基于1D卷积与特征融合的深度学习轴承诊断算法研究
Research on Deep Learning Bearing Diagnosis Algorithm Based on 1D Convolution and Feature Fusion

DOI: 10.12677/CSA.2020.1011222, PP. 2105-2121

Keywords: 轴承诊断，1D卷积，特征融合，互扰神经网络
Bearing Diagnosis, 1D Convolution, Feature Fusion, Interference Neural Network

Full-Text   Cite this paper   Add to My Lib

Abstract:

轴承损伤严重影响设备正常运行，减小设备寿命。对轴承损伤的有效识别可以帮助设备进行维护。为此，本文创造性地提出了一种基于1D卷积与特征融合的互扰神经网络(Interference neural net-work, IFNN)深度学习模型来实现轴承诊断。该模型由7层大尺寸卷积核单元、传统特征计算单元、融合单元和Softmax分类器组成。为了检验所提出方法的有效性，采用10倍交叉验证、4个数值指标和ROC曲线面积来评估分类结果。实验结果表明，本文提出的IFNN模型准确率为96.09%，精度为96.48%，召回率为96.10%，F1-score为96.08%，ROC值为1。通过与随机森林、支持向量机等模型的对比，IFNN模型的性能明显优于其他模型。因此，所提出的IFNN模型能有效地完成轴承损伤诊断任务。
Bearing damage seriously affects the normal operation of the equipment and reduces the life of the equipment. Effective identification of bearing damage can help equipment maintenance. For this reason, this paper creatively proposes a deep learning model of Interference Neural Network (IFNN) based on 1D convolution and feature fusion to realize bearing diagnosis. The model consists of 7-layer large-size convolution kernel unit, traditional feature calculation unit, fusion unit and Soft-max classifier. In order to test the effectiveness of the proposed method, 10-fold cross-validation, 4 numerical indicators and ROC curve area are used to evaluate the classification results. The experimental results show that the accuracy rate of the IFNN model proposed in this paper is 96.09%, the precision is 96.48%, the recall rate is 96.10%, the F1-score is 96.08%, and the ROC value is 1. Through comparison with models such as random forest and support vector machine, the performance of the IFNN model is significantly better than other models. Therefore, the proposed IFNN model can effectively complete the task of bearing damage diagnosis.

References

[1]	李辉, 郑海起, 杨绍普. 基于EMD和Teager能量算子的轴承故障诊断研究[J]. 振动与冲击, 2008(10): 22-24+29+195.
[2]	田晶, 李有儒, 艾延廷. 一种基于Deep-GBM的航空发动机中介轴承故障诊断方法[J]. 航空动力学报, 2019, 34(4): 756-763.
[3]	张文颢, 李永健, 张卫华. 基于K-奇异值分解和层次化分块正交匹配算法的滚动轴承故障诊断[J]. 中国机械工程, 2019, 30(4): 406-412.
[4]	刘文朋, 廖英英, 杨绍普, 刘永强, 顾晓辉. 一种基于多点峭度谱和最大相关峭度解卷积的滚动轴承故障诊断方法[J]. 振动与冲击, 2019, 38(2): 151-156+168.
[5]	欧璐, 于德介. 路图傅里叶变换及其在滚动轴承故障诊断中的应用[J]. 机械工程学报, 2015, 51(23): 76-83.
[6]	He, C., Wu, T., Liu, C.C. and Chen, T. (2020) A Novel Method of Composite Multiscale Weighted Permutation Entropy and Machine Learning for Fault Complex System Fault Diagnosis. Measurement, 158, Article ID: 107748. https://doi.org/10.1016/j.measurement.2020.107748
[7]	Mohamad, T.H., Nazari, F. and Nataraj, C. (2020) A Re-view of Phase Space Topology Methods for Vibration-Based Fault Diagnostics in Nonlinear Systems. Journal of Vibra-tion Engineering & Technologies, 8, 393-401. https://doi.org/10.1007/s42417-019-00157-6
[8]	Liu, C.Y. and Gryllias, K. (2020) A Semi-Supervised Support Vector Data Description-Based Fault Detection Method for Rolling Element Bearings Based on Cyclic Spectral Analysis. Mechanical Systems and Signal Processing, 140, Article ID: 106682. https://doi.org/10.1016/j.ymssp.2020.106682
[9]	Wang, G., Zhang, F., Cheng, B.Y. and Fang, F. (2020) DAMER: A Novel Diagnosis Aggregation Method with Evidential Reasoning Rule for Bearing Fault Diagnosis. Journal of Intelligent Manufacturing.
[10]	杜小磊, 陈志刚, 张楠, 等. 基于同步挤压S变换和深度学习的轴承故障诊断[J]. 组合机床与自动化加工技术, 2019, 543(5): 95-98+102.
[11]	庄雨璇, 李奇, 杨冰如, 等. 基于LSTM的轴承故障诊断端到端方法[J]. 噪声与振动控制, 2019, 39(6): 187-193.
[12]	吴小龙, 雷文平, 陈宏, 等. 具有多核结构的稀疏化DNN在轴承诊断中的应用[J]. 机械设计与制造, 2020(2): 248-251, 255.
[13]	涂小卫, 张士强, 王明. 基于深度置信网络的牵引电机轴承故障诊断方法[J]. 城市轨道交通研究, 2020, 23(1): 174-178, 195.
[14]	杜小磊, 陈志刚, 许旭, 等. 改进深层小波自编码器的轴承故障诊断方法[J]. 计算机工程与应用, 2020, 56(5): 263-269.
[15]	Shang, Z.W., Liu, X., Li, W.X., et al. (2020) A Rolling Bearing Fault Diagnosis Method Based on Fast DTW and an AGBDBN. Insight, 62, 457-463. https://doi.org/10.1784/insi.2020.62.8.457
[16]	Li, X., Zhang, W., Xu, N.X., et al. (2020) Deep Learning-Based Machinery Fault Diagnostics with Domain Adaptation across Sensors at Different Places. IEEE Transactions on Industrial Electronics, 67, 6785-6794. https://doi.org/10.1109/TIE.2019.2935987
[17]	Chen, X.H., Zhang, B.K. and Gao, D. (2020) Bearing Fault Diag-nosis Base on Multi-Scale CNN and LSTM Model. Journal of Intelligent Manufacturing.
[18]	Wang, Y., Ning, D.J. and Feng, S.L. (2020) A Novel Capsule Network Based on Wide Convolution and Multi-Scale Convolution for Fault Diagnosis. Applied Sciences—Basel, 10, 16. https://doi.org/10.3390/app10103659
[19]	Xue, Y., Dou, D.Y. and Yang, J.G. (2020) Multi-Fault Diagnosis of Rotating Machinery Based on Deep Convolution Neural Network and Sup-port Vector Machine. Measurement, 156, 7. https://doi.org/10.1016/j.measurement.2020.107571
[20]	Guo, C.Z., Li, L., Hu, Y.Y., et al. (2020) A Deep Learn-ing Based Fault Diagnosis Method with Hyperparameter Optimization by Using Parallel Computing. IEEE Access, 8, 131248-131256. https://doi.org/10.1109/ACCESS.2020.3009644

Full-Text