摘要
针对有标记故障样本不足和故障数据高维非线性的问题,提出了基于半监督拉普拉斯特征映射(LE)算法的故障诊断模型。该模型运用LE算法,直接从原始高维振动信号中提取低维流形特征,并将其输入到基于LE的半监督分类器,从而识别出机械设备的运行状态。与传统方法相比,该模型能明显提高滚动轴承和齿轮的故障识别性能。
Aiming at solving the problems of insufficient labeled fault samples and high-dimensional nonlinear fault data,a fault diagnosis model was proposed based on semi-supervised LE algorithm.The model directly extracted the low-dimensional manifold features from the raw high-dimensional vibration signals,by implementing LE algorithm.The features were fed into semi-supervised classifier based on LE algorithm.Thereby,the operating conditions of mechanical equipment were recognized.Compared with the traditional methods,the model is able to obviously improve fault recognition performance of rolling bearings and gears.
出处
《中国机械工程》
EI
CAS
CSCD
北大核心
2016年第14期1911-1916,共6页
China Mechanical Engineering
基金
国家自然科学基金资助项目(71171154)
湖北省自然科学基金资助项目(2015CFB698)
湖北省科技支撑计划资助项目(2014BAA032
2015BAA063)
关键词
故障诊断
特征提取
流形学习
半监督拉普拉斯特征映射
fault diagnosis
feature extraction
manifold learning
semi-supervised Laplacian eigenmap（LE）
