基于深度森林的轴承故障诊断方法

丁家满1,吴晔辉1,罗青波1,杜奕2

振动与冲击 ›› 2021, Vol. 40 ›› Issue (12) : 107-113.

PDF(2109 KB)
PDF(2109 KB)
振动与冲击 ›› 2021, Vol. 40 ›› Issue (12) : 107-113.
论文

基于深度森林的轴承故障诊断方法

  • 丁家满1,吴晔辉1,罗青波1,杜奕2
作者信息 +

A fault diagnosis method of mechanical bearing based on the deep forest

  • DING Jiaman1,WU Yehui1,LUO Qingbo1,DU Yi2
Author information +
文章历史 +

摘要

利用深度神经网络进行机械故障诊断存在复杂的调参过程,并且参数的赋值对诊断结果影响很大,为解决该问题提出一种基于深度森林的诊断模型。采用重采样技术提取了时域和频域特征;以多组简单工况下的轴承实验数据训练构建深度森林模型,在分析超参数对模型影响的基础上确定了诊断模型的关键参数;将该模型应用到复杂工况下,与随机森林模型及深度神经网络模型进行比较,实验结果表明该方法不仅有效而且具有较强的泛化能力。

Abstract

There is a complex parameter adjustment process in mechanical fault diagnosis by using deep neural network, and the assignment of parameters has a great influence on the diagnosis results.In order to solve this problem, this paper introduced the idea of deep learning and proposed a bearing fault diagnosis method based on the deep forest.Firstly, time-domain and frequency-domain features were extracted by resampling technique.Then, a deep forest model was constructed by training several groups of bearing experimental data under simple working conditions, and the key parameters of the diagnosis model were determined based on the analysis of the influence of over-parameters on the model.Finally, the model was applied to complex conditions, and compared with a random forest model and a deep neural network model, the experimental results show that the method in this paper is not only effective but also has a strong generalization ability.

关键词

轴承故障 / 故障诊断 / 深度森林 / 深度学习

Key words

bearing fault / fault diagnosis / deep forest / deep learning

引用本文

导出引用
丁家满1,吴晔辉1,罗青波1,杜奕2. 基于深度森林的轴承故障诊断方法[J]. 振动与冲击, 2021, 40(12): 107-113
DING Jiaman1,WU Yehui1,LUO Qingbo1,DU Yi2. A fault diagnosis method of mechanical bearing based on the deep forest[J]. Journal of Vibration and Shock, 2021, 40(12): 107-113

参考文献

[1]WEN L, LI X, GAO L, et al.A new convolutional neural network-based data-driven fault diagnosis method [J].IEEE Transactions on Industrial Electronics, 2018,65(7): 5990-5998.
[2]JIA F, LEI Y, LIN J, et al.Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data[J].Mechanical Systems and Signal Processing, 2016,72: 303-315.
[3]荆云建,胡晓依,宋志坤,等.基于CNN-SVM的深度卷积神经网络轴承故障识别研究[J].振动与冲击,2019,38(18): 173-178.
JING Yunjian, HU Xiaoyi, SONG Zhikun, et al.Bearing fault identification by using deep convolution neural networks based on CNN-SVM[J].Journal of Vibration and Shock, 2019,38(18): 173-178.
[4]HE M, HE D.A deep learning based approach for bearing fault diagnosis[J].IEEE Transactions on Industry Applications, 2017(99): 1-1.
[5]SCHMIDHUBER J.Deep learning in neural networks: an overview[J].Neural Netw, 2015,61: 85-117.
[6]LECUN Y, BENGIO Y, HINTON G.Deep learning[J].Nature, 2015,521(7553): 436.
[7]LU C, WANG Z, ZHOU B.Intelligent fault diagnosis of rolling bearing using hierarchical convolutional network based health state classification[J].Advanced Engineering Informatics, 2017,32: 139-151.
[8]PAN J, ZI Y, CHEN J, et al.LiftingNet: a novel deep learning network with layerwise feature learning from noisy mechanical data for fault classification[J].IEEE Transactions on Industrial Electronics, 2018,65(6): 4973-4982.
[9]SHAO S Y, SUN W J, YAN R Q, et al.A deep learning approach for fault diagnosis of induction motors in manufacturing[J].Chinese Journal of Mechanical Engineering, 2017,30(6): 1347-1356.
[10]WEI Z, GAOLIANG P, CHUANHAO L, et al.A new deep learning model for fault diagnosis with good anti-noise and domain adaptation ability on raw vibration signals[J].Sensors, 2017,17(2): 425.
[11]ZHOU Z H, FENG J.Deep forest: towards an alternative to deep neural networks[C]// Twenty-Sixth International Joint Conference on Artificial Intelligence, 2017.
[12]ZHOU Z H.Ensemble methods: foundations and algorithms[M].Chapman and Hall/CRC, 2012.
[13]ZHANG Y L, ZHOU J, ZHENG W, et al.Distributed deep forest and its application to automatic detection of cash-out fraud[J].ACM Transactions on Intelligent Systems and Technology, 2019,10(5): 1-19.
[14]GUO Y, LIU S, LI Z, et al.Towards the classification of cancer subtypes by using cascade deep forest model in gene expression data[C]//2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).IEEE, 2017.
[15]WEN H, ZHANG J, LIN Q, et al.Multi-level deep cascade trees for conversion rate prediction in recommendation system[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2019.

PDF(2109 KB)

Accesses

Citation

Detail

段落导航
相关文章

/