CN111522858B - Multi-dimensional state vector-based pumping unit performance degradation early warning method - Google Patents
Multi-dimensional state vector-based pumping unit performance degradation early warning method Download PDFInfo
- Publication number
- CN111522858B CN111522858B CN202010183841.6A CN202010183841A CN111522858B CN 111522858 B CN111522858 B CN 111522858B CN 202010183841 A CN202010183841 A CN 202010183841A CN 111522858 B CN111522858 B CN 111522858B
- Authority
- CN
- China
- Prior art keywords
- health
- performance degradation
- value
- calculating
- 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
- 238000006731 degradation reaction Methods 0.000 title claims abstract description 121
- 230000015556 catabolic process Effects 0.000 title claims abstract description 120
- 239000013598 vector Substances 0.000 title claims abstract description 70
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000005086 pumping Methods 0.000 title claims abstract description 28
- 230000036541 health Effects 0.000 claims abstract description 113
- 238000012544 monitoring process Methods 0.000 claims abstract description 112
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 53
- 239000000498 cooling water Substances 0.000 claims abstract description 32
- 230000003321 amplification Effects 0.000 claims abstract description 20
- 238000003199 nucleic acid amplification method Methods 0.000 claims abstract description 20
- 238000012216 screening Methods 0.000 claims abstract description 19
- 238000010977 unit operation Methods 0.000 claims description 6
- 230000003862 health status Effects 0.000 description 14
- 238000003491 array Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 230000002159 abnormal effect Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000010349 pulsation Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 230000006866 deterioration Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000010248 power generation Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000007619 statistical method Methods 0.000 description 2
- 241001672018 Cercomela melanura Species 0.000 description 1
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000004931 aggregating effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000010687 lubricating oil Substances 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000002904 solvent Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000011144 upstream manufacturing 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
- G06F16/2462—Approximate or statistical queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/248—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
-
- 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
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/20—Hydro energy
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Databases & Information Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Mathematical Optimization (AREA)
- Marketing (AREA)
- Pure & Applied Mathematics (AREA)
- Operations Research (AREA)
- Software Systems (AREA)
- Mathematical Analysis (AREA)
- Computational Linguistics (AREA)
- Computational Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Algebra (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Evolutionary Biology (AREA)
- Fuzzy Systems (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention provides a pumping storage unit performance degradation early warning method based on a multidimensional state vector, which comprises the following steps: acquiring health state monitoring data in preset historical time, and screening and grouping the health state monitoring data according to active power, a water head and cooling water temperature in sequence to obtain a plurality of health data subsets; respectively calculating to obtain a health state feature vector corresponding to each health data subset; calculating a unit performance degradation index threshold according to the amplification and the weight of each health characteristic value in each health state characteristic vector, and calculating a linear fitting slope threshold; acquiring unit state monitoring data in real time, and calculating a unit performance degradation index and a slope of a preset period; sequentially and respectively judging whether the degradation indexes are larger than corresponding degradation index thresholds to obtain a first judgment result; and judging whether the slope of the fitting straight line is greater than a slope threshold value or not to obtain a second judgment result, and protecting the pumping and storage unit.
Description
Technical Field
The invention relates to the technical field, in particular to a pumping unit performance degradation early warning method based on a multi-dimensional state vector.
Background
The pumped storage unit has rapid response and flexible operation mode, has various functions of peak regulation, valley filling, frequency modulation, phase modulation, emergency standby, black start and the like in a power system, and plays an important role in the safe and stable operation and the economic operation of a power grid. In addition, large-scale development of random, intermittent new energy sources requires pumped-storage power stations for consumption and storage. Therefore, the pumped storage power station is well developed. In recent years, the construction speed of pumped storage power stations is increased, and the total number of pumped storage power stations and the total number of main units in research, construction and operation are continuously expanded.
And 3, research and development of water and electricity science and technology, equipment and ecological technology are carried out, and an 'internet +' intelligent hydropower station is built. The integration of key development and information technology promotes the design, construction and management digitization, networking and intellectualization of hydropower engineering, makes full use of the technologies such as Internet of things, cloud computing and big data, develops and establishes digital regions and digital hydropower, promotes the friendly interaction of intelligent hydropower stations, intelligent power grids and intelligent energy grids, and is a great trend of hydropower technology development.
The pumped storage power station has the characteristics of high water head, high rotating speed, bidirectional rotation, complex operation condition and the like, so that the pumped storage unit is more prone to failure than a conventional hydroelectric generating set, and the operation stability of the unit becomes a key point of attention. At present, most of pumped storage units are installed on-line monitoring systems, and monitoring parameters comprise unit vibration, main shaft throw, water pressure pulsation, working condition parameters and the like. However, most of the applications of the state monitoring system still remain in the aspects of simple comparison of monitoring parameter value observation and simple threshold value alarm, and the protection on the safety performance of the unit is not timely enough and accurate.
Therefore, a new method for performing safety alarm on the unit state monitoring data is needed.
Disclosure of Invention
In view of the above, the present invention provides a method for early warning performance degradation of a pumped storage unit, so as to solve the problem that the current state monitoring system cannot protect the safety performance of the unit timely and accurately.
Based on the above purpose, the invention provides a pumping unit performance degradation early warning method based on a multidimensional state vector, which comprises the following steps:
acquiring health state monitoring data of the pumping unit in normal operation within preset historical time;
and screening and grouping the health state monitoring data in sequence according to active power, a water head and cooling water temperature to obtain a plurality of health data subsets. Each health data subset comprises a plurality of health multidimensional state vectors corresponding to the same steady-state working condition, each health multidimensional state vector corresponds to different moments, and each health multidimensional state vector comprises active power, a water head, a cooling water temperature and a plurality of other monitoring parameters;
respectively calculating health characteristic values of a plurality of other monitoring parameters in each health data subset to obtain a health state characteristic vector corresponding to each health data subset;
calculating a unit performance degradation index threshold according to the amplification and the weight of each health characteristic value in each health state characteristic vector, and calculating a linear fitting slope threshold of the unit performance degradation index threshold;
acquiring unit state monitoring data in real time, screening real-time data subsets at intervals of a preset period, and respectively calculating a real-time state feature vector corresponding to each real-time data subset;
calculating a unit performance degradation index according to the amplification and the weight of each real-time characteristic value in each real-time state characteristic vector respectively, and calculating the linear fitting slope of the unit performance degradation index;
sequentially and respectively judging whether the degradation indexes in the unit performance degradation index sequence in the preset period are larger than corresponding degradation index thresholds to obtain a first judgment result; judging whether the slope of a fitting straight line of the unit performance degradation index sequence is greater than a slope threshold value or not to obtain a second judgment result;
and protecting the pumping and storage unit according to the first judgment result and the second judgment result.
In one embodiment, the screening and grouping health state monitoring data according to active power, a water head and a cooling water temperature in sequence to obtain a plurality of health data subsets includes:
determining an active power range corresponding to typical working conditions in historical state monitoring data, and dividing the state monitoring data according to the active power range corresponding to the typical working conditions to obtain a first number of typical working condition data subsets, wherein the first number is the same as the number of the typical working conditions;
determining the maximum value and the minimum value of the water head in the historical state monitoring data, equally dividing the difference value of the maximum value and the minimum value, and screening the typical working condition data subsets according to the equally divided water head range to obtain a second number of water head data subsets, wherein the second number is equal to the product of the equally divided number of the water head and the first number;
determining the maximum value and the minimum value of the cooling water temperature in the historical state monitoring data, equally dividing the difference value of the maximum value and the minimum value, and screening each water head data subset according to the equally divided cooling water temperature range to obtain a third number of health data subsets, wherein the third number is equal to the product of the equally divided number of the cooling water temperature and the second number, and in the health data subsets, the time corresponding to the other monitoring parameters is the same as the time corresponding to the cooling water temperature.
In one embodiment, the determining the active power range corresponding to the typical operating condition in the historical state monitoring data includes:
calculating a probability density distribution curve of a data subset formed by all active power data in the health state monitoring data;
calculating an extreme point of the probability density distribution curve to obtain the power of a typical working condition;
and selecting the value in the preset error range of the extreme point as the active power range of the typical working condition.
In one embodiment, the calculating the health characteristic values of the plurality of other monitoring parameters in each health data subset respectively comprises:
respectively calculating the probability density distribution curve of each other monitoring parameter;
and respectively selecting a numerical value corresponding to the maximum value of the probability density distribution curve corresponding to each other monitoring parameter to obtain the health characteristic value of each other monitoring parameter.
In one embodiment, the unit performance degradation index is calculated by
Calculating, wherein I is a unit performance degradation index, A i For effective amplification of each real-time characteristic value, λ i Is the weight of each characteristic value, a i And amplifying each real-time characteristic value.
In one of the embodiments, the first and second parts of the device,
wherein, X i "real-time characteristic values for various other monitored parameters, X i A health characteristic value for each of the other monitored parameters.
In one embodiment, the computer group performance degradation index threshold comprises a pass through
Calculating, wherein I' is a unit performance degradation index threshold value, A i ' effective amplification of respective health characteristic value, lambda i Is the weight of each characteristic value, a i ' is the amplification of each health characteristic value.
In one of the embodiments, the first and second electrodes are,
wherein, X i Firstly, 70% of operation allowable values of various other monitoring parameters in relevant countries, industry standards and power station unit operation regulations are taken, if X is i '＜X i Then take X l ' is 100% of operation allowable value of each other monitoring parameter in relevant country, industry standard and power station unit operation regulation, if
Then get a i '＝15％，X i A health characteristic value for each of the other monitored parameters.
In one embodiment, calculating a linearly fitted slope threshold of the unit performance degradation index threshold comprises:
and setting the performance degradation index of the unit in normal operation as an initial value 0, and calculating the slope of a straight line when the value reaches the threshold value of the performance degradation index of the unit after one month (30 days) to obtain the slope threshold value.
In one embodiment, the protecting the pumping unit according to the first judgment result and the second judgment result includes:
and when at least one of the first judgment result and the second judgment result is yes, sending out unit abnormity early warning.
From the above, the pumping unit performance degradation early warning method provided by the invention can establish health data subsets under various working conditions with active power, a water head and cooling water temperature as dividing parameters, calculate corresponding health state characteristic vectors, calculate corresponding unit performance degradation index thresholds through calculating the amplification of the corresponding health state characteristic vectors, and calculate unit performance degradation index linear fitting slope thresholds. The performance degradation index of the unit during operation is obtained in real time, whether the performance degradation index is larger than a threshold value is judged by comparing the real-time performance degradation index with the corresponding threshold value, meanwhile, the real-time performance degradation index sequence is linearly fitted, whether the real-time performance degradation index sequence is larger than a slope threshold value is judged, and according to the judgment result, when the unit performance is judged to be obviously abnormal or have trend degradation, early warning is sent out in advance, so that accidents are avoided, and the safe and stable operation performance of the unit is improved. The pumping and storage unit can be efficiently and reliably protected when the unit performance has a degradation trend.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of a pumping unit performance degradation early warning method based on a multidimensional state vector according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of health status monitoring data components according to an embodiment of the present invention;
FIG. 3 is a flowchart of an embodiment of the present invention for performing condition screening grouping on health status monitoring data packets;
FIG. 4 is a flow chart of determining an active power range corresponding to typical operating conditions in historical state monitoring data;
FIG. 5 is a schematic diagram of active power distribution of a unit in approximately three months according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of the probability density distribution of active power of a certain unit in approximately three months according to an embodiment of the present invention;
FIG. 7 is a flow chart of an embodiment of the present invention for separately calculating health characteristic values for a plurality of other monitored parameters in each health data subset;
FIG. 8 is a schematic diagram of the numerical value scatter distribution of the amplitude values in the upward direction X of the unit under the P1 working condition;
FIG. 9 is a schematic diagram of the scattering distribution of the amplitude values of the lower guide X direction of the unit under the P1 working condition;
FIG. 10 is a graph of the probability density distribution of the up guide X of FIG. 7;
fig. 11 is a probability density distribution curve of the lower guide X direction in fig. 8.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to specific embodiments and the accompanying drawings.
It is to be noted that technical terms or scientific terms used in the embodiments of the present invention should have the ordinary meanings as understood by those having ordinary skill in the art to which the present disclosure belongs, unless otherwise defined. The use of "first," "second," and similar terms in this disclosure is not intended to indicate any order, quantity, or importance, but rather is used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that the element or item preceding the word comprises the element or item listed after the word and its equivalent, but does not exclude other elements or items. The terms "connected" or "coupled" and the like are not restricted to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", and the like are used merely to indicate relative positional relationships, and when the absolute position of the object being described is changed, the relative positional relationships may also be changed accordingly.
The pumping storage unit, namely a water pumping storage unit, converts the residual electric energy into mechanical energy at the time of a power load valley, and pumps the lower reservoir water to the upper reservoir; the power generation pumping device mainly comprises a water pump turbine, a power generation motor, a speed regulation system, an excitation system, a monitoring system and other equipment.
The inventor of the invention finds that the current static alarm threshold ignores the performance difference of the unit under different working conditions, lacks the early warning capability of the early latent fault of the unit and is far insufficient to fully reflect the running state of the unit in the long-term safety research work on the state of the pumping and storage unit; in addition, the existing research basically adopts the comparison between a measured parameter monitoring value and a single limit value to realize out-of-limit pre-alarming, the limit value is usually determined by referring to relevant national standards, industry standards, manufacturer suggested values and the like, the absolute value comparison method has the defects that the individual characteristics of the unit cannot be reflected, the operation working condition of the unit is limited, and the alarming practicability is not good enough; the single measurement parameter cannot reflect the performance state of the whole unit, so that the pre-alarm of the single parameter cannot reflect whether the performance state of the whole unit is subjected to trend degradation or obvious abnormality.
The inventor provides a method for solving the technical problem of safety early warning of the pumped storage unit, which comprises the steps of establishing a multi-dimensional health state vector under each typical working condition, then calculating the distance between a real-time state vector and the health state vector when the unit operates, and sending out unit abnormity early warning when the vector distance is larger than a certain preset value or the vector distance has obvious trend change. According to the invention, by comparing the distance between the real-time state vector and the health state vector of the unit and analyzing the result, the state of the running unit can be judged, and early warning can be given when the unit is in trend deterioration or obviously abnormal, so that accidents are avoided, and the safe and stable running performance of the unit is improved.
Referring to fig. 1, a pumped storage unit performance degradation early warning method based on a multidimensional state vector provided in an embodiment of the present invention includes:
s100, acquiring health state monitoring data of the pumping and storage unit in normal operation within preset historical time;
s200, screening and grouping the health state monitoring data according to active power, a water head and cooling water temperature in sequence to obtain a plurality of health data subsets respectively containing the active power, the water head, the cooling water temperature and a plurality of other monitoring parameters; each health data subset comprises a plurality of health multidimensional state vectors corresponding to the same steady-state working condition, each health multidimensional state vector corresponds to different moments, and each health multidimensional state vector comprises active power, a water head, a cooling water temperature and a plurality of other monitoring parameters;
s300, respectively calculating health characteristic values of a plurality of other monitoring parameters in each health data subset to obtain a health state characteristic vector corresponding to each health data subset;
s400, calculating a unit performance degradation index threshold according to the amplification and the weight of each health characteristic value in each health state characteristic vector, and calculating a linear fitting slope threshold of the unit performance degradation index threshold;
s500, acquiring unit state monitoring data in real time, screening real-time data subsets at intervals of a preset period, and respectively calculating a real-time state feature vector corresponding to each real-time data subset;
s600, calculating a unit performance degradation index according to the amplification and the weight of each real-time characteristic value in each real-time state characteristic vector, and calculating a linear fitting slope of the unit performance degradation index;
s700, sequentially and respectively judging whether the degradation indexes in the unit performance degradation index sequence in the preset period are larger than corresponding degradation index thresholds to obtain a first judgment result; judging whether the slope of a fitting straight line of the unit performance degradation index sequence is greater than a slope threshold value or not to obtain a second judgment result;
and S800, protecting the pumping and storage unit according to the first comparison result and the second comparison result.
In step S100, the state vector refers to a vector used to represent the state characteristics of the unit. The preset historical time may be one year or more.
The health state monitoring data only comprise data of steady-state working conditions, and the data can comprise data of unit vibration amplitude, spindle throw amplitude, water pressure pulsation amplitude, cooling water temperature, lubricating oil temperature, tile temperature, stator core temperature, stator bar temperature, water head (generally, a capillary water head is equal to the difference between the water level of an upstream reservoir and the water level of a downstream reservoir of the pumped storage power station), guide vane opening, rotating speed, active power, reactive power and the like.
The health state monitoring data of the pumped storage power station unit can be obtained through a pumped storage power station unit state monitoring system. Specifically, the state monitoring system is provided with sensors at different positions of the unit and a data acquisition system for collecting data, and the data acquisition system periodically acquires sensor data and performs corresponding calculations, such as vibration amplitude, spindle throw amplitude, water pressure pulsation amplitude and the like. For steady state conditions, the unit condition monitoring parameters, including the health condition monitoring data described above, are stored periodically (e.g., every 5 minutes) in the database.
As shown in fig. 2 below, the horizontal axis of the obtained health status monitoring data is time, and the vertical axis thereof is the value of each status monitoring parameter. At a given moment, the unit status corresponds to an array of health status monitoring data as described above, and thus there are x health status monitoring data arrays for one year or more.
Referring to fig. 3, in step S200, the screening and grouping the health status monitoring data may include:
s210, determining an active power range corresponding to typical working conditions in historical state monitoring data, and dividing the state monitoring data according to the active power range corresponding to the typical working conditions to obtain a first number of typical working condition data subsets, wherein the first number is the same as the number of the typical working conditions;
s220, determining the maximum value and the minimum value of the water head in the historical state monitoring data, equally dividing the difference value of the maximum value and the minimum value, and screening the typical working condition data subsets according to the equally divided water head range to obtain a second number of water head data subsets, wherein the second number is equal to the product of the equally divided number of the water head and the first number;
and S230, determining the maximum value and the minimum value of the cooling water temperature in the historical state monitoring data, equally dividing the difference value of the maximum value and the minimum value, and screening each water head data subset according to the equally divided cooling water temperature range to obtain a third number of health data subsets, wherein the third number is equal to the product of the equally divided quantity of the cooling water temperature and the second number. In the health data subset, the time corresponding to each of the other monitoring parameters is the same as the time corresponding to the cooling water temperature.
The vibration swing and water pressure pulsation of the conventional hydroelectric generating set are generally related to active power and a water head. The pumping and storage unit has the characteristics of high water head, high rotating speed and the like, and the vibration swing of the unit is closely related to the temperature. Therefore, active power, a water head and the temperature of cooling water are selected, the running condition of the pumped storage unit can be reflected, and the working condition corresponding to the monitoring data is accurately and efficiently determined.
In step S210, the health status monitoring data is screened according to the active power.
As shown in fig. 4, specifically, the determining an active power range corresponding to a typical operating condition in the historical state monitoring data includes:
s211, calculating a probability density distribution curve of a subset formed by all active power data in the health state monitoring data;
s212, selecting an extreme point of the probability density distribution curve to obtain the power of a typical working condition;
and S213, selecting a numerical value within the preset error range of the extreme point as the active power range of the typical working condition.
In step S211, calculating the probability density distribution curve may include summarizing the active power data in an array formed by the x acquired health status monitoring data into a sub-array, performing statistical analysis, and obtaining the probability density distribution curve of the active power sub-array through a probability density function.
In step S212, extreme points of the probability density distribution curve obtained through the function are selected, and all typical operating conditions are determined according to the extreme points, and the active power of each extreme point corresponds to one typical operating condition.
In step S213, each typical operating condition generally corresponds to an active power range, and the range of the extreme point may be expanded to obtain the range of the active power of the typical operating condition. For example, the range of the active power is obtained by adding or subtracting the error with the extreme point as the center.
For example, for typical operating condition P1, the power range is P 0 -P 1 If the array formed by the x health status monitoring data screens data according to the active power, if the active power of a certain array belongs to P 0 -P 1 Dividing the array into typical working conditions P1, and satisfying that the active power belongs to P in the x health state monitoring data arrays 0 -P 1 All arrays of (2) are divided into typical operating conditions P1. The other typical working conditions are divided into the same P1.
Through the division in step S210, the same number of first data subsets as the number of typical operating conditions can be obtained, and a first number of typical operating condition data subsets are obtained.
In step S220, all state monitoring data arrays (i.e., all multidimensional state vectors) in each typical working condition data subset are grouped according to the size of the waterhead. Specifically, the maximum value and the minimum value of the water head in the historical state monitoring data are determined, the difference value of the maximum value and the minimum value is divided by n, and the arrays in the state monitoring data are divided into water head data subsets conforming to the water head value range. n is related to the difference between the maximum head and the minimum head, and can generally take 5 (high head, medium low head, low head) or 7 (high head, medium low head, low head).
For example, when screening data according to water head, all water head data in historical state monitoring data are firstly gathered into an array, the minimum value and the maximum value of the water head array are obtained, the water head is equally divided from the minimum value to the maximum value n (the middle value of each equal division is H) 1 ，...，H n Indicated). Judging all arrays divided into the typical working conditions P1, and if the water head in a certain array belongs to H 1 Range, then the numberGroup division into P1 and H 1 The determined subset of data.
In step S230, the cooling water temperature is divided in the same manner as the water head. Specifically, when grouping, the maximum value, the minimum value and the difference value of the cooling water temperature in the historical state monitoring data are obtained, the cooling water temperature difference value m is equally divided, and the arrays in the state monitoring data in all the water head data subsets are divided into health data subsets which accord with the cooling water temperature range. m is related to the difference between the maximum cooling water temperature and the minimum cooling water temperature, and can be about 5, and the middle value of each cooling water temperature is T 1 ，...，T m And (4) showing. Finally obtain { P i ，H j ，T k A state monitoring data subset of other monitoring parameters, wherein j =1.
In a specific embodiment, the state monitoring data of a unit in the power generation direction of approximately three months is screened and grouped, the active power distribution of the unit in approximately three months is as shown in fig. 5, and the probability density distribution is as shown in fig. 6. As can be seen from FIG. 6, the typical operating conditions of the unit during this period are about 97MW and about 266MW, and the error value of the power is 10MW, then the typical operating condition P is 1 The active power interval of the power converter is 87MW-107MW, and the typical working condition P 2 The active power interval of (2) is 256MW-276MW. Plotting the state monitoring data array to P according to the active power 1 ，P 2 Two subsets. Then P is put 1 Data of the subset is scaled to { P by the size of the water head 1 ,H j (j =1.. N), other monitored parameters }, and then for { P } 1 ,H j (j =1.. N), other monitoring parameters } subset data are scaled to { P ] according to the cooling water temperature 1 ,H j (j＝1...n),T k (k =1,.. M), a subset of other monitored parameters }. P is 2 The data subsets are divided into P 1 。
As shown in fig. 7, in step S300, the calculating the health feature values of the other monitoring parameters in each health data subset respectively includes:
s310, respectively calculating the probability density distribution curve of each other monitoring parameter;
and S320, respectively selecting a numerical value corresponding to the maximum value of the probability density distribution curve corresponding to each other monitoring parameter to obtain the health characteristic value of each other monitoring parameter.
Specifically, in step S310, for a specific monitoring parameter, calculating a probability density distribution curve may include first aggregating data of the specific monitoring parameter in the array of the finally obtained health data subsets into a sub-array, performing statistical analysis, and obtaining the probability density distribution curve of the sub-array of the monitoring parameter through a probability density function.
In step S320, the health characteristic value of each of the other monitoring parameters is a numerical value corresponding to the maximum value of the probability density distribution curve corresponding to the parameter.
In a specific embodiment, the amplitude value scatter distribution plots of the upper derivative + X and the lower derivative + X are shown in the following fig. 8 and 9, respectively, for the unit under the P1 operating condition, and the probability density distribution curves are shown in the following fig. 10 and 11. Thus, the health characteristic values of the upper lead + X and the lower lead + X were determined to be 88 μm and 148 μm, respectively. The number of other condition monitoring parameters is l. Thus, each subset of health data { P } can be determined i ，H j ，T k The corresponding health status feature vector
It should be noted that each health data subset corresponds to a health status feature vector, and the health status feature vector contains a plurality of health feature values, i.e. is a multidimensional health status feature vector.
In step S400, calculating a unit performance degradation index threshold according to the amplification and weight of each health feature value in each health state feature vector includes:
by passing
Calculating, wherein I' is a unit performance degradation index threshold value, A i ' effective amplification of respective health characteristic value, lambda i Is the weight of each characteristic value, a i ' is the amplification of each health characteristic value.
In particular, the amount of the solvent to be used,
wherein, X l Firstly, 70% of operation allowable values of various other monitoring parameters in relevant countries, industry standards and power station unit operation regulations are taken, if X is i '＜X i Then take X l ' is 100% of operation allowable value of each other monitoring parameter in relevant country, industry standard and power station unit operation regulation, if
Then get a i '＝15％，X i A health characteristic value for each of the other monitored parameters.
Optionally, the weight λ i Satisfy lambda 1 +λ 2 +...+λ l ＝1。λ i Can be set empirically and can use an equal weight processing method, i.e. lambda 1 ＝λ 2 ＝...＝λ l And (1/l). The method can also be set to different numerical values according to specific influence degrees, can make full use of different monitoring parameters to influence different degrees of the unit performance degradation, and can calculate the unit performance degradation index threshold more accurately, thereby improving the safety and accuracy of early warning.
It should be noted that the unit performance degradation index threshold is a set of data, that is, each health data subset amount corresponds to one unit performance degradation index threshold.
By calculating the performance degradation index threshold of the unit, the distance between the real-time state vector and the health state vector when the unit runs can be compared in real time during real-time monitoring, and when the vector distance is larger than the preset value, abnormal early warning of the unit is sent out, so that the timeliness and the safety of the early warning are improved.
Calculating a linear fit slope threshold of the unit performance degradation index threshold includes:
setting the performance degradation index of the unit in normal operation (in a preset historical data time period) as an initial value 0, and calculating the slope of a straight line when the value reaches the threshold value of the performance degradation index of the unit after one month (30 days) to obtain a slope threshold value.
It should be noted that each subset of health data corresponds to a multi-dimensional health status feature vector, to a performance degradation index threshold, and to a degradation index slope threshold.
By calculating the slope threshold of the unit performance degradation index sequence, the unit abnormity early warning can be sent out when the distance between the state vector and the health state vector during the unit operation is compared in real time and has obvious trend change during real-time monitoring, and the timeliness and the safety of the early warning are improved.
In step S500, the method for acquiring the unit state monitoring data in real time is the same as the method for acquiring the data of the preset historical time. From { P in an established subset of health data i ，H j ，T k And fifthly, creating a new real-time data subset, screening and dividing the acquired real-time state monitoring data into different real-time data subsets, and calculating a state feature vector corresponding to each real-time data subset. The data screening and dividing method and the method and principle for calculating the real-time state feature vectors corresponding to the real-time data subsets are the same as those described above, and are not described herein again.
In particular, it can be understood that for real-time monitoring, the { P in each health data subset is taken as a basis i ，H j ，T k And fifthly, creating real-time multi-dimensional state vector subsets, dividing real-time state monitoring data in a preset period into corresponding real-time data subsets, and respectively calculating a performance degradation index corresponding to each real-time data subset. It should be noted that, because the preset period is short, the number of real-time data subsets obtained in one preset period may be smaller than the number of health data subsets. That is, part of the health data subset { P } in a predetermined period i ，H j ，T k There may not be corresponding real-time monitoring data. In one embodiment, the unit state monitoring data of the preset period is selected according to the { P ] in the established health data subset i ，H j ，T k Creating a new real-time data subset, screening and dividing the acquired real-time state monitoring data into different real-time data subsets, and respectivelyCalculating the real-time state feature vector corresponding to each real-time data subset
The preset period can be one day or one week and is determined according to the specific condition and the actual demand of the unit. In step S600, the unit performance degradation index and the unit performance serialization index threshold are calculated in the same principle. The unit performance degradation index can be obtained by
Calculating, wherein I is a unit performance degradation index, A i For effective amplification of each real-time characteristic value, lambda i Is the weight of each characteristic value, a i For the amplification of each real-time characteristic value. Wherein, the first and the second end of the pipe are connected with each other,
A i ＝{λ 1 a 1 ，λ 2 a 2 ，...，λ i a i in which X i "real-time characteristic values for various other monitored parameters, X i A health characteristic value for each of the other monitored parameters.
For each { P over a plurality of preset periods i ，H j ，T k For example, the real-time unit performance degradation indexes form a discrete sequence with uniform or non-uniform intervals. And the horizontal axis is time corresponding to a plurality of preset periods, the vertical axis is a unit performance degradation index sequence, and the time-degradation index discrete sequence is subjected to linear fitting to obtain a degradation index slope. For example, when the preset period is one week, every time a preset period is passed, all real-time monitoring data in the preset period can be selected, and a plurality of health data subsets { P } can be obtained i ，H j ，T k Dividing performance degradation indexes of a plurality of real-time data subsets obtained by dividing, after a plurality of preset periods, for each { P } i ，H j ，T k For example, the real-time unit performance degradation indexes form a discrete sequence with uniform or non-uniform intervals. For a plurality of discrete sequences respectivelyAnd performing linear fitting to obtain a plurality of degradation index slopes.
In step S700, the unit performance degradation indexes in the preset period are respectively compared with the corresponding degradation index thresholds, so as to obtain a first comparison result. In the specific comparison, when there is a deterioration index greater than the deterioration index threshold, the comparison is stopped. The first comparison result includes the presence of a degradation index greater than a degradation index threshold; and the absence, i.e., presence or absence, of a degradation index greater than a degradation index threshold.
The second comparison result comprises a slope greater than a slope threshold or a slope less than a slope threshold, i.e. greater or less.
The second comparison may be understood as selecting real-time monitoring data in a plurality of predetermined periods, and respectively corresponding the plurality of calculated real-time monitoring data to each of the subsets of health data { P } i ，H j ，T k The fitted slopes of the degradation index sequences of { P } are respectively associated with the corresponding subsets of health data i ，H j ，T k The corresponding degradation index slope threshold is compared.
Optionally, the second comparison result is used to assist the first comparison result for protection. And when the first comparison results within one month are all the degradation indexes which are not greater than the degradation index threshold, performing second comparison, namely comparing the slope of the fitting straight line with the slope threshold to obtain a second comparison result. Through the auxiliary first comparison result with the second comparison result, the comparison quality can be improved, the obvious trend change of the real-time state feature vector can be better utilized, whether the performance state of the unit is abnormal or not is accurately judged, and the protection efficiency of the safety of the pumping and storage unit is further improved.
Optionally, whether the degradation indexes in the unit performance degradation index sequence in the preset period are larger than the corresponding degradation index threshold values is sequentially and respectively judged, and a first judgment result is obtained. And judging whether the slope of the fitting straight line of the unit performance degradation index sequence is greater than a slope threshold value or not to obtain a second judgment result.
The first judgment result is yes or no, and when the judgment is performed in sequence and the judgment is stopped when the judgment result is yes. The second determination is yes or no.
In step S800, the storage unit is protected according to the result of step S700.
Protecting the storage unit according to the first comparison result and the second comparison result comprises:
when the first comparison result is that the degradation index greater than the degradation index threshold exists, sending out an early warning;
and when the first comparison result is that the degradation index larger than the degradation index threshold value does not exist and the second comparison result is larger than the degradation index threshold value, giving out early warning.
Protecting the pumping and storage unit according to the first judgment result and the second judgment result comprises the following steps:
and when at least one of the first judgment result and the second judgment result is yes, sending out unit abnormity early warning. And when the first judgment result and the second judgment result are both negative, the unit abnormity early warning is not sent out.
The pumping unit performance degradation early warning method provided by the invention can establish a health state multidimensional state vector subset under various working conditions with active power, a water head and cooling water temperature as dividing parameters, obtain corresponding health state feature vectors by taking numerical values corresponding to the maximum value of the probability density as feature values respectively, and calculate corresponding unit performance degradation index threshold values. The method comprises the steps of obtaining a performance degradation index of a unit in operation in real time, judging whether the performance degradation index is larger than a threshold value or not by comparing the real-time performance degradation index with the corresponding threshold value, simultaneously carrying out linear fitting on a degradation index sequence, judging whether the performance degradation index is larger than a slope threshold value or not, and sending early warning in advance when the larger result, namely the unit performance is judged to be obviously abnormal or trending degraded, so that accidents are avoided, and the safe and stable operation performance of the unit is improved.
It should be noted that the method of the embodiment of the present invention may be executed by a single device, such as a computer or a server. The method of the embodiment can also be applied to a distributed scene and is completed by the mutual cooperation of a plurality of devices. In the case of such a distributed scenario, one of the multiple devices may only perform one or more steps of the method according to the embodiment of the present invention, and the multiple devices interact with each other to complete the method.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
Those of ordinary skill in the art will understand that: the discussion of any embodiment above is meant to be exemplary only, and is not intended to intimate that the scope of the disclosure, including the claims, is limited to these examples; within the idea of the invention, also features in the above embodiments or in different embodiments may be combined, steps may be implemented in any order, and there are many other variations of the different aspects of the invention as described above, which are not provided in detail for the sake of brevity.
In addition, well known power/ground connections to Integrated Circuit (IC) chips and other components may or may not be shown within the provided figures for simplicity of illustration and discussion, and so as not to obscure the invention. Furthermore, devices may be shown in block diagram form in order to avoid obscuring the invention, and also in view of the fact that specifics with respect to implementation of such block diagram devices are highly dependent upon the platform within which the present invention is to be implemented (i.e., specifics should be well within purview of one skilled in the art). Where specific details (e.g., circuits) are set forth in order to describe example embodiments of the invention, it should be apparent to one skilled in the art that the invention can be practiced without, or with variation of, these specific details. Accordingly, the description is to be regarded as illustrative instead of restrictive.
While the present invention has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art in light of the foregoing description.
The embodiments of the invention are intended to embrace all such alternatives, modifications and variances which fall within the broad scope of the appended claims. Therefore, any omissions, modifications, substitutions, improvements and the like that may be made without departing from the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (10)
1. A pumping unit performance degradation early warning method based on multi-dimensional state vectors is characterized by comprising the following steps:
acquiring health state monitoring data of the pumping unit in normal operation within preset historical time;
screening and grouping health state monitoring data in sequence according to active power, a water head and cooling water temperature to obtain a plurality of health data subsets, wherein each health data subset comprises a plurality of health multidimensional state vectors corresponding to the same steady-state working condition, each health multidimensional state vector corresponds to different moments, and each health multidimensional state vector comprises the active power, the water head, the cooling water temperature and a plurality of other monitoring parameters;
respectively calculating health characteristic values of a plurality of other monitoring parameters in each health data subset to obtain a health state characteristic vector corresponding to each health data subset;
calculating a unit performance degradation index threshold according to the amplification and the weight of each health characteristic value in each health state characteristic vector, and calculating a linear fitting slope threshold of the unit performance degradation index threshold;
acquiring unit state monitoring data in real time, screening real-time data subsets at intervals of a preset period, and respectively calculating a real-time state feature vector corresponding to each real-time data subset;
calculating a unit performance degradation index according to the amplification and the weight of each real-time characteristic value in each real-time state characteristic vector respectively, and calculating the linear fitting slope of the unit performance degradation index;
sequentially and respectively judging whether the degradation indexes in the unit performance degradation index sequence in the preset period are larger than corresponding degradation index thresholds to obtain a first judgment result; judging whether the slope of a fitting straight line of the unit performance degradation index sequence is greater than a slope threshold value or not to obtain a second judgment result;
and protecting the pumping and storage unit according to the first judgment result and the second judgment result.
2. The multi-dimensional state vector-based pumping unit performance degradation early warning method according to claim 1, wherein the step of screening and grouping the health state monitoring data according to active power, a water head and a cooling water temperature in sequence to obtain a plurality of health data subsets comprises the steps of:
determining an active power range corresponding to typical working conditions in historical state monitoring data, and dividing the state monitoring data according to the active power range corresponding to the typical working conditions to obtain a first number of typical working condition data subsets, wherein the first number is the same as the number of the typical working conditions;
equally dividing the water head in the typical working condition data subsets according to the difference value between the maximum value and the minimum value to obtain a second number of water head data subsets, wherein the second number is equal to the product of the number of water head data subsets and the first number;
and equally dividing the cooling water temperature in the water head data subsets according to the difference value between the maximum value and the minimum value to obtain a third number of health data subsets, wherein the third number is equal to the product of the cooling water temperature equal number and the second number.
3. The pumped storage unit performance degradation early warning method based on the multidimensional state vector, as recited in claim 2, wherein the determining the active power range corresponding to typical operating conditions in the historical state monitoring data comprises:
calculating a probability density distribution curve of a data subset formed by all active power data in the health state monitoring data;
calculating an extreme point of the probability density distribution curve to obtain the power of a typical working condition;
and selecting the value in the preset error range of the extreme point as the active power range of the typical working condition.
4. The multi-dimensional state vector-based pumped storage unit performance degradation early warning method of claim 2, wherein the calculating the health characteristic values of the plurality of other monitoring parameters in each health data subset respectively comprises:
respectively calculating the probability density distribution curve of each other monitoring parameter;
and respectively selecting a numerical value corresponding to the maximum value of the probability density distribution curve corresponding to each other monitoring parameter to obtain the health characteristic value of each other monitoring parameter.
5. The multi-dimensional state vector-based pumped storage unit performance degradation early warning method of claim 2,
the unit performance degradation index passes
Calculating, wherein I is the unit performance degradation index, A i For effective amplification of each real-time characteristic value, λ i Is the weight of each characteristic value, a i For the amplification of each real-time characteristic value.
6. The multi-dimensional state vector-based pumped storage unit performance degradation early warning method of claim 5,
7. The multi-dimensional state vector-based pumped storage unit performance degradation early warning method of claim 2,
the computer group performance degradation index threshold value comprises passing
Calculating, wherein I' is a unit performance degradation index threshold value, A i ' effective amplification of respective health characteristic value, lambda i Is the weight of each characteristic value, a i ' is the amplification of each health characteristic value.
8. The multi-dimensional state vector-based pumped storage unit performance degradation early warning method of claim 7,
9. The pumped storage unit performance degradation early warning method based on the multidimensional state vector as recited in claim 2, wherein calculating a linear fitting slope threshold of a unit performance degradation index threshold comprises:
and setting the performance degradation index of the unit in normal operation as an initial value 0, and calculating the slope of a straight line after one month when the numerical value reaches the threshold value of the performance degradation index of the unit to obtain the slope threshold value.
10. The multi-dimensional state vector-based pumping unit performance degradation early warning method according to claim 1, wherein protecting the pumping unit according to the first determination result and the second determination result comprises:
and when at least one of the first judgment result and the second judgment result is yes, sending out unit abnormity early warning.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010183841.6A CN111522858B (en) | 2020-03-16 | 2020-03-16 | Multi-dimensional state vector-based pumping unit performance degradation early warning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010183841.6A CN111522858B (en) | 2020-03-16 | 2020-03-16 | Multi-dimensional state vector-based pumping unit performance degradation early warning method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111522858A CN111522858A (en) | 2020-08-11 |
| CN111522858B true CN111522858B (en) | 2022-11-18 |
Family
ID=71900404
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010183841.6A Active CN111522858B (en) | 2020-03-16 | 2020-03-16 | Multi-dimensional state vector-based pumping unit performance degradation early warning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111522858B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112598210A (en) * | 2020-10-23 | 2021-04-02 | 河北新天科创新能源技术有限公司 | Wind turbine generator performance evaluation and early warning method |
| CN114863651A (en) * | 2021-01-15 | 2022-08-05 | 湖南五凌电力科技有限公司 | Intelligent early warning method for monitoring state of auxiliary machine |
| CN113027658B (en) * | 2021-03-24 | 2022-08-02 | 华中科技大学 | Real-time state evaluation method for water turbine runner and application thereof |
| CN113283300B (en) * | 2021-04-27 | 2022-04-08 | 华中科技大学 | Pumped storage unit shafting degradation evaluation method and device |
| CN113806346A (en) * | 2021-08-25 | 2021-12-17 | 浙江浙能台州第二发电有限责任公司 | Turbine degradation trend measuring method and terminal based on big data analysis |
| CN114165382B (en) * | 2021-11-24 | 2023-06-20 | 华电电力科学研究院有限公司 | Method and system for testing absolute efficiency of hydroelectric generating set |
| CN114876717A (en) * | 2022-06-16 | 2022-08-09 | 西安热工研究院有限公司 | Protection method and system for running fault of water-turbine generator set |
| CN117469077B (en) * | 2023-11-15 | 2024-04-09 | 南方电网调峰调频发电有限公司检修试验分公司 | Method and device for judging operation condition of pumping and storage unit and pumping and storage unit protection equipment |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105372591B (en) * | 2015-09-28 | 2018-02-16 | 国家电网公司 | A kind of Hydropower Unit health status method for quantitatively evaluating based on transient process |
| CN106092190B (en) * | 2016-06-02 | 2019-03-29 | 国家电网公司 | Pump-storage generator operation stability state deteriorates method for early warning and system |
| CN110007652B (en) * | 2019-03-22 | 2020-12-29 | 华中科技大学 | Hydroelectric generating set degradation trend interval prediction method and system |
-
2020
- 2020-03-16 CN CN202010183841.6A patent/CN111522858B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111522858A (en) | 2020-08-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111522858B (en) | Multi-dimensional state vector-based pumping unit performance degradation early warning method | |
| CN104131950B (en) | Partitioning determination method for threshold value of temperature characteristic quantity of wind generating set | |
| CN106092190A (en) | Pump-storage generator stable sexual state deterioration method for early warning and system | |
| CN108089078A (en) | Equipment deteriorates method for early warning and system | |
| US6587737B2 (en) | Method for the monitoring of a plant | |
| Liu et al. | Research on fault diagnosis of wind turbine based on SCADA data | |
| CN105353256A (en) | Electric transmission and transformation device state abnormity detection method | |
| CN101995290A (en) | Method and system for monitoring vibration of wind driven generator | |
| CN112855408B (en) | Early warning method and early warning device for hydroelectric generating set | |
| CN105372591A (en) | A transient process-based hydroelectric generating set health status quantitative evaluation method | |
| CN107654342A (en) | A kind of abnormal detection method of Wind turbines power for considering turbulent flow | |
| CN103912448A (en) | Method for monitoring power characteristics of units of regional wind farms | |
| Ouyang et al. | Monitoring wind turbines' unhealthy status: a data-driven approach | |
| Liu et al. | Reliability evaluation of a wind-diesel hybrid power system with battery bank using discrete wind speed frame analysis | |
| CN111275295B (en) | Distributed photovoltaic fault diagnosis method based on inverse distance weight interpolation | |
| CN115750228A (en) | Fault early warning method for pitch system of wind turbine generator | |
| Huang et al. | Wind turbine health assessment framework based on power analysis using machine learning method | |
| CN113107831B (en) | Method, device and equipment for monitoring state and service life of water feed pump and storage medium | |
| CN112949181A (en) | Early warning prediction method of multi-source associated data, storage medium and electronic equipment | |
| CN110188939B (en) | Wind power prediction method, system, equipment and storage medium of wind power plant | |
| CN107045548B (en) | System and method for calculating wind power energy utilization rate | |
| CN112666458B (en) | Power generation equipment state evaluation method and evaluation device | |
| CN111219287A (en) | Remote service life evaluating system for hydroelectric generating set | |
| CN112749465A (en) | Method, processor, storage medium, and detection system for detecting electricity theft | |
| Léonard et al. | Hydro-turbine monitoring: from self-learned equipment behavior to a single global deviation indicator |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |