CN102708180B - Data mining method in unit operation mode based on real-time historical library - Google Patents
Data mining method in unit operation mode based on real-time historical library Download PDFInfo
- Publication number
- CN102708180B CN102708180B CN201210141675.9A CN201210141675A CN102708180B CN 102708180 B CN102708180 B CN 102708180B CN 201210141675 A CN201210141675 A CN 201210141675A CN 102708180 B CN102708180 B CN 102708180B
- Authority
- CN
- China
- Prior art keywords
- variable
- data
- time
- search
- process data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a data mining method in a unit operation mode based on a real-time historical library. According to the method, the operation mode rule of the unit on each operation condition can be obtained by mining and analyzing production process data stored in the real-time historical library, and a full-working-condition mode rule base is formed. Generally, the mining is finished by three parts: firstly, preprocessing data to obtain good-quality data and extract operating characteristics, secondly, conducting clustering analysis on the operating characteristics so as to gather similar data, and thirdly, extracting rule based on the clustering and finally obtaining an operating mode base. According to the method, the operating mode base is taken as the basis, the historical optimal operating mode at a present unit operating state can be obtained at real time, and a related optimal control parameter is output to an operator or a control system, so that the condition that the unit keep the highest-quality operating state in the history becomes possible, and furthermore, economic performance and environment-friendly performance of the unit can be improved.
Description
Technical field
The invention belongs to thermoelectricity operation optimisation technique field, and be based on the real-time historical data of production run, take and extract the data digging system that economy and feature of environmental protection operational mode are target, be applicable to coal fired power generation unit.
Background technology
Current ，Ge coal-fired power plant is faced with dual-pressure energy-conservation and that reduce discharging.By obtaining optimized operation pattern for current operation provides data supporting from a large amount of history datas, become the new approaches that improve unit operation quality.At present, due to operations staff's experience ability difference, that running quality is fluctuated is larger, by data mining mode, extracts unit optimized operation pattern, uses these optimization model data to instruct operation, will greatly improve unit overall operation quality.
Find at present unit optimization model algorithm and mainly have following problem:
1. the realization of traditional optimum theory and method
Traditional optimum theory depends on model and the optimized algorithm of the system of foundation.Complex system modeling difficulty, assessing the cost of optimizing process often makes reality and theory greatly differ from each other.
2. the realization of artificial intelligence approach
Although intelligent algorithm can effectively be avoided complicated mathematical modeling, it often needs large-scale calculating, and searching process assesses the cost and more still cannot avoid.
On the one hand, along with data mining technology deeply develops, make the exploration of complication system inside being contained to rule become possibility.On the other hand, along with the maturation of domestic database technology in recent years, the data mining based on mass data processing, data fusion, become the effective tool that solves numerous practical problemss.Utilize the unit magnanimity service data of storing in real time historical database, will become the inexorable trend of domestic electricity power enterprise energy-saving and emission-reduction research.
Summary of the invention
For solving in prior art, there is above problem, the invention provides a kind of unit operation mode data method for digging based on real-time history library.Content of the present invention is on the basis of unit magnanimity service data, and data are carried out to horizontal and vertical omnibearing stereo mining analysis, and final given current working optimized operation parameter.The incidence relation between data of take is guiding, first data are strictly cleaned, on the basis of cleaning, data are carried out the search of high density stable state and asked its eigenwert, and then steady state data is carried out to operating mode mapping classification, moreover characteristic is carried out to cluster analysis, on the basis of cluster analysis, extract and contain pattern rules wherein.Decision analysis system is carried out decision analysis on the basis of knowledge base allows power plant's expertise participate in construction of knowledge base, finally by pattern optimizing station real-time online, searches optimized operation pattern, and relevant control parameter is provided.
First the technical term occurring in the application is made the following instructions:
Process data: the general designation that refers to the data that the numerical value that in generating plant production run, all measuring equipments measure and the secondary calculating of carrying out for basis thus obtain, for example generated output is the process data measuring, and boiler efficiency is the process data that secondary calculating obtains.
The stable state time period: refer to the time period that meets stable state search constraints and the requirement of steady-sxtate wave motion threshold value.
Dirty data threshold value: refer to after N that sampling interval when data is greater than average period doubly and think that this partial data is dirty data, wherein the numerical value of N is dirty data threshold value.
Stable state search constraints: refer to and need satisfied logical relation between each variable in the process data of synchronization.
Steady-sxtate wave motion threshold value: refer to the smoothness that variable changes at the time period of search internal variable, comprise between setting district band and variable data and drop on the ratio in this interval band.
Measuring point: the data that generating plant sensor collects are called the data of this measuring point.
Variable: variable is the Function Mapping of measuring point, is embodied in the mathematical formulae that some measuring points form, and variable is the data that data digging system is really paid close attention to.For example: the power and variable y=x1+x2 of certain equipment, wherein x1, x2 are the power measuring point of this equipment part 1 part 2 wherein.
Eigenwert: refer to variable in stable state the statistical value in the time period, comprise average, maximal value, minimum value, variance, maximal value time, minimum value time etc.
Variable grouping: refer to according to the physical attribute difference of variable it is divided into groups, physical attribute comprises the equipment that this variable adheres to separately and belongs to operability quality, state behavior amount and performance characteristics amount etc., and every group of variable has its unique group number.
Rule chain: the orderly group number set forming for predefined group number of being divided into groups by variable is regular chain.
For realizing the present invention, adopt following technical scheme:
Unit operation mode data method for digging based on real-time history library, is characterized in that, said method comprising the steps of:
(1) set up power plant's real time historical database, from generating plant distributed monitoring control system, gather in real time the process data of each measuring point production run;
(2) to described each process data pre-service, reject the dirty data in described process data, obtain the representative high-quality process data of each measuring point in production run:
According to the variance of the process data of described each measuring point with to measuring point density, require degree set dirty data threshold value, cleaning process data sampling interval is greater than the image data in time period of product value of average sample cycle and dirty data threshold value, obtain each measuring point and clean rear time period group, the time period group obtaining after each measuring point is cleaned seeks common ground, and the process data of each measuring point in this common factor is pretreated representative high-quality process data;
(3) by stable state, search for, stability recording in the resulting high-quality process data of obtaining step (2), and obtain the characteristic of each variable under stability recording:
In the resulting high-quality process data of step (2), search for each variable all meet stable state search constraints and fluctuation threshold value all time periods, these time periods are the stable state time period, process data in these time periods is stability recording, and each variable in each stability recording is carried out to signature analysis; Wherein, variable is the Function Mapping of measuring point process data, and described stable state search constraints refers to the certain logical relation meeting between the process data of each variable of synchronization; Described fluctuation threshold value refers to the smoothness that process data changes within the time period;
(4) cluster analysis, with difference in class, minimize, between class, difference maximum turns to principle, the stability recording that step (3) is obtained carries out cluster analysis, first according to the physical attribute of variable, variable is divided into groups in advance, the characteristic data value of each variable under each stability recording is carried out to discretize, single group variable discretized values same classification that all identical stability recording is designated as under this list group variable is numbered, classification is numbered identical stability recording and is gathered for a classification under this grouping variable, to obtain thus respectively organizing variable cluster under each stability recording numbers, each stability recording correspondence is respectively organized variable all an one cluster numbering,
(5) extracting rule, stability recording is being carried out on the basis of cluster analysis, according to presetting each the related variable grouping of regular chain that will search for, obtain successively the cluster numbering under correlated variables grouping under each stability recording, the common formation of stability recording combination one rule with the combination of identical cluster numbering, the number of stability recording is the weight of this rule; In the stability recording that strictly all rules is related to, the eigenwert of each variable is carried out average merging, obtains the concrete numerical value of correlated variables in this rule, the summary value of this numerical response historical experience, and in these rules, the numerical value of each variable forms operational mode knowledge base;
(6) optimization model coupling, the operating condition of the current unit of pattern optimizing station real-time follow-up, according to the operating mode measuring point of current unit operation and optimizing strategy, in operation knowledge base, search historical optimized operation pattern, and the concrete numerical value of exporting variable in this optimized operation pattern is to corresponding opertaing device.
The present invention can obtain the knowledge base of the multiple goal operations such as unit economy and the feature of environmental protection.Along with the continuous accumulation of mining data, realize operational mode storehouse precision, generalization, optimization.
Accompanying drawing explanation
Fig. 1 is the unit operation mode data method for digging process flow diagram that the present invention is based on real-time history library;
Fig. 2 Rule Extraction schematic diagram of the present invention;
Fig. 3 data digging system topological diagram.
Embodiment
According to Figure of description, in conjunction with the preferred embodiments technical scheme of the present invention is further described below.
Fig. 1 is the unit operation mode data method for digging process flow diagram that the present invention is based on real-time history library, unit operation mode data method for digging based on real-time history library disclosed by the invention, on the basis of unit magnanimity service data, to data mining analysis, and final given current working optimized operation parameter.The incidence relation between data of take is guiding, first data are strictly cleaned, on the basis of cleaning, data are carried out the search of high density stable state and asked its eigenwert, and then steady state data is carried out to operating mode mapping classification, moreover characteristic is carried out to cluster analysis, on the basis of cluster analysis, extract and contain pattern rules wherein.Decision analysis system is carried out decision analysis on the basis of knowledge base allows power plant's expertise participate in construction of knowledge base, finally by pattern optimizing station real-time online, searches optimized operation pattern, and relevant control parameter is provided.Specifically comprise the following steps: the first, set up power plant's real time historical database, in real time from DCS(generating plant scattered control system) gather the process data of each measuring point in production run.The measuring point gathering at least comprises the measuring point of all variablees of composition data digging system.
The second, data pre-service.To described each process data pre-service, reject the dirty data in described process data, obtain the representative high-quality process data of each parameter in production run: according to the variance of the process data of described each variable with to variable density, require degree set dirty data threshold value.In engineering, we provide threshold value experimental tool, can obtain by experiment the degree of fluctuation in variable sampling period, if degree of fluctuation more greatly, larger dirty data threshold value should be set, otherwise less dirty data threshold value is set, and this threshold range is generally between 3 to 5.Cleaning process data sampling interval is greater than the image data in time period of product value of average sample cycle and dirty data threshold value, obtain each measuring point and clean rear time period group, the time period group obtaining after each measuring point is cleaned seeks common ground, and the process data of each parameter in this common factor is pretreated representative high-quality process data;
The 3rd, stability recording search.By stable state search constraints and fluctuation threshold value, in the resulting high-quality process data of obtaining step (2), meet and analyze the operation stability recording requiring, and its operation characteristic of analytical calculation obtains its characteristic: wherein, described stable state search constraints refers between each variable of process data of synchronization and meets certain logical relation; Described fluctuation threshold value refers to the smoothness that process data changes within the time period, and the degree of fluctuation of fluctuation threshold value process data when checking stable operation of unit should arrange fluctuation threshold value for the larger variable of degree of fluctuation larger, otherwise less; In the resulting high-quality process data of step (2), search for all time periods that each variable all meets stable state search constraints and fluctuation threshold value, these time periods we be referred to as stability recording, and the process data in each stability recording is carried out to signature analysis;
First zero computing time, whether section met steady state constraint and fluctuation Threshold, if satisfied carry out the time period search of expanding, the described time period expands to search for to be mobile current search time period end and again to sentence whether meet steady state constraint and fluctuation Threshold, until traveling time section end no longer meets steady state constraint and fluctuation Threshold condition, the longest time period obtaining after the search of expanding is saved as to stability recording; If initial time section does not meet steady state constraint and fluctuation Threshold, carry out translation search, be that translation time period starting point and terminal recalculate search condition, until find the time period that meets steady state constraint and fluctuation threshold value, entering again the search of expanding, moving in circles until searched for the time period after all cleanings.
The 4th, cluster analysis, with difference in class, minimize, between class, difference maximum turns to principle, the stability recording that step (3) is obtained carries out cluster analysis, first according to the physical attribute of variable, variable is divided into groups in advance, the characteristic data value of each variable under each stability recording is carried out to discretize, single group variable discretized values same classification that all identical stability recording is designated as under this list group variable is numbered, classification is numbered identical stability recording and is gathered for a classification under this grouping variable, to obtain thus respectively organizing variable cluster under each stability recording numbers, each stability recording correspondence is respectively organized variable all an one cluster numbering, for example: have two stability recordings, have two variable groupings, each stability recording all can two clusters of mark be numbered after cluster, raw four clusters numbering of common property.If these two stability recordings are all identical for the discretized values of one group of variable wherein, to should divide into groups two numberings, can be the same;
The 5th, extracting rule.On the basis of characteristic cluster result, according to each variable grouping presetting after the related cluster of the regular chain that will search for, obtain successively the cluster numbering of correlated variables grouping under each stable state, the common formation of stability recording one rule with the combination of identical cluster numbering, the number of stability recording is the weight of this rule; Each rule obtaining is carried out to aggregation of data, obtain the concrete numerical value of this rule correlated variables, the summary value of this numerical response historical experience, the numerical value of these each variablees of rule forms operational mode knowledge base;
Fig. 2 is Rule Extraction schematic diagram.In engineering construction, first can according to performance, quantity of state and operational ton, divide into groups to system variable.As three node layers in Fig. 2 represent three class variable groupings.After cluster, the stable state with identical discretized values combination can be carried out to cluster numbering, identical numbering represents to have identical discretized values combination and has identical operation characteristic.The number that forms the stable state of same rule in Rule Extraction represents regular weight, represents the historical number of times that this is regular that occurs.Rule is finally stored in database in rule tree mode, by regular end, to regular front end, represents that successively multiple operative combination can make unit operation to a certain running status, and multiple running status can make unit reach a certain performance.
The 6th, optimization model coupling, the operating condition of the current unit of pattern optimizing station real-time follow-up, according to the operating mode measuring point of current unit operation and optimizing strategy, in operation knowledge base, search historical optimized operation pattern, and the concrete numerical value of exporting variable in this optimized operation pattern is to corresponding opertaing device.Described optimizing strategy comprises three classes: it is minimum that maximum, the regular time of occurrences of historical occurrence number the latest, rule neutralizes current operation parameters difference.Obtain after matched rule, by the related variate-value output of this rule, according to the difference of rule chain, parameter will be exported to different opertaing devices.
Fig. 3 is data digging system topological diagram.System of the present invention adopts C/S mode to realize, and configures an interface message processor (IMP), for receiving generating plant distributed monitoring control system or SIS in Thermal Power PlantQ SIS data.A database server is used for moving real time historical database, is used for storing the data of sending here from interface message processor (IMP); A data mining server, excavates software for service data, from real time historical database server, obtains raw data mining rule data; A knowledge base server, excavates for storing the operational mode knowledge base obtaining; A knowledge base application server, for operational mode decision system and line model optimizing station, obtains operational mode rule for decision system and optimizing from knowledge base server.A network management all-in-service station.
Claims (6)
1. the unit operation mode data method for digging based on real-time history library, is characterized in that, said method comprising the steps of:
(1) set up power plant's real time historical database, from generating plant distributed monitoring control system, gather in real time the process data of each measuring point production run;
(2) to each measuring point process data pre-service, reject the dirty data in described process data, obtain the representative high-quality process data of each measuring point in production run:
According to the variance of the process data of described each measuring point with to measuring point density, require degree set dirty data threshold value, cleaning process data sampling interval is greater than the image data in time period of product value of average sample cycle and dirty data threshold value, obtain each measuring point and clean rear time period group, the time period group obtaining after each measuring point is cleaned seeks common ground, and the process data of each measuring point in this common factor is pretreated representative high-quality process data;
(3) by stable state, search for, stability recording in the resulting high-quality process data of obtaining step (2), and obtain the characteristic of each variable under stability recording:
In the resulting high-quality process data of step (2), search for each variable all meet stable state search constraints and fluctuation threshold value all time periods, these time periods are the stable state time period, process data in these time periods is stability recording, and each variable in each stability recording is carried out to signature analysis; Wherein, variable is the Function Mapping of measuring point process data, and described stable state search constraints refers to the certain logical relation meeting between the process data of each variable of synchronization; Described fluctuation threshold value refers to the smoothness that process data changes within the time period;
(4) cluster analysis, with difference in class, minimize, between class, difference maximum turns to principle, the stability recording that step (3) is obtained carries out cluster analysis, first according to the physical attribute of variable, variable is divided into groups in advance, the characteristic data value of each variable under each stability recording is carried out to discretize, single group variable discretized values same classification that all identical stability recording is designated as under this list group variable is numbered, classification is numbered identical stability recording and is gathered for a classification under this grouping variable, to obtain thus respectively organizing variable cluster under each stability recording numbers, each stability recording correspondence is respectively organized variable all an one cluster numbering,
(5) extracting rule, stability recording is being carried out on the basis of cluster analysis, according to presetting each the related variable grouping of regular chain that will search for, obtain successively the cluster numbering under correlated variables grouping under each stability recording, the common formation of stability recording one rule with the combination of identical cluster numbering, the number of stability recording is the weight of this rule; In the stability recording that strictly all rules is related to, the eigenwert of each variable is carried out average merging, obtains the concrete numerical value of correlated variables in this rule, the summary value of this numerical response historical experience, and in these rules, the numerical value of each variable forms operational mode knowledge base;
(6) optimization model coupling, the operating condition of the current unit of pattern optimizing station real-time follow-up, according to the operating mode measuring point of current unit operation and optimizing strategy, in operation knowledge base, search historical optimized operation pattern, and the concrete numerical value of exporting variable in this optimized operation pattern is to corresponding opertaing device.
2. the unit operation mode data method for digging based on real-time history library according to claim 1, is characterized in that:
In described step (3), first zero computing time, whether section met steady state constraint and fluctuation Threshold, if satisfied carry out the time period search of expanding, the described time period expands to search for and is mobile current search time period end and again judges whether to meet steady state constraint and fluctuation Threshold, until traveling time section end no longer meets steady state constraint and fluctuation Threshold condition, the longest time period obtaining after the search of expanding is saved as to stability recording; If initial time section does not meet steady state constraint and fluctuation Threshold, carry out translation search, be that translation time period starting point and terminal recalculate search condition, until find the time period that meets steady state constraint and fluctuation threshold value, entering again the search of expanding, moving in circles until searched for the time period after all cleanings.
3. the unit operation mode data method for digging based on real-time history library according to claim 1 and 2, is characterized in that:
In described step (3), the stable state time period searching is carried out to signature analysis, calculate all variablees in average, variance, maximal value, minimum value, maximal value time and the minimum value temporal characteristics data of each stable state time period internal procedure data.
4. the unit operation mode data method for digging based on real-time history library according to claim 1, is characterized in that:
In step (6), described optimizing strategy is, using the operational mode that in operational mode knowledge base, occurrence number is maximum in history as historical optimized operation pattern.
5. the unit operation mode data method for digging based on real-time history library according to claim 1, is characterized in that:
In step (6), described optimizing strategy is, using time of occurrence operational mode the latest in operational mode knowledge base as historical optimized operation pattern.
6. the unit operation mode data method for digging based on real-time history library according to claim 1, is characterized in that:
In step (6), described optimizing strategy is, using in operational mode knowledge base with the operational mode of current operational factor difference minimum as historical optimized operation pattern.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210141675.9A CN102708180B (en) | 2012-05-09 | 2012-05-09 | Data mining method in unit operation mode based on real-time historical library |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210141675.9A CN102708180B (en) | 2012-05-09 | 2012-05-09 | Data mining method in unit operation mode based on real-time historical library |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102708180A CN102708180A (en) | 2012-10-03 |
| CN102708180B true CN102708180B (en) | 2014-02-26 |
Family
ID=46900946
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210141675.9A Active CN102708180B (en) | 2012-05-09 | 2012-05-09 | Data mining method in unit operation mode based on real-time historical library |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102708180B (en) |
Families Citing this family (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102708420B (en) * | 2012-04-12 | 2015-01-14 | 北京合力思腾科技股份有限公司 | Method for optimizing multi-strategy-multi-rule detection scheme |
| CN103699786B (en) * | 2013-12-12 | 2017-05-24 | 广东电网公司电力科学研究院 | Energy consumption difference analysis method for load varying of ultra-supercritical generating unit of thermal power plant |
| CN104750973B (en) * | 2015-02-28 | 2019-01-29 | 国网河北能源技术服务有限公司 | Unit load (standard) steady state condition clustering algorithm based on data smoothness function |
| CN105045807A (en) * | 2015-06-04 | 2015-11-11 | 浙江力石科技股份有限公司 | Data cleaning algorithm based on Internet trading information |
| CN104951545B (en) * | 2015-06-23 | 2018-07-10 | 百度在线网络技术（北京）有限公司 | Export the data processing method and device of object |
| CN105259758A (en) * | 2015-10-22 | 2016-01-20 | 西安西热电站信息技术有限公司 | Thermal power unit operating parameter intelligent online optimization method based on massive historical data |
| CN105912564A (en) * | 2016-03-23 | 2016-08-31 | 广州新博庭网络信息科技股份有限公司 | Feature business object mining method, feature business object display method, feature business object mining device and feature business object display device |
| CN105928710B (en) * | 2016-04-15 | 2019-02-12 | 中国船舶工业系统工程研究院 | A kind of diesel engine fault monitoring method |
| CN106094744B (en) * | 2016-06-04 | 2018-10-23 | 上海大学 | Based on the determination method of thermoelectricity factory owner's operating parameter desired value of association rule mining |
| CN106056168B (en) * | 2016-08-13 | 2019-08-16 | 上海电力学院 | The determination method of gas-steam combined circulating generation unit operating condition optimal value |
| CN106960395A (en) * | 2017-03-14 | 2017-07-18 | 西安西热控制技术有限公司 | A kind of fired power generating unit historical data management device and method |
| CN108509645B (en) * | 2018-04-13 | 2020-03-24 | 华润电力风能(威海)有限公司 | Equipment early warning method |
| CN109446184B (en) * | 2018-08-28 | 2020-04-14 | 湖南大唐先一科技有限公司 | Big data analysis platform-based power generation big data preprocessing method and system |
| CN110059359A (en) * | 2019-03-21 | 2019-07-26 | 江苏东方国信工业互联网有限公司 | A kind of system and method for the control furnace body technique based on big data analysis |
| CN110703701A (en) * | 2019-09-02 | 2020-01-17 | 华电电力科学研究院有限公司 | Efficient data preprocessing method suitable for operating data of coal-fired power plant environment-friendly equipment |
| CN111474911B (en) * | 2020-04-28 | 2021-03-16 | 浙江浙能技术研究院有限公司 | Gaussian non-Gaussian characteristic collaborative analysis and monitoring method for non-steady operation of high-end coal-fired power generation equipment |
| CN113065766B (en) * | 2021-04-01 | 2024-05-14 | 中核核电运行管理有限公司 | Steam turbine operation condition optimizing method based on historical data mining analysis |
| CN115814686B (en) * | 2023-02-14 | 2023-04-18 | 博纯材料股份有限公司 | State monitoring method and system for laser gas mixing production system |
| CN116436369B (en) * | 2023-06-13 | 2023-10-03 | 威海天拓合创电子工程有限公司 | Servo motor control method based on big data analysis |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101187804A (en) * | 2006-11-15 | 2008-05-28 | 北京华电天仁电力控制技术有限公司 | Thermal power unit operation optimization rule extraction method based on data excavation |
| CN101299539A (en) * | 2007-11-08 | 2008-11-05 | 国网南京自动化研究院 | Large electric network on-line preventing control method based on static state and transient safety steady mode |
-
2012
- 2012-05-09 CN CN201210141675.9A patent/CN102708180B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101187804A (en) * | 2006-11-15 | 2008-05-28 | 北京华电天仁电力控制技术有限公司 | Thermal power unit operation optimization rule extraction method based on data excavation |
| CN101299539A (en) * | 2007-11-08 | 2008-11-05 | 国网南京自动化研究院 | Large electric network on-line preventing control method based on static state and transient safety steady mode |
Non-Patent Citations (2)
| Title |
|---|
| 基于数据挖掘的火电机组运行模式建立方法研究;隋丽颖等;《现代电力》;20100430;第27卷(第2期);第74-77页 * |
| 隋丽颖等.基于数据挖掘的火电机组运行模式建立方法研究.《现代电力》.2010,第27卷(第2期),第74-77页. |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102708180A (en) | 2012-10-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102708180B (en) | Data mining method in unit operation mode based on real-time historical library | |
| CN105427193B (en) | A kind of big data analysis device and method based on distributed time series data service | |
| CN102685221B (en) | Distributed storage and parallel mining method for state monitoring data | |
| CN105608144B (en) | A kind of big data analysis stage apparatus and method based on multilayered model iteration | |
| CN106651188A (en) | Electric transmission and transformation device multi-source state assessment data processing method and application thereof | |
| CN108228724A (en) | Power grid GIS topology analyzing method and storage medium based on chart database | |
| CN110147387A (en) | A kind of root cause analysis method, apparatus, equipment and storage medium | |
| CN110442038B (en) | Thermal power generating unit operation optimization target value determination method based on FP-Growth algorithm | |
| CN105117421B (en) | Based on the matched social network analysis method of graph structure | |
| CN103902816A (en) | Electrification detection data processing method based on data mining technology | |
| CN102609501B (en) | Data cleaning method based on real-time historical database | |
| CN107918830A (en) | A kind of distribution Running State assessment system and method based on big data technology | |
| CN103742901A (en) | Method for determining consumption difference analysis optimized target value system of circulating fluidized bed unit | |
| CN102142992A (en) | Communication alarm frequent itemset mining engine and redundancy processing method | |
| CN104155580A (en) | Voltage sag source positioning method with association analysis and electric power calculation being combined | |
| CN109446184B (en) | Big data analysis platform-based power generation big data preprocessing method and system | |
| CN105007294A (en) | System for quickly receiving and distributing power transmission and transformation equipment state monitoring big data | |
| CN106056466B (en) | Bulk power grid critical circuits recognition methods based on FP-growth algorithm | |
| CN105138650A (en) | Hadoop data cleaning method and system based on outlier mining | |
| CN110287237B (en) | Social network structure analysis based community data mining method | |
| CN106682225A (en) | Big data collecting and storing method and system | |
| CN108415355A (en) | A kind of efficient identification system of big data | |
| CN108230183A (en) | A kind of processing method of the grid equipment various dimensions comprehensive warning based on time scale measurement | |
| CN105900030A (en) | Method, system, and computer program product for analyzing production and/or process-engineering processes and/or process steps in a plant | |
| Li et al. | A distributed parallel alarm management strategy for alarm reduction in chemical plants |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| ASS | Succession or assignment of patent right |
Owner name: GUODIAN LONGYUAN POWER TECHNOLOGY ENGINEERING CO., Effective date: 20140630 |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20140630 Address after: 100039 Beijing West Fourth Ring Road, No. 16, building No. 1, Haidian District Patentee after: Beijing Huadian Tianren Electric Power Technology Co., Ltd. Patentee after: SP Longyuan Power Technology & Engineering Co., Ltd. Address before: 100039 Beijing West Fourth Ring Road, No. 16, building No. 1, Haidian District Patentee before: Beijing Huadian Tianren Electric Power Technology Co., Ltd. |
|
| CP03 | Change of name, title or address |
Address after: 101303 2nd floor, building 307, Guodian New Energy Institute, 9 Yingcai North 2nd Street, future science and Technology City, Changping District, Beijing Patentee after: Guoneng xinkong Internet Technology Co.,Ltd. Patentee after: SP LONGYUAN POWER TECHNOLOGY & ENGINEERING Co.,Ltd. Address before: Building 1, yard 16, West Fourth Ring Middle Road, Haidian District, Beijing 100039 Patentee before: BEIJING HUADIAN TIANREN ELECTRIC POWER CONTROL TECHNOLOGY Co.,Ltd. Patentee before: SP LONGYUAN POWER TECHNOLOGY & ENGINEERING Co.,Ltd. |
|
| CP03 | Change of name, title or address |