CN112855462A - Early warning method and system for fan equipment - Google Patents
Early warning method and system for fan equipment Download PDFInfo
- Publication number
- CN112855462A CN112855462A CN202011078239.2A CN202011078239A CN112855462A CN 112855462 A CN112855462 A CN 112855462A CN 202011078239 A CN202011078239 A CN 202011078239A CN 112855462 A CN112855462 A CN 112855462A
- Authority
- CN
- China
- Prior art keywords
- fan
- early warning
- time sequence
- bearing
- fault
- 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
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D17/00—Monitoring or testing of wind motors, e.g. diagnostics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Sustainable Development (AREA)
- Sustainable Energy (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- Control Of Positive-Displacement Air Blowers (AREA)
Abstract
The invention relates to a fan device early warning method and a system, wherein the method comprises the following steps: collecting a fan data time sequence; taking the fan data time sequence as input and the fan state as output, and performing model training by a machine learning method to obtain a fan early warning model; and inputting the fan data time sequence to be pre-warned into the fan pre-warning model, and outputting a fan state corresponding to the fan data time sequence to be pre-warned by the fan pre-warning model. According to the invention, the early warning information is output through the fan early warning model, so that the monitoring efficiency of the fan is improved.
Description
Technical Field
The invention relates to the technical field of power generation equipment maintenance, in particular to a fan equipment early warning method and system.
Background
The analysis of the data of the equipment management and maintenance cost of the domestic large-scale power plant in recent ten years and the early warning analysis and processing current situation of the equipment fault are not optimistic, and the production cost is increased to a great extent only by the annual equipment maintenance, maintenance and replacement cost. The fan equipment is the core of the power plant, and the maintenance and repair work of the fan equipment is particularly important. At present, the fan equipment maintenance mode mainly based on manual maintenance in China cannot meet production requirements, and the state maintenance technology cannot achieve normal efficiency in production, so that huge economic loss and over-maintenance of machine equipment are caused.
Disclosure of Invention
Based on the above, the invention aims to provide a fan device early warning method and system, which output early warning information through a fan early warning model and improve the monitoring efficiency of a fan.
In order to achieve the purpose, the invention provides the following scheme:
the invention discloses a fan device early warning method, which comprises the following steps:
collecting a fan data time sequence; the fan data time sequence comprises fan operation data and a fan fault state corresponding to the fan operation data, and the fan state comprises a normal operation state and a fault state;
performing model training by a machine learning method by taking the fan data time sequence as input and the fan state as output to obtain a fan early warning model; the fault condition includes: bearing fault early warning, fan blade fault early warning and motor fault early warning;
and inputting the fan data time sequence to be pre-warned into the fan pre-warning model and outputting a fan state corresponding to the fan data time sequence to be pre-warned.
Optionally, the fan operation data includes a bearing vibration signal, a bearing temperature, a current of the motor, a wind flow speed, a wind flow pressure, an opening degree of a motor valve, and a degree of corrosion of lubricating oil on the bearing.
Optionally, the bearing vibration signal is collected by an acceleration vibration sensor mounted on the bearing.
Optionally, the current, the wind flow speed, the wind flow pressure and the opening of the motor valve of the motor are collected by a safety instrument system connected with the fan.
Optionally, the machine learning method comprises a decision tree, a random forest, a support vector machine and an artificial neural network.
The invention also provides a fan device early warning system, which comprises:
the data acquisition module is used for acquiring a fan data time sequence; the fan data time sequence comprises fan operation data and a fan fault state corresponding to the fan operation data, and the fan state comprises a normal operation state and a fault state;
the fan early warning model training module is used for performing model training by a machine learning method by taking the fan data time sequence as input and the fan state as output to obtain a fan early warning model; the fault condition includes: bearing fault early warning, fan blade fault early warning and motor fault early warning;
and the early warning module is used for inputting the fan data time sequence to be early warned into the fan early warning model and outputting the fan state corresponding to the fan data time sequence to be early warned.
Optionally, the fan operation data includes a bearing vibration signal, a bearing temperature, a current of the motor, a wind flow speed, a wind flow pressure, an opening degree of a motor valve, and a degree of corrosion of lubricating oil on the bearing.
Optionally, the data acquisition module comprises:
and the sensor acquisition unit is used for acquiring the bearing vibration signal through an acceleration vibration sensor arranged on the bearing.
Optionally, the data acquisition module further comprises:
and the safety instrument acquisition unit is used for acquiring the current, the wind flow speed, the wind flow pressure and the opening degree of a motor valve of the motor through a safety instrument system connected with the fan.
Optionally, the machine learning method comprises a decision tree, a random forest, a support vector machine and an artificial neural network.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the invention discloses a fan device early warning method and a system, wherein the method comprises the following steps: collecting a fan data time sequence; performing model training by a machine learning method by taking the fan data time sequence as input and the fan state as output to obtain a fan early warning model; and inputting the fan data time sequence to be pre-warned into the fan pre-warning model, and outputting a fan state corresponding to the fan data time sequence to be pre-warned by the fan pre-warning model. According to the invention, the early warning information is output through the fan early warning model, so that the monitoring efficiency of the fan is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
Fig. 1 is a schematic flow chart of a fan device early warning method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a fan device early warning system according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention aims to provide a fan device early warning method and system, which output early warning information through a fan early warning model and improve the monitoring efficiency of a fan.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Fig. 1 is a schematic flow chart of a fan device early warning method, and the fan device early warning method shown in fig. 1 includes the following steps:
step 101: collecting a fan data time sequence; the fan data time sequence comprises fan operation data and a fan fault state corresponding to the fan operation data, and the fan state comprises a normal operation state and a fault state.
In step 101, the fan operation data includes a bearing vibration signal, a bearing temperature, a current of the motor, a wind flow speed, a wind flow pressure, an opening of a motor valve, and a degree of corrosion of lubricating oil on the bearing. And acquiring the bearing vibration signal through an acceleration vibration sensor arranged on the bearing. The current, the wind flow speed, the wind flow pressure and the opening degree of a motor valve of the motor are collected through a safety instrument system connected with the fan. The corrosion degree of the lubricating oil on the bearing is detected by periodically extracting a lubricating oil sample on the bearing for experiment. Because the fan operates for a long time, the metal can appear droing on the bearing, sneaks into lubricating oil, influences the effect of lubricating oil, and lubricating oil can also influence the effect of lubricating oil along with the change appearance of environment is rotten in addition, and then influences the normal work of bearing.
Step 102: taking the fan data time sequence as input and the fan state as output, and performing model training by a machine learning method to obtain a fan early warning model; the fault condition includes: bearing fault early warning, fan blade fault early warning and motor fault early warning.
In step 102, the method specifically includes: and taking the fan data time sequence at the current moment as input, taking the fan state at the next moment as output, and performing model training by a machine learning method to obtain a fan early warning model.
The machine learning method comprises a decision tree, a random forest, a support vector machine and an artificial neural network. And identifying a characteristic value in a fan data time sequence through the trained fan early warning model, giving a fault early warning, and providing operation and maintenance reference for fan operation.
The fault condition further includes a fault class, the fault class including: minor faults, more severe faults, and severe faults. The fan state of fan early warning model output can be looked over through industry internet aiduration software platform, and when the fan state of fan early warning model output, if the fan state is fault state, the aiduration software platform not only shows specifically which kind of fault state, still shows the fault level that fault state corresponds.
Step 103: and inputting the fan data time sequence to be pre-warned into the fan pre-warning model, and outputting a fan state corresponding to the fan data time sequence to be pre-warned by the fan pre-warning model.
Wherein, in step 103, specifically comprising: and inputting the fan data time sequence to be early-warned into the fan early-warning model and outputting the fan state at the next moment corresponding to the fan data time sequence to be early-warned so as to achieve the purpose of early warning.
Fig. 2 is a schematic structural diagram of a fan device early warning system according to an embodiment of the present invention. As shown in fig. 2, a fan device early warning system includes the following modules:
the data acquisition module 201 is used for acquiring a fan data time sequence; the fan data time sequence comprises fan operation data and a fan fault state corresponding to the fan operation data; the fan state comprises a normal operation state and a fault state.
The fan early warning model training module 202 is used for performing model training by a machine learning method by taking the fan data time sequence as input and the fan state as output to obtain a fan early warning model; the fault condition includes: bearing fault early warning, fan blade fault early warning and motor fault early warning.
And the early warning module 203 is used for inputting the fan data time sequence to be early warned into the fan early warning model and outputting a fan state corresponding to the fan data time sequence to be early warned.
The fan operation data comprises bearing vibration signals, bearing temperature, motor current, airflow speed, airflow pressure, opening degree of a motor valve and corrosion degree of lubricating oil on the bearing.
The data acquisition module 201 includes: and the sensor acquisition unit is used for acquiring the bearing vibration signal through an acceleration vibration sensor arranged on the bearing.
The data acquisition module 201 further includes: and the safety instrument acquisition unit is used for acquiring the current, the wind flow speed, the wind flow pressure and the opening degree of a motor valve of the motor through a safety instrument system connected with the fan.
The machine learning method comprises a decision tree, a random forest, a support vector machine and an artificial neural network.
The invention discloses a fan device early warning method and a system, wherein the method comprises the following steps: collecting a fan data time sequence; taking the fan data time sequence as input and the fan state as output, and performing model training by a machine learning method to obtain a fan early warning model; and inputting the fan data time sequence to be pre-warned into the fan pre-warning model, and outputting a fan state corresponding to the fan data time sequence to be pre-warned by the fan pre-warning model. According to the invention, the early warning information is output through the fan early warning model, the inferior situation of the operation of the fan equipment is found in time, the operation and maintenance suggestion is given, and the monitoring efficiency of the fan is improved.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (10)
1. A fan device early warning method is characterized by comprising the following steps:
collecting a fan data time sequence; the fan data time sequence comprises fan operation data and a fan fault state corresponding to the fan operation data, and the fan state comprises a normal operation state and a fault state;
taking the fan data time sequence as input and the fan state as output, and performing model training by a machine learning method to obtain a fan early warning model; the fault condition includes: bearing fault early warning, fan blade fault early warning and motor fault early warning;
and inputting the fan data time sequence to be pre-warned into the fan pre-warning model and outputting a fan state corresponding to the fan data time sequence to be pre-warned.
2. The fan device pre-warning method according to claim 1, wherein the fan operation data comprises a bearing vibration signal, a bearing temperature, a motor current, a wind flow speed, a wind flow pressure, a motor valve opening degree, and a degree of corrosion of lubricating oil on the bearing.
3. The wind turbine installation warning method of claim 2, wherein the bearing vibration signal is collected by an acceleration vibration sensor mounted on a bearing.
4. The fan device early warning method according to claim 2, wherein the current, the wind flow speed, the wind flow pressure and the opening degree of a motor valve of the motor are collected through a safety instrument system connected with the fan.
5. The wind turbine equipment early warning method according to claim 1, wherein the machine learning method comprises a decision tree, a random forest, a support vector machine and an artificial neural network.
6. A fan equipment warning system, the system comprising:
the data acquisition module is used for acquiring a fan data time sequence; the fan data time sequence comprises fan operation data and a fan fault state corresponding to the fan operation data, and the fan state comprises a normal operation state and a fault state;
the fan early warning model training module is used for performing model training by a machine learning method by taking the fan data time sequence as input and the fan state as output to obtain a fan early warning model; the fault condition includes: bearing fault early warning, fan blade fault early warning and motor fault early warning;
and the early warning module is used for inputting the fan data time sequence to be early warned into the fan early warning model and outputting the fan state corresponding to the fan data time sequence to be early warned.
7. The fan unit warning system of claim 6, wherein the fan operating data comprises a bearing vibration signal, a bearing temperature, a motor current, a wind flow rate, a wind flow pressure, a motor valve opening, and a degree of degradation of a lubricant on the bearing.
8. The wind turbine installation warning system of claim 7, wherein the data acquisition module comprises:
and the sensor acquisition unit is used for acquiring the bearing vibration signal through an acceleration vibration sensor arranged on the bearing.
9. The wind turbine installation warning system of claim 7, wherein the data acquisition module further comprises:
and the safety instrument acquisition unit is used for acquiring the current, the wind flow speed, the wind flow pressure and the opening degree of a motor valve of the motor through a safety instrument system connected with the fan.
10. The wind turbine equipment warning system of claim 6, wherein the machine learning method comprises a decision tree, a random forest, a support vector machine, and an artificial neural network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011078239.2A CN112855462A (en) | 2020-10-10 | 2020-10-10 | Early warning method and system for fan equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011078239.2A CN112855462A (en) | 2020-10-10 | 2020-10-10 | Early warning method and system for fan equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112855462A true CN112855462A (en) | 2021-05-28 |
Family
ID=75995386
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011078239.2A Pending CN112855462A (en) | 2020-10-10 | 2020-10-10 | Early warning method and system for fan equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112855462A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113947223A (en) * | 2021-10-27 | 2022-01-18 | 新疆粤水电能源有限公司 | Intelligent equipment health management system and method |
| CN115238471A (en) * | 2022-06-30 | 2022-10-25 | 华能安源发电有限责任公司 | Fan efficiency online monitoring method and device, electronic equipment and readable medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109269556A (en) * | 2018-09-06 | 2019-01-25 | 深圳市中电数通智慧安全科技股份有限公司 | A kind of equipment Risk method for early warning, device, terminal device and storage medium |
| US20190323922A1 (en) * | 2018-04-19 | 2019-10-24 | Delphisonic, Inc. | Self-learning malfunction monitoring and early warning system |
| CN110735769A (en) * | 2019-09-18 | 2020-01-31 | 西安察柏科技咨询有限公司 | method, device and system for predicting fan faults |
| CN110806743A (en) * | 2019-12-05 | 2020-02-18 | 成都天玙兴科技有限公司 | Equipment fault detection and early warning system and method based on artificial intelligence |
-
2020
- 2020-10-10 CN CN202011078239.2A patent/CN112855462A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190323922A1 (en) * | 2018-04-19 | 2019-10-24 | Delphisonic, Inc. | Self-learning malfunction monitoring and early warning system |
| CN109269556A (en) * | 2018-09-06 | 2019-01-25 | 深圳市中电数通智慧安全科技股份有限公司 | A kind of equipment Risk method for early warning, device, terminal device and storage medium |
| CN110735769A (en) * | 2019-09-18 | 2020-01-31 | 西安察柏科技咨询有限公司 | method, device and system for predicting fan faults |
| CN110806743A (en) * | 2019-12-05 | 2020-02-18 | 成都天玙兴科技有限公司 | Equipment fault detection and early warning system and method based on artificial intelligence |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113947223A (en) * | 2021-10-27 | 2022-01-18 | 新疆粤水电能源有限公司 | Intelligent equipment health management system and method |
| CN115238471A (en) * | 2022-06-30 | 2022-10-25 | 华能安源发电有限责任公司 | Fan efficiency online monitoring method and device, electronic equipment and readable medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kusiak et al. | The prediction and diagnosis of wind turbine faults | |
| CN103019135B (en) | Method and system for predicting service life of fan component | |
| CN106815771B (en) | Long-term assessment method for wind farm load | |
| CN108932580A (en) | Wind turbines pitch variable bearings wear monitoring and method for early warning based on data modeling | |
| CN108072524B (en) | Wind turbine generator gearbox bearing fault early warning method | |
| CN110674842A (en) | Wind turbine generator main shaft bearing fault prediction method | |
| CN103835882A (en) | Large wind generating set state monitoring and fault diagnosis system | |
| CN103234585A (en) | Online monitoring and fault diagnosis system of large wind turbine units | |
| CN202326011U (en) | State-monitoring and fault-diagnosis system of wind-power set | |
| CN103711645A (en) | Wind generating set state evaluation method based on modeling parameter feature analysis | |
| CN107291991A (en) | A kind of Wind turbines early defect method for early warning based on dynamic network mark | |
| CN112855462A (en) | Early warning method and system for fan equipment | |
| CN103925155A (en) | Self-adaptive detection method for abnormal wind turbine output power | |
| CN111415070A (en) | Wind turbine generator gearbox oil temperature over-temperature fault early warning method based on SCADA data | |
| CN114252216A (en) | Method for detecting leakage of lubricating oil of gas turbine | |
| CN112267972A (en) | Intelligent judgment method for abnormity of power curve of wind turbine generator | |
| CN111878322A (en) | Wind power generator device | |
| Kim et al. | Design of wind turbine fault detection system based on performance curve | |
| CN110794683A (en) | Wind power gear box state evaluation method based on deep neural network and kurtosis characteristics | |
| CN114412685B (en) | Bearing temperature analysis and anomaly monitoring method for hydroelectric generating set | |
| CN111396266A (en) | GBRT-based wind turbine generator bearing fault early warning method | |
| CN202453182U (en) | Fault diagnosis device of gearbox of wind generation set | |
| CN114295367B (en) | Wind turbine generator system gear box working condition on-line monitoring method | |
| CN102096770A (en) | Network-based performance degradation assessment method of rotary machine | |
| CN108491622A (en) | A kind of fault diagnosis method and system of Wind turbines |
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: 20210528 |
|
| RJ01 | Rejection of invention patent application after publication |