基于多尺度排列熵和支持向量机的风力发电机组齿轮箱振动故障诊断

发布时间：2018-11-04 19:39

【摘要】：伴随我国新能源事业的蓬勃发展,风力发电等可再生能源发电占全部发电总量的比重也日趋增大。然而经过十几年的发展,随着投运的风电机组使用年限的累积,许多风电场相继出现了机组关键部位故障、使用寿命不达标、维修周期冗长、无故障运行时间短等问题。尤其是在早期投运且仍在风力发电里占据较大比重的双馈式风电机组中上述情况更为明显,而此类风机核心部件齿轮箱的故障率高达40%-50%。因此,开展风电机组齿轮箱故障诊断研究具有较为重要的实际意义。鉴于此,本文以风力发电机组的齿轮箱为研究对象,并对其振动故障诊断进行了研究,主要内容有:1、本文引入排列熵算法对齿轮箱振动信号进行早期故障分析,进而引入多尺度排列熵算法实现风机齿轮箱振动信号的特征提取,为风电机组齿轮箱的振动故障诊断开启了一种新的研究思路和解决办法。2、本文在阐述支持向量机用于故障诊断的基础上,对径向基核函数宽度参数和误差惩罚参数这两个重要参数的选择加以讨论,考虑到其他方法存在样本需求量大、局限性强、泛化能力弱、早熟问题等缺陷,最终确定利用遗传算法优化支持向量机参数,进而构建分类效果理想的故障诊断模型。3、本文提出了基于多尺度排列熵与支持向量机的风力发电机组齿轮箱故障诊断方法,通过实例数据进行验证和分析,结果表明,该方法具有较高的诊断精度,平均诊断准确度达到93.333%以上研究结果表明,本文所提出的诊断方法能够较为准确的诊断出风电机组的振动故障类型,为风电齿轮箱的故障诊断研究提供了一种新的思路。
[Abstract]:With the vigorous development of new energy in China, the proportion of renewable energy such as wind power generation in the total power generation is increasing day by day. However, with the development of more than ten years, with the accumulation of the operating life of wind turbine, many wind farms have appeared some problems, such as the fault of key part of the unit, the service life is not up to the standard, the maintenance cycle is long, and the running time is short. Especially in the doubly-fed wind turbine which was put into operation in the early stage and still occupies a large proportion in wind power generation, the failure rate of the gearbox, the core part of this kind of fan, is as high as 40-50. Therefore, it is of great practical significance to study the fault diagnosis of wind turbine gearbox. In view of this, this paper takes the gearbox of the wind turbine as the research object, and studies its vibration fault diagnosis. The main contents are as follows: 1. This paper introduces the permutation entropy algorithm to carry on the early fault analysis to the gearbox vibration signal. Then the multi-scale permutation entropy algorithm is introduced to extract the vibration signal of fan gearbox, which opens a new research idea and solution for the vibration fault diagnosis of wind turbine gearbox. On the basis of describing the application of support vector machine in fault diagnosis, this paper discusses the selection of two important parameters of radial basis function width parameter and error penalty parameter, considering that other methods have large sample demand and strong limitation. Finally, the genetic algorithm is used to optimize the parameters of support vector machine, and then the fault diagnosis model with ideal classification effect is constructed. In this paper, a fault diagnosis method for wind turbine gearbox based on multi-scale permutation entropy and support vector machine is proposed. The average diagnostic accuracy is over 93.333%. The results show that the method presented in this paper can accurately diagnose the vibration fault type of wind turbine, which provides a new way for the fault diagnosis of wind turbine gearbox.
【学位授予单位】：西安理工大学
【学位级别】：硕士
【学位授予年份】：2017
【分类号】：TM315

【相似文献】