基于PIRD-CNN的航空发动机轴承故障诊断方法研究

PDF(1606 KB)

振动与冲击 ›› 2024, Vol. 43 ›› Issue (18) : 201-207.

论文

基于PIRD-CNN的航空发动机轴承故障诊断方法研究

张搏文1,2，庞新宇2，程宝安1，李峰3，宿绅正1

作者信息 +

Fault diagnosis method for aeroengine bearings based on PIRD-CNN

ZHANG Bowen1,2,PANG Xinyu2,CHENG Baoan1,LI Feng3,SU Shenzheng1

Author information +

文章历史 +

摘要

航空发动机结构与系统的复杂性导致轴承的故障诊断方法通常面临特征提取与模式识别的困难。针对以上不足，考虑实际工程诊断的实时性与准确性，提出了一种新的基于转子位移概率密度信息(probability density information of rotor displacement, PIRD)的航空发动机轴承智能故障诊断方法。其主要对一维卷积神经网络(1-Dimensional Convolutional Neural Network , 1DCNN)模型进行改进，在传统的卷积层前面增加了PIRD的提取层，可以提取转子振动位移信号的概率密度信息，有效地降低了数据的冗余度，同时保留了故障监测的重要指标。提出的PIRD-CNN诊断模型保留了1DCNN端到端的故障诊断优势，将该模型在航空发动机试验台产生的轴承故障数据进行测试，其对轴承故障诊断精度可达96.58%，与基准研究相对比表明，PIRD-CNN能够快速且更加精准地诊断航空发动机轴承的故障。

Abstract

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 real-time and accuracy of actual engineering diagnosis, a new intelligent fault diagnosis method for aviation engine bearing based on probability density information of rotor displacemen(PIRD) is proposed. It mainly improves 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 of fault monitoring. The proposed PIRD-CNN diagnostic model retains the end-to-end fault diagnosis advantages of 1DCNN. The model was tested on bearing fault data generated on an aviation engine test bench, and its accuracy in bearing fault diagnosis reached 96.58%. Compared with benchmark research, PIRD-CNN can quickly and more accurately diagnose aviation engine bearing faults.

导出引用

张搏文1, 2, 庞新宇2, 程宝安1, 李峰3, 宿绅正1. 基于PIRD-CNN的航空发动机轴承故障诊断方法研究[J]. 振动与冲击, 2024, 43(18): 201-207

ZHANG Bowen1, 2, PANG Xinyu2, CHENG Baoan1, LI Feng3, SU Shenzheng1. Fault diagnosis method for aeroengine bearings based on PIRD-CNN[J]. Journal of Vibration and Shock, 2024, 43(18): 201-207

参考文献

[1] Kumar N, Satapathy R K. Bearings in Aerospace, Application, Distress, and Life: A Review[J]. Journal of Failure Analysis and Prevention, 2023: 1-33.
[2] 宋学官, 来孝楠, 何西旺, 等. 重大装备形性一体化数字孪生关键技术[J]. 机械工程学报, 2022, 58(10): 298-325.
Song Xueguan, Lai Xiaonan, He Xiwang, etc Key technologies for digital twin integration of major equipment form and performance [J] Journal of Mechanical Engineering, 2022, 58 (10): 298-325
[3] 皮骏, 常佳泽, 刘光才. 航空发动机振动信号分析[J]. 系统仿真学报, 2020, 32(3): 525.
Pi Jun, Chang Jiaze, Liu Guangcai Analysis of Aircraft Engine Vibration Signal [J] Journal of System Simulation, 2020, 32 (3): 525
[4] 李文峰, 王永生, 杨纪明, 等. 航空发动机测试信号噪声特性分析[J]. 航空动力学报, 2005, 20(5): 900-904.
Li Wenfeng, Wang Yongsheng, Yang Jiming, et al Analysis of Noise Characteristics of Aircraft Engine Test Signals [J] Journal of Aerodynamics, 2005, 20 (5): 900-904
[5] 徐可君, 秦海勤, 江龙平. 基于 EMD 和 HHT 的航空发动机转子-机匣振动信号分析[J]. 振动与冲击, 2011, 30(7): 237-240.
XU Kejun,QIN Haiqin,JIANG Longping.Rotor-case vibration signal analysis of an aero engine based on EMD and HHT[J]. Journal of Vibration and Shoc, 2011, 30(7): 237-240.k
[6] 文成林, 吕菲亚, 包哲静, 等. 基于数据驱动的微小故障诊断方法综述[J]. 自动化学报, 2016, 42(9): 1285-1299.
Wen Chenglin, Lv Feiya, Bao Zhejing, etc Overview of data-driven small fault diagnosis methods [J] Journal of Automation, 2016, 42 (9): 1285-1299
[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, 2022: 112346.
[8] Zhong H, Lv Y, Yuan R, et al. Bearing fault diagnosis using transfer learning and self-attention ensemble lightweight convolutional neural network[J]. Neurocomputing, 2022, 501: 765-777.
[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, 2022, 122: 424-443.
[10] 雷亚国, 贾峰, 孔德同, 等. 大数据下机械智能故障诊断的机遇与挑战[J]. 机械工程学报, 2018, 54(5): 94-104.
Lei Yaguo, Jia Feng, Kong Detong, etc Opportunities and challenges for mechanical intelligent fault diagnosis under big data [J] Journal of Mechanical Engineering, 2018, 54 (5): 94-104
[11] Hou, L., Yi, H., Jin, Y., Gui, M., Sui, L., Zhang, J., & Chen, Y. (2023). Inter-shaft Bearing Fault Diagnosis Based on Aero-engine System: A Benchmarking Dataset Study. Journal of Dynamics, Monitoring and Diagnostics. https://doi.org/10.37965/jdmd.2023.314.
[12] 张搏文, 庞新宇, 关重阳. 基于 DPD-1DCNN 的行星齿轮箱故障诊断方法研究[J]. 机械传动, 2023, 47(3): 113-119.
Zhang Bowen, Pang Xinyu, Guan Chongyang Research on Fault Diagnosis Method for Planetary Gearbox Based on DPD-1DCNN [J] Mechanical transmission, 2023, 47 (3): 113-119
[13] 李允公,孔祥娜,高玉勇.基于两被联件振动信号概率密度和PCA的螺栓松动识别方法研究[J].振动与冲击,2015,34(01):63-67.
LI Yungong, KONG Xiangna, GAO Yuyong. Research on bolt loosening identification method based on vibration signal probability density and PCA of two connected parts [J]. Vibration and Shock, 2015, 34(01):63-67.
[14] Zhang L, Fan Q, Lin J, et al. A nearly end-to-end deep learning approach to fault diagnosis of wind turbine gearboxes under nonstationary conditions[J]. Engineering applications of artificial intelligence, 2023, 119: 105735.
[15] Wang D, Li L, Zhao D. Corporate finance risk prediction based on LightGBM[J]. Information Sciences, 2022, 602: 259-268.
[16] Ju Y, Sun G, Chen Q, et al. A model combining convolutional neural network and LightGBM algorithm for ultra-short-term wind power forecasting[J]. Ieee Access, 2019, 7: 28309-28318.
[17] Al Daoud E. Comparison between XGBoost, LightGBM and CatBoost using a home credit dataset[J]. International Journal of Computer and Information Engineering, 2019, 13(1): 6-10.
[18] Dyer D, Stewart R M. Detection of rolling element bearing damage by statistical vibration analysis[J]. Mechanical systems and signal processing, 1978, 100(2): 229-235.
[19] 王子为.复杂环境下新无量纲指标的构建与实验验证[D].广东工业大学,2018.
Wang Ziwen. New Dimensionless Parameter Construction and experimental verification in Complicated Environment [D].Guangdong University of Technology,2018.
[20] Weimer D, Scholz-Reiter B, Shpitalni M. Design of deep convolutional neural network architectures for automated feature extraction in industrial inspection[J]. CIRP annals, 2016, 65(1): 417-420.
[21] 仝钰, 庞新宇, 魏子涵. 基于 GADF-CNN 的滚动轴承故障诊断方法[J]. 振动与冲击, 2021, 40(5): 247-253,260.
Tong Yu, Pang Xinyu, Wei Zihan Rolling bearing fault diagnosis method based on GADF-CNN [J] Vibration and Shock, 2021, 40 (5): 247-253260
[22] Ma Z, Jiang Z, Zhang H. Hyperspectral image classification using feature fusion hypergraph convolution neural network[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 60: 1-14.