Journal: Advances in Computer and Autonomous Intelligence Research DOI: 10.32629/acair.v4i3.21356
Abstract
针对滚动轴承的频域特征,本文提出了一种加权无向频域特征图(FFG),旨在有效扩充 频域特征的维度。在此基础上,构建了一种轻量化的高效卷积神经网络(ECNN)。该网 络引入了Mish激活函数与带膨胀因子的深度可分离模块,并通过融合原始矩阵的浅层 特征与输出矩阵的深层特征,有效克服了特征提取过程中的梯度消失问题。在滚动轴 承试验台上对基于FFG- ECNN的方法进行了测试。结果表明：该方法实现了不同转速、负载下故障部位的精 确识别；在样本不平衡与噪声影响下,故障诊断准确率仍达99.2%。
Keywords
滚动轴承；故障诊断；频域特征；卷积神经网络；轻量化模型
Full Text
PDF - Viewed/Downloaded: 0 TimesReferences
[1] 胡智勇.滚动轴承振动信号处理方法综述[J].中国工程机械学报,2016,14(06):525 -531.
[2] 陈金海.智能滚动轴承监测方法与技术研究现状综述[J].机械强度,2021,43(03):5 09-516.
[3] 丁春嵘.基于深度特征提取神经网络的滚动轴承故障诊断[J].北京化工大学学报,2 022,49(01):106-112.
[4] 薛妍.基于一维卷积神经网络的滚动轴承故障程度诊断[J].轴承,2021(04):48- 54.
[5] OHJ.Convolutionalneuralnetwork and 2-D image based fault diagnosis of bearing without retraining[C].Proceedings of the 3rd international conference on compute and data analysis.2019:14-17.
[6] INCE T.Real-time motor fault detection by 1-D convolutional neural networks[J].IEEE transactions,2016,63(1):7067-7075.
[7] ZHANG W.A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load[J].Signal process,2018,100(3):439-453.
[8] LU C.Fault diagnosis of rotary machinery components using a stacked denoising autoencoder-based health state identification[J].Signal process,2017,130(1):377-388.
[9] DENG W.Study on a fault diagnosis method of rolling element bearing based on improved ACO and SVM model [J].Future gener-commun networking,2016,9(43):167-180.
[10] ZHANG R.Fault diagnosis of rolling bearing based on k-SVD dictionary learning algorithm and BP neural network[C].In proceedings of the 2019 international conference on robotics,intelligent control and artificial intelligence,2019:20-22.
[11] ABED W.A robust bearing fault detection and diagnosis technique for brushless dc motors under non-stationary operating conditions[J].Journal of control automation & electrical systems,2015,43(26):241-254.
[12] SHAO H.Rolling bearing fault diagnosis using adaptive deep belief network with dual-tree complex wavelet packet[J].ISA transactions,2017,69(3):187-201.
[13] SOHAIB M.Fault diagnosis of rotary machine bearings under inconsistent working conditions[J].IEEE transactions on instrumentation and measurement,2019,69(13):3334-3347.
[2] 陈金海.智能滚动轴承监测方法与技术研究现状综述[J].机械强度,2021,43(03):5 09-516.
[3] 丁春嵘.基于深度特征提取神经网络的滚动轴承故障诊断[J].北京化工大学学报,2 022,49(01):106-112.
[4] 薛妍.基于一维卷积神经网络的滚动轴承故障程度诊断[J].轴承,2021(04):48- 54.
[5] OHJ.Convolutionalneuralnetwork and 2-D image based fault diagnosis of bearing without retraining[C].Proceedings of the 3rd international conference on compute and data analysis.2019:14-17.
[6] INCE T.Real-time motor fault detection by 1-D convolutional neural networks[J].IEEE transactions,2016,63(1):7067-7075.
[7] ZHANG W.A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load[J].Signal process,2018,100(3):439-453.
[8] LU C.Fault diagnosis of rotary machinery components using a stacked denoising autoencoder-based health state identification[J].Signal process,2017,130(1):377-388.
[9] DENG W.Study on a fault diagnosis method of rolling element bearing based on improved ACO and SVM model [J].Future gener-commun networking,2016,9(43):167-180.
[10] ZHANG R.Fault diagnosis of rolling bearing based on k-SVD dictionary learning algorithm and BP neural network[C].In proceedings of the 2019 international conference on robotics,intelligent control and artificial intelligence,2019:20-22.
[11] ABED W.A robust bearing fault detection and diagnosis technique for brushless dc motors under non-stationary operating conditions[J].Journal of control automation & electrical systems,2015,43(26):241-254.
[12] SHAO H.Rolling bearing fault diagnosis using adaptive deep belief network with dual-tree complex wavelet packet[J].ISA transactions,2017,69(3):187-201.
[13] SOHAIB M.Fault diagnosis of rotary machine bearings under inconsistent working conditions[J].IEEE transactions on instrumentation and measurement,2019,69(13):3334-3347.
Copyright © 2026 孙晨冉, 焦萌萌, 李一帆, 秦颖辉
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License