1 齿轮异常状态智能识别方法原理
1.1 VME算法原理
1.2 一维卷积神经网络
1.3 长短时记忆神经网络
1.4 M1DCNN-LSTM异常状态识别模型
2 齿轮异常状态智能识别实现步骤
3 齿轮异常状态识别试验验证
表1 不同模型的齿轮异常状态识别准确率 |
序号 | 异常状态识别模型 | 准确率/% |
---|---|---|
1 | LSTM | 86 |
2 | M1DCNN | 88.625 |
3 | M1DCNN-LSTM | 93.25 |
4 | VME-M1DCN-LSTM | 99.25 |
Journal of Shenyang Aerospace University >
Intelligent recognition of gear abnormal states based on VME⁃ M1DCNN⁃LSTM
Received date: 2023-10-12
Online published: 2023-12-22
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 recognition method for gear abnormal states based on the variational mode extraction (VME) and the multiscale one-dimensional convolution (M1DC) fusion with long short term memory (LSTM) neural network 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 effectively achieve intelligent recognition of gear abnormal states,and the accuracy rate reaches 99.25%,which is significantly higher than other related methods.
Wenyou DU , Yuqi WANG , Xiao CUI , Wei XU , Jianguo CUI . Intelligent recognition of gear abnormal states based on VME⁃ M1DCNN⁃LSTM[J]. Journal of Shenyang Aerospace University, 2023 , 40(5) : 50 -55 . DOI: 10.3969/j.issn.2095-1248.2023.05.007
表1 不同模型的齿轮异常状态识别准确率 |
序号 | 异常状态识别模型 | 准确率/% |
---|---|---|
1 | LSTM | 86 |
2 | M1DCNN | 88.625 |
3 | M1DCNN-LSTM | 93.25 |
4 | VME-M1DCN-LSTM | 99.25 |
1 |
魏永合,尹际雄,马步芳.基于半监督随机森林分类算法的齿轮故障诊断[J].沈阳理工大学学报,2020,39(4):53-58.
|
2 |
张振,陈春俊,孙琦.双齿根裂纹下的齿轮啮合刚度劣化特性研究[J].中国测试,2020,46(5):127-133.
|
3 |
黎政,吴胜利,邢文婷,等.基于MGAN和CNN的齿轮故障智能诊断方法[J].机械传动,2022,46(7):144-150,157.
|
4 |
|
5 |
宋庭新,黄继承,刘尚奇,等.小样本下基于DWT和2D-CNN的齿轮故障诊断方法[J/OL].计算机集成制造系统.( 2023-01-15)[2023-11-28].
|
6 |
刘明昊,陆金桂,张佳坤,等.基于VMD能量熵值的齿轮箱滚动轴承故障诊断[J].煤矿机械,2023,44(10):173-175.
|
7 |
|
8 |
潘琳鑫.基于深度学习的齿轮箱故障诊断方法研究[D].盐城:盐城工学院,2023.
|
9 |
谭伦荣,王辉.基于深度卷积神经网络的无线通信网络异常攻击检测[J].重庆科技学院学报(自然科学版),2022,24(6):60-64.
|
10 |
张国山,赵阳.融合Inception-LSTM级联网络下的动态手势识别[J].光电子·激光,2021,32(4):373-381.
|
11 |
马帅,吴亚锋,郑华,等.基于改进LSTM的航空发动机气路参数预测方法[J/OL].测控技术.(2023-08-31)[2023-09-10].
|
12 |
|
13 |
齐永锋,裴晓旭,赵岩.基于多尺度卷积特征融合的癫痫脑电信号识别[J].光电子·激光,2022,33(7):778-784.
|
14 |
胡安翔,李振华.基于Faster R-CNN改进的数粒机系统[J].包装工程,2018,39(9):141-145.
|
15 |
吉哲,吕飞,王冕.基于优化VMD和深度卷积神经网络的柴油发电机组故障诊断[J].机械与电子,2023,41(8):8-13.
|
/
〈 |
|
〉 |