摘要
针对机器学习故障诊断中存在的先验知识依赖以及数据利用不充分问题,提出一种自适应邻域的局部保留极限学习机自动编码器方法。成对样本在原始数据空间和嵌入的表示空间中引入欧几里得距离惩罚因子,实现数据样本的相似性分类;提出一个统一的目标函数,可以同时学习数据表示和关联矩阵,并提出一个软判别约束防止过度拟合。实验结果表明,融合学习关联矩阵和数据表示方法具有学习速度快、泛化能力强和诊断精度高等优点。
In order to solve the problems of prior knowledge dependence and insufficient data mining in machine learning fault diagnosis,a local preserving extreme learning machine automatic encoder based on adaptive neighborhood is proposed.Euclidean distance penalty factor was introduced into the original data space and the embedded representation space for paired samples to realize the similarity classification of data samples.A unified objective function was proposed,which could simultaneously learn data representation and correlation matrix,and a soft discriminative constraint was proposed to prevent overfitting.The experimental results show that the fusion learning association matrix and data representation method has the advantages of fast learning speed,strong generalization ability and high diagnostic accuracy.
作者
张焕可
王帅旗
陈会涛
Zhang Huanke;Wang Shuaiqi;Chen Huitao(Department of Mechanical and Electrical Engineering,Xuchang Vocational College of Electrical Engineering,Xuchang 461000,Henan,China;School of Mechanical and Power Engineering,Henan University of Technology,Jiaozuo 454003,Henan,China)
出处
《计算机应用与软件》
北大核心
2024年第1期56-63,共8页
Computer Applications and Software
基金
2018年度河南省重点研发与推广专项(182102310793)。
关键词
极限学习机
自动编码器
关联矩阵学习
自适应邻域
机器故障诊断
Extreme learning machine
Automatic encoder
Affinity learning matrix
Adaptive neighborhood
Machine fault diagnosis
