CN105134456A - Water turbine fault prognosis method based on on-line monitoring - Google Patents
Water turbine fault prognosis method based on on-line monitoring Download PDFInfo
- Publication number
- CN105134456A CN105134456A CN201510451591.9A CN201510451591A CN105134456A CN 105134456 A CN105134456 A CN 105134456A CN 201510451591 A CN201510451591 A CN 201510451591A CN 105134456 A CN105134456 A CN 105134456A
- Authority
- CN
- China
- Prior art keywords
- value
- data
- diagnostics
- conditions
- water turbine
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/20—Hydro energy
Landscapes
- Testing And Monitoring For Control Systems (AREA)
Abstract
Disclosed is a water turbine fault prognosis method based on on-line monitoring. On-line monitoring of the pendulum state of a water turbine set and real-time fault prognosis are realized through collection of a pendulum data sample of the water turbine set, real-time library reading and writing, data preprocessing and making of inference rules. The water turbine fault prognosis method based on on-line monitoring comprises the steps of collecting and displaying real-time data, realizing fault early warning and vibration tread displaying, recording and displaying the diagnosis result, fault analysis and processing suggestions, and storing diagnostic reports.
Description
Technical field
The present invention relates to industrial control field, relate more specifically to the vibrating failure diagnosis method of turbine-generator units.
Background technique
For a long time, in hydro-generating Unit, mechanical vibration are the key factors threatening Hydropower Unit safety in production to run.The vibration of Hydropower Unit often machinery, electrically, the acting in conjunction of waterpower three aspect factor causes, vibration mechanism relative complex.Vibration, the throw of unit also can cause due to the reason of the aspects such as design, installation, operation, can not avoid completely and eliminate.In a word, General Oscillation can not work the mischief to unit, but seriously exceedes permitted value, and especially long-term exceedes, and will cause serious impact to unit.
At present, most diagnostic techniques is all based on expert system, by carrying out analyzing and diagnosing to historical data, cannot make and diagnoses and send early warning, present applicant proposes a kind of real-time diagnosis method for real time data.
Summary of the invention
The present invention proposes a kind of water turbine fault pre-diagnosing method based on on-line monitoring, belong to the real-time diagnosis method of water turbine, solve the problem that traditional diagnosis method cannot carry out inline diagnosis.
The present invention is concrete by the following technical solutions.
Based on a water turbine fault pre-diagnosing method for on-line monitoring, said method comprising the steps of:
Step 1: by on-Line Monitor Device Real-time Collection water turbine real time data, comprise water turbine upper spider X to, Y-direction vibration values and amplitude, on lead X and lead X to, Y-direction throw value and amplitude, rotating speed, unit load, load rejection signal, unit vibration state signal to, Y-direction throw value and amplitude, water;
Step 2: respectively following pretreatment is carried out to the data of step 1 Real-time Collection:
According to No. id in water power plant station number, water turbine units number and real-time data base, the data value collected is saved in data list;
According to value>va, the data value collected is compared, conditions for diagnostics ident value ans is obtained according to comparative result, and conditions for diagnostics ident value ans is saved in data list, wherein, value is the live data values gathered, and va is the default alarming value of certain class real time data corresponding, ans is conditions for diagnostics ident value, value is 0 or 1, and 0 represents value<va, and 1 represents value>va;
Step 3: first according to operations staff and expertise, set up knowledge base, this knowledge base comprises conditions for diagnostics particular content, diagnostic result, trouble analysis, treatment advice and rule number, utilize the corresponding content specifically described as trouble analysis of conditions for diagnostics ident value ans in step 2, treatment advice is the treatment measures for this fault, and every bar knowledge all comprises foregoing; Then, according to the conditions for diagnostics ident value that step 2 obtains, adopt the logic reasoning based on inference rule to carry out fault diagnosis, its citation form is as follows:
Work as AANDBANDCAND ..., then fault diagnosis result R is obtained, wherein A, B, C ... be the conditions for diagnostics ident value that all kinds of live data values that gather based on step 1 are obtained compared with the default alarming value of corresponding class real time data by step 2, namely the conditions for diagnostics ident value ans in step 2, wherein, AND represents that the logical relation between each conditions for diagnostics ident value is "AND", R represents final fault diagnosis result, namely be fault-free when the conditions for diagnostics ident value obtained by all kinds of real time data is not all 1 expression diagnostic result, be fault when the conditions for diagnostics ident value obtained by all kinds of real time data is 1 expression diagnostic result.
Such as: the upper spider vibration X in step 1 is to real time data, and the judgement through step 2 obtains corresponding conditions for diagnostics ident value A, represents and exceeds standard, represent normal when A is 0 when A is 1.Using the content of the description of corresponding conditions for diagnostics ident value as trouble analysis, as: upper spider X exceeds standard to vibration values; And instruction is proposed as treatment advice, and as: please check whether upper spider bolt loosens.
Step 4: after the data processing of step 2 and the fault diagnosis of step 3, after obtaining diagnostic result, trouble analysis and treatment advice, diagnostic result, trouble analysis and treatment advice are shown by man-machine interface, real-time curve and the history curve of gathered water turbine data can be inquired about, described diagnostic result, trouble analysis and treatment advice are stored as diagnosis report, and the record diagnosis time; Finally, the logical relation of this inference rule shows in man-machine interface simultaneously.
As mentioned above, be the pre-diagnostic method elementary process of this diagnosis, the advantage of the method is as follows:
1. on-line monitoring, real-time diagnosis: by gathering real time data, real-time diagnosis, and draw real-time data curve and historical data curve;
2. knowledge base is convenient to safeguard: preserve knowledge base in xml form, can carry out the interpolation of knowledge, amendment and deletion at any time;
3. diagnostic result inquiry is convenient: diagnostic method finally exports diagnosis report, preserves in the form of text, and content comprises diagnosis criterion, diagnostic result, trouble analysis, treatment advice and Diagnostic Time (can be as accurate as second);
4. man-machine interface is abundant in content: man-machine interface not only show diagnostic result, Analysis of conclusion, treatment advice, diagnostic logic, and can Monitoring Data, inquiry real-time curve and history curve.
Accompanying drawing explanation
Fig. 1 is data flow of the present invention and fault pre-diagnosing schematic flow sheet;
Embodiment
Below in conjunction with Figure of description, technological scheme of the present invention is further described in detail.Figure 1 shows that diagnostic data mining for vehicles and diagnostic flow chart.
Step 1, the vibration sample data of each monitoring channel of turbine-generator units can be gathered by runout monitoring device according to the needs of on-the-spot application service, then obtain by the driver of special device and customization the sample data that runout device produces, realize each vibrating channel sample data access real-time database, be mainly: turbine upper spider X to, Y-direction vibration values and amplitude, on lead X and lead X to, Y-direction throw value and amplitude to, Y-direction throw value and amplitude, water; And gather other related data: rotating speed, unit load, load rejection signal, unit vibration state signal.
Step 2, carries out data prediction.First, fault diagnosis module will obtain the sample data collected by runout device from real-time database, obtaining method is: the model file setting up corresponding real time data, the form of this file is XML, inside have: the plant stand in corresponding water power plant number, power station title and machine group number, the period id of institute's image data point, roll-call, description, data value and digital independent number of times, represent the title of water power with " stationname " field, corresponding " id " is plant stand number; Represent water turbine set title with " hydroturbinename ", corresponding " id " is machine group number; Represent the title at sample number strong point with " PropItemname ", corresponding " id " represents that this point stores No. id in real-time data base, and " cValue " represents alarming value or the limit value of this data point, and " flag " is then the mark of this digital independent number of times.The real-time database access interface provided by monitor supervision platform, is carried out data capture according to plant stand number, machine group number, period, and is saved in data list by data according to the content of model file, comprise the roll-call of this point, description and data value simultaneously.
After obtaining real time data, first by data being delivered to man-machine interface display, (content of display comprises roll-call to the interface provided by diagnostic module, describe, instantaneous value, alarming value), then data prediction is carried out, according to value>va, data described in the step 1 collected are calculated, according to result of calculation definition conditions for diagnostics ident value ans, if value<va, ans value is 0, value>va, ans value is 1, and ans value is saved in data list, wherein value is the live data values gathered, va is alarming value, obtain for inference machine.
Step 3, first according to operations staff and expertise, set up knowledge base, this knowledge base comprises conditions for diagnostics particular content, diagnostic result, trouble analysis, treatment advice and rule number, the content as trouble analysis will be specifically described corresponding to conditions for diagnostics ident value ans in step 2, treatment advice is the treatment measures for this fault, and every bar knowledge all comprises foregoing;
Then, utilize the conditions for diagnostics ident value ans obtained in step 2, carry out fault diagnosis, detailed process is as described below:
1. first define the intermediate variable of one group of precondition mark, the list obtained after utilizing data prediction, read the value of precondition mark " ans ", and be assigned to intermediate variable;
2. utilize precondition intermediate variable to carry out reasoning combination, form inference rule, and definition and record rule number, then this rule number is utilized to be obtained in knowledge base should the content of that knowledge of rule number by the interface function that Java code is write, if the content of an acquisition knowledge that can be complete, completes and once diagnose, if the content in knowledge base cannot be obtained by this rule number, then prompting carry out knowledge supplement, and return data obtains, and diagnoses next time;
3. after completing once diagnosis, by the reading system time, determine the time of breaking down, and record stores this time;
Step 4, after above-mentioned 3 steps, diagnostic result will be obtained, trouble analysis, treatment advice, the Man Machine Interface function provided by inference machine is by diagnosis, trouble analysis, treatment advice is delivered to man-machine interface display, show the logical relation of this rule simultaneously, this logical relation reads each conditions for diagnostics content corresponding in knowledge base by interface function, diagnostic result, conditions for diagnostics is carried out combination display according to the relation of inference rule logical "and", the data of the man-machine interface delivered to " data acquisition " stage form final man-machine interface jointly, and real-time curve and the history curve of diagnostic data can be inquired about, then, by the time of failure that the diagnostic result of record in step 3, trouble analysis, treatment advice, conditions for diagnostics describe and record, be kept in the text of specifying, as diagnosis report.
Claims (1)
1., based on a water turbine fault pre-diagnosing method for on-line monitoring, said method comprising the steps of:
Step 1: by on-Line Monitor Device Real-time Collection water turbine real time data, comprise water turbine upper spider X to, Y-direction vibration values and amplitude, on lead X and lead X to, Y-direction throw value and amplitude, rotating speed, unit load, load rejection signal, unit vibration state signal to, Y-direction throw value and amplitude, water;
Step 2: respectively following pretreatment is carried out to the water turbine real time data that step 1 gathers:
According to No. id in water power plant station number, water turbine units number and real-time data base, the data value collected is saved in data list;
According to value>va, the data value collected is compared, conditions for diagnostics ident value ans is obtained according to comparative result, and conditions for diagnostics ident value ans is saved in data list, wherein, value is the live data values gathered, and va is the default alarming value of certain class real time data corresponding, ans is conditions for diagnostics ident value, value is 0 or 1, and 0 represents value<va, and 1 represents value>va;
Step 3: according to operations staff and expertise, set up knowledge base, this knowledge base comprises conditions for diagnostics particular content, diagnostic result, trouble analysis, treatment advice and rule number, utilize the corresponding content specifically described as trouble analysis of conditions for diagnostics ident value ans in step 2, treatment advice is the treatment measures for this fault; Then, according to the conditions for diagnostics ident value that step 2 obtains, adopt the logic reasoning based on inference rule to carry out fault diagnosis, its citation form is as follows:
Work as AANDBANDCAND ..., then fault diagnosis result R is obtained, wherein A, B, C ... be the conditions for diagnostics ident value that all kinds of live data values that gather based on step 1 are obtained compared with the default alarming value of corresponding class real time data by step 2, namely the conditions for diagnostics ident value ans in step 2, wherein, AND represents that the logical relation between each conditions for diagnostics ident value is "AND", R represents final fault diagnosis result, namely be fault-free when the conditions for diagnostics ident value obtained by all kinds of real time data is not all 1 expression diagnostic result, be fault when the conditions for diagnostics ident value obtained by all kinds of real time data is 1 expression diagnostic result,
Step 4: after the data processing of step 2 and the fault diagnosis of step 3, after obtaining diagnostic result, trouble analysis and treatment advice, diagnostic result, trouble analysis and treatment advice are shown by man-machine interface, inquire about real-time curve and the history curve of the water turbine data gathered, described diagnostic result, trouble analysis and treatment advice are stored as diagnosis report, and the record diagnosis time; Finally, the logical relation of this inference rule shows in man-machine interface simultaneously.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510451591.9A CN105134456B (en) | 2015-07-29 | 2015-07-29 | Hydraulic turbine fault pre-diagnosing method based on on-line monitoring |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510451591.9A CN105134456B (en) | 2015-07-29 | 2015-07-29 | Hydraulic turbine fault pre-diagnosing method based on on-line monitoring |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105134456A true CN105134456A (en) | 2015-12-09 |
| CN105134456B CN105134456B (en) | 2018-05-18 |
Family
ID=54719970
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510451591.9A Active CN105134456B (en) | 2015-07-29 | 2015-07-29 | Hydraulic turbine fault pre-diagnosing method based on on-line monitoring |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105134456B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107015484A (en) * | 2017-01-04 | 2017-08-04 | 北京中元瑞讯科技有限公司 | The evaluation method of hydroelectric generator axis bending based on online data |
| CN107066662A (en) * | 2016-12-29 | 2017-08-18 | 北京中元瑞讯科技有限公司 | The diagnostic method of turbine-generator units quality imbalance fault based on online data |
| CN107061113A (en) * | 2017-05-09 | 2017-08-18 | 大冶市福达设备制造科技有限公司 | A kind of a ship borne type hydraulic generator group of planes and electricity-generating method |
| WO2018113165A1 (en) * | 2016-12-21 | 2018-06-28 | 国网电力科学研究院 | Configurable device for monitoring vibration and swing states of hydraulic turbine set, and data acquisition method |
| CN108412659A (en) * | 2018-01-31 | 2018-08-17 | 贵州乌江水电开发有限责任公司东风发电厂 | A kind of processing system for overhauling water turbine set |
| CN109146137A (en) * | 2018-07-23 | 2019-01-04 | 广东核电合营有限公司 | Predict the method, apparatus and terminal device of operation state of generator variation tendency |
| CN110513242A (en) * | 2019-08-13 | 2019-11-29 | 中国水利水电科学研究院 | It is a kind of with vibration frequency be main clue power station stable fault diagnostic method |
| CN110553722A (en) * | 2019-07-15 | 2019-12-10 | 乌江渡发电厂 | Water guide swing detection method for power plant generator set |
| CN114412696A (en) * | 2021-12-29 | 2022-04-29 | 腾安电子科技(江苏)有限公司 | Water turbine operation abnormity alarm method and system and water turbine monitoring system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040199573A1 (en) * | 2002-10-31 | 2004-10-07 | Predictive Systems Engineering, Ltd. | System and method for remote diagnosis of distributed objects |
| CN101158874A (en) * | 2007-09-26 | 2008-04-09 | 大亚湾核电运营管理有限责任公司 | Control system of nuclear power unit, automatic diagnostic method and subsystem thereof |
| CN103529825A (en) * | 2013-10-23 | 2014-01-22 | 上海白丁电子科技有限公司 | Automatic equipment failure analysis and diagnosis method and device thereof |
| CN203629869U (en) * | 2013-12-19 | 2014-06-04 | 太平湾发电厂 | Water turbine cavitation monitoring and analyzing system |
-
2015
- 2015-07-29 CN CN201510451591.9A patent/CN105134456B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040199573A1 (en) * | 2002-10-31 | 2004-10-07 | Predictive Systems Engineering, Ltd. | System and method for remote diagnosis of distributed objects |
| CN101158874A (en) * | 2007-09-26 | 2008-04-09 | 大亚湾核电运营管理有限责任公司 | Control system of nuclear power unit, automatic diagnostic method and subsystem thereof |
| CN103529825A (en) * | 2013-10-23 | 2014-01-22 | 上海白丁电子科技有限公司 | Automatic equipment failure analysis and diagnosis method and device thereof |
| CN203629869U (en) * | 2013-12-19 | 2014-06-04 | 太平湾发电厂 | Water turbine cavitation monitoring and analyzing system |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018113165A1 (en) * | 2016-12-21 | 2018-06-28 | 国网电力科学研究院 | Configurable device for monitoring vibration and swing states of hydraulic turbine set, and data acquisition method |
| CN107066662A (en) * | 2016-12-29 | 2017-08-18 | 北京中元瑞讯科技有限公司 | The diagnostic method of turbine-generator units quality imbalance fault based on online data |
| CN107015484A (en) * | 2017-01-04 | 2017-08-04 | 北京中元瑞讯科技有限公司 | The evaluation method of hydroelectric generator axis bending based on online data |
| CN107061113A (en) * | 2017-05-09 | 2017-08-18 | 大冶市福达设备制造科技有限公司 | A kind of a ship borne type hydraulic generator group of planes and electricity-generating method |
| CN108412659A (en) * | 2018-01-31 | 2018-08-17 | 贵州乌江水电开发有限责任公司东风发电厂 | A kind of processing system for overhauling water turbine set |
| CN109146137A (en) * | 2018-07-23 | 2019-01-04 | 广东核电合营有限公司 | Predict the method, apparatus and terminal device of operation state of generator variation tendency |
| CN110553722A (en) * | 2019-07-15 | 2019-12-10 | 乌江渡发电厂 | Water guide swing detection method for power plant generator set |
| CN110513242A (en) * | 2019-08-13 | 2019-11-29 | 中国水利水电科学研究院 | It is a kind of with vibration frequency be main clue power station stable fault diagnostic method |
| CN114412696A (en) * | 2021-12-29 | 2022-04-29 | 腾安电子科技(江苏)有限公司 | Water turbine operation abnormity alarm method and system and water turbine monitoring system |
| CN114412696B (en) * | 2021-12-29 | 2024-03-19 | 腾安电子科技(江苏)有限公司 | Water turbine operation abnormity alarm method and system and water turbine monitoring system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105134456B (en) | 2018-05-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105134456A (en) | Water turbine fault prognosis method based on on-line monitoring | |
| Hsu et al. | Wind turbine fault diagnosis and predictive maintenance through statistical process control and machine learning | |
| CN109901537B (en) | Mechanical equipment running state monitoring method and system for edge computing side | |
| CN102730571B (en) | Online monitoring and fault diagnosing system for crane | |
| CN111947928B (en) | Multi-source information fusion bearing fault prediction system and method | |
| CN110674842A (en) | Wind turbine generator main shaft bearing fault prediction method | |
| CN110766277B (en) | Health assessment and diagnosis system and mobile terminal for nuclear industry field | |
| CN102022263B (en) | A method and a system for adjusting alarm level of a component in a wind turbine | |
| CN105809255A (en) | IoT-based heat-engine plantrotary machine health management method and system | |
| CN109405889B (en) | System and method for predicting fault of working arm reducer of heading machine | |
| CN107144303A (en) | A kind of fault detection system of mineral electromechanical equipment, method and device | |
| CN104503399A (en) | Group stage wind power generator set state monitoring and fault diagnosis platform | |
| CN108896299A (en) | A kind of gearbox fault detection method | |
| CN102840979A (en) | Method and device for detecting transmission chain faults of wind turbine generator set | |
| CN111539553A (en) | Wind turbine generator fault early warning method based on SVR algorithm and skewness | |
| CN111946559B (en) | Method for detecting structures of wind turbine foundation and tower | |
| CN107061183A (en) | A kind of automation method for diagnosing faults of offshore wind farm unit | |
| CN107291991A (en) | A kind of Wind turbines early defect method for early warning based on dynamic network mark | |
| CN112061988A (en) | Crane distributed network monitoring and single machine monitoring management system and method | |
| CN103439091A (en) | Method and system for early warning and diagnosing water turbine runner blade crack breakdown | |
| CN111415070A (en) | Wind turbine generator gearbox oil temperature over-temperature fault early warning method based on SCADA data | |
| CN105487530A (en) | Diesel low-exhaust-temperature fault prediction system and method | |
| Helsen et al. | Long-term monitoring of wind farms using big data approach | |
| CN110553821A (en) | Visualized diagnosis method and system for faults of steam turbine generator unit | |
| CN102243135A (en) | Method for diagnosing and analyzing failures of heliostat of tower-type solar power plant |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |