CN110345463A - A kind of boiler incipient fault recognition methods and device - Google Patents
A kind of boiler incipient fault recognition methods and device Download PDFInfo
- Publication number
- CN110345463A CN110345463A CN201910547774.9A CN201910547774A CN110345463A CN 110345463 A CN110345463 A CN 110345463A CN 201910547774 A CN201910547774 A CN 201910547774A CN 110345463 A CN110345463 A CN 110345463A
- Authority
- CN
- China
- Prior art keywords
- boiler
- operating parameter
- incipient fault
- change value
- sample
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F22—STEAM GENERATION
- F22B—METHODS OF STEAM GENERATION; STEAM BOILERS
- F22B35/00—Control systems for steam boilers
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Physics & Mathematics (AREA)
- Thermal Sciences (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Regulation And Control Of Combustion (AREA)
- Control Of Steam Boilers And Waste-Gas Boilers (AREA)
Abstract
The invention discloses a kind of boiler incipient fault recognition methods and identification device, recognition methods includes initializing and completing the training operation of decision tree classifier；The operating parameter of acquisition boiler in real time；Calculate the variation tendency of each operating parameter；Calculate the early warning range of each operating parameter and its corresponding rate of change value；Judge each operating parameter whether in early warning range；Each operating parameter and corresponding rate of change value are formed into a sample to be tested data；The sample to be tested data are input in plan Tree Classifier, the incipient fault type of the decision tree classifier output boiler.The real time execution parameter that the present invention passes through boiler collected, calculate the rate of change value of each operating parameter, simultaneously according to operating parameter and its rate of change value, first determine whether that its data itself whether there is exception, the incipient fault in boiler running process finally is judged using Decision Classfication device, and the failure risk in boiler running process is effectively reduced.
Description
Technical field
The present invention relates to intelligent identification technology field, more specifically to a kind of boiler incipient fault recognition methods and
Device.
Background technique
Boiler is energy conversion device common in a kind of daily life, and it is suitable for the every aspects in life, such as
Heating, power generation etc..Boiler is that a kind of waste heat using in the thermal energy discharged after fuel combustion or industrial production passes in container
Water, the heat power equipment of temperature or certain pressure steam required for reaching water.Boiler " pot " and " furnace " two parts simultaneously
It carries out, water enters after boiler, and the heat transfer water supply of absorption is heated into water centainly by boiler heating surface in boiler circuit
The hot water of temperature and pressure generates steam, is brought out application.In combustion apparatus part, heat is constantly released in fuel combustion, combustion
Burn the high-temperature flue gas generated by the propagation of heat, transfer heat to boiler heating surface, and self-temperature gradually decreases, finally by
Chimney discharge.
Existing boiler plant generally passes through multiple sensors being mounted on boiler different location and detects boiler
Real time execution parameter, and detect whether boiler breaks down in real time by the operating parameter of boiler, although this detection scheme
It is out of order although can detect in time, also means that failure has occurred that when failure is detected, therefore or
More or few damage that can all cause equipment, to cause economic loss.There is no configurations correspondingly, right for i.e. existing boiler plant
Its incipient fault carries out the function of identification prediction, causes existing boiler plant failure risk higher.
Summary of the invention
The technical problem to be solved by the present invention is providing a kind of boiler incipient fault recognition methods and device, mainly
For boiler for power generation system.
The solution that the present invention solves its technical problem is:
A kind of boiler incipient fault recognition methods, comprising the following steps:
Step 100, decision tree classifier is initialized, multiple groups training sample data is inputted, completes the instruction of decision tree classifier
It drills work；
Step 200, multiple operating parameters of boiler are acquired in real time；
Step 300, the variation tendency for calculating separately each operating parameter obtains change rate corresponding to each operating parameter
Value；
Step 400, according to the control parameter of input, the pre- of each operating parameter and its corresponding rate of change value is calculated separately
Alert range；
Step 500, each operating parameter is judged respectively whether in early warning range, if so, output pre-warning signal；
Step 600, each operating parameter and corresponding rate of change value are formed into a sample to be tested data；
Step 700, the sample to be tested data are input in plan Tree Classifier, the decision tree classifier exports boiler
Incipient fault type.
As a further improvement of the above technical scheme, step 700 is replaced by step 800, Bayes classifier is set,
The sample to be tested data are input in Bayes classifier, the incipient fault type of the Bayes classifier output boiler
Probability of happening.
As a further improvement of the above technical scheme, the operating parameter includes in-furnace temperature, air pressure, combustion chamber in furnace
Temperature, combustion chamber air pressure, pressure fan revolving speed, generator speed and output electrical parameter.
It as a further improvement of the above technical scheme, include initializing and training neural network model, root in step 400
According to the control parameter of input, the neural network model calculates separately the early warning of each operating parameter and its corresponding rate of change value
Range.
The present invention discloses a kind of boiler incipient fault identification devices, comprising:
Decision tree classifier generation module for initializing decision tree classifier, and completes the instruction of decision tree classifier
It drills work；
Sensor module, for acquiring multiple operating parameters of boiler in real time；
It is right to obtain each operating parameter institute for calculating separately the variation tendency of each operating parameter for first computing module
The rate of change value answered；
Second computing module calculates separately each operating parameter and its corresponding change for the control parameter according to input
The early warning range of rate value；
Judgment module, for judging each operating parameter respectively whether in early warning range, if so, output early warning letter
Number；
Sample generation module, for each operating parameter and corresponding rate of change value to be formed a number of awaiting test sample
According to；
First warning module for the sample to be tested data to be input in plan Tree Classifier, and exports the latent of boiler
In fault type.
As a further improvement of the above technical scheme, identification device further includes the second warning module, second early warning
Module substitutes the first warning module, and second warning module is for being arranged Bayes classifier, and by the number of awaiting test sample
According to being input in Bayes classifier, Bayes classifier exports the probability of happening of the incipient fault type of boiler.
As a further improvement of the above technical scheme, the sensor module include temperature sensor, pressure sensor,
Encoder, voltage transformer and current transformer.
As a further improvement of the above technical scheme, it in second computing module, including initializes and trains nerve
Network model, according to the control parameter of input, the neural network model calculates separately each operating parameter and its corresponding change
The early warning range of rate value.
The beneficial effects of the present invention are: the present invention calculates each operation by the real time execution parameter of boiler collected
The rate of change value of parameter, while according to operating parameter and its rate of change value, first determine whether that its data itself whether there is exception, most
The incipient fault in boiler running process is judged using Decision Classfication device afterwards, and the failure wind in boiler running process is effectively reduced
Danger.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described.Obviously, described attached drawing is a part of the embodiments of the present invention, rather than is all implemented
Example, those skilled in the art without creative efforts, can also be obtained according to these attached drawings other designs
Scheme and attached drawing.
Fig. 1 is method flow schematic diagram of the invention.
Specific embodiment
It is carried out below with reference to technical effect of the embodiment and attached drawing to design of the invention, specific structure and generation clear
Chu, complete description, to be completely understood by the purpose of the present invention, feature and effect.Obviously, described embodiment is this Shen
A part of the embodiment please, rather than whole embodiments, are based on embodiments herein, and those skilled in the art is not paying
Other embodiments obtained under the premise of creative work belong to the range of the application protection.In addition, be previously mentioned in text
All connection relationships not singly refer to that component directly connects, and referring to can be according to specific implementation situation, by adding or reducing connection
Auxiliary, Lai Zucheng more preferably connection structure.Each technical characteristic in the invention, under the premise of not conflicting conflict
It can be with combination of interactions.Finally, it should be noted that such as term in text " center, upper and lower, left and right, vertical, horizontal, inside and outside "
The orientation or positional relationship of instruction is then to be based on the orientation or positional relationship shown in the drawings, and is merely for convenience of description this technology side
Case and simplified description, rather than the device or element of indication or suggestion meaning must have a particular orientation, with specific orientation
Construction and operation, therefore should not be understood as the limitation to the application.
Referring to Fig.1, this application discloses a kind of boiler incipient fault recognition methods, it is mainly used in boiler for power generation system
Occasion, first embodiment the following steps are included:
Step 100, decision tree classifier is initialized, multiple groups training sample data is inputted, completes the instruction of decision tree classifier
It drills work；
Step 200, multiple operating parameters of boiler are acquired in real time；
Step 300, the variation tendency for calculating separately each operating parameter obtains change rate corresponding to each operating parameter
Value；
Step 400, according to the control parameter of input, the pre- of each operating parameter and its corresponding rate of change value is calculated separately
Alert range；
Step 500, each operating parameter is judged respectively whether in early warning range, if so, output pre-warning signal；
Step 600, each operating parameter and corresponding rate of change value are formed into a sample to be tested data；
Step 700, the sample to be tested data are input in plan Tree Classifier, the decision tree classifier exports boiler
Incipient fault type.
Specifically, the change of each operating parameter is calculated by the real time execution parameter of boiler collected in the present embodiment
Rate value, while according to operating parameter and its rate of change value, first determines whether that its data itself whether there is exception, finally using determining
Plan classifier judges the incipient fault in boiler running process, and the failure risk in boiler running process is effectively reduced.
It is further used as preferred embodiment, in the present embodiment, the operating parameter includes in-furnace temperature, gas in furnace
Pressure, chamber temperature, combustion chamber air pressure, pressure fan revolving speed, generator speed and output electrical parameter.Specifically, the present embodiment
Mainly pass through in-furnace temperature, air pressure in furnace, chamber temperature, combustion chamber air pressure, pressure fan revolving speed, generator speed and defeated
Rate of change value corresponding to electrical parameter and parameters identifies the failure or incipient fault of boiler out.
It is further used as preferred embodiment, includes initializing and training neural network in the present embodiment, in step 400
Model, according to the control parameter of input, the neural network model calculates separately each operating parameter and its corresponding change rate
The early warning range of value.Specifically, the present embodiment is to calculate each operating parameter and its corresponding variation using neural network model
The early warning range of rate value, based on a large amount of data in boiler normal course of operation operating parameter and its rate of change value unite
Meter can effectively improve the accuracy in computation of the early warning range of each operating parameter and its corresponding rate of change value, guarantee pot
Safety when furnace is run.
The second embodiment of herein described recognition methods, difference is to substitute step 700 compared with first embodiment
For step 800, Bayes classifier is set, the sample to be tested data are input in Bayes classifier, the Bayes
Classifier exports the probability of happening of the incipient fault type of boiler.In the second embodiment of recognition methods, Bayes's classification is utilized
Device can accurately judge the probability of happening of the incipient fault type of boiler, this is function not available for decision tree classifier
Can, the present embodiment is capable of providing the probability of happening of incipient fault, and relevant staff can be according to the probability of happening of incipient fault
Judge whether to need to take corresponding emergency measure.
The application also discloses a kind of boiler incipient fault identification device, first embodiment simultaneously, comprising:
Decision tree classifier generation module for initializing decision tree classifier, and completes the instruction of decision tree classifier
It drills work；
Sensor module, for acquiring multiple operating parameters of boiler in real time；
It is right to obtain each operating parameter institute for calculating separately the variation tendency of each operating parameter for first computing module
The rate of change value answered；
Second computing module calculates separately each operating parameter and its corresponding change for the control parameter according to input
The early warning range of rate value；
Judgment module, for judging each operating parameter respectively whether in early warning range, if so, output early warning letter
Number；
Sample generation module, for each operating parameter and corresponding rate of change value to be formed a number of awaiting test sample
According to；
First warning module for the sample to be tested data to be input in plan Tree Classifier, and exports the latent of boiler
In fault type.
It is further used as preferred embodiment, in the present embodiment, the sensor module includes temperature sensor, pressure
Sensor, encoder, voltage transformer and current transformer.Wherein the temperature sensor for detect in-furnace temperature and
Chamber temperature, the pressure sensor are sent for detecting air pressure and combustion chamber air pressure in furnace, the encoder for detecting
Rotation speed of fan and generator speed, the voltage transformer and current transformer are for detecting generator output electrical parameter.
It is further used as preferred embodiment, in the present embodiment, in second computing module, including initializes and instruct
Practice neural network model, according to the control parameter of input, the neural network model calculates separately each operating parameter and its right
The early warning range for the rate of change value answered.
The second embodiment of herein described boiler incipient fault identification device, compared with first embodiment, difference exists
It further include the second warning module in the identification device, second warning module substitutes the first warning module, and described second is pre-
The sample to be tested data are input in Bayes classifier by alert module for Bayes classifier to be arranged, Bayes point
Class device exports the probability of happening of the incipient fault type of boiler.
The better embodiment of the application is illustrated above, but the application is not limited to the specific embodiments,
Those skilled in the art can also make various equivalent modifications or replacement on the premise of without prejudice to spirit of the invention, this
Equivalent variation or replacement are all included in the scope defined by the claims of the present application a bit.
Claims (8)
1. a kind of boiler incipient fault recognition methods, which comprises the following steps:
Step 100, decision tree classifier is initialized, multiple groups training sample data are inputted, completes the training behaviour of decision tree classifier
Make；
Step 200, multiple operating parameters of boiler are acquired in real time；
Step 300, the variation tendency for calculating separately each operating parameter obtains rate of change value corresponding to each operating parameter；
Step 400, according to the control parameter of input, the early warning model of each operating parameter and its corresponding rate of change value is calculated separately
It encloses；
Step 500, each operating parameter is judged respectively whether in early warning range, if so, output pre-warning signal；
Step 600, each operating parameter and corresponding rate of change value are formed into a sample to be tested data；
Step 700, the sample to be tested data are input in plan Tree Classifier, the decision tree classifier output boiler is dived
In fault type.
2. a kind of boiler incipient fault recognition methods according to claim 1, which is characterized in that step 700 to be replaced by
Step 800, Bayes classifier is set, the sample to be tested data are input in Bayes classifier, the Bayes point
Class device exports the probability of happening of the incipient fault type of boiler.
3. a kind of boiler incipient fault recognition methods according to claim 2, which is characterized in that the operating parameter includes
Air pressure, chamber temperature, combustion chamber air pressure, pressure fan revolving speed, generator speed and output electrical parameter in in-furnace temperature, furnace.
4. a kind of boiler incipient fault recognition methods according to claim 3, which is characterized in that include just in step 400
Beginningization and training neural network model, according to the control parameter of input, the neural network model calculates separately each operation ginseng
The early warning range of several and its corresponding rate of change value.
5. a kind of boiler incipient fault identification device characterized by comprising
Decision tree classifier generation module for initializing decision tree classifier, and completes the training behaviour of decision tree classifier
Make；
Sensor module, for acquiring multiple operating parameters of boiler in real time；
First computing module obtains corresponding to each operating parameter for calculating separately the variation tendency of each operating parameter
Rate of change value；
Second computing module calculates separately each operating parameter and its corresponding change rate for the control parameter according to input
The early warning range of value；
Judgment module, for judging each operating parameter respectively whether in early warning range, if so, output pre-warning signal；
Sample generation module, for each operating parameter and corresponding rate of change value to be formed a sample to be tested data；
First warning module for the sample to be tested data to be input in plan Tree Classifier, and exports the potential event of boiler
Hinder type.
6. a kind of boiler incipient fault identification device according to claim 5, which is characterized in that further include the second early warning mould
Block, second warning module substitute the first warning module, and second warning module is used to be arranged Bayes classifier, and will
The sample to be tested data are input in Bayes classifier, and Bayes classifier exports the generation of the incipient fault type of boiler
Probability.
7. a kind of boiler incipient fault identification device according to claim 6, which is characterized in that the sensor module packet
Include temperature sensor, pressure sensor, encoder, voltage transformer and current transformer.
8. a kind of boiler incipient fault identification device according to claim 7, which is characterized in that second computing module
In, including neural network model is initialized and trains, according to the control parameter of input, the neural network model is calculated separately respectively
The early warning range of a operating parameter and its corresponding rate of change value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910547774.9A CN110345463A (en) | 2019-06-24 | 2019-06-24 | A kind of boiler incipient fault recognition methods and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910547774.9A CN110345463A (en) | 2019-06-24 | 2019-06-24 | A kind of boiler incipient fault recognition methods and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110345463A true CN110345463A (en) | 2019-10-18 |
Family
ID=68182835
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910547774.9A Pending CN110345463A (en) | 2019-06-24 | 2019-06-24 | A kind of boiler incipient fault recognition methods and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110345463A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110579675A (en) * | 2019-10-30 | 2019-12-17 | 国投云顶湄洲湾电力有限公司 | Load short circuit identification method, device, equipment and storage medium |
| CN111998690A (en) * | 2020-08-24 | 2020-11-27 | 中国测试技术研究院 | Fault alarm method for smoke exhaust fan of low-temperature kiln |
| CN112215503A (en) * | 2020-10-19 | 2021-01-12 | 青岛鹏海软件有限公司 | Reliability monitoring method based on SPC |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102331772A (en) * | 2011-03-30 | 2012-01-25 | 浙江省电力试验研究院 | Method for carrying out early warning of abnormal superheated steam temperature and fault diagnosis on direct current megawatt unit |
| CN104037103A (en) * | 2013-03-04 | 2014-09-10 | 阿自倍尔株式会社 | Fault Detecting System And Fault Detecting Method |
| CN105974793A (en) * | 2016-05-04 | 2016-09-28 | 华中科技大学 | Power plant boiler combustion intelligent control method |
| CN108133326A (en) * | 2017-12-22 | 2018-06-08 | 华润电力（菏泽）有限公司 | A kind of status early warning method and system based on thermal power generating equipment |
| CN108932531A (en) * | 2018-07-09 | 2018-12-04 | 朱卫列 | Equipment state on-line checking algorithm based on model feature value |
| CN109635873A (en) * | 2018-12-19 | 2019-04-16 | 佛山科学技术学院 | A kind of UPS failure prediction method |
-
2019
- 2019-06-24 CN CN201910547774.9A patent/CN110345463A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102331772A (en) * | 2011-03-30 | 2012-01-25 | 浙江省电力试验研究院 | Method for carrying out early warning of abnormal superheated steam temperature and fault diagnosis on direct current megawatt unit |
| CN104037103A (en) * | 2013-03-04 | 2014-09-10 | 阿自倍尔株式会社 | Fault Detecting System And Fault Detecting Method |
| CN105974793A (en) * | 2016-05-04 | 2016-09-28 | 华中科技大学 | Power plant boiler combustion intelligent control method |
| CN108133326A (en) * | 2017-12-22 | 2018-06-08 | 华润电力（菏泽）有限公司 | A kind of status early warning method and system based on thermal power generating equipment |
| CN108932531A (en) * | 2018-07-09 | 2018-12-04 | 朱卫列 | Equipment state on-line checking algorithm based on model feature value |
| CN109635873A (en) * | 2018-12-19 | 2019-04-16 | 佛山科学技术学院 | A kind of UPS failure prediction method |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110579675A (en) * | 2019-10-30 | 2019-12-17 | 国投云顶湄洲湾电力有限公司 | Load short circuit identification method, device, equipment and storage medium |
| CN110579675B (en) * | 2019-10-30 | 2022-03-01 | 国投云顶湄洲湾电力有限公司 | Load short circuit identification method, device, equipment and storage medium |
| CN111998690A (en) * | 2020-08-24 | 2020-11-27 | 中国测试技术研究院 | Fault alarm method for smoke exhaust fan of low-temperature kiln |
| CN111998690B (en) * | 2020-08-24 | 2021-05-25 | 中国测试技术研究院 | Fault alarm method for smoke exhaust fan of low-temperature kiln |
| CN112215503A (en) * | 2020-10-19 | 2021-01-12 | 青岛鹏海软件有限公司 | Reliability monitoring method based on SPC |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110345463A (en) | A kind of boiler incipient fault recognition methods and device | |
| CN112200433B (en) | Power plant thermal performance analysis and optimization system | |
| US20230383943A1 (en) | Method and Smart System for Fault Detection and Prevention in Industrial Boilers | |
| CN110045594B (en) | Intelligent management and control system and method for predicting state risk of four tubes of boiler | |
| CN109253870B (en) | The assessment device and method in biomass fuel boiler heat-exchange tube service life | |
| CN103256620A (en) | Multi-information-fusion intelligent flame detecting device and detecting method thereof | |
| CN103925155A (en) | Self-adaptive detection method for abnormal wind turbine output power | |
| KR20200114130A (en) | Method and system for fault diagnosis of photovotaic generation | |
| TW202208746A (en) | Fault diagnosis system and method for wind turbine wherein the hidden faults in the operation process can be found in time through the real-time monitoring and trend prediction of the operating status of wind power generation equipment | |
| CN111596643A (en) | Visual dynamic energy consumption diagnosis, analysis and pre-control system based on big data | |
| CN116592386A (en) | Flue gas oxygen content control system | |
| CN106768000A (en) | A kind of wind driven generator set converter water-cooling system pressure anomaly detection method | |
| CN113485262B (en) | SVM-based fault analysis method for fuel system of thermal power plant | |
| CN110488125A (en) | Amount of state information based on breaker realizes the method and its system of active forewarning processing | |
| CN203082859U (en) | Boiler detection system | |
| CN112240267B (en) | Fan monitoring method based on wind speed correlation and wind power curve | |
| CN108151834A (en) | It is a kind of to be used for industrial furnace, the sensor self checking method of boiler and system | |
| CN107505927B (en) | CFB Boiler cigarette equipment fault monitoring method component-based and device | |
| CN114267468A (en) | Fixed-point detection and early warning system for nuclear power station key equipment | |
| CN117989559A (en) | Method and system for monitoring flame combustion state of heating furnace | |
| CN115628777A (en) | On-line monitoring system for thermal generator set performance based on component characteristics | |
| CN205065681U (en) | Boiler microcomputer control system | |
| CN210772277U (en) | Air preheater monitoring and early warning system | |
| CN108730943B (en) | Flue gas dynamic temperature evaluation method | |
| CN110873461B (en) | Fault detection method for three-way valve in dual-purpose furnace |
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: 20191018 |
|
| RJ01 | Rejection of invention patent application after publication |