基于FIR神经网络的风电场虚拟风速传感器

计算机应用 ›› 2012, Vol. 32 ›› Issue (05): 1446-1449.

基于FIR神经网络的风电场虚拟风速传感器

苏永新,罗培屿,段斌

湘潭大学信息工程学院,湖南湘潭 411105

收稿日期:2011-10-18 修回日期:2011-12-08 发布日期:2012-05-01 出版日期:2012-05-01
通讯作者: 罗培屿
作者简介:苏永新（1975-），男，湖南永州人，博士研究生，主要研究方向：绿色电力自动化、智能计算；罗培屿（1987-），男，湖南浏阳人，硕士研究生，主要研究方向：智能计算；段斌（1966-），男，湖南湘潭人，教授，博士生导师，主要研究方向：可信计算及其在电力系统中的应用。
基金资助:
国家自然科学基金资助项目(61040026);湖南省自然科学基金资助项目(08JJ6031,09JJ8004)

Common virtual wind speed sensors for wind farm based on finite impulse response neural network

SU Yong-xin,LUO Pei-yu,DUAN Bin

School of Information Engineering, Xiangtan University, Xiangtan Hunan 411105, China

Received:2011-10-18 Revised:2011-12-08 Online:2012-05-01 Published:2012-05-01
Contact: LUO Pei-yu

摘要/Abstract

摘要： 风电机组风速传感器易发故障，故障可能导致机组安全风险和发电量损失。针对现行的故障处理方法因与机组控制策略紧密耦合而日益面临挑战，提出了一种基于数据处理的虚拟风速传感器原理与方法：由风电场上风向测量风速计算下风向推算风速，用推算风速取代故障传感器。着重讨论了基于FIR神经网络的推算风速计算方法和计算模型，探讨了系统实现的关键技术。实验证明了虚拟传感器的误差在机组控制系统可接受的程度内。提出的方法独立于机组自身属性，具有普遍适用性，可部署在任意类型的场，在物理传感器故障时向机组提供风速信号，支撑风电机组持续安全运行。

关键词: FIR神经网络, 虚拟传感器, 容错, 风电机组, 风速传感器

Abstract: Wind speed sensors of wind turbines has high fault rate, those faults may lead wind turbines into safety risks and energy production loss. However, many current methods of improving reliability of wind speed information face the challenges of high cost or high error. A virtual wind speed sensor based on spatial correlation was presented in this paper. Its key character is generating a downwind turbine's logic wind speed based on a special upwind turbine's real wind speed. The calculation mode of logic wind speed just need the outputs of the existed wind speed and direction sensors. A FIR (Finite Impulse Response) neural network computing model was proposed for deal with the complexity of logic wind speed calculating. Moreover，key technologies were discussed for building the virtual wind speed sensor system. The logic wind speed generated by virtual sensor can be used for providing reliable wind speed information input to a turbine controller. The approach presented in this paper is applicable to wind turbines of any type in wind farms.

Key words: FIR neural network, virtual sensor, fault tolerance, wind turbine, wind speed sensor

中图分类号:

TP391
TM614

苏永新罗培屿段斌. 基于FIR神经网络的风电场虚拟风速传感器[J]. 计算机应用, 2012, 32(05): 1446-1449.

SU Yong-xin LUO Pei-yu DUAN Bin. Common virtual wind speed sensors for wind farm based on finite impulse response neural network[J]. Journal of Computer Applications, 2012, 32(05): 1446-1449.

参考文献

［1］程启明，程尹曼，汪明媚，等.风力发电中风速测量技术的发展［J］. 自动化仪表, 2010,31(7):1-4.

［2］QIAO W, ZHOU W, ALLE J M, et al. Wind speed estimation based sensorless output maximization control for a wind turbine driving a DFIG［J］. IEEE Transactions on Power Electronics, 2008, 23(3):1156-1169.

［3］THONGAM J S, BOUCHARD P, PZZAIDI H,et al.Wind speed sensorless maximum power point tracking control of variable speed wind energy conversion systems［C］// IEEE International Electric Machines and Drives Conference. Washington, DC: IEEE Computer Society,2009:1832-1837.

［4］WEI X, VERHAEGEN M. Sensor and actuator fault diagnosis for wind turbine systems by using robust observer and filter［J］. Wind Energy,2011,14(4): 491-516.

［5］冯双磊，王伟胜.风电场功率预测物理方法研究［J］.中国电机工程学报，2010，30(2):1-6.

［6］KUSIAK A, ZHENG HAIYANG, ZHANG ZIJUN. A wind speed virtual sensor for wind turbines［J］.Journal of Energy Engineering,2011,137(2):59-69.

［7］SIDERATOS G, HATZIARGYRIOU N D. An advanced statistical method for wind power forecasting［J］. IEEE Transaction on Power System, 2007,22(1): 258-265.

［8］ALECIADIS M C，DOKOPOULOS P S. Wind speed and power forecasting based on spatial correlation models［J］. IEEE Transactions on Energy Conversion,1999,14(3):836-842.

［9］CADENAS E, RIVERA W. Wind speed forecasting in the south coast of Oaxaca, Mexico［J］. Renewable Energy, 2007,32(12): 2116-2128.

［10］李文良，卫志农，孙国强，等．基于改进空间相关法和径向基神经网络的风电场短期风速分时预测模型［J］．电力自动化设备，2009，29(6)：89-92．

［11］BECHRAKIS D A, SPARIS P D. Correlation of wind speed between neighboring measuring stations［J］.IEEE Transactions on Energy Conversion,2004,19(2): 400-406.

［12］BACK A D, TSOI A C. FIR and IIR synapses： A new neural network architecture for time series modeling［J］. Neural Computation,1991,3(3): 375-385.

［13］CRABTREE C J. Survey of commercially available condition monitoring systems for wind turbines［EB/OL］. ［2011-08-21］.http://www.supergen-wind.org.uk/docs/Survey%20of%20commercially%20available%20CMS%20for%20WT.pdf.

［14］WAN E A. Temporal back propagation for FIR neural networks［C］// 1990 IJCNN International Joint Conference on Neural Networks. Washington, DC: IEEE Computer Society, 1990,1:575-580.

［15］WAN E A. Finite impulse response neural networks with applications in time series prediction［D］. Stanford： Stanford University, 1993.

［16］WAN E A. FIR neural networks and time series prediction［EB/OL］.［2011-09-05］. http://choosh.csee.ogi.edu/FIR.

[1]	杨龙海, 王学渊, 蒋和松. 改进SM2签名方法的区块链数字签名方案[J]. 计算机应用, 2021, 41(7): 1983-1988.
[2]	李静, 罗金飞, 李炳超. 主动容错副本存储系统的可靠性分析模型[J]. 计算机应用, 2021, 41(4): 1113-1121.
[3]	刘宇, 朱朝阳, 李金泽, 劳源基, 覃团发. 检测型的联盟区块链共识算法d-PBFT[J]. 计算机应用, 2021, 41(3): 756-762.
[4]	林腾涛, 查思明, 陈蕾, 龙显忠. 图趋势过滤诱导的噪声容错多标记学习模型[J]. 计算机应用, 2021, 41(1): 8-14.
[5]	李靖, 景旭, 杨会君. 基于实用拜占庭容错算法的区块链电子计票方案[J]. 计算机应用, 2020, 40(4): 954-960.
[6]	王可可, 陈志德, 徐健. 基于联盟区块链的农产品质量安全高效追溯体系[J]. 计算机应用, 2019, 39(8): 2438-2443.
[7]	甘俊, 李强, 陈子豪, 张超. 区块链实用拜占庭容错共识算法的改进[J]. 计算机应用, 2019, 39(7): 2148-2155.
[8]	潘建国, 李豪. 基于实用拜占庭容错的物联网入侵检测方法[J]. 计算机应用, 2019, 39(6): 1742-1746.
[9]	王海勇, 郭凯璇, 潘启青. 基于投票机制的拜占庭容错共识算法[J]. 计算机应用, 2019, 39(6): 1766-1771.
[10]	贾梦瑶, 王兴伟, 张爽, 易波, 黄敏. 基于软件定义网络的卫星网络容错路由机制[J]. 计算机应用, 2019, 39(6): 1772-1779.
[11]	刘帅, 刘长良, 甄成刚. 风电机组齿轮箱的多变量时间序列故障预警[J]. 计算机应用, 2019, 39(4): 1229-1233.
[12]	杨玉星, 李晓慧. 超立方体网络的3路结构连通度及子结构连通度[J]. 计算机应用, 2019, 39(2): 509-512.
[13]	郭荣佐, 冯朝胜, 秦志光. 物联网智能物流系统容错服务组合建模与分析[J]. 计算机应用, 2019, 39(2): 589-597.
[14]	李静, 刘冬实. 主动容错云存储系统的可靠性评价模型[J]. 计算机应用, 2018, 38(9): 2631-2636.
[15]	徐佳庆, 万文, 蔡东京, 唐付桥, 何杰, 张磊. 高维胖树系统中确定性路由容错策略实现[J]. 计算机应用, 2018, 38(5): 1393-1398.