噪声与振动控制2025，Vol.45Issue(4)：176-182,298,8.DOI:10.3969/j.issn.1006-1355.2025.04.028
转速往复变化下基于SESF的机械故障智能诊断方法
Mechanical Fault Intelligent Diagnosis Method Based on SESF under Reciprocal Change of Speed
摘要
Abstract
The mapping relationship between signal signs and fault modes is very complicated due to reciprocal change of speed condition,which is an important challenge for equipment fault diagnosis.In this work,an SE attention guided sparse filtering(SESF)method is proposed for intelligent fault diagnosis of mechanical equipment under reciprocal change of speed.Firstly,the SE attention mechanism is used to improve the sparse filtering algorithm.Then,the unsupervised fea-ture extraction is carried out on the reciprocal change of speed signal samples,and the adaptive screening and weighting for the training results are performed so as to cause the model to focus on the region which has the most classified differentia-tion.Thus,the ability of the model to obtain useful information is improved.Finally,two sets of specially designed gear and bearing tests under the condition of reciprocal change of rotating speed are used to verify the performance of the proposed method.The experimental results show that the proposed method can suppress the influence of reciprocal change of speed to achieve accurate identification of different mechanical faults,and obtain the higher accuracy than other methods.关键词
故障诊断/注意力机制/稀疏滤波/转速往复变化Key words
fault diagnosis/attention mechanism/sparse filtering/reciprocal change of speed分类
机械制造引用本文复制引用
李博,陈录平,韩瑞,王金瑞..转速往复变化下基于SESF的机械故障智能诊断方法[J].噪声与振动控制,2025,45(4):176-182,298,8.基金项目
国家能源集团科技资助项目(GJNY-21-166) （GJNY-21-166）
