CN110162555A - A kind of fired power generating unit start and stop and drop power output measure of supervision - Google Patents
A kind of fired power generating unit start and stop and drop power output measure of supervision Download PDFInfo
- Publication number
- CN110162555A CN110162555A CN201910444049.9A CN201910444049A CN110162555A CN 110162555 A CN110162555 A CN 110162555A CN 201910444049 A CN201910444049 A CN 201910444049A CN 110162555 A CN110162555 A CN 110162555A
- Authority
- CN
- China
- Prior art keywords
- data
- power output
- drop
- stop
- supervision
- 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
- 238000000034 method Methods 0.000 claims abstract description 32
- 238000000605 extraction Methods 0.000 claims abstract description 6
- 238000004458 analytical method Methods 0.000 claims description 13
- 238000013500 data storage Methods 0.000 claims description 9
- 230000003247 decreasing effect Effects 0.000 claims description 9
- 241001269238 Data Species 0.000 claims description 5
- 238000004140 cleaning Methods 0.000 claims description 4
- 238000011068 loading method Methods 0.000 claims description 4
- 238000003860 storage Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 8
- 238000007726 management method Methods 0.000 description 18
- 230000008569 process Effects 0.000 description 13
- 238000012544 monitoring process Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 230000007812 deficiency Effects 0.000 description 4
- 238000003745 diagnosis Methods 0.000 description 4
- 230000005611 electricity Effects 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000005923 long-lasting effect Effects 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 238000010561 standard procedure Methods 0.000 description 1
- 230000008646 thermal stress Effects 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/248—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- General Engineering & Computer Science (AREA)
- Marketing (AREA)
- Computational Linguistics (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Public Health (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a kind of fired power generating unit start and stop and drop power output measure of supervision, belong to power engineering field.Described method includes following steps: acquiring the power data of unit；Data pick-up is carried out to the power data；Data prediction is carried out to the data of the extraction and obtains valid data；The valid data are stored in database profession；By analyzing the historical data in the database, judge whether current data is non-programmed halt event or unplanned drop power output event.The advantages that fired power generating unit start and stop and drop power output supervision application technology of the invention have quickly, accurately, convenient, and rate of failing to report is low, and automatization level is high.
Description
Technical field
The invention belongs to power engineering fields, and in particular to a kind of fired power generating unit start and stop and drop power output measure of supervision.
Background technique
The application of fired power generating unit remote supervisory function, not only can economically be thought deeply, while in safety, resource
It is designed in integration；In conjunction with the non-centralized management stopped of unit, not only current state anticipation can be carried out by history, while can
To be used to learn and accident analysis, achievees the purpose that drop is non-and stop；Long-range suggestion and prompt can be given by remote diagnostic center,
Promote unit start and stop in the state of economy, safety.Unit Commitment system refers to starting and stopping for unit, in shutdown process gold
The temperature difference, thermal deformation, thermal stress will be generated by belonging to component, and control is improper will to be cracked or even damage, and therefore, Unit Commitment process is
Complicated for operation in production process, operating condition changes fast, safety, energy saving influence factor compares the link of concentration.By using advanced
Computer and network technologies efficiently use remote diagnostic center expert team, reinforce the supervision and management of shutdown process.
The Li Jun et al. of the world Hua electricity has studied fired power generating unit shutdown process inline diagnosis method and corrective measure, establishes
Shutdown process supervises standard, develops start and stop monitor system, realizes target deviation, change rate calculating, abnormity prompt, operation are built
The functions such as view.Start and stop record can also be shown with opening machine record, outage record in power plant, query region company historical time section
It opens machine, shut down energy consumption index parameter and alarming index parameter, major parameter curve and standard curve are compared；Energy consumption parameter pair
Than.Supervision is shut down by selection monitoring unit stopping process and starting, off-the-line, is stopped working, the information such as jiggering and end time is thrown and comes
It monitors stopping process major parameter trend and stopping process trend and standard procedure trend compares and the real-time tendency of major parameter
Situation of change, and to out-of-limit parameter warning note.The system is applied successfully on 3 grade units such as Laizhou, Zou County, effectively controls
The generation of start and stop abnormal problem is made.
The Xu Hongrui in state's net Shanxi stops event for Shanxi Power Network generating set is non-, is monitored on-line using harmonious scheduling system
Function, develops that harmonious system unit is non-to stop monitoring modular, and has applied it to non-stop in the analysis of causes.It, can by analysis
To judge the non-potential risk and failure cause stopped of unit in advance.The non-sky for stopping influencing electricity net safety stable of unit is effectively filled up
It is white, in a few days or a few days ago grid balance carries out adequate preparation, and strong technical guarantee is provided for power network safety operation.When
Unit opens machine output 1, shuts down output -1, when start and stop occurs for unit, can trigger longitudinal access start and stop event high frequency automatically
Access task carries out high-frequency data acquisition.
When fired power generating unit reliability management is by by unit reliability basic data according to reporting and submitting as defined in superintendent office
Between and after review procedure reports, counted by supervisor and determined.However there are still deficiencies for current management method, mainly
There are following three points: 1) original data volume is big, and direct surveillance collects and makes a report on information, very time-consuming and great work intensity,
Situations such as in the presence of failing to report and reporting by mistake；2) information collect lag, power plant unit failure after cannot report without delay, to scheduling and
Power balance brings pressure；3) data make a report on accuracy deficiency, can not directly make a definite diagnosis compressor emergency shutdown reason from feedback information is made a report on,
Interference is brought for the subsequent analysis of causes and statistics.
Summary of the invention
In view of the deficiencies of the prior art, the purpose of the present invention is to provide a kind of fired power generating unit start and stop and drop power output supervision skill
Art and research method, big to solve original data volume existing in the prior art, it is big to collect and make a report on information work intensity, exists
The problem of failing to report and reporting by mistake.
A kind of fired power generating unit start and stop and drop power output measure of supervision, described method includes following steps:
Acquire the power data of unit；
Data pick-up is carried out to the power data；
Data prediction is carried out to the data of the extraction and obtains valid data；
The valid data are stored in database profession；
By analyzing the historical data in the database, judge whether current data is non-programmed halt event or non-
Plan drop power output event.
Further, the determination method of the non-programmed halt event includes:
Obtain 20 to 60 minutes before each downtime in the database any one time points；
The historical data in period formed to the time point and downtime is analyzed, and acquisition is non-to stop criterion of identification value
Stop identifying required value with non-；
The performance number of current data is greater than non-when stopping criterion of identification value, then is determined as non-programmed halt event；
The performance number of the current data it is non-stop criterion of identification and it is non-stop identify required value between then by decreasing order column judgement be
No is non-programmed halt event.
Further, the decreasing order column determination method includes:
The downtime point of current data is taken into forward ten minute datas, sequence of successively decreasing if continuous two data taper off rule
Number scale record plus one, when successively decreasing, ordinal number is less than specified steep drop characteristic value, then regards as non-programmed halt.
Further, the judgment method of the unplanned drop power output event includes:
To the historical data in the database carry out analysis obtain absolutely drop power output threshold values, drop power output threshold values and specified maximum it is poor
Value；
When the performance number of current data is lower than absolutely drop power output threshold values, then it is determined as unplanned drop power output event；
When the performance number of the current data is located at when absolutely dropping power output threshold values between drop power output threshold values, by assisting check post
Judge whether it is unplanned drop power output event.
Further, auxiliary check post judgment method includes:
Obtain 20 to 60 minutes before the current data any one time points；
It obtains the time point and power maximum value that current data corresponds in the period of time point composition is used as and tests for auxiliary
Card point；
Calculate the power of auxiliary check post and the difference of the current power of the assembling unit；
When the difference is greater than specified maximum difference, mark starts this moment for drop power output, persistently monitors load measuring point 90 minutes
Internal loading does not drop to shutdown threshold values, and is plan drop power output event when finally ging up to stable operation load, is otherwise unplanned
Power output event drops.
Further, the data prediction includes coding, cleaning, association and state aware.
Further, the storage includes time series data storage, unstructured data storage and structural data storage
Deng.
Further, the data are acquired in real time by ECell；The data are extracted by ETL tool.
To solve prior art problem, the technical scheme adopted by the invention is as follows:
Compared with prior art, the present invention have it is following the utility model has the advantages that
1) present invention is realized by building data model to equipment condition monitoring, is solved site problems using specialized software, is adopted
With on-line monitoring technique, unit reliability management module is developed, start and stop, drop power output supervision pipe are carried out to fired power generating unit of generating electricity by way of merging two or more grid systems
Reason, switching and the correct time of set state are provided by real-time tracking, and compared to manual oversight, rate of failing to report is low, are determined quasi-
True property improves, and reduces the time of information processing；2) present invention finds suitable characteristics value, exploitation by the excavation to historical data
Drop power output model, realizes the automatic monitoring of drop power output event, when solving manual identified data be difficult to acquire and with actively drop out
Force information divides the problems such as obscurity boundary, and by on-line analysis, expert verifies to form closed loop management, and automatization level is high；3) originally
Invention is to be supported mass data to be uploaded to private clound based on cloud computing technology platform, passed through network while guaranteeing data security
Quickly and easily business support is provided for scene.
Detailed description of the invention
Fig. 1 is sharp think of energy management platform；
Fig. 2 power data figure of 10 minutes for 20 minutes before certain 600MW unit non-programmed halt and after shutting down；
Fig. 3 power data figure of 10 minutes for 20 minutes before certain 600MW unit planned shut-down and after shutting down；
The power data comparison diagram that Fig. 4 is 15 minutes before certain 600MW unit non-programmed halt and planned shut-down；
The power data comparison diagram that Fig. 5 is 10 minutes before certain 600MW unit non-programmed halt and planned shut-down；
The power data comparison diagram that Fig. 6 is 10 minutes before certain 600MW unit non-programmed halt and planned shut-down；
The power data comparison diagram that Fig. 7 is 2 minutes before certain 600MW unit non-programmed halt and planned shut-down；
The power data comparison diagram that Fig. 8 is 1 minute before certain 600MW unit non-programmed halt and planned shut-down；
The power data comparison diagram that Fig. 9 is 0 minute before certain 600MW unit non-programmed halt and planned shut-down；
Figure 10 is drop power output identification process figure, wherein confirms unit starting and power is more than that stable state a reference value takes different units to transport
Historical data (i.e. not shutdown status) under row state calculates the power expectation Sigma's lower limit that subtracts one according to three-sigma criterion
Value is iterated study to historical events drop power output event, orderly closedown event, determines and drops power threshold value out and triggering drop power output
20 minutes specified maximum differences before threshold；
Figure 11 is that power output event case drops in certain 600MW unit；
Figure 12 is that unit drops power output event with reference to figure；
Figure 13 is that power output event case-status indication figure drops in certain 600MW unit.
Specific embodiment
The invention will be further described below in conjunction with the accompanying drawings.Following embodiment is only used for clearly illustrating the present invention
Technical solution, and not intended to limit the protection scope of the present invention.
As shown in Figure 1, a kind of fired power generating unit start and stop and drop power output measure of supervision, described method includes following steps: acquisition
The power data of unit；Data pick-up is carried out to the power data；Data prediction acquisition is carried out to the data of the extraction
Valid data；The valid data are stored in database profession；By analyzing the historical data in the database, sentence
Whether disconnected current data is non-programmed halt event or unplanned drop power output event.
The power data of above-mentioned unit is obtained, the sharp think of energy by sharp think of energy management platform (referred to as sharp think of platform SRT)
The bottom of management platform is the data active layer that platform can be acquired and be stored comprising creation data (such as DCS, SIS) is managed
Data (such as MIS, ERP) and external data (weather, coal/gas price etc.) etc., these product practices can pass through platform
In ECell acquired (support various data communication protocols) in real time, while by ETL tool carry out structuring with it is non-structural
Change the extraction of data；The data prediction service of platform itself will be passed through after various data sources are acquired or extracted, including encode,
Cleaning, association and state aware, are stored in each database of platform according to data characteristics after pretreatment, entire platform includes
Time series data storage, unstructured data storage and structural data storage etc., while distributed coordination service, distribution being provided
The services such as formula message caching；The service of calculating is provided by magnificent cloud computing platform, including the time calculates SEvent, statistics calculates SReal,
The services such as unmounted model calculating；Each service application service is deployed on the sharp data Layer for thinking platform, and mobile terminal is supported to show
And data sharing.
Big data technology has gradually been goed deep into the application of power industry at present, such as ARMIA model returns, grey projection,
Random forests algorithm and shot and long term Memory Neural Networks utilize fuzzy theory, Petri net to the application in load forecast
Network, genetic algorithm carry out power system failure diagnostic.But to firepower Power System Reliability administrative section correlative study and application
Less, by the way that 10MW ~ 1060MW, totally 230 fired power generating units are studied, wherein 600MW or more unit is 66 total.To original
Beginning data, which are analyzed, collects sharp think of big data platform for data, cleans analysis software, the suitable number of building using specialization
It learns model to be monitored Unit Commitment and drop power output, management is marked to non-programmed halt and drop power output, and carry out visual
Change and presents.Allow expert's remote validation and user to check oneself by private network, realizes equipment condition monitoring and performance evaluation, make a living
Production, maintenance and safety provide guidance, provide analysis for technical supervision and refer to, and provide data for leader's business decision and support.
Reliability management
It is divided under equipment use state in management of electric power dependability technical standard available and unavailable.It is able to carry out according to equipment pre-
The state for determining function is divided into operation and spare two kinds again, and down state is divided into planned outage and unplanned outage (non-to stop).Its
Middle electricity power enterprise is primarily upon shutdown event and drops power output event, unplanned drop power output embodiment device " in spite of illness " operating condition, and
When equipment is checked and is overhauled, can by security risk eliminate in the early stage.The unplanned outage of generating set is often adjoint
Great safety accident brings electric quantity loss, economic loss, credibility loss to enterprise.
The identification of non-programmed halt event and determination method
It is counted according between the non-stopping time of fired power generating unit in recent years, non-the reason of stopping is caused to have boiler system, turbine system, generator
System and heat power engineering system etc..Wherein boiler system accounts for about 60%, and turbine system accounts for about 10%, and generator system accounts for about 10%.Suddenly
The non-event of stopping of tripping and emergency outage accounts for number big absolutely, by being characterized in function in data to historical time comparative analysis
Rate value drops suddenly and shuts down in first 5 minutes that numerical value is higher, and data are analyzed and extracted as point of penetration as shown in Figure 2 and Figure 3
Feature.
As shown in Fig. 4 to 9, history is used to determine that event for training dataset, obtains each downtime in database
First 20 to 60 minutes any one time points；The historical data in period formed to the time point and downtime is divided
Analysis, first takes 20 minute datas before downtime to be analyzed here, is analyzed for this series of scatterplot, use is artificial
Non-programmed halt thing, the orderly closedown event of verifying are learnt as object set.In order to allow, data are more representative, enrich sample
This quantity, using capacitance grade as sample packet foundation, by carrying out feature extraction to 58 600MW grade compressor emergency shutdown data,
Capacitance grade unit expansion individuation data is excavated, it is verified to have preferable applicability.To shut down preceding 15 minute data into
Row comparison, it is higher to compare orderly closedown for performance number before non-programmed halt, this phenomenon before shutdown 2 minutes it is especially pronounced, data go out
Now obvious layering.First 2 minutes power Value Datas of over cleaning of learning from else's experience are classified, and are carried out classification boundaries and are retouched side, final to determine
It is non-stop criterion of identification value and it is non-stop identify required value.By stopping characteristic value with non-to the performance number into 2 minutes before shutdown threshold
Be compared, when performance number be greater than it is non-stop criterion of identification value be then determined as it is non-stop event, performance number is in the non-criterion of identification and non-of stopping
Stop identifying that entering descending series between required value determines: downtime point takes forward ten minute datas, and continuous two data present
Subtract regular then successively decrease ordinal number record plus one, ordinal number is less than specified steep drop characteristic value when successively decreasing, then regards as non-programmed halt.
Identification and the determination method of power output event drop
Unit drop power output refers to that maximum capacity operation is not achieved in unit or spare state (does not include normally adjusting by load curve
Whole power output), unit derating, which can be divided into plan, reduces power output and unplanned derating.Subtract under normal circumstances in network load
When few, in order to keep mains frequency to keep stablizing, need to reduce station output, this part is according to load scheduling curve tune
Whole power output belongs to normal adjustment.Plan reduces reduction power output of the power output unit according to plan in given time period, for example, it is seasonal or
Monthly adjustment.Present invention is primarily concerned with because the reason that subsidiary engine equipment fault or equipment deficiency etc. cannot expect leads to unplanned drop
Power output event is specific to differentiate that process is as shown in Figure 10.
History is used to determine that event for training dataset, as shown in figure 11, carries out typical unplanned drop power output event special
Sign is extracted, and is taken the unit by verifying to operate normally data and is determined that unit can be floated downward long lasting for the power low value of normal operation
Specified amount is absolutely to drop threshold values of contributing；
20 to 60 minutes any one time points before acquisition current data；
It obtains the time point and power maximum value that current data corresponded in the period of time point composition is used as auxiliary verifying
Point；Take preceding 20 minutes internal loading maximum values for auxiliary check post in the present embodiment.
The detailed process of judgement is:
When the performance number of current data is lower than absolutely drop power output threshold values, then it is determined as unplanned drop power output event；
It is effective to data cleansing confirmation data when the power of the assembling unit is lower than drop power output threshold values, take the current power of the assembling unit and auxiliary to test
Card point calculated load difference is verified；
Difference is greater than specified maximum difference, and mark starts this moment for drop power output, persistently monitors 90 minutes internal loadings of load measuring point not
It is down to shutdown threshold values, and finally gos up to stable operation load to think at this time that drop power output terminates, complete drop power output event is carried out
Record, unplanned drop power output event judging result are as shown in Figure 12 and Figure 13 as follows: drop power output event is lower than 250MW from load value
Start, until load value is increased to terminate when 300MW.
Fired power generating unit shutdown process is that complicated for operation, operating condition changes fast, safety, energy saving influence factor compares in production process
The link of concentration reinforces the supervision and management of shutdown process, and using advanced computer and network technologies, effective use is remotely examined
Disconnected center expert team reaches safety, the Energy Saving Control target of unit starting, is conducive to mention by the timely interaction with power plant
The fine-grained management for rising power plant is horizontal.
The present invention provides computing resource using big data distributed arithmetic system and supports, based on the big number of Internet technology exploitation
It realizes and Centralized Monitoring, management, diagnosis is carried out to thermal power generation unit by establishing expert model as data source according to platform
And analysis.
The it is proposed of hardware and software platform management is provided for effective solution approach, flat using Internet technology exploitation big data
Platform is realized and carries out Centralized Monitoring, management, diagnosis and analysis to thermal power generation unit.Sharp think of big data platform passes through to unit base
Plinth data are collected, and storage forms private clound shared data warehouse, handles online data in real time, and high accuracy provides point
Analysis determines as a result, auxiliary direction produces each link.Platform constantly accumulates the reliability data of equipment by Improving Equipment account,
Adequately reference and foundation are provided to analyse the reliability of each equipment scientifically, summarizes accident experience and lessons, research accident development rule
Rule finds the generation point of the weak link of power equipment, potential dangerous point and high failure rate, finally further increases power plant
Reliability management it is horizontal, to improve the economy of electric utility.
Fired power generating unit start and stop and drop power output supervision application technology of the invention have quickly, and accurately, convenient, rate of failing to report is low,
The advantages that automatization level is high.
Particular embodiments described above, pair present invention solves the technical problem that, technical scheme and beneficial effects carry out
Be further described, should the technical means disclosed in the embodiments of the present invention be not limited only to skill disclosed in above embodiment
Art means, also include technical solutions formed by any combination of the above technical features.It should be pointed out that for the art
For those of ordinary skill, various improvements and modifications may be made without departing from the principle of the present invention, these improvement
Also it is considered as protection scope of the present invention with retouching.
Claims (8)
1. a kind of fired power generating unit start and stop and drop power output measure of supervision, which is characterized in that described method includes following steps:
Acquire the power data of unit；
Data pick-up is carried out to the power data；
Data prediction is carried out to the data of the extraction and obtains valid data；
The valid data are stored in database profession；
By analyzing the historical data in the database, judge whether current data is non-programmed halt event or non-
Plan drop power output event.
2. a kind of fired power generating unit start and stop according to claim 1 and drop power output measure of supervision, which is characterized in that the non-meter
Draw shutdown event determination method include:
Obtain 20 to 60 minutes before each downtime in the database any one time points；
The historical data in period formed to the time point and downtime is analyzed, and acquisition is non-to stop criterion of identification value
Stop identifying required value with non-；
The performance number of current data is greater than non-when stopping criterion of identification value, then is determined as non-programmed halt event；
The performance number of the current data it is non-stop criterion of identification and it is non-stop identify required value between then by decreasing order column judgement be
No is non-programmed halt event.
3. a kind of fired power generating unit start and stop according to claim 2 and drop power output measure of supervision, which is characterized in that the decreasing order
Column determination method includes:
The downtime point of current data is taken into forward ten minute datas, sequence of successively decreasing if continuous two data taper off rule
Number scale record plus one, when successively decreasing, ordinal number is less than specified steep drop characteristic value, then regards as non-programmed halt.
4. a kind of fired power generating unit start and stop according to claim 1 and drop power output measure of supervision, which is characterized in that the non-meter
Draw drop power output event judgment method include:
To the historical data in the database carry out analysis obtain absolutely drop power output threshold values, drop power output threshold values and specified maximum it is poor
Value；
When the performance number of current data is lower than absolutely drop power output threshold values, then it is determined as unplanned drop power output event；
When the performance number of the current data is located at when absolutely dropping power output threshold values between drop power output threshold values, by assisting check post
Judge whether it is unplanned drop power output event.
5. a kind of fired power generating unit start and stop according to claim 4 and drop power output measure of supervision, which is characterized in that the auxiliary
Check post judgment method includes:
Obtain 20 to 60 minutes before the current data any one time points；
It obtains the time point and power maximum value that current data corresponds in the period of time point composition is used as and tests for auxiliary
Card point；
Calculate the power of auxiliary check post and the difference of the current power of the assembling unit；
When the difference is greater than specified maximum difference, mark starts this moment for drop power output, persistently monitors load measuring point 90 minutes
Internal loading does not drop to shutdown threshold values, and is plan drop power output event when finally ging up to stable operation load, is otherwise unplanned
Power output event drops.
6. a kind of fired power generating unit start and stop according to claim 1 and drop power output measure of supervision, which is characterized in that the data
Pretreatment includes coding, cleaning, association and state aware.
7. a kind of fired power generating unit start and stop according to claim 1 and drop power output measure of supervision, which is characterized in that
The storage includes time series data storage, unstructured data storage and structural data storage etc..
8. a kind of fired power generating unit start and stop according to claim 1 and drop power output measure of supervision, which is characterized in that the data
It is acquired in real time by ECell；The data are extracted by ETL tool.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910444049.9A CN110162555A (en) | 2019-05-27 | 2019-05-27 | A kind of fired power generating unit start and stop and drop power output measure of supervision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910444049.9A CN110162555A (en) | 2019-05-27 | 2019-05-27 | A kind of fired power generating unit start and stop and drop power output measure of supervision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110162555A true CN110162555A (en) | 2019-08-23 |
Family
ID=67632887
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910444049.9A Pending CN110162555A (en) | 2019-05-27 | 2019-05-27 | A kind of fired power generating unit start and stop and drop power output measure of supervision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110162555A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110989432A (en) * | 2019-11-29 | 2020-04-10 | 北京京能电力股份有限公司 | System and method for analyzing unit start-stop sequence logic |
| CN111026031A (en) * | 2019-12-13 | 2020-04-17 | 红云红河烟草(集团)有限责任公司 | Steady state identification method for cigarette filament making process data |
| CN111445138A (en) * | 2020-03-26 | 2020-07-24 | 华润电力技术研究院有限公司 | Method, system and device for contrastively analyzing starting working conditions of cluster-level thermal power generating unit |
| CN111768884A (en) * | 2020-06-08 | 2020-10-13 | 核动力运行研究所 | Nuclear power plant unit running state monitoring system and method |
| CN113034306A (en) * | 2021-03-05 | 2021-06-25 | 西安热工研究院有限公司 | Method for judging startup and shutdown states of thermal power generating unit on line |
| CN114924188A (en) * | 2022-05-13 | 2022-08-19 | 上海擎测机电工程技术有限公司 | Thermal power generating unit startup and shutdown monitoring method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102588210A (en) * | 2011-12-21 | 2012-07-18 | 中能电力科技开发有限公司 | Filtering method for preprocessing fitting data of power curve |
| CN103234753A (en) * | 2013-04-11 | 2013-08-07 | 华北电力大学 | Gaussian process modeling based wind turbine shafting state monitoring method |
| CN107069963A (en) * | 2017-04-13 | 2017-08-18 | 华能澜沧江水电股份有限公司小湾水电厂 | A kind of unattended hydropower plant intelligently supervises disk method and system |
-
2019
- 2019-05-27 CN CN201910444049.9A patent/CN110162555A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102588210A (en) * | 2011-12-21 | 2012-07-18 | 中能电力科技开发有限公司 | Filtering method for preprocessing fitting data of power curve |
| CN103234753A (en) * | 2013-04-11 | 2013-08-07 | 华北电力大学 | Gaussian process modeling based wind turbine shafting state monitoring method |
| CN107069963A (en) * | 2017-04-13 | 2017-08-18 | 华能澜沧江水电股份有限公司小湾水电厂 | A kind of unattended hydropower plant intelligently supervises disk method and system |
Non-Patent Citations (1)
| Title |
|---|
| 冯泽磊 等: "基于大数据平台的火电机组实时运行状态监测", 《华电技术》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110989432A (en) * | 2019-11-29 | 2020-04-10 | 北京京能电力股份有限公司 | System and method for analyzing unit start-stop sequence logic |
| CN111026031A (en) * | 2019-12-13 | 2020-04-17 | 红云红河烟草(集团)有限责任公司 | Steady state identification method for cigarette filament making process data |
| CN111445138A (en) * | 2020-03-26 | 2020-07-24 | 华润电力技术研究院有限公司 | Method, system and device for contrastively analyzing starting working conditions of cluster-level thermal power generating unit |
| CN111768884A (en) * | 2020-06-08 | 2020-10-13 | 核动力运行研究所 | Nuclear power plant unit running state monitoring system and method |
| CN111768884B (en) * | 2020-06-08 | 2023-02-21 | 核动力运行研究所 | Nuclear power plant unit running state monitoring system and method |
| CN113034306A (en) * | 2021-03-05 | 2021-06-25 | 西安热工研究院有限公司 | Method for judging startup and shutdown states of thermal power generating unit on line |
| CN113034306B (en) * | 2021-03-05 | 2023-04-07 | 西安热工研究院有限公司 | On-line judgment thermal power generating unit method for starting a standstill |
| CN114924188A (en) * | 2022-05-13 | 2022-08-19 | 上海擎测机电工程技术有限公司 | Thermal power generating unit startup and shutdown monitoring method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110162555A (en) | A kind of fired power generating unit start and stop and drop power output measure of supervision | |
| CN109543210A (en) | A kind of Wind turbines failure prediction system based on machine learning algorithm platform | |
| CN103793859B (en) | A kind of wind power plant operation monitoring and event integrated evaluating method | |
| CN110320892A (en) | The sewage disposal device fault diagnosis system and method returned based on Lasso | |
| CN104952000A (en) | Wind turbine operating state fuzzy synthetic evaluation method based on Markov chain | |
| CN113705924B (en) | Intelligent diagnosis method and system for thermal control equipment | |
| CN105787606A (en) | Power dispatching online trend early warning system based on ultra short term load prediction | |
| CN101859409A (en) | Power transmission and transformation equipment state overhauling system based on risk evaluation | |
| CN110929927A (en) | Artificial intelligence prediction model construction method applying power distribution network universe big data | |
| CN108256713A (en) | Nuclear power plant system measure of supervision based on ERDB | |
| CN110320893B (en) | Thermal power generating unit equipment maintenance method based on RCM | |
| CN107256449A (en) | A kind of relay protection device of intelligent substation state evaluation and appraisal procedure | |
| CN102521672A (en) | Safety risk automatic recognition method based on network-distribution production operation plan | |
| CN102830682A (en) | Energy consumption police module for regional power generation corporation to run intelligent management and control system | |
| CN109902447A (en) | A kind of huge Condition Maintenance for Hydraulic Power Plant model and construction method | |
| CN112001569A (en) | Power grid operation risk analysis method based on multi-voltage-level fault | |
| CN116128145A (en) | Power equipment state maintenance strategy optimization method | |
| CN112950064B (en) | Power grid security risk influence factor analysis method and device | |
| CN112418662A (en) | Power distribution network operation reliability analysis method using artificial neural network | |
| CN110245163A (en) | A kind of Operation of Electric Systems hidden troubles removing method | |
| CN113537681A (en) | Method and system for refining enterprise equipment management informatization | |
| CN110261693A (en) | A kind of online thermal test method and system based on stable state sampling technique | |
| CN115936663A (en) | Maintenance method and device for power system | |
| CN108256663A (en) | A kind of nuclear power interruption of service risk real-time predicting method | |
| CN113283679A (en) | AI artificial intelligence based power load prediction system |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190823 |