基于小波包和改进核最近邻算法的风机齿轮箱故障诊断方法
|
摘要
齿轮箱作为风力机组的核心部件,故障频发,研究风机齿轮箱的故障诊断方法意义重大。针对最近邻(KNN)诊断方法对离群噪声不敏感和诊断精度较低的缺陷,提出了基于小波包和改进核最近邻算法的风机齿轮箱故障诊断方法。该方法应用小波包分析技术对故障特征进行提取,利用互近邻准则将故障数据集中的离群噪声点剔除,构建出基于核空间的改进型最近邻分类决策规则来识别齿轮箱的故障类型。试验表明:该方法可以有效地提升故障诊断精度和鲁棒性,为智能诊断技术的研究提供新思路。
As the core component of wind turbines, gearboxes frequently fail. It is significant to study the fault diagnosis methods of the wind turbine gearboxes. Considering that the K-nearest neighbors(KNN) diagnosis method was insensitive to noise and the accuracy of fault diagnosis was low, a fault diagnosis method based on wavelet packet and improved kernel K-nearest neighbors algorithm was proposed. This method used wavelet packet analysis technology to extract the fault features, and eliminated the noise by mutual nearest neighbor criterion. Then, an improved K-nearest neighbors classification decision rule based on kernel method was established. Experiments showed that this method could effectively improve fault diagnosis accuracy and robustness, and provide new ideas for the research of intelligent diagnosis technology.
As the core component of wind turbines, gearboxes frequently fail. It is significant to study the fault diagnosis methods of the wind turbine gearboxes. Considering that the K-nearest neighbors(KNN) diagnosis method was insensitive to noise and the accuracy of fault diagnosis was low, a fault diagnosis method based on wavelet packet and improved kernel K-nearest neighbors algorithm was proposed. This method used wavelet packet analysis technology to extract the fault features, and eliminated the noise by mutual nearest neighbor criterion. Then, an improved K-nearest neighbors classification decision rule based on kernel method was established. Experiments showed that this method could effectively improve fault diagnosis accuracy and robustness, and provide new ideas for the research of intelligent diagnosis technology.
引文
[1] 曾军,陈艳峰,杨苹,等.大型风力发电机组故障诊断综述[J].电网技术,2018,42(3): 849.
[2] 张文秀,武新芳.风电机组状态监测与故障诊断相关技术研究[J].电机与控制应用,2014,41(2): 50.
[3] 徐志翔.基于改进PSO和参数优化的LSSVM的风力发电机齿轮箱故障诊断[D].上海: 华东理工大学,2012.
[4] RICHARD C, LENGELLé R. Joint recursive implementation of time-frequency representations and their modified version by the reassignment method[J].Signal Processing,1997,60(2): 163.
[5] MELTZER G, DIENB N P. Fault diagnosis in gears operating under non-stationary rotational speed using polar wavelet amplitude maps[J].Mechanical Systems & Signal Processing,2004,18(5): 985.
[6] 卢锦玲,绳菲菲,赵洪山.基于相关向量机的风机齿轮箱故障诊断方法[J].华北电力大学学报(自然科学版),2017,44(2): 91.
[7] 杨明莉,刘三明,张卫,等.基于振动分析的风力机齿轮箱故障诊断[J].电机与控制应用,2015,42(1): 66.
[8] 朱俊,刘天羽,王致杰,等.基于蜂群算法的选择性神经网络集成的风机齿轮箱轴承故障诊断[J].电机与控制应用,2017,44(1): 6.
[9] 刘凡,张昀,姚晓,等.基于K近邻算法的换流变压器局部放电模式识别[J].电力自动化设备,2013,33(5): 89.
[10] 孙斌,刘立远,牛翀.基于局部切空间排列和K-最近邻分类器的转子故障诊断方法[J].中国机械工程,2015,26(1): 74.
[11] 侯平智,张明,徐晓滨,等.基于K近邻证据融合的故障诊断方法[J].控制与决策,2017,32(10): 1767.
[12] 陈法法,汤宝平,苏祖强.基于等距映射与加权KNN的旋转机械故障诊断[J].仪器仪表学报,2013,34(1): 215.
[13] 于志伟,苏宝库,曾鸣.小波包分析技术在大型电机转子故障诊断系统中的应用[J].中国电机工程学报,2005,25(22): 158.
[14] 武瑞兵.基于8层小波包分解的电机定子电流故障诊断新方法[J].电机与控制应用,2015,42(4): 32.
[15] 汪庆华,刘江炜,张兰兰.交叉验证K近邻算法分类研究[J].西安工业大学学报,2015,35(2): 119.
[2] 张文秀,武新芳.风电机组状态监测与故障诊断相关技术研究[J].电机与控制应用,2014,41(2): 50.
[3] 徐志翔.基于改进PSO和参数优化的LSSVM的风力发电机齿轮箱故障诊断[D].上海: 华东理工大学,2012.
[4] RICHARD C, LENGELLé R. Joint recursive implementation of time-frequency representations and their modified version by the reassignment method[J].Signal Processing,1997,60(2): 163.
[5] MELTZER G, DIENB N P. Fault diagnosis in gears operating under non-stationary rotational speed using polar wavelet amplitude maps[J].Mechanical Systems & Signal Processing,2004,18(5): 985.
[6] 卢锦玲,绳菲菲,赵洪山.基于相关向量机的风机齿轮箱故障诊断方法[J].华北电力大学学报(自然科学版),2017,44(2): 91.
[7] 杨明莉,刘三明,张卫,等.基于振动分析的风力机齿轮箱故障诊断[J].电机与控制应用,2015,42(1): 66.
[8] 朱俊,刘天羽,王致杰,等.基于蜂群算法的选择性神经网络集成的风机齿轮箱轴承故障诊断[J].电机与控制应用,2017,44(1): 6.
[9] 刘凡,张昀,姚晓,等.基于K近邻算法的换流变压器局部放电模式识别[J].电力自动化设备,2013,33(5): 89.
[10] 孙斌,刘立远,牛翀.基于局部切空间排列和K-最近邻分类器的转子故障诊断方法[J].中国机械工程,2015,26(1): 74.
[11] 侯平智,张明,徐晓滨,等.基于K近邻证据融合的故障诊断方法[J].控制与决策,2017,32(10): 1767.
[12] 陈法法,汤宝平,苏祖强.基于等距映射与加权KNN的旋转机械故障诊断[J].仪器仪表学报,2013,34(1): 215.
[13] 于志伟,苏宝库,曾鸣.小波包分析技术在大型电机转子故障诊断系统中的应用[J].中国电机工程学报,2005,25(22): 158.
[14] 武瑞兵.基于8层小波包分解的电机定子电流故障诊断新方法[J].电机与控制应用,2015,42(4): 32.
[15] 汪庆华,刘江炜,张兰兰.交叉验证K近邻算法分类研究[J].西安工业大学学报,2015,35(2): 119.