Please wait a minute...
 首页  期刊介绍 期刊订阅 联系我们 横山亮次奖 百年刊庆
 
最新录用  |  预出版  |  当期目录  |  过刊浏览  |  阅读排行  |  下载排行  |  引用排行  |  横山亮次奖  |  百年刊庆
清华大学学报(自然科学版)  2018, Vol. 58 Issue (6): 539-546    DOI: 10.16511/j.cnki.qhdxxb.2018.26.026
  机械工程 本期目录 | 过刊浏览 | 高级检索 |
基于PCA和SPC-动态神经网络的风电机组齿轮箱油温趋势预测
黄忠山1,2, 田凌1,2, 向东1,2, 韦尧中1,2
1. 清华大学 机械工程系, 北京 100084;
2. 精密超精密制造装备及控制北京市重点实验室, 北京 100084
Prediction of oil temperature variations in a wind turbine gearbox based on PCA and an SPC-dynamic neural network hybrid
HUANG Zhongshan1,2, TIAN Ling1,2, XIANG Dong1,2, WEI Yaozhong1,2
1. Department of Mechanical Engineering, Tsinghua University, Beijing 100084, China;
2. Beijing Key Lab of Precision/Ultra-precision Manufacturing Equipment and Control, Beijing 100084, China
全文: PDF(2258 KB)  
输出: BibTeX | EndNote (RIS)      
摘要 针对风电机组齿轮箱油温趋势预测中存在的信号非线性、多变量相关、各相关变量之间存在数据冗余等问题,同时为了克服人工神经网络离线训练的不足,该文提出了一种基于主成分分析(principal component analysis,PCA)和动态神经网络的齿轮箱油温趋势预测模型,并结合统计过程控制(statistical process control,SPC)实现该模型在线学习能力。确定影响油温变化的相关变量集,利用PCA消除相关变量间的数据冗余,采用有外部输入的非线性自回归动态神经网络(nonlinear autoregressive with external input,NARX)对油温和相关变量集进行建模,采用考虑残差分布规律的SPC方法控制模型在线学习行为。实际应用结果表明:该方法具有较高的稳定性和准确度,能够有效实现油温趋势预测。
服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
黄忠山
田凌
向东
韦尧中
关键词 风电机组齿轮箱油温主成分分析动态神经网络统计过程控制    
Abstract:The oil temperatures in wind turbine gearboxes are difficult to predict due to the strong nonlinearities. Multivariable correlations have been developed, but they are difficult to use due to the data redundancy between the correlation variables and the shortage of off-line training data for the artificial neural networks This paper presents a gearbox oil temperature prediction model based on a principal component analysis (PCA) and a dynamic neural network. The model uses online learning based on statistical process control (SPC). The PCA method deals with the data redundancy problem for the variables affecting the oil temperature. The nonlinear autoregressive with external input (NARX) dynamic neural network is then used to model the oil temperature. The SPC method analyzes the residual distribution to control the online learning behavior. Tests show that the method is stable and can accurately predict the oil temperature variations.
Key wordswind turbines    gearbox oil temperature    principal component analysis    dynamic neural network    statistical process control
收稿日期: 2018-01-15      出版日期: 2018-06-15
通讯作者: 田凌,教授,E-mail:tianling@tsinghua.edu.cn     E-mail: tianling@tsinghua.edu.cn
引用本文:   
黄忠山, 田凌, 向东, 韦尧中. 基于PCA和SPC-动态神经网络的风电机组齿轮箱油温趋势预测[J]. 清华大学学报(自然科学版), 2018, 58(6): 539-546.
HUANG Zhongshan, TIAN Ling, XIANG Dong, WEI Yaozhong. Prediction of oil temperature variations in a wind turbine gearbox based on PCA and an SPC-dynamic neural network hybrid. Journal of Tsinghua University(Science and Technology), 2018, 58(6): 539-546.
链接本文:  
http://jst.tsinghuajournals.com/CN/10.16511/j.cnki.qhdxxb.2018.26.026  或          http://jst.tsinghuajournals.com/CN/Y2018/V58/I6/539
  表1 相关性分析结果
  图1 NARX神经网络结构
  图2 基于 PCA和SPCG动态神经网络的模型算法
  表2 KMO 与 Bartlett相关性检验结果
  表3 解释的总方差
  表4 成分得分系数矩阵
  图3 拟合优度系数R 及残差自相关评价指标
  表5 NARX模型和 BP模型的性能指标结果
  图4 残差序列的 Gauss分布特性
  图5 正常工况与大风工况样本
  表6 正常工况下模型误差统计指标
  图6 不同工况下各模型预测值与真实值拟合结果
[1] TAN C M, RAGHAVAN N. A framework to practical predictive maintenance modeling for multi-state systems[J]. Reliability Engineering & System Safety, 2008, 93(8):1138-1150.
[2] ZHAO Y X. On preventive maintenance policy of a critical reliability level for system subject to degradation[J]. Reliability Engineering & System Safety, 2003, 79(3):301-308.
[3] HESS A, FILA L, editors. The joint strike fighter (JSF) PHM concept:Potential impact on aging aircraft problems[C]//Proceedings of 2002 IEEE Aerospace Conference. Big Sky, USA:IEEE Press, 2002:3021-3026.
[4] 谷振宇, 何彦, 刘军. 基于运行信息融合的大型设备视情维修系统[J]. 计算机集成制造系统, 2010, 16(10):2094-2100. GU Z Y, HE Y, LIU J. Condition-based maintenance system for large equipment based on running information fusion[J]. Computer Integrated Manufacturing Systems, 2010, 16(10):2094-2100. (in Chinese)
[5] HAMEED Z, HONG Y S, CHO Y M, et al. Condition monitoring and fault detection of wind turbines and related algorithms:A review[J]. Renewable & Sustainable Energy Reviews, 2009, 13(1):1-39
[6] AMIRAT Y, BENBOUZID M E H, AL-AHMAR E, et al. A brief status on condition monitoring and fault diagnosis in wind energy conversion systems[J]. Renewable & Sustainable Energy Reviews, 2009, 13(9):2629-2636
[7] CRABTREE C J, FENG Y, TAVNER P J. Detecting incipient wind turbine gearbox failure:A signal analysis method for on-line condition monitoring[J]. Journal of Organic Chemistry, 2010, 75(18):6122-6140.
[8] 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. ZHAO H S, HU Q C, LI Z W. Failure prediction of wind turbine gearbox based on statistical process control[J]. Power System Protection and Control, 2012, 40(13):67-73. (in Chinese)
[9] 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. GUO P, INFIELD D, YANG X Y. Wind turbine gearbox condition monitoring using temperature trend analysis[J]. Proceedings of the CSEE, 2011, 31(32):129-136. (in Chinese)
[10] 姚万业, 邸帅, 宋鹏, 等. 考虑样本优化的风电机组齿轮箱轴承故障预测[J]. 华北电力技术, 2017, (4):44-49.YAO W Y, DI S, SONG P, et al. Wind turbine gearbox bearing fault prediction with sample optimization[J]. North China Electric Power, 2017, (4):44-49. (in Chinese)
[11] 曾承志, 姚兴佳, 唐德尧, 等. 基于改进型HMM的风电机组齿轮箱故障预测[J]. 太阳能学报, 2016, 37(4):1017-1023. ZENG C Z, YAO X J, TANG D Y, et al. Fault prediction of the gearbox of wind turbine based on improved HMM[J]. Acta Energiae Solaris Sinica, 2016, 37(4):1017-1023. (in Chinese)
[12] 顾煜炯, 宋磊, 徐天金, 等. 变工况条件下的风电机组齿轮箱故障预警方法[J]. 中国机械工程, 2014, 25(10):1346-1351. GU Y J, SONG L XU T J, et al. Research on wind turbine gearbox fault warning method under variable working conditions[J]. China Mechanical Engineering, 2014, 25(10):1346-1351. (in Chinese)
[13] 肖成, 刘作军, 张磊. 基于SCADA系统的风电变桨故障预测方法研究[J]. 可再生能源, 2017, 35(2):278-284.XIAO C, LIU Z J, ZHANG L. Research on fault prediction method of wind power variable propeller based on SCADA system[J]. Renewable Energy Resources, 2017, 35(2):278-284. (in Chinese)
[14] 肖成, 焦智, 孙介涛, 等. 基于小波BP神经网络的风电机组变桨系统故障预测[J]. 可再生能源, 2017, 35(6):893-899. XIAO C, JIAO Z, SUN J T, et al. Fault prediction of variable propeller system of wind turbine based on wavelet BP neural network[J]. Renewable Energy Resources, 2017, 35(6):893-899. (in Chinese)
[15] 宁少华. 基于数据的风电机组故障趋势预测方法研究[D]. 北京:华北电力大学, 2015.NING S H. Research on fault trend prediction method of wind turbine based on data[D]. Beijing:North China Electric Power University, 2015. (in Chinese)
[16] 顾煜炯, 苏璐玮, 钟阳, 等. 基于区间划分的风电齿轮箱在线故障预警方法[J]. 电力科学与工程, 2014, 30(8):1-5.GU Y J, SU L W, ZHONG Yang, et al. On line fault early warning method for wind power gear box based on interval division[J]. Electric Power Science and Engineering, 2014, 30(8):1-5. (in Chinese)
[17] 姚万业, 杨金彭. 一种基于区间划分的风机故障预警方法[J]. 可再生能源, 2016, 34(6):861-866.YAO W Y, YANG J P. A fault early warning method for wind turbines based on interval division[J]. Renewable Energy Resources, 2016, 34(6):861-866. (in Chinese)
[18] 张小田. 基于回归分析的风机主要部件的故障预测方法研究[D]. 北京:华北电力大学, 2013.ZHANG X T. Research on fault prediction of turbine main components based on regression analysis[D]. Beijing:North China Electric Power University, 2013. (in Chinese)
[19] 彭宇, 刘大同. 数据驱动故障预测和健康管理综述[J]. 仪器仪表学报, 2014, 35(3):481-495.PENG Y, LIU D T. Data-driven prognostics and health management:A review of recent advances[J]. Chinese Journal of Scientific Instrument, 2014, 35(3):481-495. (in Chinese)
[20] BELHUMEUR P N, HESPANHA J P, KRIEGMAN D J. Eigenfaces vs. fisherfaces:Recognition using class specific linear projection[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2002, 19(7):711-720.
[21] SUN W, CHEN J, LI J. Decision tree and PCA-based fault diagnosis of rotating machinery[J]. Mechanical Systems & Signal Processing, 2007, 21(3):1300-1317.
[22] 张若青, 裘丽华. 基于动态神经网络的液压伺服系统故障检测[J]. 机械工程学报, 2002, 38(3):46-49.ZHANG R Q, QIU L H. Fault detection of hydraulic servo system based on dynamic neural network[J]. Journal of Mechanical Engineering, 2002, 38(3):46-49. (in Chinese)
[23] 赵晨. 动态神经网络在量化投资预测中的应用[D]. 上海:复旦大学, 2014.ZHAO C. Application of dynamic neural network in quantitative investment forecast[D]. Shanghai:Fudan University, 2014. (in Chinese)
[24] 郭秀才, 尚赛花. 基于三次收敛LM算法的神经网络研究[J]. 计算机应用与软件, 2014, 31(1):271-274.GUO X C, SHANG S H. Neural network research based on cubic convergent LM algorithm[J]. Computer Applications and Software, 2014, 31(1):271-274. (in Chinese)
[25] ALAEDDINI A, DOGAN I. Using Bayesian networks for root cause analysis in statistical process control[J]. Expert Systems with Applications, 2011, 38(9):11230-11243.
[26] 崔敬巍, 谢里阳. 基于贝叶斯动态模型的自相关控制图[J]. 北京航空航天大学学报, 2007, 33(3):375-378.CUI J W, XIE L Y. Auto-correlated charts based on dynamic Bayesian model[J]. Journal of Beijing University of Aeronautics and Astronautics, 2007, 33(3):375-378. (in Chinese)
[27] 郑昊. 统计过程控制(SPC)在精密连接器生产过程中的应用[D]. 西安:西安电子科技大学, 2009.ZHENG H. The application of SPC (Statistical Process Control) in the produce process of precision connector[D]. Xi'an:Xidian University, 2009. (in Chinese)
[28] 杨军, 梅雪松, 冯斌, 等. 时序分析在电主轴热误差建模中的应用[J]. 计算机集成制造系统, 2015, 21(5):1359-1367.YANG J, MEI X S, FENG B, et al. Application of time series analysis in thermal error modeling of motorized spindle[J]. Computer Integrated Manufacturing Systems, 2015, 21(5):1359-1367. (in Chinese)
[1] 熊谦, 唐文哲, 王忠静. 雄安新区水资源一体化管理要素分析与体系构建[J]. 清华大学学报(自然科学版), 2023, 63(2): 255-263.
[2] 赵日, 刘立业, 李君利. 基于主成分分析和Mahalanobis距离的异常γ能谱识别[J]. 清华大学学报(自然科学版), 2017, 57(8): 826-831.
[3] 路文焕, 曲悦欣, 杨亚龙, 王建荣, 党建武. 无声语音接口中超声图像的混合特征提取[J]. 清华大学学报(自然科学版), 2017, 57(11): 1159-1162,1169.
[4] 宋胜利, 杨健. 基于鲁棒主成分分析的SAR舰船检测[J]. 清华大学学报(自然科学版), 2015, 55(8): 844-848.
[5] 黄必清, 何焱, 王婷艳. 基于模糊综合评价的海上直驱风电机组运行状态评估[J]. 清华大学学报(自然科学版), 2015, 55(5): 543-549.
[6] 杨文韬, 耿华, 肖帅, 杨耕. 最大功率跟踪控制下大型风电机组的轴系扭振分析及抑制[J]. 清华大学学报(自然科学版), 2015, 55(11): 1171-1177.
[7] 谢旭东,袁兆君,郭伟,张毅. 基于噪点检测与邻域权值内插的彩色人脸图像去噪[J]. 清华大学学报(自然科学版), 2014, 54(4): 536-539.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 《清华大学学报(自然科学版)》编辑部
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持:support@magtech.com.cn