112731903A (en) * | 2020-11-27 | 2021-04-30 | 成都飞机工业（集团）有限责任公司 | Diagnosis system and method for all-electric transmission flight control fault |
| CN112464565B (en) * | 2020-12-01 | 2022-10-04 | 国网江苏省电力有限公司 | Equipment fault early warning method integrating intelligent modeling and fuzzy rules |
| CN112464565A (en) * | 2020-12-01 | 2021-03-09 | 国网江苏省电力有限公司 | Equipment fault early warning method, system and storage medium integrating intelligent modeling and fuzzy rule |
| CN114760332A (en) * | 2020-12-29 | 2022-07-15 | 江苏金恒信息科技股份有限公司 | Efficient equipment monitoring and analyzing method |
| CN112947177A (en) * | 2021-02-04 | 2021-06-11 | 中国神华能源股份有限公司国华电力分公司 | Equipment point inspection system, method, device and storage medium |
| CN113240140A (en) * | 2021-06-04 | 2021-08-10 | 海尔数字科技(青岛)有限公司 | Fault detection method, device, equipment and storage medium of physical equipment |
| CN113655774A (en) * | 2021-07-21 | 2021-11-16 | 大唐互联科技(武汉)有限公司 | Machine tool remote diagnosis method and system based on industrial internet big data |
| CN113726583A (en) * | 2021-09-24 | 2021-11-30 | 贵州电网有限责任公司 | Remote control unit communication state judgment method based on FSM model |
| CN114154662A (en) * | 2021-12-13 | 2022-03-08 | 龙岩烟草工业有限责任公司 | Fault diagnosis method and device for operating system, computer equipment and storage medium |
| CN115469643A (en) * | 2022-09-15 | 2022-12-13 | 中国核动力研究设计院 | A method, system and medium for health management of nuclear power plant rotating machinery |
| CN115616997A (en) * | 2022-10-17 | 2023-01-17 | 华能威海发电有限责任公司 | Thermal control state monitoring and knowledge base fusion method and system |
| CN117193273A (en) * | 2023-11-07 | 2023-12-08 | 广东鑫钻节能科技股份有限公司 | Positioning and tracing system and method for digital energy air compression station |
| CN117193273B (en) * | 2023-11-07 | 2024-01-12 | 广东鑫钻节能科技股份有限公司 | Positioning and tracing system and method for digital energy air compression station |
| CN118194152A (en) * | 2024-05-16 | 2024-06-14 | 苏州顶裕节能环保有限公司 | Dynamic balance instrument data processing method, device and equipment |
| CN118194152B (en) * | 2024-05-16 | 2024-08-02 | 苏州顶裕节能环保有限公司 | Dynamic balance instrument data processing method, device and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110377001A (en) | Industrial equipment intelligent Fault Diagnose Systems and method based on data fusion | |
| CN105809255B (en) | A kind of thermal power plant's rotating machinery health control method and system based on Internet of Things | |
| Yam et al. | Intelligent predictive decision support system for condition-based maintenance | |
| CN110322018A (en) | A kind of power plant fans fault early warning system based on fuzzy reasoning | |
| CN110766277B (en) | Health assessment and diagnosis system and mobile terminal for nuclear industry field | |
| CN104503399B (en) | The regimental Wind turbines status monitoring of one kind collection and fault diagnosis platform | |
| KR100815032B1 (en) | Power plant online real time performance monitoring system | |
| CN108154291A (en) | A kind of electric power supply plant performance indicator evaluation method and system based on policy library | |
| CN108133311A (en) | A kind of Wind turbines fault mode risk assessment and analysis method for reliability | |
| Zaher et al. | A multi-agent fault detection system for wind turbine defect recognition and diagnosis | |
| CN110529202B (en) | Steam turbine fault diagnosis detection and early warning method and system based on power plant data | |
| CN113962299A (en) | Intelligent operation monitoring and fault diagnosis general model for nuclear power equipment | |
| CN108629430A (en) | A kind of substantial equipment intelligence operation management system | |
| CN101025618A (en) | Power plant thermal equipment intelligent state diagnosing and analyzing system | |
| CN109492790A (en) | Wind turbines health control method based on neural network and data mining | |
| CN102063119A (en) | Equipment failure prediction method based on point polling data and DCS (Data Communication System) online data | |
| CN116228186A (en) | Intelligent operation and maintenance system of ship engine room based on human factors engineering | |
| CN110879586A (en) | Phase modulator fault diagnosis and state monitoring method and system | |
| CN109902447A (en) | A kind of huge Condition Maintenance for Hydraulic Power Plant model and construction method | |
| CN106802599A (en) | A kind of diagnosing fault of power transformer system based on expert database | |
| CN110033181B (en) | Power generation equipment state evaluation method based on self-encoder | |
| CN108491622A (en) | A kind of fault diagnosis method and system of Wind turbines | |
| CN117605620A (en) | Fan preventive maintenance method based on equipment state diagnosis | |
| CN117307499A (en) | On-line monitoring system and method for slurry circulating pump of desulfurizing tower based on LSTM algorithm | |
| CN116628544A (en) | Fault diagnosis method based on hydraulic winch state on-line monitoring |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191025 |
|
| RJ01 | Rejection of invention patent application after publication |