WO2020181786A1 - 一种基于风电机组运行数据清洗方法及系统 - Google Patents

一种基于风电机组运行数据清洗方法及系统 Download PDF

Info

Publication number
WO2020181786A1
WO2020181786A1 PCT/CN2019/114299 CN2019114299W WO2020181786A1 WO 2020181786 A1 WO2020181786 A1 WO 2020181786A1 CN 2019114299 W CN2019114299 W CN 2019114299W WO 2020181786 A1 WO2020181786 A1 WO 2020181786A1
Authority
WO
WIPO (PCT)
Prior art keywords
wind turbine
speed
data
rated
curve
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.)
Ceased
Application number
PCT/CN2019/114299
Other languages
English (en)
French (fr)
Inventor
毕然
秦世耀
王瑞明
李少林
薛扬
马晓晶
王文卓
于雪松
代林旺
徐婷
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.)
China Electric Power Research Institute Co Ltd CEPRI
State Grid Corp of China SGCC
Original Assignee
China Electric Power Research Institute Co Ltd CEPRI
State Grid Corp of China SGCC
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 China Electric Power Research Institute Co Ltd CEPRI, State Grid Corp of China SGCC filed Critical China Electric Power Research Institute Co Ltd CEPRI
Publication of WO2020181786A1 publication Critical patent/WO2020181786A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06F16/21—Design, administration or maintenance of databases
    • G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Definitions

  • the present disclosure relates to the technical field related to wind power generation, for example, to a method and system for cleaning based on wind turbine operation data.
  • Wind farm power curve monitoring and wind power prediction constitute the research foundation of wind power generation. Because accurate wind resource modeling is difficult to achieve, coupled with the nonlinear characteristics of wind turbines, researchers are more willing to use data mining methods to obtain complex practical information from simple real-time recorded wind power data than analysis methods. However, the collection and transmission of wind power data rely on sensors, and the sensors are located in an open and complex environment, and reliability cannot be guaranteed, and erroneous data must be generated. Therefore, data preprocessing is very important.
  • the present disclosure provides a method and system for cleaning operation data based on wind turbines.
  • a cleaning method based on wind turbine operation data including the following steps:
  • the theoretical operation curve model of the wind turbine is constructed by using the behavior parameters of the wind turbine as parameters of the theoretical operation curve of the wind turbine.
  • the construction of the theoretical operating curve model of the wind turbine includes:
  • the multiple operation phases include the startup and grid connection phase as the first phase, the maximum wind speed phase as the second phase, the constant speed control phase as the third phase, and the constant power control phase as the fourth phase.
  • n is the generator speed of the wind turbine
  • n LOS is the minimum grid-connected speed of the wind turbine
  • n Max is the maximum speed of the wind turbine
  • n rated is the rated speed of the wind turbine
  • T is the wind turbine torque
  • T Max1 is the wind turbine startup and The maximum torque in the grid stage
  • T 1 is the maximum torque in the wind turbine maximum power tracking stage
  • T rated is the wind turbine rated torque
  • T 2 is the minimum torque in the wind turbine constant power control stage.
  • n is the wind turbine generator speed
  • n LOS is the lowest grid-connected speed of the wind turbine
  • n Max is the maximum speed of the wind turbine
  • n rated is the rated speed of the wind turbine
  • P is the output active power of the wind turbine
  • P Max1 is the start of the wind turbine.
  • P 1 is the maximum power of the wind turbine in the maximum power tracking phase
  • P rated is the rated output power of the wind turbine.
  • n is the wind turbine generator speed
  • n LOS is the lowest grid-connected speed of the wind turbine
  • n rated is the rated speed of the wind turbine
  • ⁇ is the pitch angle of the wind turbine
  • ⁇ 1 is the maximum pitch angle of the wind turbine connected to the grid.
  • the performing data cleaning based on the data deviation degree and a preset data deviation degree threshold includes:
  • the data deviation degree is compared with the preset data deviation degree threshold, and the current operating data corresponding to the data deviation degree greater than the data deviation threshold value is deleted.
  • the data deviation threshold is 0.02.
  • a cleaning system based on wind turbine operation data including:
  • the acquisition module is set to acquire the current operating data of the wind turbine
  • the calculation module is configured to normalize the current operating data of the wind turbine, calculate the distance from the measured data to each pre-built theoretical operating curve of the wind turbine in the theoretical operating curve model of the wind turbine, and calculate the distance As the degree of data deviation;
  • a cleaning module configured to perform data cleaning based on the data deviation degree and a preset data deviation degree threshold
  • the theoretical operation curve model of the wind turbine is constructed by using the behavior parameters of the wind turbine as parameters of the theoretical operation curve of the wind turbine.
  • the calculation module includes:
  • a processing sub-module configured to normalize the current operating data of the wind turbine to obtain processed data
  • the construction sub-module of the curve model is set to obtain key parameters from the basic parameter table of the wind turbine; according to the key parameters and the change law of each operating parameter in the multiple operation phases of the wind turbine, construct the wind turbine Power speed curve, torque control curve, pitch angle control curve and the respective mathematical expressions of these three curves;
  • the multiple operation phases include the startup and grid connection phase as the first phase, the maximum wind speed phase as the second phase, the constant speed control phase as the third phase, and the constant power control phase as the fourth phase.
  • n is the generator speed of the wind turbine
  • n LOS is the minimum grid-connected speed of the wind turbine
  • n Max is the maximum speed of the wind turbine
  • n rated is the rated speed of the wind turbine
  • T is the wind turbine torque
  • T Max1 is the wind turbine startup and The maximum torque in the grid stage
  • T 1 is the maximum torque in the wind turbine maximum power tracking stage
  • T rated is the wind turbine rated torque
  • T 2 is the minimum torque in the wind turbine constant power control stage.
  • n is the wind turbine generator speed
  • n LOS is the lowest grid-connected speed of the wind turbine
  • n Max is the maximum speed of the wind turbine
  • n rated is the rated speed of the wind turbine
  • P is the output active power of the wind turbine
  • P Max1 is the start of the wind turbine.
  • P 1 is the maximum power of the wind turbine in the maximum power tracking phase
  • P rated is the rated output power of the wind turbine.
  • n is the wind turbine generator speed
  • n LOS is the lowest grid-connected speed of the wind turbine
  • n rated is the rated speed of the wind turbine
  • ⁇ is the pitch angle of the wind turbine
  • ⁇ 1 is the maximum pitch angle of the wind turbine connected to the grid.
  • the cleaning module includes:
  • a comparison sub-module configured to compare the data deviation degree with the preset data deviation degree threshold
  • the deletion sub-module is set to delete the current operating data corresponding to the data deviation degree greater than the data deviation degree threshold.
  • the data deviation threshold is 0.02.
  • the present disclosure provides a cleaning method based on wind turbine operating data, including the following steps: acquiring current operating data of the wind turbine; after normalizing the current operating data of the wind turbine, calculating the measured data to the theoretical operating curve model of the wind turbine The distance of each pre-built theoretical operation curve of wind turbines in the data set, and the distance is used as the data deviation degree; data cleaning is performed based on the data deviation degree and the preset data deviation degree threshold; the wind turbine theoretical operation curve The model is constructed by using the behavior parameters of the wind turbine as the parameters of the theoretical operating curve of the wind turbine.
  • the technical solution provided by the present disclosure realizes data cleaning of wind power data so as to improve the quality and reliability of wind power data.
  • FIG. 1 is a schematic flowchart of a method for cleaning operation data based on wind turbine generators according to an embodiment
  • Figure 2 is a schematic diagram of a SCADA second-level data cleaning process provided by an embodiment
  • FIG. 3 is a schematic diagram of the operation area division of a wind turbine according to an embodiment
  • Fig. 4 is a schematic diagram of a theoretical operation curve and deviation degree of a wind turbine according to an embodiment.
  • FIG. 1 a method for cleaning operation data based on a wind turbine generator, including the following steps.
  • the theoretical operating curve model of the wind turbine is constructed by using the behavior parameters of the wind turbine as parameters of the theoretical operating curve of the wind turbine.
  • step S1 the Supervisory Control And Data Acquisition (SCADA) system generally measures digital and switch values, including: wind speed, wind direction, temperature of key components, rotating component speed, active power, etc.
  • SCADA Supervisory Control And Data Acquisition
  • step S2 the data is collected in real time and stored and processed by the main control system of the wind turbine on the spot, and then sent to the SCADA server of the wind farm centralized control center. Therefore, the update cycle is millisecond, second and minute respectively.
  • minute-level data is mainly used in engineering applications. With the need for in-depth research, the demand for 1-minute average data or even second-level data continues to increase. Existing extensive data screening and cleaning methods can no longer satisfy the preprocessing of second-level data.
  • the present disclosure divides multiple different operating stages of the wind turbine based on the wind turbine control mode, and each operating stage is divided according to the two measured quantities of generator speed and output power standard. As shown in Figure 3, the operation of wind turbines can be divided into four stages according to different control strategies for grid-connected power generation of wind turbines.
  • the first phase is the start-up phase.
  • the wind speed rises from zero to the cut-in wind speed and keeps it for a period of time.
  • the wind turbine releases the braking device and enters the start state from the stop state.
  • This stage is mainly grid-connected constant speed control. Its purpose is to achieve grid-connected wind turbines.
  • the variable pitch control of the wind turbines makes the generator speed increase quickly and smoothly, and adjusts the generator for changes in wind speed when the speed reaches the synchronous range. Speed to keep it constant.
  • the second stage is the maximum power tracking (MPPT) stage.
  • MPPT maximum power tracking
  • the wind speed is less than the rated wind speed
  • the rotation speed of the wind turbine is less than the rated rotation speed
  • the wind turbine should maintain variable speed and constant frequency operation.
  • the maximum wind energy tracking control is implemented to ensure that the wind turbines operate under the maximum wind energy utilization rate C pmax , so this operating area is also called the C p constant zone.
  • the wind turbine pitch system implements constant pitch control, that is, the pitch angle is set at the maximum wind energy absorption angle.
  • the generator control system controls the generator's output power to control the speed of the unit. Realize variable speed and constant frequency operation.
  • the third stage is the constant speed control stage. As the wind speed increases, the speed of the wind turbine continues to increase, eventually reaching the rated speed of the wind turbine, but at this time the wind speed does not reach the rated wind speed, and the output power of the wind turbine does not reach the rated value. Change, that is, run at a constant speed.
  • the fourth stage is the constant power control stage.
  • the control objective of this operating phase is to ensure that the wind turbine speed decreases and the C p value decreases rapidly, thereby ensuring constant power.
  • step S3 according to the change law of each operating parameter in the multiple operating stages of the wind turbine, multiple theoretical operating curves can be obtained, for example, wind power curve (power-wind speed), power speed curve (power-speed) , Torque control curve (torque-speed), pitch angle control curve (pitch angle-speed), etc.
  • the operating data of the wind turbine under normal operation should be distributed on the operating curve. If the data points deviate from the operating curve, the operating data of the wind turbine can be regarded as abnormal data and should be cleaned out during data preprocessing to avoid subsequent analysis. influences.
  • the present disclosure provides a cleaning method based on wind turbine operating data, including the following steps: acquiring current operating data of the wind turbine; after normalizing the current operating data of the wind turbine, calculating the measured data to the theoretical operating curve model of the wind turbine The distance of each pre-built theoretical operation curve of wind turbines in the data set, and the distance is used as the data deviation degree; data cleaning is performed based on the data deviation degree and the preset data deviation degree threshold; the wind turbine theoretical operation curve The model is constructed by using the behavior parameters of the wind turbine as parameters of the theoretical operating curve of the wind turbine.
  • the technical solution provided by the present disclosure realizes the preprocessing of wind power data to improve the quality and reliability of wind power data, and lays a foundation for the improvement of wind power big data analysis and data mining capabilities.
  • the theoretical operating curve model of the wind turbine must be established, that is, the mathematical expression of the operating curve of the wind turbine must be established. Due to the uncertainty and uncertainty of wind speed, the distribution of second-level operating data on the wind power curve is discrete, and the data points are not concentrated around the theoretical curve. Therefore, the wind power curve is not suitable for second-level data.
  • the present disclosure mainly uses the wind turbine power speed curve, torque control curve, and pitch angle control curve to establish a theoretical operating curve model, as shown in FIG. 4. Different from the wind speed, the parameters involved in the selection of the operating curve in the present disclosure are all parameters describing the behavior of the wind turbine itself, so there is no wind speed inaccuracy characteristic and will not be affected by it.
  • the generator speed changes from 0 to the lowest grid-connected speed n LOS .
  • the active power and torque are both zero.
  • the speed will be controlled near n LOS .
  • the torque varies from 0 to the maximum value T Max1 during the startup phase, and the active power varies from 0 to the maximum value P Max1 during the startup phase.
  • the generator speed changes between the grid-connected minimum speed n LOS and the rated speed n rated , and the pitch angle generally remains at 0 degrees.
  • the wind turbine power P, speed n and torque T have the following relationship:
  • P is the output active power of the wind turbine
  • P rated is the rated output power of the wind turbine
  • T is the wind turbine torque
  • T rated is the wind turbine rated torque
  • n is the wind turbine generator speed
  • n rated is the wind turbine rated speed .
  • the generator speed is maintained at the rated speed n rated , the active power increases from the maximum value P 1 in the second stage to the rated power P rated , and the torque increases from T 1 to T rated accordingly .
  • the pitch angle remains unchanged.
  • the speed falls between the rated speed n rated and the maximum speed n Max , the active power remains rated, the torque is slowly reduced to T 2 , and the torque angle increases from 0 to the maximum operating value ⁇ 1 .
  • n is the generator speed of the wind turbine
  • n LOS is the minimum grid-connected speed of the wind turbine
  • n Max is the maximum speed of the wind turbine
  • n rated is the rated speed of the wind turbine
  • T is the wind turbine torque
  • T Max1 is the wind turbine startup and Maximum torque in the grid phase (or minimum torque in the maximum power tracking phase)
  • T 1 is the maximum torque in the maximum power tracking phase of the wind turbine
  • T rated is the rated torque of the wind turbine
  • T 2 is the minimum torque in the constant power control phase of the wind turbine
  • P is the output active power of the wind turbine
  • P Max1 is the maximum power of the wind turbine during startup and grid connection (or the minimum power during the maximum power tracking stage)
  • P 1 is the maximum power of the wind turbine during the maximum power tracking stage
  • P rated is the rated output power of the wind turbine
  • ⁇ is the pitch angle of the wind turbine
  • ⁇ 1 is the maximum pitch angle of the wind turbine grid-connected operation
  • ⁇ Max is the maximum
  • Each expression in the mathematical expression of the theoretical curve represents the shape of the theoretical curve on the corresponding plane, and defines the variation range of each parameter of the wind turbine in a specific operation stage.
  • the theoretical change interval of each parameter in the normal operation phase of the wind turbine can be determined, and thus determined in the three two-dimensional planes of torque-speed plane, power-speed plane, and pitch angle-speed plane .
  • the running trajectory of the wind turbine data that is, the corresponding points on the three two-dimensional planes of each parameter of the wind turbine at any time in the normal operation state should fall near the theory. Then, if the key parameter values in the expression can be determined, three theoretical curve expressions can be determined, and data points that deviate from the theoretical curve can be judged as abnormal operating data.
  • the key parameters of the three theoretical operating curve models can be directly queried from the basic parameter table of the wind turbine.
  • the data recorded by the SCADA system will also mark the status of the wind turbine to distinguish its operating state. This parameter can directly display the wind turbine.
  • the distance from the measured data to each ideal operating curve in the theoretical operating curve model of the wind turbine is calculated as the data deviation.
  • the data deviation threshold is set to 0.02 (2%), that is, data points with a data deviation D greater than 0.02 need to be cleaned.
  • a cleaning system based on wind turbine operation data including:
  • the acquisition module is set to acquire the current operating data of the wind turbine
  • the calculation module is configured to normalize the current operating data of the wind turbine and calculate the distance from the measured data to each pre-built theoretical operating curve of the wind turbine in the theoretical operating curve model of the wind turbine as the degree of data deviation;
  • the cleaning module is configured to perform data cleaning based on the data deviation degree and a preset data deviation degree threshold.
  • the theoretical operating curve model of the wind turbine is constructed by using the behavior parameters of the wind turbine as parameters of the theoretical operating curve of the wind turbine.
  • the calculation module includes: a processing sub-module and a curve model construction sub-module.
  • the processing sub-module is set to normalize the current operating data of the wind turbine to obtain processed data.
  • the construction sub-module of the curve model is set to obtain key parameters from the basic parameter table of the wind turbine; construct the wind power plant according to the key parameters and the change law of each operating parameter in the multiple operation stages of the wind turbine
  • the multiple operation phases include the startup and grid connection phase as the first phase, the maximum wind speed phase as the second phase, the constant speed control phase as the third phase, and the constant power control phase as the fourth phase;
  • n is the wind turbine generator speed
  • n LOS is the lowest grid-connected speed of the wind turbine
  • n Max is the maximum speed of the wind turbine
  • n rated is the rated speed of the wind turbine
  • T is the wind turbine torque
  • T Max1 is the start of the wind turbine.
  • T 1 is the maximum torque in the maximum power tracking phase of the wind turbine
  • T rated is the rated torque of the wind turbine
  • T 2 is the minimum torque in the constant power control phase of the wind turbine.
  • n is the generator speed of the wind turbine
  • n LOS is the minimum grid-connected speed of the wind turbine
  • n Max is the maximum speed of the wind turbine
  • n rated is the rated speed of the wind turbine
  • P is the output active power of the wind turbine
  • P Max1 is the wind turbine.
  • the maximum power in the grid-connected phase is started
  • P 1 is the maximum power in the maximum power tracking phase of the wind turbine
  • P rated is the rated output power of the wind turbine.
  • n is the generator speed of the wind turbine
  • n LOS is the lowest grid-connected speed of the wind turbine
  • n rated is the rated speed of the wind turbine
  • ⁇ is the pitch angle of the wind turbine
  • ⁇ 1 is the maximum pitch angle of the wind turbine connected to the grid.
  • the cleaning module includes: a comparison sub-module and a deletion sub-module.
  • the comparison sub-module is configured to compare the data deviation degree with the preset data deviation degree threshold.
  • the deletion submodule is configured to delete the current running data corresponding to the data deviation degree greater than the data deviation degree threshold.
  • the data deviation threshold is 0.02.
  • the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this application can be used on at least one computer-usable storage medium (including but not limited to magnetic disk storage, Compact Disc Read-Only Memory (CD-ROM), optical storage, etc.) containing computer-usable program codes. The form of the implemented computer program product.
  • CD-ROM Compact Disc Read-Only Memory
  • These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing equipment to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing equipment are generated It is a device that implements at least one function specified in at least one process in the flowchart and at least one block in the block diagram.
  • These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing equipment to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including the instruction device.
  • the device implements at least one function specified in at least one process of the flowchart and at least one block in the block diagram.
  • These computer program instructions can also be loaded on a computer or other programmable data processing equipment, so that a series of operation steps are executed on the computer or other programmable equipment to produce computer-implemented processing, so as to execute on the computer or other programmable equipment.
  • the instructions provide steps for implementing at least one function specified in at least one flow of the flowchart and at least one block in the block diagram.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Economics (AREA)
  • Databases & Information Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Marketing (AREA)
  • Quality & Reliability (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • Data Mining & Analysis (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Control Of Eletrric Generators (AREA)
  • Wind Motors (AREA)

Abstract

一种基于风电机组运行数据清洗方法，包括如下步骤：获取风电机组的当前运行数据（S1）；将所述风电机组的当前运行数据归一化后，计算被测数据到风电机组理论运行曲线模型中每个预先构建的风电机组理论运行曲线的距离，并将所述距离作为数据偏离度（S2）；基于所述数据偏离度和预设的数据偏离度阈值进行数据清洗（S3）；其中，所述风电机组理论运行曲线模型由所述风电机组的行为参数作为所述风电机组的理论运行曲线的参量构建而成。

Description

一种基于风电机组运行数据清洗方法及系统
本申请要求在2019年03月14日提交中国专利局、申请号为201910195729.1的中国专利申请的优先权，该申请的全部内容通过引用结合在本申请中。
技术领域
本公开涉及风力发电相关技术领域，例如涉及一种基于风电机组运行数据清洗方法及系统。
背景技术
风电场功率曲线监测和风功率预测构成了风力发电的研究基础。由于精确的风资源建模难以实现，加上风电机组的非线性特点，因此相比分析法，研究人员更愿意用数据挖掘的方法从简单的实时记录的风电数据中获取复杂的实用信息。但是，风电数据的采集和传输依赖于传感器，而传感器位于开放且复杂的环境中，可靠性无法保障，必然有错误数据产生，因此数据预处理是非常重要的。
发明内容
本公开提供一种基于风电机组运行数据清洗方法及系统。
一种基于风电机组运行数据清洗方法，包括如下步骤：
获取风电机组的当前运行数据；
将所述风电机组的当前运行数据归一化后，计算被测数据到风电机组理论运行曲线模型中每个预先构建的风电机组理论运行曲线的距离，并将所述距离作为数据偏离度；
基于所述数据偏离度和预设的数据偏离度阈值进行数据清洗；
其中，所述风电机组理论运行曲线模型由所述风电机组的行为参数作为所述风电机组理论运行曲线的参量构建而成。
其中，所述风电机组理论运行曲线模型的构建包括：
从风电机组基本参数表中获取关键参数；
根据所述关键参数和所述风电机组的多个运行阶段内每个运行参数的变化规律，构建所述风电机组的功率转速曲线、转矩控制曲线、桨距角控制曲线和这三条曲线各自的数学表达式；
其中，所述多个运行阶段包括启动并网阶段为第一阶段，最大风速阶段为第二阶段、恒转速控制阶段为第三阶段和恒功率控制阶段为第四阶段。
其中，所述转矩控制曲线的数学表达式，如下所示：
Figure PCTCN2019114299-appb-000001
其中，n为风电机组发电机转速，n LOS为风电机组最低并网转速，n Max为风电机组最大转速，n rated为风电机组额定转速，T为风电机组转矩，T Max1为风电机组启动并网阶段最大转矩，T 1为风电机组最大功率追踪阶段最大转矩，T rated为风电机组额定转矩，T 2为风电机组恒功率控制阶段最小转矩。
其中，所述功率转速曲线的数学表达式，如下所示：
Figure PCTCN2019114299-appb-000002
其中，n为风电机组发电机转速，n LOS为风电机组最低并网转速，n Max为风电机组最大转速，n rated为风电机组额定转速，P为风电机组输出有功功率，P Max1为风电机组启动并网阶段最大功率，P 1为风电机组最大功率追踪阶段最大功率，P rated为风电机组额定输出功率。
其中，所述桨距角控制曲线的数学表达式，如下所示：
Figure PCTCN2019114299-appb-000003
其中，n为风电机组发电机转速，n LOS为风电机组最低并网转速，n rated为风电机组额定转速，β为风电机组桨距角，β 1为风电机组并网运行最大桨距角。
其中，所述基于所述数据偏离度和预设的数据偏离度阈值进行数据清洗，包括：
将所述数据偏离度与所述预设的数据偏离度阈值进行比较，将大于所述数据偏离度阈值的数据偏离度对应的当前运行数据删除。
其中，所述数据偏离度阈值为0.02。
一种基于风电机组运行数据清洗系统，包括：
获取模块，设置为获取风电机组的当前运行数据；
计算模块，设置为将所述风电机组的当前运行数据据归一化后，计算被测数据到风电机组理论运行曲线模型中每个预先构建的风电机组理论运行曲线的 距离，并将所述距离作为数据偏离度；
清洗模块，设置为基于所述数据偏离度和预设的数据偏离度阈值进行数据清洗；
其中，所述风电机组理论运行曲线模型由所述风电机组的行为参数作为所述风电机组理论运行曲线的参量构建而成。
其中，所述计算模块包括：
处理子模块，设置为将所述风电机组的当前运行数据进行归一化处理，得到处理后的数据；
曲线模型的构建子模块，设置为从风电机组基本参数表中获取关键参数；根据所述关键参数和所述风电机组的多个运行阶段内每个运行参数的变化规律，构建所述风电机组的功率转速曲线、转矩控制曲线、桨距角控制曲线和这三条曲线各自的数学表达式；
其中，所述多个运行阶段包括启动并网阶段为第一阶段，最大风速阶段为第二阶段、恒转速控制阶段为第三阶段和恒功率控制阶段为第四阶段。
其中，所述转矩控制曲线的数学表达式，如下所示：
Figure PCTCN2019114299-appb-000004
其中，n为风电机组发电机转速，n LOS为风电机组最低并网转速，n Max为风电机组最大转速，n rated为风电机组额定转速，T为风电机组转矩，T Max1为风电机组启动并网阶段最大转矩，T 1为风电机组最大功率追踪阶段最大转矩，T rated 为风电机组额定转矩，T 2为风电机组恒功率控制阶段最小转矩。
其中，所述功率转速曲线的数学表达式，如下所示：
Figure PCTCN2019114299-appb-000005
其中，n为风电机组发电机转速，n LOS为风电机组最低并网转速，n Max为风电机组最大转速，n rated为风电机组额定转速，P为风电机组输出有功功率，P Max1为风电机组启动并网阶段最大功率，P 1为风电机组最大功率追踪阶段最大功率，P rated为风电机组额定输出功率。
其中，所述桨距角控制曲线的数学表达式，如下所示：
Figure PCTCN2019114299-appb-000006
其中，n为风电机组发电机转速，n LOS为风电机组最低并网转速，n rated为风电机组额定转速，β为风电机组桨距角，β 1为风电机组并网运行最大桨距角。
其中，所述清洗模块，包括：
比较子模块，设置为将所述数据偏离度与所述预设的数据偏离度阈值进行比较；
删除子模块，设置为将大于所述数据偏离度阈值的数据偏离度对应的当前运行数据删除。
其中，所述数据偏离度阈值为0.02。
本公开提供一种基于风电机组运行数据清洗方法，包括如下步骤：获取风电机组的当前运行数据；将所述风电机组的当前运行数据归一化后，计算被测数据到风电机组理论运行曲线模型中每个预先构建的风电机组理论运行曲线的距离，并将所述距离作为数据偏离度；基于所述数据偏离度和预设的数据偏离度阀值进行数据清洗；所述风电机组理论运行曲线模型由所述风电机组的行为参数作为所述风电机组理论运行曲线的参量构建而成。本公开提供的技术方案实现对风电数据进行数据清洗从而提高风电数据的质量与可靠性。
附图说明
图1为一实施例提供的一种基于风电机组运行数据清洗方法流程示意图；
图2为一实施例提供的SCADA秒级数据清洗流程示意图；
图3为一实施例提供的风电机组运行区域划分示意图；
图4为一实施例提供的风电机组理论运行曲线及偏离度示意图。
具体实施方式
为了更好地理解本公开，下面结合说明书附图和实例对本公开的内容做进一步的说明。
实施例1：
本实施例提供的技术方案如图1所示一种基于风电机组运行数据清洗方法，包括如下步骤。
S1、获取风电机组的当前运行数据。
S2、将所述风电机组的当前运行数据归一化后，计算被测数据到风电机组理论运行曲线模型中每个预先构建的风电机组理论运行曲线的距离，并将所述 距离作为数据偏离度。
S3、基于所述数据偏离度和预设的数据偏离度阈值进行数据清洗。
所述风电机组理论运行曲线模型由所述风电机组的行为参数作为所述风电机组理论运行曲线的参量构建而成。
在步骤S1中，数据采集与监视控制(Supervisory Control And Data Acquisition，SCADA)系统一般测量数字量和开关量，包括：风电机组风速、风向、关键部件温度、旋转部件转速、有功功率等。
在步骤S2中，数据经实时采集后由风电机组主控系就地存储并处理，随后发往风电场集控中心的SCADA服务器，因此其更新周期分别有毫秒级、秒级和分钟级。目前在工程应用中还是主要以使用分钟级数据为主。随着研究深入的需要，对1分钟均值数据甚至秒级数据的需求不断提高。现有粗放式的数据筛选和清洗手段已无法满足对秒级数据的预处理。
区别于单一依靠风速为标准划定风电机组运行区间，本公开以风电机组控制模式为依据划分风电机组的多个不同运行阶段，每一运行阶段依据发电机转速和输出功率两个测量量为划分标准。如图3所示，按照风电机组并网发电控制策略的不同，风电机组运行可分为四个阶段。
第一阶段为启动并网阶段。此阶段中，风速从零上升到切入风速，并保持一段时间，风电机组解除制动装置，由停机状态进入启动状态。该阶段主要是并网恒转速控制，其目的是实现风电机组的并网，其中风电机组的变桨距控制使发电机转速快速平稳提升，并在转速达到同步范围时针对风速的变化调节发电机转速，使其保持恒定。
第二阶段为最大功率追踪(MPPT)阶段。此阶段中，风速小于额定风速，风电机组的转速小于额定转速，风电机组要保持变速恒频运行。在这个阶段内 实行最大风能追踪控制，保证风电机组在最大风能利用率C pmax下运行，因此该运行区域又称为C p恒定区。在C p恒定区追踪最大风能时，风电机组变桨系统实行定桨距控制，即将桨距角设定在最大风能吸收角度，发电机控制系统通过控制发电机的输出功率来控制机组的转速，实现变速恒频运行。
第三阶段为恒转速控制阶段。随着风速的增大，风电机组的转速也不断增大，最终将达到风电机组的额定转速，但此时风速未达到额定风速，风电机组的输出功率未达到额定值，风电机组维持该转速不变，即在恒转速下运行。
第四阶段为恒功率控制阶段。当风速继续增加时，风电机组输出功率也继续增大，最终导致发电机和变换器的功率达到极限。因此，此运行阶段的控制目标是保证风电机组转速降低，C p值迅速降低，从而保证功率恒定。
在步骤S3中，依据风电机组的多个运行阶段内每个运行参数的变化规律，可以得到多条的理论运行曲线，例如，风功率曲线(功率-风速)、功率转速曲线(功率-转速)、转矩控制曲线(转矩-转速)、桨距角控制曲线(桨距角-转速)等。正常运行下的风电机组，其运行数据应该分布在运行曲线上，若数据点偏离运行曲线，则可以认为风电机组运行数据属于非正常数据，应该在数据预处理时清洗掉，以免对后续分析产生影响。
本公开提供一种基于风电机组运行数据清洗方法，包括如下步骤：获取风电机组的当前运行数据；将所述风电机组的当前运行数据归一化后，计算被测数据到风电机组理论运行曲线模型中每个预先构建的风电机组理论运行曲线的距离，并将所述距离作为数据偏离度；基于所述数据偏离度和预设的数据偏离度阀值进行数据清洗；所述风电机组理论运行曲线模型由所述风电机组的行为参数作为所述风电机组的理论运行曲线的参量构建而成。本公开提供的技术方案实现了对风电数据的预处理进而提高风电数据的质量与可靠性，为风电大数 据分析及数据挖掘能力的提升奠定基础。
实施例2
本实施例具体流程如图2所示，首先要建立风电机组理论运行曲线模型，即需要建立风电机组运行曲线的数学表达式。由于风速的不确定性和测不准特点，秒级运行数据在风功率曲线上的分布离散，数据点并不集中分布在理论曲线附近，因此，风功率曲线不适合作为秒级数据正常与否的判断依据。本公开主要利用风电机组功率转速曲线、转矩控制曲线、桨距角控制曲线建立理论运行曲线模型，如图4所示。与风速不同，本公开选取运行曲线涉及的参量均是描述风电机组自身行为的参数，因而不存在风速测不准特性，也不会受到其影响。
第一阶段(启动并网阶段)发电机转速在0到并网最低转速n LOS间变化，在风电机组并网前，由于没有与电网相连，有功功率与转矩均为0。而在风电机组并网后，转速将控制在n LOS附近，同时，转矩在0到启动阶段最大值T Max1间变化，有功功率在0到启动阶段最大值P Max1间变化。
第二阶段(最大风速)发电机转速在并网最低转速n LOS和额定转速n rated间变化，桨距角一般保持0度位置不变。根据流体力学中的相似律，在该阶段风电机组功率P、转速n和转矩T存在如下关系：
Figure PCTCN2019114299-appb-000007
其中，P为风电机组输出有功功率，P rated为风电机组额定输出功率，T为风电机组转矩，T rated为风电机组额定转矩，n为风电机组发电机转速，n rated为风电机组额定转速。
第三阶段(恒转速控制)发电机转速保持在额定转速n rated，有功功率则从第二阶段的最大值P 1增长到额定功率P rated，转矩则相应从T 1增长到T rated。桨距角保持不变。
第四阶段(恒功率控制)转速落在额定转速n rated和最大转速n Max间，有功功率保持额定，转矩缓慢减小到T 2，转矩角则由0增加到运行最大值β 1。
综上所述，可以得到三条曲线的数学表达。
转矩控制曲线的数学表达式，如下所示：
Figure PCTCN2019114299-appb-000008
功率转速曲线的数学表达式，如下所示：
Figure PCTCN2019114299-appb-000009
桨距角控制曲线的数学表达式，如下所示：
Figure PCTCN2019114299-appb-000010
其中，n为风电机组发电机转速，n LOS为风电机组最低并网转速，n Max为风电机组最大转速，n rated为风电机组额定转速，T为风电机组转矩，T Max1为风电 机组启动并网阶段最大转矩(或最大功率追踪阶段最小转矩)，T 1为风电机组最大功率追踪阶段最大转矩，T rated为风电机组额定转矩，T 2为风电机组恒功率控制阶段最小转矩，P为风电机组输出有功功率，P Max1为风电机组启动并网阶段最大功率(或最大功率追踪阶段最小功率)，P 1为风电机组最大功率追踪阶段最大功率，P rated为风电机组额定输出功率，β为风电机组桨距角，β 1为风电机组并网运行最大桨距角，β Max为风电机组最大桨距角。
理论曲线数学表达式中的每个表达式表示了对应平面上理论曲线的形状，限定了风电机组在特定运行阶段的每个参数变化范围。通过以上三条曲线的数学表达式，可以确定风电机组正常运行阶段每个参数的理论变化区间，从而确定在转矩-转速平面、功率-转速平面、桨距角-转速平面三个二维平面中，风电机组数据的运行轨迹，即正常运行状态下任何时刻的风电机组每个参数在这三个二维平面上对应的点应该落在理论附近。那么，如果能够确定表达式中的关键参数值，则可以确定三条理论曲线表达式，对于偏离理论曲线的数据点则可判定为非正常运行数据。
三条理论运行曲线模型的关键参数可以由风电机组基本参数表中直接查询获得，SCADA系统记录的数据的同时会标记风电机组的状态量以区分其所处的运行状态，该参量可直接显示风电机组所处的运行阶段。按照图4(d)所示，将运行数据归一化后，计算被测数据到风电机组理论运行曲线模型中每个理想运行曲线的距离作为数据偏离度。考虑到数据的波动性，设置数据偏离度阈值为0.02(2％)，即数据偏离度D大于0.02的数据点均需要清洗掉。
实施例3
一种基于风电机组运行数据清洗系统，包括：
获取模块，设置为获取风电机组的当前运行数据；
计算模块，设置为将所述风电机组的当前运行数据据归一化后，计算被测数据到风电机组理论运行曲线模型中每个预先构建的风电机组理论运行曲线的距离作为数据偏离度；
清洗模块，设置为基于所述数据偏离度和预设的数据偏离度阈值进行数据清洗。
所述风电机组理论运行曲线模型由所述风电机组的行为参数作为所述风电机组理论运行曲线的参量构建而成。
所述计算模块包括：处理子模块和曲线模型的构建子模块。
所述处理子模块，设置为将风电机组的当前运行数据进行归一化处理，得到处理后的数据。
所述曲线模型的构建子模块，设置为从风电机组基本参数表中获取关键参数；根据所述关键参数和所述风电机组的多个运行阶段内每个运行参数的变化规律，构建所述风电机组的功率转速曲线、转矩控制曲线、桨距角控制曲线和这三条曲线各自的数学表达式。
其中，所述多个运行阶段包括启动并网阶段为第一阶段，最大风速阶段为第二阶段、恒转速控制阶段为第三阶段和恒功率控制阶段为第四阶段；
所述转矩控制曲线的数学表达式，如下所示：
Figure PCTCN2019114299-appb-000011
式中：n为风电机组发电机转速，n LOS为风电机组最低并网转速，n Max为风电机组最大转速，n rated为风电机组额定转速，T为风电机组转矩，T Max1为风电机组启动并网阶段最大转矩，T 1为风电机组最大功率追踪阶段最大转矩，T rated为风电机组额定转矩，T 2为风电机组恒功率控制阶段最小转矩。
所述功率转速曲线的数学表达式，如下所示：
Figure PCTCN2019114299-appb-000012
式中：n为风电机组发电机转速，n LOS为风电机组最低并网转速，n Max为风电机组最大转速，n rated为风电机组额定转速，P为风电机组输出有功功率，P Max1为风电机组启动并网阶段最大功率，P 1为风电机组最大功率追踪阶段最大功率，P rated为风电机组额定输出功率。
所述桨距角控制曲线的数学表达式，如下所示：
Figure PCTCN2019114299-appb-000013
式中：n为风电机组发电机转速，n LOS为风电机组最低并网转速，n rated为风电机组额定转速，β为风电机组桨距角，β 1为风电机组并网运行最大桨距角。
所述清洗模块，包括：比较子模块和删除子模块。
所述比较子模块，设置为将所述数据偏离度与所述预设的数据偏离度阈值进行比较。
所述删除子模块，设置为将大于所述数据偏离度阈值的数据偏离度对应的当前运行数据删除。
其中，所述数据偏离度阈值为0.02。
本领域内的技术人员应明白，本申请的实施例可提供为方法、系统、或计算机程序产品。因此，本申请可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本申请可采用在至少一个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、只读光盘(Compact Disc Read-Only Memory，CD-ROM)、光学存储器等)上实施的计算机程序产品的形式。
本申请是参照根据本申请实施例的方法、设备(系统)、和计算机程序产品的流程图和方框图中至少之一来描述的。应理解可由计算机程序指令实现流程图和方框图中至少之一的每一流程和方框中至少之一、以及流程图和方框图中至少之一的流程和方框中至少之一的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图至少一个流程和方框图至少一个方框中至少之一指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图至少一个流程和方框图至少一个方框中至少之一指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处 理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图至少一个流程和方框图至少一个方框中至少之一指定的功能的步骤。

Claims (14)

  1. 一种基于风电机组运行数据清洗方法，包括：
    获取风电机组的当前运行数据；
    将所述风电机组的当前运行数据归一化后，计算被测数据到风电机组理论运行曲线模型中每个预先构建的风电机组理论运行曲线的距离，并将所述距离作为数据偏离度；
    基于所述数据偏离度和预设的数据偏离度阈值进行数据清洗；
    其中，所述风电机组理论运行曲线模型由所述风电机组的行为参数作为所述风电机组理论运行曲线的参量构建而成。
  2. 如权利要求1所述的方法，其中，所述风电机组理论运行曲线模型的构建包括：
    从风电机组基本参数表中获取关键参数；
    根据所述关键参数和所述风电机组的多个运行阶段内每个运行参数的变化规律，构建所述风电机组的功率转速曲线、转矩控制曲线、桨距角控制曲线和这三条曲线各自的数学表达式；
    其中，所述多个运行阶段包括启动并网阶段为第一阶段，最大风速阶段为第二阶段、恒转速控制阶段为第三阶段和恒功率控制阶段为第四阶段。
  3. 如权利要求2所述的方法，其中，所述转矩控制曲线的数学表达式，如下所示：
    Figure PCTCN2019114299-appb-100001
    其中，n为风电机组发电机转速，n LOS为风电机组最低并网转速，n Max为风电机组最大转速，n rated为风电机组额定转速，T为风电机组转矩，T Max1为风电机组启动并网阶段最大转矩，T 1为风电机组最大功率追踪阶段最大转矩，T rated为风电机组额定转矩，T 2为风电机组恒功率控制阶段最小转矩。
  4. 如权利要求2所述的方法，其中，所述功率转速曲线的数学表达式，如下所示：
    Figure PCTCN2019114299-appb-100002
    其中，n为风电机组发电机转速，n LOS为风电机组最低并网转速，n Max为风电机组最大转速，n rated为风电机组额定转速，P为风电机组输出有功功率，P Max1为风电机组启动并网阶段最大功率，P 1为风电机组最大功率追踪阶段最大功率，P rated为风电机组额定输出功率。
  5. 如权利要求2所述的方法，其中，所述桨距角控制曲线的数学表达式，如下所示：
    Figure PCTCN2019114299-appb-100003
    其中，n为风电机组发电机转速，n LOS为风电机组最低并网转速，n rated为风电机组额定转速，β为风电机组桨距角，β 1为风电机组并网运行最大桨距角。
  6. 如权利要求1所述的方法，其中，所述基于所述数据偏离度和预设的数据偏离度阈值进行数据清洗，包括：
    将所述数据偏离度与所述预设的数据偏离度阈值进行比较，将大于所述数据偏离度阈值的数据偏离度对应的运行数据删除。
  7. 如权利要求6所述的方法，其中，所述数据偏离度阈值为0.02。
  8. 一种基于风电机组运行数据清洗系统，包括：
    获取模块，设置为获取风电机组的当前运行数据；
    计算模块，设置为将所述风电机组的当前运行数据据归一化后，计算被测数据到风电机组理论运行曲线模型中每个预先构建的风电机组理论运行曲线的距离，并将所述距离作为数据偏离度；
    清洗模块，设置为基于所述数据偏离度和预设的数据偏离度阈值进行数据清洗；
    其中，所述风电机组理论运行曲线模型由所述风电机组的行为参数作为所述风电机组理论运行曲线的参量构建而成。
  9. 如权利要求8所述的系统，其中，所述计算模块包括：
    处理子模块，设置为将所述风电机组的当前运行数据进行归一化处理，得到处理后的数据；
    曲线模型的构建子模块，设置为从风电机组基本参数表中获取关键参数；根据所述关键参数和所述风电机组的多个运行阶段内每个运行参数的变化规律，构建所述风电机组的功率转速曲线、转矩控制曲线、桨距角控制曲线和这三条曲线各自的数学表达式；
    其中，所述多个运行阶段包括启动并网阶段为第一阶段，最大风速阶段为第二阶段、恒转速控制阶段为第三阶段和恒功率控制阶段为第四阶段。
  10. 如权利要求9所述的系统，其中，所述转矩控制曲线的数学表达式，如下所示：
    Figure PCTCN2019114299-appb-100004
    其中，n为风电机组发电机转速，n LOS为风电机组最低并网转速，n Max为风电机组最大转速，n rated为风电机组额定转速，T为风电机组转矩，T Max1为风电机组启动并网阶段最大转矩，T 1为风电机组最大功率追踪阶段最大转矩，T rated为风电机组额定转矩，T 2为风电机组恒功率控制阶段最小转矩。
  11. 如权利要求9所述的系统，其中，所述功率转速曲线的数学表达式，如下所示：
    Figure PCTCN2019114299-appb-100005
    其中，n为风电机组发电机转速，n LOS为风电机组最低并网转速，n Max为风电机组最大转速，n rated为风电机组额定转速，P为风电机组输出有功功率，P Max1为风电机组启动并网阶段最大功率，P 1为风电机组最大功率追踪阶段最大功率，P rated为风电机组额定输出功率。
  12. 如权利要求9所述的系统，其中，所述桨距角控制曲线的数学表达式，如下所示：
    Figure PCTCN2019114299-appb-100006
    其中，n为风电机组发电机转速，n LOS为风电机组最低并网转速，n rated为风电机组额定转速，β为风电机组桨距角，β 1为风电机组并网运行最大桨距角。
  13. 如权利要求8所述的系统，其中，所述清洗模块，包括：
    比较子模块，设置为将所述数据偏离度与所述预设的数据偏离度阈值进行比较；
    删除子模块，设置为将大于所述数据偏离度阈值的数据偏离度对应的当前运行数据删除。
  14. 如权利要求13所述的系统，其中，所述数据偏离度阈值为0.02。
PCT/CN2019/114299 2019-03-14 2019-10-30 一种基于风电机组运行数据清洗方法及系统 Ceased WO2020181786A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910195729.1 2019-03-14
CN201910195729.1A CN111309714A (zh) 2019-03-14 2019-03-14 一种基于风电机组运行数据清洗方法及系统

Publications (1)

Publication Number Publication Date
WO2020181786A1 true WO2020181786A1 (zh) 2020-09-17

Family

ID=71154308

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/114299 Ceased WO2020181786A1 (zh) 2019-03-14 2019-10-30 一种基于风电机组运行数据清洗方法及系统

Country Status (2)

Country Link
CN (1) CN111309714A (zh)
WO (1) WO2020181786A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115905788A (zh) * 2022-10-26 2023-04-04 西安热工研究院有限公司 风电机组功率曲线的构建方法
CN116975532A (zh) * 2023-07-31 2023-10-31 中国长江三峡集团有限公司 一种处理多弃风情况下的风机异常数据清洗方法及装置
CN117249049A (zh) * 2023-10-17 2023-12-19 北京华能新锐控制技术有限公司 基于有功功率、转速、启动转速判断机组运行状态的方法

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115059586A (zh) * 2022-06-24 2022-09-16 中国船舶重工集团海装风电股份有限公司 数据预处理方法、功率曲线生成方法及存储介质

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102562450A (zh) * 2012-01-12 2012-07-11 三一电气有限责任公司 一种风力发电机及其变桨控制方法、变桨控制系统
CN102588210A (zh) * 2011-12-21 2012-07-18 中能电力科技开发有限公司 一种用于功率曲线拟合数据预处理的滤波方法
KR20140111802A (ko) * 2013-03-12 2014-09-22 서울대학교산학협력단 풍력발전기 데이터 분류 시스템
CN105809293A (zh) * 2016-03-29 2016-07-27 国网青海省电力公司 一种多模型风电场短期功率组合预测方法
CN107394817A (zh) * 2017-08-01 2017-11-24 华北电力大学 一种风电参与电力系统调频的方法及系统
CN108171400A (zh) * 2017-12-06 2018-06-15 浙江大学 一种基于异常点及离群点检测的风机功率曲线数据预处理方法
CN108549689A (zh) * 2018-04-12 2018-09-18 华北电力大学 一种风电机组运行数据清洗方法

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103573550A (zh) * 2012-07-27 2014-02-12 华锐风电科技(集团)股份有限公司 一种风力发电机组的控制方法与系统
US10992675B2 (en) * 2014-04-14 2021-04-27 Oracle International Corporation Anomaly detection using tripoint arbitration
CN108229784A (zh) * 2017-11-09 2018-06-29 中国电力科学研究院有限公司 一种智能配电网的多维数据质量评价方法及系统
CN109118057A (zh) * 2018-07-20 2019-01-01 西安西热电站信息技术有限公司 一种基于实时功率曲线的风电机组出力评价方法

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102588210A (zh) * 2011-12-21 2012-07-18 中能电力科技开发有限公司 一种用于功率曲线拟合数据预处理的滤波方法
CN102562450A (zh) * 2012-01-12 2012-07-11 三一电气有限责任公司 一种风力发电机及其变桨控制方法、变桨控制系统
KR20140111802A (ko) * 2013-03-12 2014-09-22 서울대학교산학협력단 풍력발전기 데이터 분류 시스템
CN105809293A (zh) * 2016-03-29 2016-07-27 国网青海省电力公司 一种多模型风电场短期功率组合预测方法
CN107394817A (zh) * 2017-08-01 2017-11-24 华北电力大学 一种风电参与电力系统调频的方法及系统
CN108171400A (zh) * 2017-12-06 2018-06-15 浙江大学 一种基于异常点及离群点检测的风机功率曲线数据预处理方法
CN108549689A (zh) * 2018-04-12 2018-09-18 华北电力大学 一种风电机组运行数据清洗方法

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
LOU, JIANLOU ET AL.: "Wind Turbine Data-cleaning Algorithm Based on Power Curve", AUTOMATION OF ELECTRIC POWER SYSTEMS, vol. 40, no. 10, 25 May 2016 (2016-05-25), DOI: 9040312 *
SHEN, XIAOJUN ET AL.: "Characteristics of Outliers in Wind Speed-Power Operation Data of Wind Turbines and Its Cleaning Method", TRANSACTIONS OF CHINA ELECTROTECHNICAL SOCIETY, vol. 33, no. 14, 25 July 2018 (2018-07-25), DOI: 9040313 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115905788A (zh) * 2022-10-26 2023-04-04 西安热工研究院有限公司 风电机组功率曲线的构建方法
CN116975532A (zh) * 2023-07-31 2023-10-31 中国长江三峡集团有限公司 一种处理多弃风情况下的风机异常数据清洗方法及装置
CN117249049A (zh) * 2023-10-17 2023-12-19 北京华能新锐控制技术有限公司 基于有功功率、转速、启动转速判断机组运行状态的方法

Also Published As

Publication number Publication date
CN111309714A (zh) 2020-06-19

Similar Documents

Publication Publication Date Title
WO2020181786A1 (zh) 一种基于风电机组运行数据清洗方法及系统
CN107689638B (zh) 一种基于相轨迹分析的含风电电力系统暂态协调控制方法
CN108242814A (zh) 变速变频风电机组的一次调频方法和设备
CN109802438B (zh) 发电机组调频迫切度评估方法
Hemeyine et al. Robust takagi sugeno fuzzy models control for a variable speed wind turbine based a DFI-generator
CN114447952B (zh) 永磁风机风电场一次调频能力评估方法
CN118572790A (zh) 一种基于智能电网的风力发电需求预测与优化调度方法
CN110148973B (zh) 一种基于风速预测的风电机组调频控制方法、装置及系统
CN119628108A (zh) 利用pid技术的水电机组功率反馈控制方法及系统
CN113036822B (zh) 一种风储协调控制方法、系统、设备及存储介质
EP4579075A1 (en) Method and apparatus for determining representative wind generating set, and control method and apparatus
CN116388231B (zh) 一种基于频率与风速的风电集群聚合等值方法
CN113328461A (zh) 一种双馈风电机组的电力系统频率动态分析方法和系统
CN114221379B (zh) 孤网黑启动中风储联合系统无功电压控制方法及系统
CN113279904B (zh) 一种风电机组最大功率跟踪的桨距角寻优方法及装置
CN113090453B (zh) 风力发电机组的控制方法、装置和风力发电机组
CN120262557A (zh) 一种电气自动化控制系统及方法
CN109888838B (zh) 风电机组参与电网紧急控制的可调功率计算方法及系统
CN109378817B (zh) 一种基于一次调频稳定性评价方法
Sl-Subhi et al. Novel MPPT algorithm for low cost wind energy conversion systems
CN114444291B (zh) 一种风机发电量损失精细化测算方法、系统、设备和介质
CN118008695A (zh) 高原山地风电机组参与电网调频的先进模糊变桨控制方法
CN113346523B (zh) 一种风电场次同步振荡风险评估、抑制方法及系统
CN117439063A (zh) 基于自适应时间窗的暂态频率稳定预测方法及介质
CN117039926A (zh) 风电场多集群可用惯量评估方法及装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19919490

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 04/02/2022)

122 Ep: pct application non-entry in european phase

Ref document number: 19919490

Country of ref document: EP

Kind code of ref document: A1