CN113922416A - Wind power generator tripping early warning method for severe weather based on numerical weather forecast - Google Patents

Wind power generator tripping early warning method for severe weather based on numerical weather forecast Download PDF

Info

Publication number
CN113922416A
CN113922416A CN202111148770.7A CN202111148770A CN113922416A CN 113922416 A CN113922416 A CN 113922416A CN 202111148770 A CN202111148770 A CN 202111148770A CN 113922416 A CN113922416 A CN 113922416A
Authority
CN
China
Prior art keywords
wind
wind speed
early warning
tripping
generator
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.)
Granted
Application number
CN202111148770.7A
Other languages
Chinese (zh)
Other versions
CN113922416B (en
Inventor
张兴友
王楠
王士柏
王玥娇
陈健
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shandong University
Electric Power Research Institute of State Grid Shandong Electric Power Co Ltd
Original Assignee
Shandong University
Electric Power Research Institute of State Grid Shandong Electric Power Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shandong University, Electric Power Research Institute of State Grid Shandong Electric Power Co Ltd filed Critical Shandong University
Priority to CN202111148770.7A priority Critical patent/CN113922416B/en
Publication of CN113922416A publication Critical patent/CN113922416A/en
Application granted granted Critical
Publication of CN113922416B publication Critical patent/CN113922416B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
    • H02J3/381—Dispersed generators
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
    • H02J3/46—Controlling of the sharing of output between the generators, converters, or transformers
    • H02J3/466—Scheduling the operation of the generators, e.g. connecting or disconnecting generators to meet a given demand
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
    • H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
    • H02J2300/20—The dispersed energy generation being of renewable origin
    • H02J2300/28—The renewable source being wind energy
    • 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
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A30/00—Adapting or protecting infrastructure or their operation
    • 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
    • Y02E10/70—Wind energy
    • Y02E10/76—Power conversion electric or electronic aspects

Landscapes

  • Engineering & Computer Science (AREA)
  • Power Engineering (AREA)
  • Wind Motors (AREA)

Abstract

A wind power generator tripping early warning method for severe weather based on numerical weather forecast constructs a short-term (0-24 hours the next day) early warning function and an ultra-short-term (4 hours in the future) early warning function for accurately predicting a wind power sudden change event of the severe weather, has a wind power sudden tripping early warning function under severe weather such as strong convection and the like, and has important reference values for planning, regulating and controlling operation.

Description

Wind power generator tripping early warning method for severe weather based on numerical weather forecast
Technical Field
The invention relates to the technical field of wind power generation, in particular to a wind power cutter early warning method for severe weather based on numerical weather forecast.
Background
The intermittent and fluctuating characteristics of wind power output have great influence on the dispatching operation of the power grid. The wind power output has a typical nonlinear characteristic, when the wind speed is less than the cut-in wind speed, the fan is static, and the output power is zero; when the wind speed is between the cut-in wind speed and the rated wind speed, the output power increases nonlinearly along with the increase of the wind speed; when the wind speed is from the rated wind speed to the cut-off wind speed, the output power of the fan is the rated power; when the wind speed is higher than the cut-out wind speed, the fan automatically protects the action cutter to give an early warning for protecting the blades. The cut-out wind speed is a dividing point of the fan from full generation to zero generation, and under special weather, if the wind speed of the fan is too high, a generator tripping is caused, which may cause insufficient power supply capacity of a power grid, and threatens the operation safety of the power grid.
Disclosure of Invention
In order to overcome the defects of the technology, the invention provides a method for early warning of sudden wind power cutting in severe weather with strong convection.
The technical scheme adopted by the invention for overcoming the technical problems is as follows:
a wind power generator tripping early warning method for severe weather based on numerical weather forecast comprises the following steps:
a) screening records of the wind power generator which are overlarge in operation based on the operation data of the wind power generator in the past N years, and forming a wind turbine database by the screened records;
b) monitoring wind speed data based on historical numerical weather forecast and actual wind speed of a tower anemograph of the wind driven generator based on a relation model of a BP neural network;
c) obtaining the generator tripping capacity of the wind driven generator when the wind tripping occurs and the probability that the wind speed is greater than the wind speed of the generator tripping through a relation model of a BP neural network;
d) calculating to obtain the cutter early warning capacity;
e) by the formula
Figure BDA0003285850080000021
Establishing an ARMA-based ultra-short term power mutation early warning model, wherein a0、aiAnd bjAre all constant, vtPredicting wind speed, v, for a target momentt-iIn order to be the actual wind speed,
Figure BDA0003285850080000022
is an autoregressive regression term of the AMRA model, i is the number of advanced time points, n is the total time number, epsilont-jIs a white noise source, and is,
Figure BDA0003285850080000023
is the sliding average term of white noise sequence, m is the number of error terms, j is the rank of error terms, epsilont-jAnd epsilontAre all error terms;
f) at the wind speed v at the current time ttAiming at the actual wind speed data v of n points before the time tt-1,vt-2,…vt-nTaking the obtained result as input, and obtaining an autoregressive coefficient corresponding to the t moment;
g) for the t +1 moment, solving by adopting a time series model to obtain an autoregressive coefficient, and calculating by vt,vt-1,vt-2,…vt-n+1Obtaining the predicted wind speed v at the moment of t +1 as the input of the ultra-short-term power sudden change early warning modelt+1；
h) Repeating the step g) until the predicted wind speed of n points is obtained;
i) if there is a wind speed v at time ttWind speed v greater than or equal to that of cutting machinecut_outThen there is the risk of cutting the machine at time t. Further, the value of N in the step a) is 5.
Further, the data recorded by the large wind cutting machine in the step a) comprise an actual measured wind speed value, a wind direction, a temperature value, a pressure value and a protection fixed value of the fan cutting machine of the wind turbine generator tower anemometer.
Further, step c) comprises the steps of:
c-1) taking wind speed data of historical numerical weather forecast as input, taking actual measurement wind speed of a wind power generator tower anemograph corresponding to the historical weather forecast data as data, and establishing a multilayer BP neural network model to obtain weight parameters of each layer and the BP neural network model;
c-2) obtaining the predicted wind speed through the output of the BP neural network model, if the predicted wind speed is larger than the wind speed of the wind generator tripping machine, the wind generator tripping machine occurs, and the statistical tripping capacity is Pcut_out；
c-3) calculating the probability a that the wind speed is greater than the wind speed of the wind cutting machine by a formula a-N/N, wherein N is the frequency of the wind power generator generating the wind cutting machine, and N is the number of samples of the calculated wind speed.
Further, in step d) by formula Pt(t)＝α·Pcut_out(t) calculating to obtain early warning capacity P of cutter cutting machine at t momentt(t) in the formula Pcut_outAnd (t) is the cutter capacity at the time t.
The invention has the beneficial effects that:
Detailed Description
The present invention is further explained below.
A wind power generator tripping early warning method for severe weather based on numerical weather forecast comprises the following steps:
the method comprises the following steps that a station end and a main station end develop a wind power generator tripping pre-estimation early warning function in severe weather by means of numerical weather forecast, the basic principle is that wind speed from 0 to 24 days on the next day is predicted by combining the numerical weather forecast, a fan tripping pre-warning is established by combining a fan tripping protection fixed value and based on historical tripping data, and the basic steps are as follows:
a) and screening records of the wind power generator which are overlarge in wind power generation based on the running data of the wind power generator in the past N years, and forming a wind power generator database by using the screened records.
b) Wind speed data based on historical numerical weather forecast and wind speed actually measured by a tower anemograph of the wind driven generator are monitored based on a relation model of a BP neural network.
c) And obtaining the generator tripping capacity of the wind driven generator when the wind speed is greater than the generator tripping wind speed through a relation model of the BP neural network.
d) And calculating to obtain the cutter early warning capacity.
Thus, the short-term power sudden change early warning function is completed.
The station end has detailed fan operation data and is familiar with local microclimate conditions. And (4) early warning of severe weather power sudden change of a test point at a station end of a construction site in the Bohai sea area. The short-term early warning of the station end is an important component of the short-term early warning of the main station end, and the short-term early warning is based on numerical weather forecast and is carried out by analyzing local weather 24 hours the next day and combining the conditions of all fans. The station side anemometer tower and the cabin anemometer are used as bases for the ultra-short term early warning at the station side, the early warning of the tripping machine in the next 4 hours is issued, and reference is provided for real-time regulation and control operation of a power grid.
e) By the formula
Figure BDA0003285850080000031
Establishing an ARMA-based ultra-short term power mutation early warning model, wherein a0、aiAnd bjAre all constant, vtPredicting wind speed, v, for a target momentt-iIn order to be the actual wind speed,
Figure BDA0003285850080000041
is an autoregressive regression term of the AMRA model, i is the number of advanced time points, n is the total time number, epsilont-jIs a white noise source, and is,
Figure BDA0003285850080000042
is the sliding average term of white noise sequence, m is the number of error terms, j is the rank of error terms, epsilont-jAnd epsilontAre error terms.
f) At the wind speed v at the current time ttAiming at the actual wind speed data v of n points before the time tt-1,vt-2,…vt-nAs an input, an autoregressive coefficient corresponding to time t is obtained.
g) For the t +1 moment, solving by adopting a time series model to obtain an autoregressive coefficient, and calculating by vt,vt-1,vt-2,…vt-n+1Obtaining the predicted wind speed v at the moment of t +1 as the input of the ultra-short-term power sudden change early warning modelt+1。
h) Repeating the step g) until n points of predicted wind speed are obtained. For instance, for time t +2, v ist+1Step g) is repeated as deemed known, with v)t+1,vt,vt-1,…vt-n+2Obtaining the predicted wind speed v at the moment of t +1 as the input of the ultra-short-term power sudden change early warning modelt+2. By analogy once, the predicted wind speed values of 15min, 30min, … … and 4h in the future can be obtained.
i) If there is a wind speed v at time ttWind speed v greater than or equal to that of cutting machinecut_outThen there is the risk of cutting the machine at time t. Corresponding cutting machineCapacity Pcut_outIf the wind speed is greater than the sum of the rated capacity of the fan with the wind speed of the cutter, the early warning capacity of the cutter can be calculated as follows: pt(t)＝α·Pcut_out(t) of (d). Therefore, the wind power sudden change early warning power in the future 4 hours is obtained.
And thus, the prediction early warning of the ultra-short-term wind power sudden change is completed.
In order to accurately predict the wind power sudden change event in severe weather, a short-term (0-24 hours the next day) early warning function and an ultra-short-term (4 hours in the future) early warning function are constructed, and the wind power sudden change machine early warning function in severe weather such as strong convection is provided, so that the method has important reference values for planning, regulating and controlling operation.
Example 1:
preferably, the value of N in step a) is 5.
Example 2:
further, the data recorded by the large wind cutting machine in the step a) comprise an actual measured wind speed value, a wind direction, a temperature value, a pressure value and a protection fixed value of the fan cutting machine of the wind turbine generator tower anemometer.
Example 3:
the step c) comprises the following steps:
and c-1) taking wind speed data of historical numerical weather forecast as input, taking the actually measured wind speed of the wind power generator tower anemograph corresponding to the historical weather forecast data as data, and establishing a multilayer BP neural network model to obtain weight parameters of each layer and the BP neural network model.
c-2) obtaining the predicted wind speed through the output of the BP neural network model, if the predicted wind speed is larger than the wind speed of the wind generator tripping machine, the wind generator tripping machine occurs, and the statistical tripping capacity is Pcut_out。
c-3) calculating the probability a that the wind speed is greater than the wind speed of the wind cutting machine by a formula a-N/N, wherein N is the frequency of the wind power generator generating the wind cutting machine, and N is the number of samples of the calculated wind speed.
In step d) by the formula Pt(t)＝α·Pcut_out(t) calculating to obtain early warning capacity P of cutter cutting machine at t momentt(t) in the formula Pcut_outAnd (t) is the cutter capacity at the time t.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art will understand that various changes, modifications and substitutions can be made without departing from the spirit and scope of the invention as defined by the appended claims. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (5)

1. A wind power generator tripping early warning method for severe weather based on numerical weather forecast is characterized by comprising the following steps:
a) screening records of the wind power generator which are overlarge in operation based on the operation data of the wind power generator in the past N years, and forming a wind turbine database by the screened records;
b) monitoring wind speed data based on historical numerical weather forecast and actual wind speed of a tower anemograph of the wind driven generator based on a relation model of a BP neural network;
c) obtaining the generator tripping capacity of the wind driven generator when the wind tripping occurs and the probability that the wind speed is greater than the wind speed of the generator tripping through a relation model of a BP neural network;
d) calculating to obtain the cutter early warning capacity;
e) by the formula
Figure FDA0003285850070000011
Establishing an ARMA-based ultra-short-term power mutation early warning model, wherein a0、aiAnd bjAre all constant, vtPredicting wind speed, v, for a target momentt-iIn order to be the actual wind speed,
Figure FDA0003285850070000012
is an autoregressive regression term of the AMRA model, i is the number of advanced time points, n is the total time number, epsilont-jIs a white noise source, and is,
Figure FDA0003285850070000013
is the moving average term of white noise sequence, m is the number of error terms, j is the rank of error terms, epsilont-jAnd epsilontAre all error terms;
f) at the wind speed v at the current time ttAiming at the actual wind speed data v of n points before the time tt-1,vt-2,…vt-nTaking the obtained result as input, and obtaining an autoregressive coefficient corresponding to the t moment;
g) for the t +1 moment, solving by adopting a time series model to obtain an autoregressive coefficient, and calculating by vt,vt-1,vt-2,…vt-n+1Obtaining the predicted wind speed v at the moment of t +1 as the input of the ultra-short-term power sudden change early warning modelt+1；
h) Repeating the step g) until the predicted wind speed of n points is obtained;
i) if there is a wind speed v at time ttWind speed v greater than or equal to that of cutting machinecut_outThen there is the risk of cutting the machine at time t.
2. The severe weather wind generator tripping early warning method based on numerical weather forecast as recited in claim 1, wherein: the value of N in the step a) is 5.
3. The severe weather wind generator tripping early warning method based on numerical weather forecast as recited in claim 1, wherein: the data recorded by the large wind cutting machine in the step a) comprise an actually measured wind speed value, a wind direction, a temperature value, a pressure value and a protection fixed value of the wind cutting machine of the wind driven generator tower.
4. The severe weather wind generator tripping early warning method based on numerical weather forecast as recited in claim 1, wherein step c) comprises the following steps:
c-1) taking wind speed data of historical numerical weather forecast as input, taking the current actual wind speed of a wind driven generator tower anemograph corresponding to the historical weather forecast data as data, and establishing a multilayer BP neural network model to obtain a weight parameter of each layer and the BP neural network model;
c-2) obtaining the predicted wind speed through the output of the BP neural network model, if the predicted wind speed is larger than the wind speed of the wind generator tripping machine, the wind generator tripping machine occurs, and the statistical tripping capacity is Pcut_out；
c-3) calculating the probability a that the wind speed is greater than the wind speed of the generator tripping according to a formula a-N/N, wherein N is the frequency of the generator tripping and N is the number of samples of the calculated wind speed.
5. The severe weather wind generator tripping early warning method based on numerical weather forecast as recited in claim 1, wherein: in step d) by the formula Pt(t)＝α·Pcut_out(t) calculating to obtain early warning capacity P of cutter cutting machine at t momentt(t) in the formula Pcut_outAnd (t) is the cutter capacity at the time t.
CN202111148770.7A 2021-09-29 2021-09-29 Severe weather wind power generator cutting early warning method based on numerical weather forecast Active CN113922416B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111148770.7A CN113922416B (en) 2021-09-29 2021-09-29 Severe weather wind power generator cutting early warning method based on numerical weather forecast

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111148770.7A CN113922416B (en) 2021-09-29 2021-09-29 Severe weather wind power generator cutting early warning method based on numerical weather forecast

Publications (2)

Publication Number Publication Date
CN113922416A true CN113922416A (en) 2022-01-11
CN113922416B CN113922416B (en) 2023-07-18

Family

ID=79236749

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111148770.7A Active CN113922416B (en) 2021-09-29 2021-09-29 Severe weather wind power generator cutting early warning method based on numerical weather forecast

Country Status (1)

Country Link
CN (1) CN113922416B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2008086608A1 (en) * 2007-01-17 2008-07-24 New World Generation Inc. Multiple generator wind turbine and method of operation
US7542852B1 (en) * 2005-01-25 2009-06-02 Weather Channel Inc Derivation and production of high-resolution, very short-term weather forecasts
CN102269124A (en) * 2011-06-30 2011-12-07 内蒙古电力勘测设计院 Ultra-short term wind power station generated power forecasting system
CN109830979A (en) * 2019-01-25 2019-05-31 重庆大学 A kind of electricity generation system flexibility appraisal procedure of calculating and conventional power unit random fault based on timing simulation

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7542852B1 (en) * 2005-01-25 2009-06-02 Weather Channel Inc Derivation and production of high-resolution, very short-term weather forecasts
WO2008086608A1 (en) * 2007-01-17 2008-07-24 New World Generation Inc. Multiple generator wind turbine and method of operation
CN102269124A (en) * 2011-06-30 2011-12-07 内蒙古电力勘测设计院 Ultra-short term wind power station generated power forecasting system
CN109830979A (en) * 2019-01-25 2019-05-31 重庆大学 A kind of electricity generation system flexibility appraisal procedure of calculating and conventional power unit random fault based on timing simulation

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
陈家扬;陈华;张旭;: "基于NWP和深度学习神经网络短期风功率预测", 现代电子技术, no. 08 *

Also Published As

Publication number Publication date
CN113922416B (en) 2023-07-18

Similar Documents

Publication Publication Date Title
Dinmohammadi et al. A fuzzy-FMEA risk assessment approach for offshore wind turbines
US9097236B2 (en) Method of operating a wind power plant
Uluyol et al. Power curve analytic for wind turbine performance monitoring and prognostics
US10907611B2 (en) Methods and systems for generating wind turbine control schedules
US10871146B2 (en) Methods and systems for generating wind turbine control schedules
CN103001249B (en) Based on the method for forecasting short-term power in wind power station of BP neural net
US10746160B2 (en) Methods and systems for generating wind turbine control schedules
CN103248051A (en) Method for evaluating grid operation safety risk caused by wind farm power fluctuation
Amayri et al. Condition based maintenance of wind turbine systems considering different turbine types
Rashid et al. Forecasting of wind turbine output power using machine learning
CN105427005A (en) Operation risk assessment method of wind power station
Cevasco et al. O&M cost-Based FMECA: Identification and ranking of the most critical components for 2-4 MW geared offshore wind turbines
Kim et al. Design of wind turbine fault detection system based on performance curve
Lu et al. Wind power forecast by using improved radial basis function neural network
Maron et al. Artificial intelligence-based condition monitoring and predictive maintenance framework for wind turbines
Wilson et al. Modeling the relationship between wind turbine failure modes and the environment
CN113922416A (en) Wind power generator tripping early warning method for severe weather based on numerical weather forecast
Asgarpour et al. O&M modeling of offshore wind farms—State of the art and future developments
KR102665051B1 (en) Time Series Output Prediction Method of Wind Generator Using Weather Data
Sahnoun et al. Modelling of maintenance strategy of offshore wind farms based multi-agent system
Răzuşi et al. Prediction of wind power by artificial intelligence techniques
CN114510815A (en) Wind turbine generator power characteristic evaluation method and system
Dao et al. Impacts of reliability on operational performance and cost of energy evaluation of multi-megawatt, far-offshore wind turbines
CN117094475B (en) Fault analysis system for electric power distribution network
Zhao et al. Wind Power Generator Output Model Based on the Statistical Wind Speed Distribution Derived From the Historical Data

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