CN112612819A - Big data analysis and mining method and system for pumped storage power station - Google Patents
Big data analysis and mining method and system for pumped storage power station Download PDFInfo
- Publication number
- CN112612819A CN112612819A CN202011380160.5A CN202011380160A CN112612819A CN 112612819 A CN112612819 A CN 112612819A CN 202011380160 A CN202011380160 A CN 202011380160A CN 112612819 A CN112612819 A CN 112612819A
- Authority
- CN
- China
- Prior art keywords
- power station
- data
- storage power
- pumped
- pumped storage
- 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
- 238000003860 storage Methods 0.000 title claims abstract description 142
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000007418 data mining Methods 0.000 title claims abstract description 42
- 238000007405 data analysis Methods 0.000 title claims abstract description 30
- 238000004458 analytical method Methods 0.000 claims abstract description 36
- 238000012544 monitoring process Methods 0.000 claims abstract description 28
- 238000013507 mapping Methods 0.000 claims abstract description 9
- 238000010977 unit operation Methods 0.000 claims abstract description 9
- 238000012097 association analysis method Methods 0.000 claims abstract description 7
- 230000008569 process Effects 0.000 claims abstract description 7
- 238000004519 manufacturing process Methods 0.000 claims description 26
- 238000011156 evaluation Methods 0.000 claims description 20
- 238000005065 mining Methods 0.000 claims description 20
- 238000005086 pumping Methods 0.000 claims description 19
- 238000012423 maintenance Methods 0.000 claims description 10
- 238000012800 visualization Methods 0.000 claims description 9
- 230000000694 effects Effects 0.000 claims description 8
- 238000007794 visualization technique Methods 0.000 claims description 6
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 6
- 238000007621 cluster analysis Methods 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 claims description 4
- 241001672018 Cercomela melanura Species 0.000 claims description 3
- 238000009960 carding Methods 0.000 claims description 3
- 230000001932 seasonal effect Effects 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000009412 basement excavation Methods 0.000 claims 1
- 238000011160 research Methods 0.000 description 17
- 238000005516 engineering process Methods 0.000 description 11
- 230000006870 function Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 238000007726 management method Methods 0.000 description 9
- 230000004927 fusion Effects 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 238000003066 decision tree Methods 0.000 description 6
- 238000011161 development Methods 0.000 description 6
- 230000018109 developmental process Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 238000013524 data verification Methods 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 230000000875 corresponding effect Effects 0.000 description 3
- 238000013500 data storage Methods 0.000 description 3
- 230000001419 dependent effect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010219 correlation analysis Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000000611 regression analysis Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000001364 causal effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000013079 data visualisation Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005553 drilling Methods 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000033772 system development Effects 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
Images
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
- 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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- 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)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Probability & Statistics with Applications (AREA)
- Mathematical Physics (AREA)
- Fuzzy Systems (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a big data analysis and mining method and a big data analysis and mining system for a pumped storage power station, wherein the method comprises the following processes: collecting data information of a power grid side and a pumped storage power station side; performing big data mining based on the collected power grid side and pumped storage power station side data, and evaluating the service power grid capacity of the pumped storage power station; performing big data mining based on the collected pumped storage power station data, and monitoring the running state of a pumped storage power station unit; and visualizing the analysis result. The method establishes the mapping relation between the unit operation characteristic data set and the power grid operation characteristic data set by using an association analysis method, and comprehensively evaluates and analyzes the capacity of the pumped storage unit for serving the power grid in a multi-angle and multi-level manner.
Description
Technical Field
The invention belongs to the technical field of pumped storage systems, and particularly relates to a pumped storage power station big data analysis mining method and a pumped storage power station big data analysis mining system.
Background
In recent years, with the development of economic society and the adjustment of energy structures in China, the power supply structure, the power grid scale, the load characteristics, the supply and demand conditions, the trans-regional (provincial) transmission and the development of new energy in China are fundamentally changed. The pumped storage function positioning also changes greatly, but the corresponding theoretical research lags behind, which is not beneficial to the perfection of policies such as pumped storage development planning, operation evaluation and reasonable profit mechanism. The method has the advantages that double peaks of construction and management are developed, scientific positioning and reasonable planning are realized, the essential functions of the pumped storage power station and the scientific monitoring and evaluation system of the service power grid of the pumped storage power station are researched through advanced theories, and the speaking right for guiding policy and industry health development is mastered.
Although the existing data mining and information fusion technology is successfully applied to an electric power system, a plurality of domestic organizations have quite abundant results in the research of pumped storage power station function positioning, peak shaving power supply selection, various power supply joint management strategies and the like. However, the phenomenon that mass data cannot be fully utilized still exists at present, and the main problem of the phenomenon is that the research on the pumped storage operation characteristic and the actual service power grid capacity is lack of actual mass data verification; secondly, most research is unilateral on the power grid side and the power plant side, and the research on big data mining and information fusion associated with = users is only focused, and the demonstration of the matching degree of the big data mining and the information fusion is not sufficient.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provides a big data analysis and mining method and a big data analysis and mining system for a pumped storage power station.
In order to solve the technical problem, the invention provides a big data analysis and mining method for a pumped storage power station, which comprises the following processes:
collecting data information of a power grid side and a pumped storage power station side;
performing big data mining based on the collected power grid side and pumped storage power station side data, and evaluating the service power grid capacity of the pumped storage power station;
performing big data mining based on the collected pumped storage power station data, and monitoring the running state of a pumped storage power station unit;
and visualizing the analysis result.
Further, the power grid side data mainly comprises the installed scale of the power grid, a power supply structure, electric power and electric quantity, a grid structure, special energy sources such as a power transmission and transformation system, renewable energy sources and nuclear power units and the operation state of the power grid.
Further, the mining of big data and the evaluation of the service power grid capacity of the pumped storage power station based on the collected data of the power grid side and the pumped storage power station side include:
firstly, determining a pumped storage power station service power grid capacity evaluation index;
and evaluating the service power grid capacity of the pumped storage power station by adopting a big data analysis method based on the evaluation index.
Further, the pumped storage power station service grid capacity evaluation index includes:
peak load regulation, frequency modulation and phase modulation, accident standby, black start and other five service power grid capability evaluation indexes of the pumped storage service.
Further, the evaluating the pumped storage power station service power grid capacity by adopting a big data analysis method based on the evaluation index comprises the following steps:
analyzing the time variation trends of the incoming telegram electric quantity outside the east China power grid area, the cluster generated electric quantity of the pumped storage power station and the pumped storage electric quantity by using a time sequence algorithm to obtain the incidence relation among the three, and explaining the seasonal consumption effect of the pumped storage power station on the incoming telegram outside the power grid area;
the method comprises the following steps of performing regional division on the power receiving capacity of an incoming call outside a region by using cluster analysis, matching the peak-load-shifting capacity of pumped storage power stations in various regions, and reasonably allocating peak-load-shifting resources by means of energy mutual aid of the whole network and overall arrangement of pumped storage cluster pumping and dispatching modes;
and establishing a mapping relation between the unit operation characteristic data set and the power grid operation characteristic data set by using an association analysis method, and comprehensively evaluating the power grid capability of the pumped storage cluster service at multiple angles and multiple levels.
Further, based on the pumped storage power station data that collects, carry out big data mining, monitor pumped storage power station unit running state, include: analyzing the running state of the unit:
considering the runout as an important index for reflecting the running state of the pumping and storage unit, combining the runout of the unit with real-time production data,
based on the real-time monitoring data of the vibration of a machine frame, the swing degree of a guide bearing, the oil temperature of the guide bearing and the temperature of a bush when the machine set stably operates, the running state data of the machine set, the running age, the running time and the maintenance times, the constant data of a rated rotating speed, a rated load and a rated water head machine set, the characteristic analysis of the machine set vibration and the influence factors thereof is developed,
and evaluating the auxiliary maintenance effect of the unit runout, and simultaneously exploring the incidence relation between the typical fault and the runout.
Further, based on the pumped storage power station data that collects, carry out big data mining, monitor pumped storage power station unit running state, include: analyzing the production real-time data of the pumping and storage unit:
analyzing the data characteristics of the pumping and storage equipment in a steady operation state based on a basic database;
counting historical fault cases of the carding storage unit;
forming an equipment production real-time running state analysis model;
and the production data is input into the equipment to produce the real-time running state analysis model, and the real-time production data of the pumping unit is obtained through analysis.
Further, the visualization method comprises the following steps:
a visualization method of a parallel coordinate system, a data flow graph, a tree graph, a radar chart and a word cloud chart.
Correspondingly, the invention also provides a big data analysis and mining system of the pumped storage power station, which comprises the following components:
the data acquisition module is used for collecting data information of a power grid side and a pumped storage power station side;
the service capacity mining module is used for mining big data based on the collected power grid side and pumped storage power station side data and evaluating the service power grid capacity of the pumped storage power station;
the operation state monitoring module is used for mining big data based on the collected pumped storage power station data and monitoring the operation state of a pumped storage power station unit;
and the visualization module is used for visualizing the analysis result.
Compared with the prior art, the invention has the following beneficial effects: the method utilizes big data and data mining technology, establishes the mapping relation between the unit operation characteristic data set and the power grid operation characteristic data set by using an association analysis method, and comprehensively evaluates and analyzes the capacity of the pumped storage unit for serving the power grid in a multi-angle and multi-level manner.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
The pumped storage power station pumps water to an upper reservoir by using electric energy in the low ebb period of the electric load and discharges water to a hydropower station for generating power in a lower reservoir in the peak period of the electric load. Also known as energy storage hydropower stations. The device can convert redundant electric energy when the load of a power grid is low into high-value electric energy during the peak period of the power grid, is also suitable for frequency modulation and phase modulation, stabilizes the cycle wave and voltage of a power system, is suitable for emergency standby, and can improve the efficiency of a medium-temperature power station and a nuclear power station of the system.
The invention has the following inventive concept: effective information is extracted from mass data of power grid and power plant operation, a mapping relation between a unit operation characteristic data set and a power grid operation characteristic data set is established by using an association analysis method, comprehensive assessment and analysis are performed on the capacity of a pumped storage unit service power grid in multiple angles and multiple levels, finally, a visualization technology is used for designing a pumped storage power station service power grid research result into a monitoring display model, relevant index levels of the power grid capacity of a power station group service power grid are visually reflected, the capacity of the pumped storage power station service power grid is improved, and the power grid safety and the flexible and stable operation capacity of the power grid are better guaranteed.
Example 1
The big data analysis and mining method for the pumped storage power station, disclosed by the invention, is shown in figure 1 and comprises the following steps:
and step S1, collecting data information of the power grid side and the pumped storage power station side.
The method mainly analyzes the operation state of the pumped storage and the influence of the pumped storage on the power grid, so that the acquired information mainly comprises data of the power grid side and the pumped storage power station side.
1) Pumped storage unit information acquisition
In order to master the operation condition of the pumping storage unit, a production real-time system, a production management information system, an equipment state monitoring and evaluating system, an equipment reliability system, a hydraulic structure safety monitoring system and the like are constructed and operated, all equipment facilities of each power station are covered, and data of each system are displayed and stored in real time. Through the construction of the system, the operation data of the pumping and storage unit to which the company belongs are stored in a centralized manner, the data scale reaches TB level, and the data analysis can be subsequently supported.
2) Power grid data acquisition
The power grid side data mainly comprise special energy sources such as a power grid installed scale, a power supply structure, electric power and electricity quantity, a grid structure, a power transmission and transformation system, renewable energy sources, a nuclear power unit and the like, and mass data of the power grid running state.
And importing the pumped storage unit information and the power grid data into a Hive data warehouse of a big data platform. And processing the acquired original data according to an analysis target, including data quality inspection and data cleaning and conversion, establishing each analysis dimension according to research content, and extracting and converting the data according to the analysis dimension to obtain the broad-table data required by analysis.
And step S2, performing big data mining based on the collected data, and evaluating the service power grid capacity of the pumped storage power station.
Data Mining (Data Mining) is a process of extracting information and knowledge hidden in it that is not known a priori, but is potentially useful, from a large amount of incomplete, noisy, fuzzy, random Data. On the basis of large-scale data analysis, the relevance between the power grid operation parameters and the operation state of the pumped storage unit under the uncertain model condition is mainly analyzed, and the service level provided by pumped storage electricity for the power grid is quantized. Data mining is generally divided into 5 broad categories of methods.
In the time series
The time sequence mining is to mine frequent patterns, evolution rules and the like in the time sequence data and predict the future development trend. The main time series mining algorithm comprises the following steps: autoregressive model (AR), moving average Model (MA), autoregressive moving average model (ARMA), autoregressive cumulative moving average model (ARIMA), and the like. The time series analysis can predict future trends after a model is established according to the existing data information.
In the central section linear regression
Regression analysis is a method that attempts to find some kind of law from actual data. Regression analysis establishes and analyzes the functional relationship between certain response variables (dependent variables) and important factors (independent variables). The regression value represents any one of the expected values of the condition, and in data modeling is often the expected value of the condition of the dependent variable given the condition variable. With the prediction attributes as independent variables and the prediction targets as dependent variables, regression techniques can be used for prediction.
In-pixel clustering algorithm
Cluster analysis refers to the process of analysis of a collection of physical or abstract objects grouped into classes composed of similar objects. It is an important human behavior. The goal of cluster analysis is to collect data on a similar basis for classification. Clustering is derived from many fields, including mathematics, computer science, statistics, biology and economics. In different application fields, many clustering techniques have been developed, and these techniques are used to describe data, measure the similarity between different data sources, and classify data sources into different clusters. Clustering is to classify data into several categories according to similarity, where data in the same category are similar to each other and data in different categories are different. Clustering analysis can build macroscopic concepts, discover distribution patterns of data, and possibly correlations between data attributes.
In-wing association rules
The association rule mining means that certain regularity exists between values of two or more variables. Data association is an important, discoverable class of knowledge that exists in databases. Associations are divided into simple associations, timing associations and causal associations. The purpose of the correlation analysis is to find out the hidden correlation network in the database. Generally, two thresholds of support degree and credibility are used for measuring the correlation of the association rule, and parameters such as interestingness and correlation are continuously introduced, so that the mined rule is more in line with the requirement.
In the decision tree
Decision tree (DecisionTree) is a decision analysis method for evaluating the risk of a project and judging the feasibility of the project by constructing a decision tree to obtain the probability that the expected value of the net present value is greater than or equal to zero on the basis of the known occurrence probability of various conditions, and is a graphical method for intuitively applying probability analysis. This decision branch is called a decision tree because it is drawn to resemble a branch of a tree. In machine learning, a decision tree is a predictive model that represents a mapping between object attributes and object values.
Based on the collected data, big data mining is carried out, and the pumped storage power station service power grid capacity is evaluated, and the method specifically comprises the following steps:
21) firstly, determining the evaluation index of the service power grid capacity of the pumped storage power station
Based on the research on the characteristics of the pumped storage power station and the combing of evaluation indexes, five major functions of peak load regulation, frequency modulation and phase modulation, accident backup, black start and other services (service extra-high voltage development and political power protection) are established, and the evaluation index of the power grid capacity of the pumped storage service can be quantified.
22) Evaluation index-based big data analysis method for evaluating pumped storage power station service power grid capacity
Analyzing the time variation trends of the incoming telegram electric quantity outside the east China power grid area, the cluster generated electric quantity of the pumped storage power station and the pumped storage electric quantity by using a time sequence algorithm to obtain the incidence relation among the three, and explaining the seasonal consumption effect of the pumped storage power station on the incoming telegram outside the power grid area;
the method comprises the following steps of performing regional division on the power receiving capacity of an incoming call outside a region by using cluster analysis, matching the peak-load-shifting capacity of pumped storage power stations in various regions, and reasonably allocating peak-load-shifting resources by means of energy mutual aid of the whole network and overall arrangement of pumped storage cluster pumping and dispatching modes;
and establishing a mapping relation between the unit operation characteristic data set and the power grid operation characteristic data set by using an association analysis method, and comprehensively evaluating the power grid capability of the pumped storage cluster service at multiple angles and multiple levels.
And step S3, performing big data mining based on the collected pumped storage power station data, and monitoring the operation state of the pumped storage power station unit.
And (4) carrying out data exploration by combining the new source data condition, selecting a proper data mining model for analysis, and constructing a pumped storage service power grid comprehensive intelligent monitoring analysis model.
31) Analyzing the running state of the unit
Considering the vibration as an important index for reflecting the operation state of the pumping and storage unit, combining the vibration of the unit with production real-time data, taking mining analysis of the value of the production real-time data as a fundamental point, taking pulse production and operation practical problems as a starting point, considering from the aspects of type, water head, rotating speed and the like, selecting the ten pumping and storage power stations 40 units with relatively complete data such as natural terrace, pleasure and the like as research objects, developing characteristic analysis of the vibration of the unit and influence factors thereof based on real-time monitoring data such as frame vibration, swing degree of a guide bearing, oil temperature of the guide bearing, tile temperature and the like, unit operation state data such as operation age, operation duration, maintenance times and the like, and unit constant data such as rated rotating speed, rated load, rated water head and the like during stable operation of the unit, evaluating the auxiliary maintenance effect of the vibration of the unit, and simultaneously exploring the incidence relation between typical faults and.
32) Data storage policy research
Based on the mass data of a production management information system, an equipment state monitoring and evaluating system, a production real-time system and a hydraulic building safety monitoring system, the data storage of each system is optimized, the system load is reduced, the data of each system are correlated, and the data monitoring, inquiring and visualization levels are improved. The following studies were carried out in particular:
researching a data monitoring mode of a user in the middle-rail system;
a system in front and back and user data classification and correlation studies;
the method comprises the following steps of (1) conducting research on a user in the middle of the production and a monitoring data storage method;
data query and visualization method research is customized in the middle and over;
based on the automatic and manual input data of the inspection data, the production management system data, the hydraulic building safety monitoring system, the production implementation system and the like, the equipment state is comprehensively analyzed, the equipment health level is evaluated, and the strategy of equipment state maintenance is researched and formulated
33) Production real-time data analysis of pumping and storage unit
Although the existing data mining and information fusion technology is successfully applied to an electric power system, a plurality of domestic organizations have quite abundant results in the research of pumped storage power station function positioning, peak shaving power supply selection, various power supply joint management strategies and the like. However, the phenomenon that mass data cannot be fully utilized still exists at present, and the main problem of the phenomenon is that the research on the pumped storage operation characteristic and the actual service power grid capacity is lack of actual mass data verification; secondly, most research is unilateral on the power grid side and the power plant side, and the research on big data mining and information fusion associated with = users is only focused, and the demonstration of the matching degree of the big data mining and the information fusion is not sufficient. The data mining and information fusion technology is introduced, potential useful information and knowledge hidden in the data are extracted, specific relevance and rules existing in a large amount of data are mined, the power grid requirements are used as guidance, meanwhile, relevance analysis is carried out by combining power plant side data, and relevant data verification is carried out.
The method is characterized in that the vibration of the unit is surrounded from a big data angle, the vibration and the influence factors thereof, the vibration auxiliary maintenance effect evaluation, the vibration and typical fault association relation and other aspects are researched, and a decision reference is provided for the fine management of the safety production operation of the company power station. The following aspects are specifically developed:
and in the positive well, based on a basic database, researching data characteristics of the extraction and storage equipment in a running steady state by adopting mathematical algorithms such as classification, summarization, comparison and analysis and the like, summarizing the difference and the rule of the running stability of the extraction and storage unit of the company, and providing suggestions for equipment management.
And counting and carding historical fault cases of the pumping unit in the positive and negative direction, developing correlation analysis by using stability data and fault defects of pumping equipment, mining signs related to vibration and swing faults of the pumping unit, and summarizing typical fault rules.
And forming a real-time running state analysis model of equipment production in the positive and negative sides, developing real-time data verification, including effect evaluation before and after state maintenance and auxiliary maintenance, and gradually applying to production practice.
And the production data analysis is applied to the analysis interactive platform and the equipment state monitoring and evaluation system development in the positive and negative sides.
Step S4, the above analysis result is visualized.
The data assets become important assets of enterprises, the capability and the speed of application data are considered to be one of core competitiveness of the enterprises, through designing a data asset panoramic visualization platform, the professional data which are relatively independent in the past are intensively applied to generate rich cross-department, cross-business and cross-process monitoring analysis contents, quantification, visualization and concretization of the analysis result of the operation and supervision center main business are realized, the operation and supervision center main business is vividly displayed in front of users, and the understanding and the key point catching are facilitated. The construction of the data asset panoramic visualization platform can integrate all information resources to be applied to company decision assistance, and powerful support is provided for improving the professional management level and the fusion degree of each business.
In-side parallel coordinate system technology
Parallel coordinates are one of the earliest proposed visualization techniques to represent n-dimensional data in two dimensions. The basic idea is to display by dimension reduction mapping the K-dimensional space into two dimensions using coordinate axes that are parallel and equidistant to each other. These coordinate axes correspond to different spatial dimensions, respectively, and vary linearly from the minimum value to the maximum value of the corresponding dimension. Each data item has a broken line representation, the broken line and each coordinate axis have an intersection, and the intersection value is the value of the data item corresponding to the coordinate axis.
In-pixel dataflow graph techniques
Flow graphs are commonly used to show the trend of a number of variables over time. Each variable is represented by a bar. The width of the color bar represents the value or the size of the ratio of the variable at a certain point in time.
In-wing tree diagram technology
Each rectangle in the tree represents a node of the tree, and the smaller rectangle in the large rectangle represents a child node contained by the parent node. Different nodes are distinguished by different colors, the value of the node is represented by the size of a rectangular area, and the node has the function of drilling down.
In the radar chart
Radar plots can be used to demonstrate the degree of similarity between samples by presenting information in multiple dimensions on a circle.
In-term cloud picture technology
The word cloud picture is also called character cloud or label cloud, the labels of the word cloud picture are generally independent words, the importance degree of the words can be expressed by changing the font size or the color, and therefore the label cloud can flexibly search one label according to the word sequence or the hot degree.
A visualization technology is utilized to design a pumped storage power station service power grid research result into a monitoring display model, and the related index level of the power station group service power grid capacity is visually reflected.
By adopting a big data visualization technology, dynamic display of the analysis result and the model of the pumped storage power station service power grid capacity on a new source company operation monitoring large screen is realized, intelligent trend analysis and intelligent grading early warning of the unit operation state are realized, and safe and stable operation of the unit is guaranteed.
The method utilizes big data and data mining technology, establishes the mapping relation between the unit operation characteristic data set and the power grid operation characteristic data set by using an association analysis method, and comprehensively evaluates and analyzes the capacity of the pumped storage unit for serving the power grid in a multi-angle and multi-level manner.
Example 2
Correspondingly, the big data analysis and mining system for the pumped storage power station comprises the following components:
the data acquisition module is used for collecting data information of a power grid side and a pumped storage power station side;
the service capacity mining module is used for mining big data based on the collected power grid side and pumped storage power station side data and evaluating the service power grid capacity of the pumped storage power station;
the operation state monitoring module is used for mining big data based on the collected pumped storage power station data and monitoring the operation state of a pumped storage power station unit;
and the visualization module is used for visualizing the analysis result.
The specific implementation technical scheme of each module of the system is shown in the implementation process of each step in the method in the embodiment 1.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
Claims (9)
1. A big data analysis and mining method for a pumped storage power station is characterized by comprising the following processes:
collecting data information of a power grid side and a pumped storage power station side;
performing big data mining based on the collected power grid side and pumped storage power station side data, and evaluating the service power grid capacity of the pumped storage power station;
performing big data mining based on the collected pumped storage power station data, and monitoring the running state of a pumped storage power station unit;
and visualizing the analysis result.
2. The big data analysis and mining method for the pumped storage power station as claimed in claim 1, wherein the grid-side data mainly comprises grid installed scale, power structure, electric power quantity, grid structure, special energy sources such as power transmission and transformation system, renewable energy sources and nuclear power unit, and grid operation state.
3. The pumped-storage power station big data analysis and mining method as claimed in claim 1, wherein the big data mining for evaluating the service grid capacity of the pumped-storage power station based on the collected grid-side and pumped-storage power station-side data comprises:
firstly, determining a pumped storage power station service power grid capacity evaluation index;
and evaluating the service power grid capacity of the pumped storage power station by adopting a big data analysis method based on the evaluation index.
4. The pumped-storage power station big data analysis mining method as claimed in claim 3, wherein the pumped-storage power station service grid capacity evaluation index comprises:
peak load regulation, frequency modulation and phase modulation, accident standby, black start and other five service power grid capability evaluation indexes of the pumped storage service.
5. The big data analysis mining method for the pumped storage power station as claimed in claim 4, wherein the big data analysis method is used for evaluating the service grid capacity of the pumped storage power station based on the evaluation index, and comprises the following steps:
analyzing the time variation trends of the incoming telegram electric quantity outside the east China power grid area, the cluster generated electric quantity of the pumped storage power station and the pumped storage electric quantity by using a time sequence algorithm to obtain the incidence relation among the three, and explaining the seasonal consumption effect of the pumped storage power station on the incoming telegram outside the power grid area;
the method comprises the following steps of performing regional division on the power receiving capacity of an incoming call outside a region by using cluster analysis, matching the peak-load-shifting capacity of pumped storage power stations in various regions, and reasonably allocating peak-load-shifting resources by means of energy mutual aid of the whole network and overall arrangement of pumped storage cluster pumping and dispatching modes;
and establishing a mapping relation between the unit operation characteristic data set and the power grid operation characteristic data set by using an association analysis method, and comprehensively evaluating the power grid capability of the pumped storage cluster service at multiple angles and multiple levels.
6. The pumped-storage power station big data analysis and mining method as claimed in claim 1, wherein the big data mining based on the collected pumped-storage power station data to monitor the operation state of the pumped-storage power station unit comprises: analyzing the running state of the unit:
considering the runout as an important index for reflecting the running state of the pumping and storage unit, combining the runout of the unit with real-time production data,
based on the real-time monitoring data of the vibration of a machine frame, the swing degree of a guide bearing, the oil temperature of the guide bearing and the temperature of a bush when the machine set stably operates, the running state data of the machine set, the running age, the running time and the maintenance times, the constant data of a rated rotating speed, a rated load and a rated water head machine set, the characteristic analysis of the machine set vibration and the influence factors thereof is developed,
and evaluating the auxiliary maintenance effect of the unit runout, and simultaneously exploring the association relation between the typical fault and the runout.
7. The pumped-storage power station big data analysis and mining method as claimed in claim 6, wherein the big data mining based on the collected pumped-storage power station data to monitor the operation state of the pumped-storage power station unit comprises: analyzing the production real-time data of the pumping and storage unit:
analyzing the data characteristics of the pumping and storage equipment in a steady operation state based on a basic database;
counting historical fault cases of the carding storage unit;
forming an equipment production real-time running state analysis model;
and the production data is input into the equipment to produce the real-time running state analysis model, and the real-time production data of the pumping unit is obtained through analysis.
8. The pumped-storage power station big data analysis mining method according to claim 1, wherein the visualization method comprises:
a parallel coordinate system, a data flow graph, a tree graph, a radar chart and a word cloud chart visualization method.
9. The utility model provides a big data analysis excavation system of pumped storage power station, characterized by includes:
the data acquisition module is used for collecting data information of a power grid side and a pumped storage power station side;
the service capacity mining module is used for mining big data based on the collected power grid side and pumped storage power station side data and evaluating the service power grid capacity of the pumped storage power station;
the operation state monitoring module is used for mining big data based on the collected pumped storage power station data and monitoring the operation state of a pumped storage power station unit;
and the visualization module is used for visualizing the analysis result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011380160.5A CN112612819A (en) | 2020-12-01 | 2020-12-01 | Big data analysis and mining method and system for pumped storage power station |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011380160.5A CN112612819A (en) | 2020-12-01 | 2020-12-01 | Big data analysis and mining method and system for pumped storage power station |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112612819A true CN112612819A (en) | 2021-04-06 |
Family
ID=75229778
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011380160.5A Pending CN112612819A (en) | 2020-12-01 | 2020-12-01 | Big data analysis and mining method and system for pumped storage power station |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112612819A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113139759A (en) * | 2021-05-19 | 2021-07-20 | 杭州市电力设计院有限公司余杭分公司 | Power grid data asset management method and system |
CN113515896A (en) * | 2021-08-06 | 2021-10-19 | 红云红河烟草(集团)有限责任公司 | Data missing value filling method for real-time cigarette acquisition |
CN113553358A (en) * | 2021-07-27 | 2021-10-26 | 国网天津市电力公司电力科学研究院 | Data mining-based power grid equipment invalid data identification method and device |
CN113592281A (en) * | 2021-07-26 | 2021-11-02 | 内蒙古呼和浩特抽水蓄能发电有限责任公司 | Power station performance analysis method, device, equipment and storage medium |
CN113139759B (en) * | 2021-05-19 | 2024-06-04 | 杭州市电力设计院有限公司余杭分公司 | Power grid data asset management method and system |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN209896770U (en) * | 2019-04-04 | 2020-01-03 | 国网新源控股有限公司 | Intelligent monitoring and analyzing system for pumped storage power station service power grid |
-
2020
- 2020-12-01 CN CN202011380160.5A patent/CN112612819A/en active Pending
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN209896770U (en) * | 2019-04-04 | 2020-01-03 | 国网新源控股有限公司 | Intelligent monitoring and analyzing system for pumped storage power station service power grid |
Non-Patent Citations (2)
Title |
---|
李国和 等: "基于生产实时大数据的抽水蓄能机组稳定性研究与应用", 《水电与抽水蓄能》 * |
魏敏 等: "基于大数据分析的抽水蓄能电站服务华东电网能力探索", 《抽水蓄能发展规划与建设管理》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113139759A (en) * | 2021-05-19 | 2021-07-20 | 杭州市电力设计院有限公司余杭分公司 | Power grid data asset management method and system |
CN113139759B (en) * | 2021-05-19 | 2024-06-04 | 杭州市电力设计院有限公司余杭分公司 | Power grid data asset management method and system |
CN113592281A (en) * | 2021-07-26 | 2021-11-02 | 内蒙古呼和浩特抽水蓄能发电有限责任公司 | Power station performance analysis method, device, equipment and storage medium |
CN113553358A (en) * | 2021-07-27 | 2021-10-26 | 国网天津市电力公司电力科学研究院 | Data mining-based power grid equipment invalid data identification method and device |
CN113553358B (en) * | 2021-07-27 | 2022-12-06 | 国网天津市电力公司电力科学研究院 | Data mining-based power grid equipment invalid data identification method and device |
CN113515896A (en) * | 2021-08-06 | 2021-10-19 | 红云红河烟草(集团)有限责任公司 | Data missing value filling method for real-time cigarette acquisition |
CN113515896B (en) * | 2021-08-06 | 2022-08-09 | 红云红河烟草(集团)有限责任公司 | Data missing value filling method for real-time cigarette acquisition |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112612819A (en) | Big data analysis and mining method and system for pumped storage power station | |
Daim et al. | Patent analysis of wind energy technology using the patent alert system | |
CN107918830A (en) | A kind of distribution Running State assessment system and method based on big data technology | |
Lei et al. | Short-term load forecasting with clustering–regression model in distributed cluster | |
Ji et al. | Research on the algorithm of education data mining based on big data | |
CN112884452A (en) | Intelligent operation and maintenance multi-source data acquisition visualization analysis system | |
CN110826237A (en) | Bayesian belief network-based wind power equipment reliability analysis method and device | |
CN109522297A (en) | A kind of grid operating monitoring cloud platform | |
CN115564071A (en) | Method and system for generating data labels of power Internet of things equipment | |
Li et al. | The clean energy development path and sustainable development of the ecological environment driven by big data for mining projects | |
CN111260206A (en) | Photovoltaic power generation influence factor evaluation model, construction method and application | |
Guan et al. | Customer load forecasting method based on the industry electricity consumption behavior portrait | |
CN116611813B (en) | Intelligent operation and maintenance management method and system based on knowledge graph | |
Wei et al. | Glad: A method of microgrid anomaly detection based on esd in smart power grid | |
CN117033923A (en) | Method and system for predicting crime quantity based on interpretable machine learning | |
Tang et al. | Application technology of big data in smart grid and its development prospect | |
Huang et al. | An intelligent operation and maintenance system for power consumption based on deep learning | |
Ghasemi et al. | Big Data Analytics in Smart Energy Systems and Networks: A Review | |
Keyan et al. | Anomaly detection method of distribution network line loss based on hybrid clustering and LSTM | |
CN117934209B (en) | Regional power system carbon emission big data analysis method based on knowledge graph | |
Liu | Effective combination and application path of computer big data analysis and cloud computing network technology | |
Kotriwala | Load Forecasting for Temporary Power Installations | |
Kumar et al. | AI-Empowered IoT for Sustainable Energy Technologies | |
Yang et al. | Modelling and design of wind power forecast error estimation system | |
Tao et al. | Power consumption behavior analysis for customer side flexible resources based on data mining |
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: 20210406 |
|
RJ01 | Rejection of invention patent application after publication |