基于改进DEMD和ICA的海上风机传动系统早期故障诊断

发布时间：2018-02-08 12:33

本文关键词： 海上风电传动系统早期故障诊断经验模式分解独立分量分析　出处：《电机与控制学报》2017年11期 　论文类型：期刊论文

【摘要】：针对传动系统早期故障振动信号较弱的情况,提出基于改进微分经验模式分解(DEMD)和独立分量分析(ICA)的海上风机传动系统早期故障诊断方法。为克服传统的DEMD算法在分解低阶本征模态函数(IMF)时存在失真现象,提出改进的微分经验模式算法将原始振动信号分解成若干个独立的IMF信号,结合ICA进一步进行原始振动信号故障特征分量的提取,并基于标准数据和风机动力传动故障诊断实验平台进行了仿真研究,最后选取海上风电机组传动系统常出现的发电机轴承故障进行诊断分析。结果表明,相对于传统的故障诊断方法,该方法能更好地放大故障分量,减少噪声和其他振动干扰信号的影响,提高了海上风电机组传动系统早期故障诊断的准确性。
[Abstract]:In view of the weak vibration signal of the transmission system in the early stage, An early fault diagnosis method for offshore fan transmission system based on improved differential empirical mode decomposition (DEMD) and independent component analysis (ICA) is proposed. In order to overcome the distortion of the traditional DEMD algorithm in decomposing low order intrinsic mode function (IMF). An improved differential empirical mode algorithm is proposed to decompose the original vibration signal into several independent IMF signals, and further extract the fault feature components of the original vibration signal with ICA. Based on the standard data and the experimental platform for fault diagnosis of fan power transmission, a simulation study is carried out. At last, the fault diagnosis of generator bearing, which often occurs in the transmission system of offshore wind turbine, is selected for diagnosis and analysis. The results show that, Compared with the traditional fault diagnosis method, this method can better amplify the fault component, reduce the influence of noise and other vibration interference signals, and improve the accuracy of early fault diagnosis of offshore wind turbine transmission system.
【作者单位】：上海电力学院自动化工程学院;国网浙江省电力公司金华供电公司;上海东海风力发电有限公司;
【基金】：国家自然科学基金(51507098)
【分类号】：TM315

【相似文献】