CN109488526B - 基于比例-极限学习机稳态估计的变桨距控制方法 - Google Patents

基于比例-极限学习机稳态估计的变桨距控制方法 Download PDF

Info

Publication number
CN109488526B
CN109488526B CN201811409937.9A CN201811409937A CN109488526B CN 109488526 B CN109488526 B CN 109488526B CN 201811409937 A CN201811409937 A CN 201811409937A CN 109488526 B CN109488526 B CN 109488526B
Authority
CN
China
Prior art keywords
learning machine
extreme learning
wind
output
pitch control
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
Application number
CN201811409937.9A
Other languages
English (en)
Other versions
CN109488526A (zh
Inventor
秦斌
王欣
陈金林
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.)
Hunan University of Technology
Original Assignee
Hunan University of Technology
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 Hunan University of Technology filed Critical Hunan University of Technology
Priority to CN201811409937.9A priority Critical patent/CN109488526B/zh
Publication of CN109488526A publication Critical patent/CN109488526A/zh
Application granted granted Critical
Publication of CN109488526B publication Critical patent/CN109488526B/zh
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F03MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
    • F03DWIND MOTORS
    • F03D7/00Controlling wind motors 
    • FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F05INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
    • F05BINDEXING SCHEME RELATING TO WIND, SPRING, WEIGHT, INERTIA OR LIKE MOTORS, TO MACHINES OR ENGINES FOR LIQUIDS COVERED BY SUBCLASSES F03B, F03D AND F03G
    • F05B2270/00Control
    • F05B2270/30Control parameters, e.g. input parameters
    • F05B2270/32Wind speeds
    • FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F05INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
    • F05BINDEXING SCHEME RELATING TO WIND, SPRING, WEIGHT, INERTIA OR LIKE MOTORS, TO MACHINES OR ENGINES FOR LIQUIDS COVERED BY SUBCLASSES F03B, F03D AND F03G
    • F05B2270/00Control
    • F05B2270/30Control parameters, e.g. input parameters
    • F05B2270/328Blade pitch angle
    • FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F05INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
    • F05BINDEXING SCHEME RELATING TO WIND, SPRING, WEIGHT, INERTIA OR LIKE MOTORS, TO MACHINES OR ENGINES FOR LIQUIDS COVERED BY SUBCLASSES F03B, F03D AND F03G
    • F05B2270/00Control
    • F05B2270/30Control parameters, e.g. input parameters
    • F05B2270/335Output power or torque
    • FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F05INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
    • F05BINDEXING SCHEME RELATING TO WIND, SPRING, WEIGHT, INERTIA OR LIKE MOTORS, TO MACHINES OR ENGINES FOR LIQUIDS COVERED BY SUBCLASSES F03B, F03D AND F03G
    • F05B2270/00Control
    • F05B2270/70Type of control algorithm
    • FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F05INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
    • F05BINDEXING SCHEME RELATING TO WIND, SPRING, WEIGHT, INERTIA OR LIKE MOTORS, TO MACHINES OR ENGINES FOR LIQUIDS COVERED BY SUBCLASSES F03B, F03D AND F03G
    • F05B2270/00Control
    • F05B2270/70Type of control algorithm
    • F05B2270/705Type of control algorithm proportional-integral
    • FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F05INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
    • F05BINDEXING SCHEME RELATING TO WIND, SPRING, WEIGHT, INERTIA OR LIKE MOTORS, TO MACHINES OR ENGINES FOR LIQUIDS COVERED BY SUBCLASSES F03B, F03D AND F03G
    • F05B2270/00Control
    • F05B2270/70Type of control algorithm
    • F05B2270/709Type of control algorithm with neural networks
    • YGENERAL 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
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02EREDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E10/00Energy generation through renewable energy sources
    • Y02E10/70Wind energy
    • Y02E10/72Wind turbines with rotation axis in wind direction

Landscapes

  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Sustainable Development (AREA)
  • Sustainable Energy (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Mechanical Engineering (AREA)
  • General Engineering & Computer Science (AREA)
  • Wind Motors (AREA)

Abstract

本发明针对风力发电系统变桨距控制问题,提出了一种基于比例‑极限学习机稳态估计的变桨距控制方法;首先通过ELM学习风电机组在各风速下的PI控制器的稳态输出,然后采用训练后的ELM和比例控制器相结合的方法进行风电机组的变桨控制;本发明可以改善传统PI变桨距控制滞后的缺点,有利于风电机组输出功率的稳定。

Description

基于比例-极限学习机稳态估计的变桨距控制方法
技术领域
本发明涉及的是一种风力发电技术领域的控制方法,具体地说,涉及一种基于比例-极限学习机稳态估计的变桨距控制方法。
背景技术
风电机组变桨距系统通过桨距控制器,完成叶片节距角的控制,在切入风速以上到额定风速以下范围内时,保持风力机桨距角不变,通过改变电机转速使风力机运行在最佳叶尖速比下来实现最大风能跟踪控制;在额定风速以上到切出风速时,使转速维持在额定转速附近,通过调节桨距角使发电机组输出保持功率恒定,当风速大于切出风速时,进行停机保护。
由于风速的随机性、风电机组参数的时变性,驱动大质量叶轮负载的惯性环节,使得变桨距控制系统具有参数非线性、参数时变性、滞后性等特点,造成风电机组输出功率的不稳定。
发明内容
技术问题:本发明提供了一种基于比例-极限学习机稳态估计的变桨距控制方法,利用极限学习机来给出风电机组在不同风况下的变桨控制信号的稳态值,再与比例控制器结合在一起进行变桨控制,用于改善传统PI变桨距控制滞后的缺点。
技术方案:为了克服上述问题,将比例控制器和极限学习机算法相结合,,弥补传统方法的不足,使得系统响应快、控制精度高,具有良好的动态品质,保证风电机组正常、高效和可靠地运行。
本发明提出的基于比例-极限学习机稳态估计的变桨距控制方法,其特征在于该变桨距控制系统采用极限学习机来给出传统PI变桨距控制器的稳态值,控制系统结构图如附图1所示,用风速风向传感器采集关于风速等数据信号,当风速信号超过额定值且满足风力机运行条件时,则启动风机的变桨距调节,控制系统分为两阶段,阶段实现如下:
阶段1:先采用传统的PI控制器进行变桨距控制,采集风电机组在额定风速以上及切出风速以下风速数据xi,以及各风速对应的PI控制器的稳态输出值yi,用极限学习机来拟合出各风速与该额定风速下的PI控制器稳态输出值的关系。含有F个隐含神经元的单隐层前馈神经网络模型可表示为:
式中:βi为第i个隐层节点的输出权重;ωi为第i个隐层节点的输入权重;g(x)表示激活函数;bi是第i个隐含层偏置。
理想状态下,神经网络以零误差逼近训练样本,则要满足:
由此可知存在bi、ωi和βi使得下式成立:
上式用矩阵可表示为:
Hβ=y (4)
H为隐含层输出矩阵,β为输出权重矩阵,y则为期望输出,H、β、y可用以下矩阵表示:
ELM算法的训练过程等价为求解一个线性系统,其解为:
其中H+是矩阵H的Moore-Penrose广义逆。
通过求解,可以得到以风速为输入,以PI控制器稳态值为输出的极限学习机模型。
将采集的数据中的80%作为训练样本,剩余20%作为测试样本,将风速xi作为极限学习机的输入,各风速所对应的PI控制器稳态输出值yi作为极限学习机的输出,具体步骤如下:
Step1将xi和yi进行归一化处理,极限学习机的隐含层神经元个数设为k,设k=0;
Step2极限学习机的隐含层神经元个数k=k+1,将归一化处理后数据放入极限学习机算法中进行训练;
Step3计算训练后极限学习机的测试均方根误差,如果前次测试均方根误差减当前测试均方根误差小于设定的阈值δ且当前均方根误差小于预设值σ,则训练结束,否则返回step2。
阶段2:将训练好的极限学习机用于变桨距控制,风速信号作为极限学习机的输入,极限学习机的输出即为PI控制器稳态值输出。为加快风电机组由暂态到稳态的过程,将风轮实际转速ω与风轮额定转速ωref相减,经比例控制器调节,输出信号再与极限学习机的输出相叠加,最后的叠加信号进入变桨距执行机构进行变桨控制,由此来稳定风轮的转速,同时保持发电机转矩恒定,实现风电机组的输出功率稳定。
附图说明
图1为基于比例-极限学习机稳态估计的变桨距控制系统结构图
具体实施方式:以某型号2MW风电机组为例,其工作的额定风速为13m/s,切出风速为25m/s,选择训练时选取的风速数据xi为13m/s、13.1m/s、13.2m/s、13.3m/s…24.9m/s,选取风速xi所对应的PI控制器稳态输出值yi,将xi和yi作为极限学习机的训练数据,共129组数据,随机选择其中的103组作为训练数据,剩余的26组数据作为测试数据。用极限学习机来拟合出各风速与该额定风速下的PI控制器稳态输出值的关系。含有F个隐含神经元的单隐层前馈神经网络模型可表示为:
式中:βi为第i个隐层节点的输出权重;ωi为第i个隐层节点的输入权重;g(x)表示激活函数;bi是第i个隐含层偏置。
理想状态下,神经网络以零误差逼近训练样本,则要满足:
由此可知存在bi、ωi和βi使得下式成立:
上式用矩阵可表示为:
Hβ=y (4)
H为隐含层输出矩阵,β为输出权重矩阵,y则为期望输出,H、β、y可用以下矩阵表示:
ELM算法的训练过程等价为求解一个线性系统,其解为:
其中H+是矩阵H的Moore-Penrose广义逆。
通过求解,可以得到以风速为输入,以PI控制器稳态值为输出的极限学习机模型。
将采集的数据中的80%作为训练样本,剩余20%作为测试样本,选取δ=0.01,σ=0.00,2,将风速xi作为极限学习机的输入,各风速所对应的PI控制器稳态输出值yi作为极限学习机的输出,具体步骤如下:
Step1将xi和yi进行归一化处理,极限学习机的隐含层神经元个数设为k,设k=0;
Step2极限学习机的隐含层神经元个数k=k+1,将归一化处理后数据放入极限学习机算法中进行训练;
Step3计算训练后极限学习机的测试均方根误差,如果前次测试均方根误差减当前测试均方根误差小于设定的阈值δ且当前均方根误差小于预设值σ,则训练结束,否则返回step2。
阶段2:将训练好的极限学习机用于变桨距控制,风速信号作为极限学习机的输入,极限学习机的输出即为PI控制器稳态值输出。为加快风电机组由暂态到稳态的过程,将风轮实际转速ω与风轮额定转速ωref相减,经比例控制器调节,输出信号再与极限学习机的输出相叠加,最后的叠加信号进入变桨距执行机构进行变桨控制,由此来稳定风轮的转速,同时保持发电机转矩恒定,实现风电机组的输出功率稳定。
上述具体实现只是本发明的较佳实现而已,当然,本发明还可有其他多种实施例,在不背离本发明精神及其本质的情况下,熟悉本领域的技术人员当可根据本发明作为各种相应的改变和变形,但这些相应的改变和变形都应属于本发明的权利要求的保护范围。

Claims (1)

1.一种基于比例-极限学习机稳态估计的变桨距控制方法,其特征在于该变桨距控制系统采用极限学习机来给出传统PI变桨距控制器的稳态值,用风速传感器采集关于风速数据信号,当风速信号超过额定值且满足风电机组运行条件时,则启动风电机组的变桨距调节,控制系统分为两阶段,阶段实现如下:
阶段1:先采用传统的PI控制器进行变桨距控制,采集风电机组在各额定风速以上及切出风速以下的风速xi及在该风速下的PI控制器的稳态输出值yi,xi作为极限学习机的输入,yi作为极限学习机的输出,用极限学习机来拟合出各风速与该额定风速下的PI控制器稳态输出值的关系。将采集的数据中的80%作为训练样本,剩余20%作为测试样本,将风速作为极限学习机的输入,各风速所对应的PI控制器稳态输出值作为极限学习机的输出,根据极限学习机的学习特点,初始神经元个数设为1,然后不断增加神经元个数,不断观察极限学习机在各神经元下的均方根误差,选择训练误差和测试误差都较小时所对应的神经元个数作为极限学习机最终确定的神经元个数;具体步骤如下:
Step1 将xi和yi进行归一化处理,极限学习机的隐含层神经元个数设为k,设k=0;
Step2 极限学习机的隐含层神经元个数k=k+1,将归一化处理后数据放入极限学习机算法中进行训练:
ELM算法的训练过程等价为求解一个线性系统,其解为:
其中H+是矩阵H的Moore-Penrose广义逆,H为隐含层输出矩阵,β为输出权重矩阵,y则为期望输出,H、β、y可用以下矩阵表示:
式中:βi为第i个隐层节点的输出权重;ωi为第i个隐层节点的输入权重;g(x)表示激活函数;bi是第i个隐含层偏置;
Step3 计算训练后极限学习机的测试均方根误差,如果前次测试均方根误差减当前测试均方根误差小于设定的阈值δ且当前均方根误差小于预设值σ,则训练结束,否则返回step2;
阶段2:将训练好的极限学习机用于变桨距控制,风速信号作为极限学习机的输入,极限学习机的输出即为PI控制器稳态值输出,为加快风电机组由暂态到稳态的过程,将风轮实际转速ω与风轮额定转速ωref相减,经比例控制器调节,输出信号再与极限学习机的输出相叠加,最后的叠加信号进入变桨距执行机构进行变桨控制,由此来稳定风轮的转速,同时保持发电机转矩恒定,实现风电机组的输出功率稳定。
CN201811409937.9A 2018-11-23 2018-11-23 基于比例-极限学习机稳态估计的变桨距控制方法 Active CN109488526B (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811409937.9A CN109488526B (zh) 2018-11-23 2018-11-23 基于比例-极限学习机稳态估计的变桨距控制方法

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811409937.9A CN109488526B (zh) 2018-11-23 2018-11-23 基于比例-极限学习机稳态估计的变桨距控制方法

Publications (2)

Publication Number Publication Date
CN109488526A CN109488526A (zh) 2019-03-19
CN109488526B true CN109488526B (zh) 2019-11-01

Family

ID=65696481

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811409937.9A Active CN109488526B (zh) 2018-11-23 2018-11-23 基于比例-极限学习机稳态估计的变桨距控制方法

Country Status (1)

Country Link
CN (1) CN109488526B (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3751360A1 (en) * 2019-06-11 2020-12-16 Siemens Gamesa Renewable Energy A/S Method for computer-implemented determination of a drag coefficient of a wind turbine
CN110412878B (zh) * 2019-09-02 2022-12-02 湖南工业大学 Pid-rbf稳态估计与lssvm软测量污水bod控制方法
CN110985286B (zh) * 2019-12-04 2020-11-24 浙江大学 一种基于elm的风电机组桨距角控制方法

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105046374B (zh) * 2015-08-25 2019-04-02 华北电力大学 一种基于核极限学习机模型的功率区间预测方法
CN105243259A (zh) * 2015-09-02 2016-01-13 上海大学 基于极限学习机的脉动风速快速预测方法
CN106355980A (zh) * 2016-10-27 2017-01-25 江苏方天电力技术有限公司 一种基于限定记忆极限学习机的电网调节能力预测方法
CN108468622B (zh) * 2018-02-09 2019-10-11 湖南工业大学 基于极限学习机的风电机组叶根载荷估计方法

Also Published As

Publication number Publication date
CN109488526A (zh) 2019-03-19

Similar Documents

Publication Publication Date Title
CN109488526B (zh) 基于比例-极限学习机稳态估计的变桨距控制方法
Heier Grid integration of wind energy: onshore and offshore conversion systems
CN109185054B (zh) 风力发电机桨距角控制方法、系统、装置及可读存储介质
CN104005909B (zh) 非线性前馈与模糊pid结合的风力发电机组变桨距控制方法
CN101603502B (zh) 一种基于人工智能的风能控制方法
CN107947228B (zh) 基于Markov理论的含风电电力系统随机稳定性分析方法
CN110781574A (zh) 大规模风电场中多风力发电机组建模方法
CN104454347A (zh) 一种独立变桨距风力发电机桨距角的控制方法
CN105673322A (zh) 实现风力机mppt控制的变参数非线性反馈控制方法
Zamzoum et al. Active and reactive power control of wind turbine based on doubly fed induction generator using adaptive sliding mode approach
CN104675629A (zh) 一种变速风力发电机组的最大风能捕获方法
CN117418999B (zh) 一种海上风电机组出力控制方法及相关装置
Lamnadi et al. Modeling and control of a doubly-fed induction generator for wind turbine-generator systems
CN105041565A (zh) 提高风电机组弱风发电量的变桨控制方法
Neammanee et al. Maximum peak power tracking-based control algorithms with stall regulation for optimal wind energy capture
Belaimeche et al. A comparative study between a simplified fuzzy PI and classic PI input-output linearizing controller for the wind-turbine doubly fed induction generator
Aleksandr et al. MPPT algorithms for wind turbines: review and comparison
CN105484940B (zh) 最大功率点跟踪控制方法及风力发电系统
Yao et al. Variable speed wind turbine maximum power extraction based on fuzzy logic control
Yao et al. RBF neural network based self-tuning PID pitch control strategy for wind power generation system
Naba et al. Power curve based-fuzzy wind speed estimation in wind energy conversion systems
CN105927470A (zh) 一种基于动态转矩限值的风电机组最大风能捕获控制方法
Bertašienė et al. Synergies of Wind Turbine control techniques
Kumari et al. A comprehensive review of traditional and smart MPPT techniques in PMSG based Wind energy conversion system
Shi et al. A novel control of a small wind turbine driven generator based on neural networks

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