CN111076962B - Electromechanical equipment fault diagnosis method for intelligent hydraulic power plant - Google Patents
Electromechanical equipment fault diagnosis method for intelligent hydraulic power plant Download PDFInfo
- Publication number
- CN111076962B CN111076962B CN202010003961.3A CN202010003961A CN111076962B CN 111076962 B CN111076962 B CN 111076962B CN 202010003961 A CN202010003961 A CN 202010003961A CN 111076962 B CN111076962 B CN 111076962B
- Authority
- CN
- China
- Prior art keywords
- diagnosis
- fault
- power plant
- hydraulic power
- steps
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M99/00—Subject matter not provided for in other groups of this subclass
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a fault diagnosis method for electromechanical equipment of an intelligent hydraulic power plant, which is called a bidirectional diagnosis method for short. Forward diagnosis, based on the diagnosis direction of the health characteristic model, calling the health characteristic model in the database; and (4) performing reverse diagnosis, and calling a Fault Tree (FTA) model in the database based on the diagnosis direction of the fault rule sample expert knowledge base. And by adopting an internal program algorithm, the functions of fault feature extraction, principal component analysis and mode matching are realized, and the fault diagnosis of the electromechanical equipment is completed. The bidirectional diagnosis method fully utilizes characteristic parameters, measuring point data and an expert knowledge base of the electromechanical equipment to identify and diagnose the state and the fault of the electromechanical equipment, and provides a technical basis for a user to make a maintenance decision. The intelligent hydraulic power plant electromechanical equipment intelligent diagnosis system makes full use of industrial big data, meets the intelligent manufacturing requirement of intelligent hydraulic power plant electromechanical equipment, and has the advantages of intelligent advanced logic reasoning mechanism and high diagnosis accuracy.
Description
Technical Field
The invention relates to a fault diagnosis method for electromechanical equipment of an intelligent hydraulic power plant, and relates to the field of hydroelectric power generation.
Background
The state monitoring system is installed on all hydropower station units of the intelligent hydropower plant, but the traditional state monitoring system lacks an advanced fault diagnosis method, can only give an alarm when the unit fails, has simple alarm logic, and cannot analyze the reason of the failure. With the continuous improvement of the safe and stable operation, standardization and fine management levels of power grids and power stations, the demand of the power stations on intelligent and advanced fault diagnosis methods of electromechanical equipment is more urgent.
Disclosure of Invention
The invention aims to provide an electromechanical equipment fault diagnosis method for an intelligent hydraulic power plant, which fully utilizes characteristic parameters, measuring point data and an expert knowledge base of electromechanical equipment to identify and diagnose the state and the fault of the electromechanical equipment so as to improve the timeliness of alarming and the accuracy of processing. The purpose of the invention is realized by the following technical scheme:
an electromechanical device fault diagnosis method for an intelligent hydraulic power plant is characterized by comprising the following steps: the method comprises the following steps:
1) data V for monitoring points of electromechanical equipment of hydraulic power plant state monitoring systemR；
2) Respectively carrying out forward diagnosis and reverse diagnosis;
the forward diagnosis comprises the following steps:
a-1, a health feature model threshold request of a monitoring point, wherein the threshold comprises VRU、VRDAt least one of, VRUIs an upper threshold value, VRDIs a lower threshold; the health feature model boundary consists of a threshold;
a-2, calculating data V of monitoring pointsRDifference from threshold value, if VR-VRU> 0 or VR-VRDIf the value is less than 0, the numerical value of the monitoring point exceeds the limit, and a data abnormity alarm of forward judgment is sent out; giving confidence D of the forward diagnosisP；
The reverse diagnosis comprises the following steps:
b-1, a fault rule sample criterion formula request, wherein the fault rule sample criterion formula is a fault rule criterion formula which is established by an industry expert through manufacturing service experience summary and is compiled based on a fault tree FTA logic form and on the basis of a function formula unit;
b-2, calling monitoring point data VRSubstituting the fault rule sample criterion formula into the fault rule sample criterion formula, and triggering the fault when the function formula in the criterion is established; confidence D of given inverse diagnosisR；
3) Determining a main diagnosis method and an auxiliary diagnosis method; calling forward diagnostic confidence DPConfidence of the inverse diagnostic method DRWhen D is presentP＞DRWhen the method is a main method, a forward diagnosis method is used as a main method, a reverse diagnosis report is used for auxiliary judgment, and when D is usedR＞DPThen, the reverse diagnosis method is a main method, and the forward diagnosis alarm is used for auxiliary judgment; when D is presentPHas a value of DRWhen the diagnosis is empty, the forward diagnosis method is a diagnosis method; when D is presentRHas a value of DPWhen the diagnosis is empty, the reverse diagnosis method is a diagnosis method; when D is presentRIs empty, DPWhen the state is empty, the diagnosis is not triggered, and the equipment normally operates;
4) processing a diagnosis result; using different treatment schemes, D) depending on the different results of step 3)R＞DPDirectly calling a fault criterion of a fault rule sample, generating a fault diagnosis report, and sending the fault diagnosis report to a user in an alarm mode; dP＞DRAnd sending a comprehensive evaluation report to the user after the evaluation of the artificial experts.
Further, in step A-1, VRUIs an upper threshold value, VRDIs a lower threshold value, VRU、VRDTaken from national or industry standards.
Further, in step A-2, a confidence D is provided based on the numerical offsetP。
Further, in step A-2, DP＝(VR-VRU) Z or (V)RD-VR) And Z is an experience value which is manually written, and the experience value is combined with relevant parameter industry standards and the actual operation condition of the hydropower station.
Further, in step B-2, DRThe criterion formula is the number of established criterion/total number of criterion formula.
The electromechanical equipment fault diagnosis method for the intelligent hydraulic power plant realizes bidirectional diagnosis, is different from the conventional unidirectional diagnosis method, carries out bidirectional reasoning from forward direction and reverse direction in diagnosis by the bidirectional diagnosis method, verifies each other, is closer to the diagnosis idea of human brain, has high diagnosis accuracy, and is a diagnosis method advanced to the industry.
The invention can perform bidirectional diagnosis at the same time, and cross-verify each other, thereby not only improving the timeliness of alarming, but also ensuring the accuracy of diagnosis and fault processing.
Moreover, by conveying cases during reverse diagnosis, fault cases are accumulated, the system can continuously optimize fault rule samples in a conditional mode, fault judgment criteria and function formulas are enriched, and more comprehensive and reliable operation and maintenance suggestions of the electromechanical equipment are provided for users. Meanwhile, for unknown faults, new fault mining is realized through expert approval of abnormal data.
Drawings
Fig. 1 is a schematic diagram of a fault diagnosis method for electromechanical equipment of an intelligent hydraulic power plant.
Fig. 2 is a fault report diagram of bidirectional diagnosis results of a certain electromechanical device.
Detailed Description
The specific implementation mode of the invention is explained by taking the 'failure of the upper guide bearing' of the No. 2 unit of the 200MW hydro-generator as an example. According to the schematic diagram shown in fig. 1, the specific implementation is as follows:
1) and calling monitoring point data of the electromechanical equipment. The hydropower station state monitoring system acquires and stores data of temperature, pressure, vibration and the like of electromechanical equipment through various sensors, and calls the data of the hydropower station state monitoring system through a data interface, such as the swing peak and the peak of a pilot bearing at a certain timeValue V1277 mu m, lower guide bearing swing peak value V2150 μm peak value V of water guide bearing swing3155 mu m, and the frequency multiplication ratio R of the swing degree 1 of the upper guide bearing is 92%.
2) The forward and reverse diagnoses were performed in parallel. Wherein, the forward diagnosis comprises the following steps:
2A-1) health feature model threshold request. The boundary of the health characteristic model consists of threshold values, and according to the national standard GB/T11348-5, the upper limit threshold value V of the upper lead swing range peak value of the unitRU270 μm. The forward diagnosis method requests an upper limit threshold V of the peak value of the lead swing degree from a system databaseRU。
2A-2) forward diagnosis, giving confidence. Forward diagnostic method invocation V1Calculate V277 μm1-VRU277 and 270 are larger than 0, the numerical value of the monitoring point exceeds the limit, the forward diagnosis method sends out a data abnormity alarm, Z is 10 according to the empirical value (according to the empirical method, the new power station Z is 10, the old power station Z is 15), and confidence D is providedP＝(V1-VRU)/Z＝(277-270)/10＝0.7。
The reverse diagnosis comprises the following steps:
2B-1) a fault rule sample criterion request. According to a fault rule sample expert knowledge base, the 'failure cause of upper guide bearing' is 'the upper end shaft of the generator is not concentric with the rotor central body', and a criterion formula is as follows:
equation one: the frequency multiplication ratio of the swing degree 1 of the upper guide bearing is more than 90 percent;
equation two: the upper lead swing peak value > the lower lead swing peak value;
equation three: and the upper lead swing peak value is greater than the water lead swing peak value.
The reverse diagnostic method requests the above criterion formula from the system database.
2B-1) inverse diagnosis, giving confidence. The reverse diagnosis method requests the pendulum peak value V of the upper guide bearing1277 mu m, lower guide bearing swing peak value V2150 μm peak value V of water guide bearing swing3And substituting the frequency multiplication ratio R of 155 mu m and the swing 1 of the upper guide bearing into 92 percent into a fault rule criterion formula:
equation one: the frequency multiplication ratio R of the swing degree 1 of the upper guide bearing is 92 percent and accounts for more than 90 percent; the formula is established;
equation two: the peak value of the upper lead swing degree is 277 mu m and the peak value of the lower lead swing degree is 150 mu m; the formula is established;
equation three: the peak value of the upper lead swing degree peak is 277 mu m and is more than the peak value of the water lead swing degree peak is 155 mu m; the formula is established; .
The function formulas in the three criteria are all established, the fault is triggered, and the confidence coefficient D is providedR＝3/3＝1。
3) And determining a main diagnosis method and an auxiliary diagnosis method. Calling forward diagnostic confidence DP0.7, confidence of inverse diagnostic method DR＝1，DR＞DPThe reverse diagnosis method is the main method, and the forward diagnosis method is used for auxiliary judgment.
4) And (6) processing the diagnosis result. The two-way diagnostic method uses different processing schemes depending on the different results of 3). DR＞DPMeanwhile, the bidirectional diagnosis method directly calls a fault criterion, generates a fault report as shown in the attached figure 2, and sends the fault report to a user in an alarm mode.
The above description is only an embodiment of the present invention, and the technical features of the present invention are not limited thereto, and any changes or modifications within the field of the present invention by those skilled in the relevant art are covered by the protection scope of the present invention.
Claims (6)
1. An electromechanical device fault diagnosis method for an intelligent hydraulic power plant is characterized by comprising the following steps: the method comprises the following steps:
1) data V for monitoring points of electromechanical equipment of hydraulic power plant state monitoring systemR,VRThe unit is um;
2) respectively carrying out forward diagnosis and reverse diagnosis;
the forward diagnosis comprises the following steps:
a-1, a health feature model threshold request of a monitoring point, wherein the threshold comprises VRU、VRDAt least one of, VRUIs an upper threshold value, VRDIs a lower threshold; health feature model boundaryConsisting of a threshold value, VRUUnit is um, VRDThe unit is um;
a-2, calculating data V of monitoring pointsRDifference from threshold value, if VR-VRU> 0um or VR-VRDIf the value is less than 0um, the numerical value of the monitoring point exceeds the limit, and a data abnormity alarm of forward judgment is sent out; giving confidence D of the forward diagnosisP；
The reverse diagnosis comprises the following steps:
b-1, a fault rule sample criterion formula request, wherein the fault rule sample criterion formula is a fault rule criterion formula which is established by an industry expert through manufacturing service experience summary and is compiled based on a fault tree FTA logic form and on the basis of a function formula unit;
b-2, calling monitoring point data VRSubstituting the fault rule sample criterion formula into the fault rule sample criterion formula, and triggering the fault when the function formula in the criterion is established; confidence D of given inverse diagnosisR；
3) Determining a main diagnosis method and an auxiliary diagnosis method; calling forward diagnostic confidence DPConfidence of the inverse diagnostic method DRWhen D is presentP＞DRWhen the method is a main method, a forward diagnosis method is used as a main method, a reverse diagnosis report is used for auxiliary judgment, and when D is usedR＞DPThen, the reverse diagnosis method is a main method, and the forward diagnosis alarm is used for auxiliary judgment; when D is presentPHas a value of DRWhen the diagnosis is empty, the forward diagnosis method is a diagnosis method; when D is presentRHas a value of DPWhen the diagnosis is empty, the reverse diagnosis method is a diagnosis method; when D is presentRIs empty, DPWhen the state is empty, the diagnosis is not triggered, and the equipment normally operates;
4) processing a diagnosis result; using different treatment schemes, D) depending on the different results of step 3)R＞DPDirectly calling a fault criterion of a fault rule sample, generating a fault diagnosis report, and sending the fault diagnosis report to a user in an alarm mode; dP＞DRAnd sending a comprehensive evaluation report to the user after the evaluation of the artificial experts.
2. A process as claimed in claim 1An electromechanical device fault diagnosis method for an intelligent hydraulic power plant is characterized by comprising the following steps: in step A-1, VRUIs an upper threshold value, VRDIs a lower threshold value, VRU、VRDTaken from national or industry standards.
3. The method for diagnosing the faults of the electromechanical devices oriented to the intelligent hydraulic power plant as claimed in claim 1, wherein the method comprises the following steps: in step A-2, a confidence D is provided based on the numerical offsetP。
4. The method for diagnosing the faults of the electromechanical devices oriented to the intelligent hydraulic power plant as claimed in claim 3, wherein the method comprises the following steps: in step A-2, DP＝(VR-VRU) Z or (V)RD-VR) Z, wherein Z is an artificially written empirical value and the unit of Z is um.
5. The method for diagnosing the faults of the electromechanical devices oriented to the intelligent hydraulic power plant as claimed in claim 1, wherein the method comprises the following steps: in step B-2, DRThe criterion formula is the number of established criterion/total number of criterion formula.
6. The method for diagnosing the faults of the electromechanical devices oriented to the intelligent hydraulic power plant as claimed in claim 1, wherein the method comprises the following steps: and (5) repeating the steps 1) to 4), and performing fault diagnosis on each monitoring point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010003961.3A CN111076962B (en) | 2020-01-03 | 2020-01-03 | Electromechanical equipment fault diagnosis method for intelligent hydraulic power plant |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010003961.3A CN111076962B (en) | 2020-01-03 | 2020-01-03 | Electromechanical equipment fault diagnosis method for intelligent hydraulic power plant |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111076962A CN111076962A (en) | 2020-04-28 |
| CN111076962B true CN111076962B (en) | 2022-03-29 |
Family
ID=70321747
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010003961.3A Active CN111076962B (en) | 2020-01-03 | 2020-01-03 | Electromechanical equipment fault diagnosis method for intelligent hydraulic power plant |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111076962B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117009828B (en) * | 2023-09-28 | 2023-12-12 | 中国长江电力股份有限公司 | Hydropower equipment fault diagnosis method based on fault matching algorithm |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5081629A (en) * | 1989-05-08 | 1992-01-14 | Unisys Corporation | Fault isolation for multiphase clock signals supplied to dual modules which are checked by comparison using residue code generators |
| US8417432B2 (en) * | 2008-04-30 | 2013-04-09 | United Technologies Corporation | Method for calculating confidence on prediction in fault diagnosis systems |
| CN105372557A (en) * | 2015-12-03 | 2016-03-02 | 国家电网公司 | Power grid resource fault diagnosis method based on association rules |
| CN107727392A (en) * | 2017-10-12 | 2018-02-23 | 中国人民解放军国防科技大学 | State index evaluation and optimization method based on signal detection and ROC analysis |
| CN108181105A (en) * | 2017-11-28 | 2018-06-19 | 杭州安脉盛智能技术有限公司 | Logic-based returns and the rolling bearing fault of J divergences examines method and system in advance |
| CN108458885A (en) * | 2017-11-30 | 2018-08-28 | 镇江赛尔尼柯自动化有限公司 | Ship Remote Fault Diagnosis and Decision-making support system |
| CN109117353A (en) * | 2018-08-20 | 2019-01-01 | 中国石油大学(北京) | The fusion method and device of fault diagnosis result |
| CN109919495A (en) * | 2019-03-12 | 2019-06-21 | 中国计量大学 | Photovoltaic plant monitoring data exception and degree judgment method based on threshold calculations |
| CN110274762A (en) * | 2019-07-16 | 2019-09-24 | 贵州北盘江电力股份有限公司董箐分公司 | A kind of turbine guide bearing fault diagnosis system based on big data |
| CN110579709A (en) * | 2019-08-30 | 2019-12-17 | 西南交通大学 | fault diagnosis method for proton exchange membrane fuel cell for tramcar |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107168285B (en) * | 2017-05-26 | 2019-04-09 | 大连理工大学 | A kind of automobile intelligent fault diagnosis and maintenance householder method and system |
| CN109612173A (en) * | 2018-11-15 | 2019-04-12 | 南京航空航天大学 | A kind of assessment of fault and diagnostic method of vapor cycle refrigeration system |
-
2020
- 2020-01-03 CN CN202010003961.3A patent/CN111076962B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5081629A (en) * | 1989-05-08 | 1992-01-14 | Unisys Corporation | Fault isolation for multiphase clock signals supplied to dual modules which are checked by comparison using residue code generators |
| US8417432B2 (en) * | 2008-04-30 | 2013-04-09 | United Technologies Corporation | Method for calculating confidence on prediction in fault diagnosis systems |
| CN105372557A (en) * | 2015-12-03 | 2016-03-02 | 国家电网公司 | Power grid resource fault diagnosis method based on association rules |
| CN107727392A (en) * | 2017-10-12 | 2018-02-23 | 中国人民解放军国防科技大学 | State index evaluation and optimization method based on signal detection and ROC analysis |
| CN108181105A (en) * | 2017-11-28 | 2018-06-19 | 杭州安脉盛智能技术有限公司 | Logic-based returns and the rolling bearing fault of J divergences examines method and system in advance |
| CN108458885A (en) * | 2017-11-30 | 2018-08-28 | 镇江赛尔尼柯自动化有限公司 | Ship Remote Fault Diagnosis and Decision-making support system |
| CN109117353A (en) * | 2018-08-20 | 2019-01-01 | 中国石油大学(北京) | The fusion method and device of fault diagnosis result |
| CN109919495A (en) * | 2019-03-12 | 2019-06-21 | 中国计量大学 | Photovoltaic plant monitoring data exception and degree judgment method based on threshold calculations |
| CN110274762A (en) * | 2019-07-16 | 2019-09-24 | 贵州北盘江电力股份有限公司董箐分公司 | A kind of turbine guide bearing fault diagnosis system based on big data |
| CN110579709A (en) * | 2019-08-30 | 2019-12-17 | 西南交通大学 | fault diagnosis method for proton exchange membrane fuel cell for tramcar |
Non-Patent Citations (2)
| Title |
|---|
| "水轮发电机组故障诊断及预测与状态评估方法研究";朱文龙;《中国博士学位论文全文数据库 工程科技Ⅱ辑》;20170830;全文 * |
| "风力机健康状态监测及评估关键技术研究";王双园;《中国博士学位论文全文数据库 工程科技Ⅱ辑》;20190930;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111076962A (en) | 2020-04-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110766277B (en) | Health assessment and diagnosis system and mobile terminal for nuclear industry field | |
| CN110866314A (en) | Method for predicting residual life of rotating machinery of multilayer bidirectional gate control circulation unit network | |
| CN112834211A (en) | Fault early warning method for transmission system of wind turbine generator | |
| CN104573850A (en) | Method for evaluating state of thermal power plant equipment | |
| CN109583386A (en) | A kind of intelligent rotating mechanical breakdown depth network characterization discrimination method | |
| CN110672332B (en) | Gas turbine fault early warning system based on SARIMA model | |
| CN110046409B (en) | ResNet-based steam turbine component health state evaluation method | |
| CN110513336B (en) | Method for determining offline water washing time of gas turbine of power station | |
| CN105547730A (en) | Fault detection system of water-wheel generator set | |
| CN103278728A (en) | Method and system for diagnosing interturn short circuit fault of generator rotor | |
| CN104976139A (en) | Mechanical equipment state diagnosis method based on Gaussian model | |
| CN111076962B (en) | Electromechanical equipment fault diagnosis method for intelligent hydraulic power plant | |
| CN115453267A (en) | Fault diagnosis system for electric power information system | |
| CN111664083A (en) | Nuclear power main pump fault diagnosis method based on Bayesian network | |
| CN107103425B (en) | Intelligent energy evaluation system for power generation equipment running state computer | |
| CN106126875A (en) | A kind of Transformer condition evaluation theoretical based on Situation Awareness | |
| WO2023273378A1 (en) | Bolt fault diagnosis method and apparatus | |
| CN109613372B (en) | Power grid fault diagnosis method based on multi-element power grid database | |
| CN113987817A (en) | Degradation analysis method for power generation equipment of hydraulic power plant | |
| CN116910680B (en) | Remote fault detection method and system for fitness equipment | |
| CN109409758B (en) | Hydropower station equipment health state evaluation method and system | |
| CN107274112B (en) | Diagnostic algorithm model for improving dissolved gas in oil | |
| CN115982578A (en) | Fault positioning method and device, electronic equipment and storage medium | |
| CN116050613A (en) | Method for predicting residual service life of top cover drainage pump of hydroelectric generating set | |
| CN114417704A (en) | Wind turbine generator health assessment method based on improved stack type self-coding |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |