CN102680228B - Method for detecting state of fan gear box - Google Patents
Method for detecting state of fan gear box Download PDFInfo
- Publication number
- CN102680228B CN102680228B CN201110140393.2A CN201110140393A CN102680228B CN 102680228 B CN102680228 B CN 102680228B CN 201110140393 A CN201110140393 A CN 201110140393A CN 102680228 B CN102680228 B CN 102680228B
- Authority
- CN
- China
- Prior art keywords
- gear case
- blower
- probability assignment
- elementary probability
- shock sensor
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Abstract
The invention discloses a method for detecting a state of a fan gear box, which comprises the following steps of collecting vibration state of the fan gear box through multiple vibration sensors, and obtaining multiple basic probability assignments reflecting the state of the fan gear box; and merging the multiple basic probability assignments according to the data synchronization (DS) theory to obtain multiple merged results; and implementing the judgment according to the multiple merged results to obtain the state of the fan gear box.
Description
Technical field
The present invention relates to wind-powered electricity generation field, in particular to a kind of method that detects gear case of blower state.
Background technology
Gear case condition detecting system is a vital ring in blower fan control system, and gear case condition detecting system is generally comprised of shock sensor, data acquisition module, communication module, data processing module etc.The gear case of each blower fan is equipped with set of gears case condition detecting system.During fan operation, the running status of the real-time detection of gear case of gear case condition detecting system, when gear case breaks down, gear case condition detecting system can promptly and accurately judge, thereby allows blower fan make corresponding shutdown or other emergency measure.
The gear case condition detecting system of existing relatively intelligent is by the vibration information at each position of the real-time detection of gear case of shock sensor substantially, by vibration information and historical data are contrasted to the vibrating state that obtains this inspection area.
DS evidence theory is first to be proposed in 1967 by Dempster, a kind of inexact reasoning being further developed in 1976 by his student shafer is theoretical, also referred to as Dempster/Shafer evidence theory (D-S evidence theory), belong to artificial intelligence category, be applied to the earliest in expert system, there is the ability of processing uncertain information.As a kind of uncertain reasoning method, the principal feature of evidence theory is: meet than the more weak condition of Bayesian probability opinion; The ability with direct expression " uncertain " and " not knowing ".
In many applications such as medical diagnosis, target identification, military commandings, need to consider the uncertain information from multi-source, as the information of a plurality of sensors, multidigit expertise etc., with solving of Completion problem, and the union rule of evidence theory solving in this respect brought into play vital role.
Yet, in prior art, exist noise or failure cause due to indivedual shock sensors to cause false alarm phenomenon.
Summary of the invention
The invention provides a kind of method that detects gear case of blower state, in order to the running status of accurate judgement gear case of blower.
For achieving the above object, the invention provides a kind of method that detects gear case of blower state, it comprises the following steps: by a plurality of shock sensors, the vibrating state of gear case of blower is gathered, obtain reflecting a plurality of elementary probability assignment of gear case of blower state; According to DS theory, a plurality of elementary probability assignment are merged, obtain a plurality of fusion results; According to a plurality of fusion results, adjudicate, obtain the state of gear case of blower;
Wherein, according to DS theory, a plurality of elementary probability assignment are merged, obtain a plurality of fusion results steps and comprise:
If total N of a plurality of shock sensors, first group of elementary probability assignment that first shock sensor is corresponding is (u
1, w
1, e
1), second second group of elementary probability assignment corresponding to shock sensor is (u
2, w
2, e
2), the 3rd the 3rd group of elementary probability assignment corresponding to shock sensor is (u
3, w
3, e
3) ..., N N group elementary probability assignment corresponding to shock sensor is (u
n, w
n, e
n), N is greater than 3 natural number, u
i(i=1,2,3 ..., N) for having the elementary probability assignment of malfunction, w
i(i=1,2,3 ..., N) be the elementary probability assignment of unfaulty conditions, e
i(i=1,2,3 ..., N) be the elementary probability assignment of nondeterministic statement, u
i, w
iand e
ivalue respectively between 0 and 1, and u
i+ w
i+ e
i=1;
According to following formula, by (u
1, w
1, e
1) as m
1three burnt (A of unit
1, A
2, A
3), by (u
2, w
2, e
2) as m
2three burnt (B of unit
1, B
2, B
3), first group of elementary probability assignment and second group of elementary probability assignment are merged and obtain m (C),
M (C) and the 3rd group of elementary probability assignment are merged according to above-mentioned formula, and the rest may be inferred, until the elementary probability assignment data of N shock sensor has been merged, thereby obtains the fusion results (u of N shock sensor
o, w
o, e
o);
According to a plurality of fusion results, adjudicate, the state step that obtains gear case of blower comprises:
To u
o, w
oand e
omagnitude relationship judge;
If w
omaximum, gear case of blower operates in unfaulty conditions;
If e
omaximum, gear case of blower operates in nondeterministic statement;
If u
omaximum, makes m (A
1)=u
o, m (A
2)=w
o, m (A
k)=e
oif, u
o, w
oand e
omeet following formula:
Gear case of blower operates in malfunction, wherein ε
1, ε
2for predefined threshold value.
Preferably, by a plurality of shock sensors, the vibrating state of gear case of blower is gathered, obtains reflecting that a plurality of elementary probability assignment steps of gear case of blower state comprise:
By a plurality of shock sensors, the vibrating state of gear case of blower is gathered, the data of collection and the historical data being stored in database are contrasted, and the possibility that gear case of blower is operated in to malfunction, unfaulty conditions and nondeterministic statement judges;
According to judged result, obtain the elementary probability assignment that many group reflection gear case of blowers operate in malfunction, unfaulty conditions and nondeterministic statement, wherein, the elementary probability assignment sum that has malfunction, unfaulty conditions and nondeterministic statement that each shock sensor records equals 1.
Preferably, said method is further comprising the steps of:
If gear case of blower has operated in malfunction, gear case of blower is made to corresponding protection action.
Preferably, said method is further comprising the steps of:
If gear case of blower operates in nondeterministic statement, user is sent to alarm.
Above-described embodiment carries out data fusion by the analysis result of a plurality of shock sensors, each shock sensor is no matter be through time-domain analysis or through frequency-domain analysis, all will obtain an analysis result: running state of gear box is to have fault, the concrete probability size of non-fault and uncertainty, and then these analysis results are carried out to a high-level data fusion, obtain a total gear case operation result, thereby can reduce the false alarm phenomenon that indivedual shock sensors cause due to noise or failure cause.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, to the accompanying drawing of required use in embodiment or description of the Prior Art be briefly described below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skills, do not paying under the prerequisite of creative work, can also obtain according to these accompanying drawings other accompanying drawing.
Fig. 1 is for detecting according to an embodiment of the invention the method flow diagram of gear case of blower state;
Fig. 2 is the system chart of Fig. 1 embodiment.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is only the present invention's part embodiment, rather than whole embodiment.Embodiment based in the present invention, those of ordinary skills, not paying the every other embodiment obtaining under creative work prerequisite, belong to the scope of protection of the invention.
Fig. 1 is for detecting according to an embodiment of the invention the method flow diagram of gear case of blower state.As shown in Figure 1, the method comprises the following steps:
S102, gathers the vibrating state of gear case of blower by a plurality of shock sensors, obtains reflecting a plurality of elementary probability assignment of gear case of blower state;
S104, merges a plurality of elementary probability assignment according to DS theory, obtains a plurality of fusion results;
S106, adjudicates according to a plurality of fusion results, obtains the state of gear case of blower.
In the present embodiment, the vibration information of a plurality of shock sensor Real-Time Monitoring gear casees is installed respectively at each position of gear case, the vibration information that each shock sensor is collected passes to controller, controller is analyzed the real time data of each shock sensor and historical data, obtain the judged result of each sensor to gear case vibrating state, finally use DS evidence theory to carry out top data fusion the judged result of each sensor, obtain the running status of gear case.
Fig. 2 is the system chart of Fig. 1 embodiment.As shown in Figure 2, the present embodiment is not limited to the data analysis of single shock sensor, but the analysis result of a plurality of shock sensors is carried out to data fusion, each shock sensor is no matter be through time-domain analysis or through frequency-domain analysis, all will obtain an analysis result: running state of gear box is to have fault, the concrete probability size of non-fault and uncertainty, and then these analysis results are carried out to a high-level data fusion, obtain a total gear case operation result, thereby can reduce the false alarm phenomenon that indivedual shock sensors cause due to noise or failure cause.
For example, by a plurality of shock sensors, the vibrating state of gear case of blower is gathered, obtains reflecting that a plurality of elementary probability assignment steps of gear case of blower state comprise:
By a plurality of shock sensors, the vibrating state of gear case of blower is gathered, the data of collection and the historical data being stored in database are contrasted, and the possibility that gear case of blower is operated in to malfunction, unfaulty conditions and nondeterministic statement judges;
According to judged result, obtain the elementary probability assignment that many group reflection gear case of blowers operate in malfunction, unfaulty conditions and nondeterministic statement, wherein, the elementary probability assignment sum that has malfunction, unfaulty conditions and nondeterministic statement that each shock sensor records equals 1.
Definition 1: establish V represent X a likely domain set of value, and be mutual exclusive between all elements in V, claim that V is the identification framework of X.
Definition 2: establishing V is an identification framework, function m:2
v→ [0,1] (2
vthe set forming for all subsets of V) meet following condition:
(1)m(φ)=0 (1)
(2)
Claim m (A) for the elementary probability assignment (BPA) of A, represent the accurate trusting degree to proposition A, represented the direct support to A.
For example, according to DS theory, a plurality of elementary probability assignment are merged, obtain a plurality of fusion results steps and comprise:
If total N of a plurality of shock sensors, first group of elementary probability assignment that first shock sensor is corresponding is (u
1, w
1, e
1), second second group of elementary probability assignment corresponding to shock sensor is (u
2, w
2, e
2), the 3rd the 3rd group of elementary probability assignment corresponding to shock sensor is (u
3, w
3, e
3) ..., N N group elementary probability assignment corresponding to shock sensor is (u
n, w
n, e
n), N is greater than 3 natural number, u
i(i=1,2,3 ..., N) for having the elementary probability assignment of malfunction, w
i(i=1,2,3 ..., N) be the elementary probability assignment of unfaulty conditions, e
i(i=1,2,3 ..., N) be the elementary probability assignment of nondeterministic statement, u
i, w
iand e
ivalue respectively between 0 and 1, and u
i+ w
i+ e
i=1;
Wherein the size of e is determined by its corresponding shock sensor measurement measuring accuracy.The running status of the gear case that corresponding this sensor of each u value provides.U value corresponding to each shock sensor is between 0 and 1, and better the closer to 0 running state of gear box, larger the closer to the possibility of 1 gearbox fault, when u=0, out of order probability is 0.So be the BPA that has malfunction using the u value of each sensor as corresponding shock sensor check result; The same BPA that is unfaulty conditions as corresponding shock sensor check result using w value; The BPA that e value is nondeterministic statement as corresponding shock sensor check result.Thereby meet the requirement of formula (1) and formula (2), can be used as corresponding elementary probability assignment;
Definition 3: establish BEL
1and BEL
2two belief functions on same identification framework V, m
1and m
2be respectively its corresponding elementary probability assignment (BPA), burnt unit is respectively A
1... A
kand B
1... B
r, establish again
In the above in formula, if K
1≠ 1, m determines an elementary probability assignment; K
1=1, think m
1, m
2contradiction, can not combine elementary probability assignment.Definition 3 evidences that provide meet law of association and exchange rate, for the combination of a plurality of evidences, can adopt the rule of combination of definition 3 evidence to be carried out comprehensive between two.
According to formula (3) and (4), by (u
1, w
1, e
1) as m
1three burnt (A of unit
1, A
2, A
3), by (u
2, w
2, e
2) as m
2three burnt (B of unit
1, B
2, B
3), first group of elementary probability assignment and second group of elementary probability assignment are merged and obtain m (C), m (C) is merged to (3) and (4) with the 3rd group of elementary probability assignment according to above-mentioned formula, the rest may be inferred, until the data fusion of N shock sensor is completed, thereby obtain the fusion results (u of N shock sensor
o, w
o, e
o).
Decision-making based on elementary probability assignment: establish
meet
M(A
2)=max{m (A
i),
and A
i≠ A
1, (6)
A
1for court verdict, ε wherein
1, ε
2for predefined thresholding.
For example, according to a plurality of fusion results, adjudicate, the state step that obtains gear case of blower comprises:
To u
o, w
oand e
omagnitude relationship judge;
If w
omaximum, gear case of blower operates in unfaulty conditions;
If e
omaximum, gear case of blower operates in nondeterministic statement;
If u
omaximum, makes m (A
1)=u
o, m (A
2)=w
o, m (A
k)=e
oif, u
o, w
oand e
omeet formula (7), gear case of blower operates in malfunction, wherein ε
1, ε
2for predefined threshold value.
For example, said method is further comprising the steps of:
If gear case of blower has operated in malfunction, gear case of blower is made to corresponding protection action.
For example, said method is further comprising the steps of:
If gear case of blower operates in nondeterministic statement, user is sent to alarm.
From the description of above-described embodiment, can find out, the status information at each position that the present invention records a plurality of shock sensors with DS evidence theory is carried out data fusion, and then obtain the overall operation state of whole gear case, thereby provide strong assurance for the normal operation of whole blower fan.
One of ordinary skill in the art will appreciate that: accompanying drawing is the schematic diagram of an embodiment, the module in accompanying drawing or flow process might not be that enforcement the present invention is necessary.
One of ordinary skill in the art will appreciate that: the module in the device in embodiment can be described and be distributed in the device of embodiment according to embodiment, also can carry out respective change and be arranged in the one or more devices that are different from the present embodiment.The module of above-described embodiment can be merged into a module, also can further split into a plurality of submodules.
The invention described above embodiment sequence number, just to describing, does not represent the quality of embodiment.
One of ordinary skill in the art will appreciate that: all or part of step that realizes said method embodiment can complete by the relevant hardware of programmed instruction, aforesaid program can be stored in a computer read/write memory medium, this program, when carrying out, is carried out the step that comprises said method embodiment; And aforesaid storage medium comprises: various media that can be program code stored such as ROM, RAM, magnetic disc or CDs.
Finally it should be noted that: above embodiment only, in order to technical scheme of the present invention to be described, is not intended to limit; Although the present invention is had been described in detail with reference to previous embodiment, those of ordinary skill in the art is to be understood that: its technical scheme that still can record previous embodiment is modified, or part technical characterictic is wherein equal to replacement; And these modifications or replacement do not make the essence of appropriate technical solution depart from the spirit and scope of embodiment of the present invention technical scheme.
Claims (4)
1. a method that detects gear case of blower state, is characterized in that, comprises the following steps:
By a plurality of shock sensors, the vibrating state of gear case of blower is gathered, obtain reflecting a plurality of elementary probability assignment of described gear case of blower state;
According to DS theory, described a plurality of elementary probability assignment are merged, obtain a plurality of fusion results, comprising: establish total N of described a plurality of shock sensor, first group of elementary probability assignment that described in first, shock sensor is corresponding is (u
1, w
1, e
1), second second group of elementary probability assignment corresponding to described shock sensor is (u
2, w
2, e
2), the 3rd the 3rd group of elementary probability assignment corresponding to described shock sensor is (u
3, w
3, e
3) ..., N N group elementary probability assignment corresponding to described shock sensor is (u
n, w
n, e
n), N is greater than 3 natural number, u
i(i=1,2,3 ..., N) for having the elementary probability assignment of malfunction, w
i(i=1,2,3 ..., N) be the elementary probability assignment of unfaulty conditions, e
i(i=1,2,3 ..., N) be the elementary probability assignment of nondeterministic statement, u
i, w
iand e
ivalue respectively between 0 and 1, and u
i+ w
i+ e
i=1;
According to following formula, by (u
1, w
1, e
1) as m
1three burnt (A of unit
1, A
2, A
3), by (u
2, w
2, e
2) as m
2three burnt (B of unit
1, B
2, B
3), described first group of elementary probability assignment and described second group of elementary probability assignment are merged and obtain m (C),
M (C) and described the 3rd group of elementary probability assignment are merged according to above-mentioned formula, and the rest may be inferred, until the elementary probability assignment data of N shock sensor has been merged, thereby obtains the fusion results (u of N shock sensor
o, w
o, e
o);
According to described a plurality of fusion results, adjudicate, obtain the state of described gear case of blower, comprising:
To u
o, w
oand e
omagnitude relationship judge;
If w
omaximum, described gear case of blower operates in unfaulty conditions;
If e
omaximum, described gear case of blower operates in nondeterministic statement;
If u
omaximum, makes m (A
1)=u
o, m (A
2)=w
o, m (A
k)=e
oif, u
o, w
oand e
omeet following formula:
Described gear case of blower operates in malfunction, wherein ε
1, ε
2for predefined threshold value.
2. method according to claim 1, is characterized in that, by a plurality of shock sensors, the vibrating state of gear case of blower is gathered, and obtains reflecting that a plurality of elementary probability assignment steps of described gear case of blower state comprise:
By a plurality of shock sensors, the vibrating state of gear case of blower is gathered, the data of collection and the historical data being stored in database are contrasted, and the possibility that described gear case of blower is operated in to malfunction, unfaulty conditions and nondeterministic statement judges;
According to judged result, obtain the elementary probability assignment that the described gear case of blower of many group reflections operates in malfunction, unfaulty conditions and nondeterministic statement, wherein, the elementary probability assignment sum that has malfunction, unfaulty conditions and nondeterministic statement that described in each, shock sensor records equals 1.
3. method according to claim 1, is characterized in that, further comprising the steps of:
If described gear case of blower has operated in malfunction, described gear case of blower is made to corresponding protection action.
4. method according to claim 1, is characterized in that, further comprising the steps of:
If described gear case of blower operates in nondeterministic statement, user is sent to alarm.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201110140393.2A CN102680228B (en) | 2011-05-27 | 2011-05-27 | Method for detecting state of fan gear box |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201110140393.2A CN102680228B (en) | 2011-05-27 | 2011-05-27 | Method for detecting state of fan gear box |
Publications (2)
Publication Number | Publication Date |
---|---|
CN102680228A CN102680228A (en) | 2012-09-19 |
CN102680228B true CN102680228B (en) | 2014-09-10 |
Family
ID=46812493
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201110140393.2A Active CN102680228B (en) | 2011-05-27 | 2011-05-27 | Method for detecting state of fan gear box |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102680228B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103728134B (en) * | 2012-10-16 | 2016-05-18 | 华锐风电科技(集团)股份有限公司 | The detection method of unit bearing and device and wind-powered electricity generation unit |
CN103868689B (en) * | 2014-02-20 | 2017-02-22 | 温州大学 | Vibration frequency analysis-based gear defect rapid detection system and method |
CN108318249B (en) * | 2018-01-24 | 2020-04-17 | 广东石油化工学院 | Fault diagnosis method for rotary mechanical bearing |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1920511A (en) * | 2006-08-01 | 2007-02-28 | 东北电力大学 | Fusion diagnosing method of centrifugal pump vibration accidents and vibration signals sampling device |
CN101201370A (en) * | 2006-12-13 | 2008-06-18 | 上海海事大学 | Fault diagnosis system adopting circuit information amalgamation and implementing method thereof |
-
2011
- 2011-05-27 CN CN201110140393.2A patent/CN102680228B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1920511A (en) * | 2006-08-01 | 2007-02-28 | 东北电力大学 | Fusion diagnosing method of centrifugal pump vibration accidents and vibration signals sampling device |
CN101201370A (en) * | 2006-12-13 | 2008-06-18 | 上海海事大学 | Fault diagnosis system adopting circuit information amalgamation and implementing method thereof |
Non-Patent Citations (6)
Title |
---|
《基于D-S证据理论的齿轮箱故障诊断》;熊健等;《微计算机信息》;20081105;第24卷(第31期);第192-193页 * |
《基于决策级信息融合的设备故障诊断方法研究》;饶泓等;《中国机械工程》;20090228;第20卷(第4期);第433-436页 * |
《灰色关联和D-S证据理论在变速箱齿轮故障诊断中的应用》;曲晓慧等;《测试技术学报》;20040630;第18卷;第41-44页 * |
曲晓慧等.《灰色关联和D-S证据理论在变速箱齿轮故障诊断中的应用》.《测试技术学报》.2004,第18卷第41-44页. |
熊健等.《基于D-S证据理论的齿轮箱故障诊断》.《微计算机信息》.2008,第24卷(第31期),第192-193页. |
饶泓等.《基于决策级信息融合的设备故障诊断方法研究》.《中国机械工程》.2009,第20卷(第4期),第433-436页. |
Also Published As
Publication number | Publication date |
---|---|
CN102680228A (en) | 2012-09-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103163877B (en) | Method and system for root cause analysis and quality monitoring of system-level faults | |
CN101590918B (en) | Method for automatic fault diagnosis of satellite and diagnostic system thereof | |
CN109581871B (en) | Industrial control system intrusion detection method of immune countermeasure sample | |
CN100412993C (en) | System for intelligent maintaince of muclear power paltn based on state monitoring | |
EP2478423A1 (en) | Supervised fault learning using rule-generated samples for machine condition monitoring | |
CN113339204B (en) | Wind driven generator fault identification method based on hybrid neural network | |
CN108780315A (en) | Method and apparatus for the diagnosis for optimizing slewing | |
CN101299004A (en) | Vibrating failure diagnosis method based on determined learning theory | |
CN105487009A (en) | Motor fault diagnosis method based on k-means RBF neural network algorithm | |
Dadashi et al. | A framework to support human factors of automation in railway intelligent infrastructure | |
CN102680228B (en) | Method for detecting state of fan gear box | |
Son et al. | Deep learning-based anomaly detection to classify inaccurate data and damaged condition of a cable-stayed bridge | |
Borissova et al. | An integrated framework of designing a decision support system for engineering predictive maintenance | |
CN110705849A (en) | Inspection robot effect evaluation method and system, storage medium and robot | |
Singh et al. | Trends in the development of system-level fault dependency matrices | |
CN117170303B (en) | PLC fault intelligent diagnosis maintenance system based on multivariate time sequence prediction | |
CN206488924U (en) | Automatic gearbox failure diagnostic apparatus based on virtual instrument | |
CN108415819A (en) | Hard disk fault tracking method and device | |
CN114577470A (en) | Fault diagnosis method and system for fan main bearing | |
CN116523722A (en) | Environment monitoring analysis system with machine learning capability | |
Duan et al. | Diagnosis strategy for micro-computer controlled straight electro-pneumatic braking system using fuzzy set and dynamic fault tree | |
Coble et al. | Adaptive monitoring, fault detection and diagnostics, and prognostics system for the IRIS nuclear plant | |
CN206656749U (en) | Heat-engine plant sensor fault diagnosis system | |
Gámiz et al. | Dynamic reliability and sensitivity analysis based on HMM models with Markovian signal process | |
Lu et al. | Integration of wavelet decomposition and artificial neural network for failure prognosis of reciprocating compressors |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant |