基于改进DBSCAN算法的风机故障诊断研究Research on wind turbine fault diagnosis based on improved DBSCAN algorithm
林涛,马同宽,秦冬阳,董栅
摘要(Abstract)：
针对风电集控中心需监控多个类型风机并对故障的风机进行故障诊断问题,通过运用DBSCAN聚类算法对风机运行数据进行密度聚类,判定齿轮箱和主轴方面的故障,并针对DBSCAN算法中需人为设定参数的确定进行了改进。首先在KNN分布曲线上假定陡增点,采用循环迭代的方法进行分段拟合计算出最优参数Eps;然后利用数学统计原理分析计算MinPts,实现聚类全过程的自动化,减小了根据经验判断参数的误差。最后利用风场实际数据进行试验,提取并分析聚类结果中的噪声点,通过数据异常值进行故障诊断,验证了此方法的可行性和有效性。
关键词(KeyWords)： 风机;密度聚类;DBSCAN;曲线拟合;噪声点;故障诊断
基金项目(Foundation): 河北科技计划项目(17214304D)~~
作者(Author): 林涛,马同宽,秦冬阳,董栅
DOI: 10.16652/j.issn.1004-373x.2018.21.033
参考文献(References)：
- [1]沈艳霞,杨雄飞,赵芝璞.风力发电系统传感器故障诊断[J].控制理论与应用,2017,34(3):321-328.SHEN Yanxia,YANG Xiongfei,ZHAO Zhipu. Sensor fault diagnosis for wind turbine system[J]. Control theory&applications,2017,34(3):321-328.
- [2]刘旭.数据挖掘在风力发电机组故障诊断中的应用[D].北京:中国地质大学,2016.LIU Xu. Application of data mining in wind turbine fault diagnosis[D]. Beijing:China University of Geosciences,2016.
- [3]孙鹤旭,孙泽贤,林涛.数据挖掘技术在风电机组故障诊断中的应用[J].中南民族大学学报(自然科学版),2016,35(4):81-85.SUN Hexu,SUN Zexian,LIN Tao. Application of data mining technology in fault diagnosis of wind turbogenerator[J]. Journal of South-Central University for Nationalities(natural science edition),2016,35(4):81-85.
- [4]郜立焕,张利娜,朱建国,等.基于小波分析的齿轮箱振动信号消噪处理[J].机械传动,2010,34(3):50-52.GAO Lihuan,ZHANG Lina,ZHU Jianguo,et al. Gearbox vibration signal de-noising processing based on wavelet analysis[J]. Journal of mechanical transmission,2010,34(3):50-52.
- [5]冷军发,荆双喜,吴中青.基于RBF神经网络的齿轮箱故障诊断[J].机械强度,2010,32(1):17-20.LENG Junfa,JING Shuangxi,WU Zhongqing. Fault diagnosis for gearbox based on RBF neural network[J]. Journal of mechanical strength,2010,32(1):17-20.
- [6]王斌,董兴辉,刘浩,等.基于故障树的专家系统在风电齿轮箱上的应用[J].装备制造技术,2011(10):104-107.WANG Bin,DONG Xinghui,LIU Hao,et al. Application of expert system based on fault tree for wind gear box[J]. Equipment manufacturing technology,2011(10):104-107.
- [7]王林,刘志军,田强,等.柔性支持向量回归算法在故障诊断中的应用[J].控制工程,2017,24(6):1261-1265.WANG Lin,LIU Zhijun,TIAN Qiang,et al. A flexible support vector regression method and its application in fault diagnosis[J]. Control engineering of China,2017,24(6):1261-1265.
- [8]安计勇,韩海英,侯效礼.一种改进的DBSCAN聚类算法[J].微电子学与计算机,2015,32(7):68-71.AN Jiyong,HAN Haiying,HOU Xiaoli. An improved DBSCAN clustering algorithm[J]. Microelectronics&computer,2015,32(7):68-71.
- [9]周治平,王杰锋,朱书伟,等.一种改进的自适应快速AF-DBSCAN聚类算法[J].智能系统学报,2016,11(1):93-98.ZHOU Zhiping,WANG Jiefeng,ZHU Shuwei,et al. An improved adaptive and fast AF-DBSCAN clustering algorithm[J].CAAI transactions on intelligent systems,2016,11(1):93-98.
- [10]韩利钊,钱雪忠,罗靖,等.基于区域划分的DBSCAN多密度聚类算法[J].计算机应用研究,2018,35(6):1-2.HAN Lizhao,QIAN Xuezhong,LUO Jing,et al. Multi-density clustering algorithm DBSCAN based on region division[J].Application research of computers,2018,35(6):1-2.
- [11]冯振华,钱雪忠,赵娜娜.Greedy DBSCAN:一种针对多密度聚类的DBSCAN改进算法[J].计算机应用研究,2016,33(9):2693-2696.FENG Zhenhua,QIAN Xuezhong,ZHAO Nana. Greedy DBSCAN:an improved DBSCAN algorithm on multi-density clustering[J]. Application research of computers,2016,33(9):2693-2696.
- [12]李宗林,罗可.DBSCAN算法中参数的自适应确定[J].计算机工程与应用,2016,52(3):70-73.LI Zonglin,LUO Ke. Research on adaptive parameters determination in DBSCAN algorithm[J]. Computer engineering and applications,2016,52(3):70-73.
- [13]夏鲁宁,荆继武.SA-DBSCAN:一种自适应基于密度聚类算法[J].中国科学院研究生院学报,2009,26(4):530-538.XIA Luning,JING Jiwu. SA-DBSCAN:a self-adaptive densitybased clustering algorithm[J]. Journal of the Graduate School of the Chinese Academy of Sciences,2009,26(4):530-538.