[1]方瑞明,江顺辉,尚荣艳,等.采用趋势状态分析的风机齿轮箱状态在线评估云模型[J].华侨大学学报(自然科学版),2016,37(1):32-37.[doi:10.11830/ISSN.1000-5013.2016.01.0032]
　FANG Ruiming,JIANG Shunhui,SHANG Rongyan,et al.Online Wind Turbine Gearbox Condition Assessment Cloud Model Using Trend Condition Analysis[J].Journal of Huaqiao University(Natural Science),2016,37(1):32-37.[doi:10.11830/ISSN.1000-5013.2016.01.0032]
点击复制

采用趋势状态分析的风机齿轮箱状态在线评估云模型()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第37卷
期数:
2016年第1期
页码:
32-37
栏目:
出版日期:
2016-01-03

文章信息/Info

Title:
Online Wind Turbine Gearbox Condition Assessment Cloud Model Using Trend Condition Analysis
文章编号:
1000-5013(2016)01-0032-06
作者:
方瑞明;  江顺辉;  尚荣艳;  王黎
华侨大学 信息科学与工程学院, 福建 厦门 361021
Author(s):
FANG Ruiming;  JIANG Shunhui;  SHANG Rongyan;  WANG Li
College of Information Science and Engineering, Huaqiao University, Xiamen 361021, China
关键词:
齿轮箱;  风电机组;  正态云模型;  趋势状态分析;  逆向正态云发生器
Keywords:
gearbox;  wind turbine;  normal cloud model;  trend condition analysis;  backward cloud generator
分类号:
TM715
DOI:
10.11830/ISSN.1000-5013.2016.01.0032
文献标志码:
A
摘要:
为预防风机齿轮箱严重故障的发生,提出了一种结合正态云模型和趋势状态分析法的齿轮箱状态评估模型.首先,基于数据采集与监控(SCADA)系统的历史数据,采用支持向量机方法建立齿轮箱运行温度预测模型,对齿轮箱不同状态下的趋势预测特征进行分析,求取正常和异常状态时预测值的相对误差序列.然后,采用改进无确定度逆向正态云发生器,利用所求取的相对误差序列提取正常云和异常云的数字特征,构建齿轮箱状态评估云模型.该模型能够根据风机SCADA系统的实测数据,求取齿轮箱当前状态对正常云和异常云的贴近度,并采用最大贴近度原则确定齿轮箱状态.最后,利用辽宁某风机齿轮箱的实测数据对所提模型进行验证.结果表明:该模型能够对齿轮箱的早期缺陷及时预警,达到实时监测的目的.
Abstract:
To prevent wind turbine gearbox severe faults occurrence, combined normal cloud model and trend condition analysis, this paper presents a novel condition assessment model. Firstly, based on supervisory control and data acquisition(SCADA)historical data, the forecasting model of gearbox operating temperature is established by adapting SVM, and the relative errors sequence of the forecasting values under normal and abnormal conditions are calculated after analyzing characteristics of trend forecasting. Then, inputting the relative errors sequence into improved backward normal cloud generator with the non-certainty degree, the digital features of normal and abnormal cloud model are obtained. Furthermore, the gearbox condition assessment cloud model is given, which is based on online SCADA data of wind turbine to calculate the closeness degree of normal and abnormal cloud model for gearbox current condition, and use the principle of maximum closeness degree to determine the gearbox condition. Finally, the proposed model is verified by online data of a wind turbine gearbox in Liaoning province, the results show that this model is capable of alarming early defects timely of a gearbox, achieving the aim of online condition assessment.

参考文献/References:

[1] TAVNER P J,XIANG J,SPINATO F.Reliability analysis for wind turbines[J].Wind Energy,2007,10(1):1-18.
[2] YUE Wang,INFIELD D.Supervisory control and data acquisition data-based non-linear state estimation technique for wind turbine gearbox condition monitoring[J].IEEE Transactions on Renewable Power Generation,2013,7(4):350-358.
[3] 郭鹏,INFIELD D,杨锡运.风电机组齿轮箱温度趋势状态监测及分析方法[J].中国电机工程学报,2011,31(32):129-136.
[4] 赵洪山,胡庆春,李志为.基于统计过程控制的风机齿轮箱故障预测[J].电力系统保护与控制,2012,40(13):67-73.
[5] 郭鹏,李淋淋,马登昌.基于IPSO-BP的风电机组齿轮箱状态监测研究[J].太阳能学报,2012,33(3):439-445.
[6] QIU Yingning,SUN Juan,CAO Mengnan,et al.Model based wind turbine gearbox fault detection on SCADA data[C]//IET Conference on Renewable Power Generation.Naples:IEEE Press,2014:1-5.
[7] 赵洪山,郭伟,邵玲,等.基于子空间方法的风机齿轮箱故障预测算法[J].电力自动化设备,2015,35(3):27-32.
[8] 李德毅,刘常昱,杜鹢,等.不确定性人工智能[J].软件学报,2004,15(1):1583-1594.
[9] 李如琦,苏浩益.基于可拓云理论的电能质量综合评估模型[J].电力系统自动化,2012,36(1):66-70.
[10] ZHOU Quan,WANG Shizheng,AN Wendou,et al.Power transformer fault diagnosis based on DGA combined with cloud model[C]//International Conference on High Voltage Engineering and Application.Poznan:IEEE Press,2014:1-4.
[11] SUN Yong,LI Zenglu,MENG Hong,et al.Fault diagnosis of flight control system based on correction high dimensional cloud model[C]//International Conference on Computer Science & Service System.Nanjing:IEEE Press,2012:1793-1797.
[12] 董磊,阎芳,王鹏.基于修正高维云的故障映射模型[J].系统工程与电子技术,2015,37(2):354-359.
[13] 徐岩,陈昕.基于合作博弈和云模型的变压器状态评估方法[J].电力自动化设备,2015,35(3):88-93.
[14] 梁永亮,李可军,牛林,等.变压器状态评估多层次不确定模型[J].电力系统自动化,2013,37(22):73-78.
[15] 方瑞明.支持向量机理论及其应用分析[M].北京:中国电力出版社,2007:15-17.
[16] 陈雪娟,吴春华,李智华,等.基于灰色预测的光伏组件阴影类型诊断研究[J],电网技术,2014,38(14):3293-3299.
[17] 凌武能,杭乃善,李如琦.基于云支持向量机模型的短期风电功率预测[J].电力自动化设备,2013,33(7):34-38.
[18] 李德仁.空间数据挖掘理论与应用[M].北京:科学出版社,2013:149-155.
[19] 刘常昱,李德毅,杜鹢,等.正态云模型的统计分析[J].信息与控制,2005,34(2):236-239.

备注/Memo

备注/Memo:
收稿日期: 2015-08-15
通信作者: 方瑞明(1972-),男,教授,博士,主要从事电力设备在线监测与故障诊断等的研究.E-mail:fangrm@126.com.
基金项目: 国家自然科学基金资助项目(51177039); 福建省自然科学基金资助项目(2012J01223); 福建省厦门市重大科技创新平台项目(3502Z20111008)
更新日期/Last Update: 2016-01-20