【作者】 毕锦烟； 李巍华；

【Author】 BI Jin-yan, LI Wei-hua (School of Automotive Engineering, South China University of Technology, Guangzhou 510640, China)

【机构】 华南理工大学汽车工程学院；

【摘要】 研究核聚类方法在机械故障检测中的应用问题,将基于半监督学习的模糊核聚类方法用于齿轮箱早期故障的检测。机械故障早期检测的难点是故障特征不明显、样本差异小。基于半监督学习的核聚类方法利用少量已知模式的样本,结合大量未知模式的样本进行半监督学习,得到较好的识别效果。进行了齿轮箱正常运行和齿轮轻微剥落的故障实验,比较了基于半监督学习的核聚类方法与无监督学习核聚类方法的检测效果。结果表明,基于半监督学习的核聚类方法性能更优越。更多还原

【Abstract】 Kernel clustering is investigated together with some application in mechanical fault detection, and a semi-supervised kernel-based fuzzy clustering is applied for gear fault early detection. The difficulty in mechanical fault early detection is to detect the weakly fault information immerged in noises. The semi-supervised kernel clustering method utilizes a few of known samples, combined with a larger amount of unknown samples to perform semi-supervised learning, and obtains good efficiency. The experiments are conducted on a gearbox, where a surface defect of tooth spalling is introduced .The effect of semi-supervised kernel clustering is compared with that of unsupervised kernel clustering, and it also demonstrates the superiority of the semi-supervised method for gear failure detection.更多还原