摘要
提出了一种基于模糊C-均值的永磁直流电机故障模式识别方法。首先通过模糊C-均值聚类算法对无类别标识的故障样本数据进行模糊划分,并根据模糊聚类的隶属度矩阵,判断定位每一样本数据的所属类,并定位样本数据中的野点,消除野点后,再利用基于支持向量机的模式识别方法对模糊划分后的数据进行训练。研究结果表明:该方法解决了永磁直流电机故障在线监测与诊断中缺少已知类别标签的训练样本问题,抑制了复杂环境中噪声,提高了含有大量噪声数据的永磁直流电机在线故障识别精度。
An improved failure recognize method based on fuzzy C-means for permanent magnetic DC motors was proposed in this paper. The online data were clustered by the fuzzy C-means and the outliers were recognized according to the membership grade calculated from the fuzzy C-means. And then the data which removed the outliers were trained and tested by the support vector machine algorithm above mentioned. The experimental results show that support vector machine algorithm based on fuzzy C-means have better tolerance of noise and anti-noise performance. It enhances fault recognition precision in the complex case for the online faults diagnosis of permanent-magnetic DC motors.
出处
《微电机》
北大核心
2011年第10期78-80,共3页
Micromotors
关键词
永磁直流电机
支持向量机
模糊C-均值
模式识别
故障诊断
permanent magnetic DC motor
support vector machines
fuzzy C-means
failure recognize
failure diagnosis
