Fault diagnosis method for aeroengine bearings based on PIRD-CNN

被引：0

作者：

Zhang, Bowen ^{[1
,2
]}

Pang, Xinyu ^{[2
]}

Cheng, Baoan ^{[1
]}

Li, Feng ^{[3
]}

Su, Shenzheng ^{[1
]}

机构：

[1] State Owned Sida Machinery Manufacturing Company, Xianyang

[2] School of Mechanical and Transportation Engineering, Taiyuan University of Technology, Taiyuan

[3] School of Aeronautics and Astronautics, Taiyuan University of Technology, Taiyuan

来源：

Zhendong yu Chongji/Journal of Vibration and Shock | / 43卷 / 18期

关键词：

aircraft engine; bearing; convolutional neural network; fault diagnosis; probability density information of rotor displacement ( PIRD );

D O I：

10.13465/j.cnki.jvs.2024.18.022

中图分类号：

学科分类号：

摘要：

The complexity of aircraft engine structures and systems often leads to difficulties in feature extraction and pattern recognition in bearing fault diagnosis methods. In response to the above shortcomings and considering the realtime performance and accuracy of actual engineering diagnosis, a new intelligent fault diagnosis method for aviation engine bearings baseds on probability density information of rotor displacemen ( PIRD ) was proposed. It mainly improved the 1-dimensional convolutional neural network ( 1DCNN ) model by adding an PIRD extraction layer in front of the traditional convolutional layer, which can extract the probability density information of the rotor vibration displacement signal, effectively reducing data redundancy, while retaining the important indicators in fault monitoring. The proposed PIRD-CNN diagnostic model retains the end-to-end fault diagnosis advantages of 1DCNN. The model was tested by using the bearing fault data generated on an aviation engine test bench, and its accuracy in bearing fault diagnosis reaches 96. 58%. Compared with the benchmark research, PIRD-CNN can quickly and more accurately diagnose aviation engine bearing faults. © 2024 Chinese Vibration Engineering Society. All rights reserved.

引用

页码：201 / 207and231

共 21 条

[1] Kumar N., Satapathy R.K., Bearings in aerospace, application, distress, and life: a review [J], Journal of Failure Analysis and Prevention, 23, pp. 915-947, (2023)
[2] Song X., Lai X., He X., Et al., Key technologies for digital twin integration of major equipment form and performance [J], Journal of Mechanical Engineering, 58, 10, pp. 298-325, (2022)
[3] Pi J., Chang J., Liu G., Analysis of aircraft engine vibration signal [J], Journal of System Simulation, 32, 3, pp. 525-532, (2020)
[4] Li W., Wang Y., Yang J., Et al., Analysis of noise characteristics of aircraft engine test signals [J], Journal of Aerodynamics, 20, 5, pp. 900-904, (2005)
[5] Xu K., Qin H., Jiang L., Rotor-case vibration signal analysis of an aero engine based on EMD and HHT [J], Journal of Vibration and Shock, 30, 7, pp. 237-240, (2011)
[6] Wen C., Lu F., Bao Z., Et al., Overview of data-driven small fault diagnosis methods [J], Journal of Automation, 42, 9, pp. 1285-1299, (2016)
[7] Zhu Z., Lei Y., Qi G., Et al., A review of the application of deep learning in intelligent fault diagnosis of rotating machinery [J], Measurement, 206, (2022)
[8] Zhong H., Lu Y., Yuan R., Et al., Bearing fault diagnosis using transfer learning and self-attention ensemble lightweight convolutional neural network [J], Neurocomputing, 501, pp. 765-777, (2022)
[9] Chen S., Yu J., Wang S., One-dimensional convolutional neural network-based active feature extraction for fault detection and diagnosis of industrial processes and its understanding via visualization[J], ISA Transactions, 122, pp. 424-443, (2022)
[10] Lei Y., Jia F., Kong D., Et al., Opportunities and challenges for mechanical intelligent fault diagnosis under big data [J], Journal of Mechanical Engineering, 54, 5, pp. 94-104, (2018)

← 1 2 3 →