沈阳航空航天大学学报2023，Vol.40Issue(5)：50-55,6.DOI:10.3969/j.issn.2095-1248.2023.05.007
基于VME-M1DCNN-LSTM的齿轮异常状态智能识别
Intelligent recognition of gear abnormal states based on VME-M1DCNN-LSTM
摘要
Abstract
In engineering practice,the vibration signal of gears is severely polluted by noise,making it difficult to accurately identify their abnormal states.To address the problem,a new intelligent recogni-tion method for gear abnormal states based on the variational mode extraction(VME)and the multi-scale one-dimensional convolution(M1DC)fusion with long short term memory(LSTM)neural net-work was proposed.Firstly,the VME method was used to preprocess the original vibration signals in five states:normal state,gear tooth fragmentation,gear breakage,root crack,and gear wear.The noise in original vibration signals was removed,and the principal mode components of gears in different states were extracted as the feature information of the gear state.Secondly,a training data set and a test data set were constructed from the extracted principal mode components of the gear state.Finally,an M1DC-LSTM abnormal state recognition model was designed,and the constructed data set was used to test and verify the designed model.The results show that the method proposed in this paper can effec-tively achieve intelligent recognition of gear abnormal states,and the accuracy rate reaches 99.25%,which is significantly higher than other related methods.关键词
齿轮/异常状态识别/变分模态提取/多尺度一维卷积/长短时记忆神经网络Key words
gear/abnormal state recognition/variational mode extraction/multiscale one-dimensional convolution/long short term memory neural network分类
信息技术与安全科学引用本文复制引用
杜文友,王宇琦,崔霄,徐伟,崔建国..基于VME-M1DCNN-LSTM的齿轮异常状态智能识别[J].沈阳航空航天大学学报,2023,40(5):50-55,6.基金项目
国家自然科学基金(项目编号:61903262) （项目编号:61903262）
辽宁省自然科学基金(项目编号:2020-BS-176) （项目编号:2020-BS-176）
