基于转子端数据驱动LSTM-CNN模型的高速旋转系统运行状态识别方法

doi:10.3901/JME.2023.01.131

机械工程学报 ›› 2023, Vol. 59 ›› Issue (1): 131-140.doi: 10.3901/JME.2023.01.131

扫码分享

基于转子端数据驱动LSTM-CNN模型的高速旋转系统运行状态识别方法

易聪^1,2, 杜建军¹, 尹际雄^2,3, 朱海斌^2,3, 邓炜坤^2,3, 白宝亮⁴, 付从艺⁴

1. 哈尔滨工业大学(深圳)机电工程与自动化学院深圳 518000;
2. 浙江清华柔性电子技术研究院检测与装备事业部嘉兴 314006;
3. 嘉兴市柔性电子智能感知与先进制造技术重点实验室嘉兴 314006;
4. 浙江荷清柔性电子技术有限公司新技术研究中心杭州 310000

收稿日期:2021-12-22 修回日期:2022-08-08 出版日期:2023-01-05 发布日期:2023-03-30
通讯作者: 朱海斌(通信作者),男,1986年出生,博士,研究员。主要研究方向为实验力学测量方法、装备检测与诊断分析。E-mail:zhuhaibin@ifet-tsinghua.org
作者简介:易聪,男,1997年出生。主要研究方向为机械故障自动化诊断。E-mail:19S053042@stu.hit.edu.cn
基金资助:
国家自然科学基金（12072323，12002314）、浙江省自然科学基金重点项目（LZ22A020006）和电子元器件可靠性物理及其应用技术重点实验室开发基金（ZHD202104）资助项目。

Running Condition Identification of High-speed Shaft Based on Shaft-end-data Driven LSTM-CNN

YI Cong^1,2, DU Jianjun¹, YIN Jixiong^2,3, ZHU Haibin^2,3, DENG Weikun^2,3, BAI Baoliang⁴, FU Congyi⁴

1. School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, Shenzhen 518000;
2. Department of Testing and Equipment, Institute of Flexible Technology of THU, Jiaxing 314006;
3. Jiaxing Key Laboratory of Flexible Electronics based Intelligent Sensing and Advanced Manufacturing Technology, Jiaxing 314006;
4. New Technology Center, Zhejiang Heqing Flexible Electronics Company, Hangzhou 310000

Received:2021-12-22 Revised:2022-08-08 Online:2023-01-05 Published:2023-03-30

摘要/Abstract

摘要： 针对复杂结构高速转轴运行状态难以准确实时监测与识别的问题，提出了一种基于转子系统数据驱动的复合神经网络转轴工况识别方法。首先，提出了一种基于长短期记忆网络（Long short-term memory，LSTM）和卷积神经网络（Convolutional neural networks，CNN）的复合神经网络模型（LSTM-CNN）。然后，建立双盘转子动力学仿真模型，并利用Newmark-β法对转子系统进行数值求解，获得转子系统关键固定节点动力学响应特征；同时基于有限元仿真获得关键旋转节点的动力学响应特征，并将两类数据分别导入LSTM-CNN模型中进行工况识别，并对其准确率和效率进行比较分析。最后，设计搭建高速转子实验平台，获取转子端和固定端数据分别对模型进行训练与验证，比较不同模型对高速转轴运行状态的识别能力。仿真数据与实验验证分析结果均表明基于转子端数据驱动的LSTM-CNN模型识别比传统的基于固定端数据驱动的识别方法具有更优的识别精度和效率。

关键词: 高速转轴, 原位在线测量, 复合神经网络, 运行状态识别

Abstract: Aiming at the problem that it is difficult to accurately real-time monitor and identify the running condition of high-speed shafts with complex structures, a composite neural network shaft running condition identification method based on the shaft-end-data driven is proposed. Firstly, a composite neural network model (LSTM-CNN) based on Long short-term memory (LSTM) and Convolutional neural networks (CNN) is proposed. A dual-disk shaft dynamics simulation model is then established. The Newmark-β method is used to numerically solve the shaft system for acquiring the dynamic response characteristics of the key fixed nodes of the shaft system; at the same time, the dynamic response characteristics of the key rotating nodes are obtained based on the finite element simulation. Two types of data are input into the LSTM-CNN model for running condition identification, and its accuracy and efficiency are compared and analyzed. Finally, a high-speed shaft experimental platform is designed and established, and the shaft-end data and fixed-end data are respectively used to train and test the LSTM-CNN model. The performance of different models for the running condition identification of the high-speed shaft is compared. Simulation and experimental verification analysis results show that the shaft-end-data driven LSTM-CNN have better running condition identification accuracy and efficiency than that based on the fixed-end-data driven.

Key words: high speed shaft, in-situ measurement, compound neural network, running condition identification

中图分类号:

TH17

易聪, 杜建军, 尹际雄, 朱海斌, 邓炜坤, 白宝亮, 付从艺. 基于转子端数据驱动LSTM-CNN模型的高速旋转系统运行状态识别方法[J]. 机械工程学报, 2023, 59(1): 131-140.

YI Cong, DU Jianjun, YIN Jixiong, ZHU Haibin, DENG Weikun, BAI Baoliang, FU Congyi. Running Condition Identification of High-speed Shaft Based on Shaft-end-data Driven LSTM-CNN[J]. Journal of Mechanical Engineering, 2023, 59(1): 131-140.

参考文献

[1] 李贵三, 张正松, 唐锡宽. 大型高速旋转机械故障特征及其识别[J]. 石油化工设备技术, 1991, 12(1):45-49. LI Guisan, ZHANG Zhengsong, TANG Xikuan. Fault characteristics and identification of large-scale high-speed rotating machinery[J]. Petrochemical Equipment Technology, 1991, 12(1):45-49.
[2] LU Q, YANG R, ZHONG M, et al. An improved fault diagnosis method of rotating machinery using sensitive features and RLS-BP neural network[J]. IEEE Transactions on Instrumentation and Measurement, 2020, 69(4):1585-1593.
[3] JIA Z, LIU Z, VONG C, et al. A rotating machinery fault diagnosis method based on feature learning of thermal images[J]. IEEE Access, 2019, 7:12348-12359.
[4] HE Y, LIU Y, SHAO S, et al. Application of CNN-LSTM in gradual changing fault diagnosis of rod pumping system[J]. Mathematical Problems in Engineering, 2019, 2019:1-9.
[5] PARK M, LEE J, KANG W, et al. Predictive model for PV power generation using RNN (LSTM)[J]. Journal of Mechanical Science and Technology, 2021, 35:795-803.
[6] SHANG S, LUO Q, ZHAO J, et al. LSTM-CNN network for human activity recognition using WiFi CSI data[J]. Journal of Physics:Conference Series, 2021, 1883(1).
[7] HUANG T, ZHANG Q, TANG X, et al. A novel fault diagnosis method based on CNN and LSTM and its application in fault diagnosis for complex systems[J]. Artificial Intelligence Review, 2022, 55:1289-1316.
[8] SHAO B, HU X, BIAN G, et al. A multichannel LSTM-CNN method for fault diagnosis of chemical process[J]. Mathematical Problems in Engineering, 2019, 2019:1-14.
[9] RAI P, LONDHE N, RAJ R. Fault classification in power system distribution network integrated with distributed generators using CNN[J]. Electric Power Systems Research, 2021, 192:106914.
[10] JIANG P, CONG H, WANG J, et al. Fault diagnosis of gearbox in multiple conditions based on fine-grained classification CNN algorithm[J]. Shock and Vibration, 2020, 2020:9238908.
[11] 付文秀, 李弘扬, 靳东明. 基于LSTM的列车测速测距设备故障诊断[J]. 北京交通大学学报, 2020, 44(2):9-16. FU Wenxiu, LI Hongyang, JIN Dongming. Fault diagnosis of train speed and ranging equipment based on LSTM[J]. Journal of Beijing Jiaotong University, 2020, 44(2):9-16.
[12] BELAGOUNE S, BALI N, BAKDI A, et al. Deep learning through LSTM classification and regression for transmission line fault detection, diagnosis and location in large-scale multi-machine power systems[J]. Measurement, 2021, 177:109330.
[13] 沈涛, 李舜酩. 针对滚动轴承故障的批标准化CNN-LSTM诊断方法[J]. 计算机集成制造系统, 2021, 27(3):583-596. SHEN Tao, LI Shunming. CNN-LSTM method with batch normalization for rolling bearing fault diagnosis[J]. Computer Integrated Manufacturing Systems, 2021, 27(3):583-598.
[14] TANG X, WANG J, LU J, et al. Improving bearing fault diagnosis using maximum information coefficient based feature selection[J]. Applied Sciences, 2018, 8(11):2143.
[15] BEATTY R. Differentiating rotor response due to radial rubbing[J]. Journal of Vibration, Acoustics, Stress, and Reliability in Design, 1985, 107(2):151-160.
[16] CHU F, LU W. Determination of the rubbing location in a multi-disk rotor system by means of dynamic stiffness identification[J]. Journal of Sound and Vibration, 2001, 248(2):235-246.
[17] GAN C, CHEN Y, CUI X, et al. Investigation of rotor strength and rotor dynamics for high-speed high-power switched reluctance machines[J]. IET Electric Power Applications, 2020, 14(9):1624-1630.
[18] CHEN S, HANSEN J, TORTORELLI D. Unconditionally energy stable implicit time integration:Application to multibody system analysis and design[J]. International Journal for Numerical Methods in Engineering, 2000, 48(6):791-822.
[19] 陈昱, 吴宗莲, 龙胜刚. 高速旋转应变遥测系统在发动机试验中的应用[C]. 第三届中国航空学会青年科技论坛, 中国贵州贵阳, 2008. CHEN Yu, WU Zonglian, LONG Shenggang. Application of high-speed rotating strain telemetry system in engine test[C]. The 3rd China Aeronautical Society Youth Science and Technology Forum, Guiyang, Guizhou, China, 2008.

基于转子端数据驱动LSTM-CNN模型的高速旋转系统运行状态识别方法

Running Condition Identification of High-speed Shaft Based on Shaft-end-data Driven LSTM-CNN

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价