基于多尺度注意力深度强化学习网络的行星齿轮箱智能诊断方法

doi:10.3901/JME.2022.11.133

机械工程学报 ›› 2022, Vol. 58 ›› Issue (11): 133-142.doi: 10.3901/JME.2022.11.133

扫码分享

基于多尺度注意力深度强化学习网络的行星齿轮箱智能诊断方法

王辉¹, 徐佳文¹, 严如强^1,2

1. 东南大学仪器科学与工程学院南京 210096;
2. 西安交通大学机械工程学院西安 710049

收稿日期:2021-08-29 修回日期:2022-02-06 出版日期:2022-06-20 发布日期:2022-08-08
通讯作者: 严如强(通信作者),男,1975年出生,博士,教授,博士研究生导师。主要研究方向为机械系统状态监测与故障诊断、信号处理、无线传感网络。E-mail:ruqiang@seu.edu.cn
作者简介:王辉,男,1992年出生,博士研究生。主要研究方向为旋转机械的智能诊断。E-mail:230189693@seu.edu.cn
基金资助:
国家重点研发计划资助项目（2018YFB1702400）

Multi-Scale Attention Based Deep Reinforcement Learning for Intelligent Fault Diagnosis of Planetary Gearbox

WANG Hui¹, XU Jiawen¹, YAN Ruqiang^1,2

1. School of Instrument Science and Engineering, Southeast University, Nanjing 210096;
2. School of Mechanical Engineering, Xi'an Jiaotong University, Xi'an 710049

Received:2021-08-29 Revised:2022-02-06 Online:2022-06-20 Published:2022-08-08

摘要/Abstract

摘要： 针对行星齿轮箱在多工况下故障表征具有差异性，现有方法中存在特征提取不足，且泛化性和诊断准确率低的问题，提出一种基于多尺度深度注意Q网络（Multiscale deep attention Q network，MSDAQN）的深度强化学习行星齿轮箱多工况智能诊断方法。首先定义分类马尔科夫决策过程描述诊断过程，建立故障诊断模拟环境；其次构造MSDAQN深度强化学习智能体结构，其通过多尺度卷积神经网络提取多尺度故障特征，并利用自适应通道注意力进行加权融合、突出关键信息；最后依据所建智能体与诊断模拟环境交互的经验，自主学习最佳诊断策略。通过行星齿轮箱的多工况试验和实际案例的测试与分析，表明所提方法具有更高的诊断准确率和较强的工况适应性。

关键词: 行星齿轮箱, 故障诊断, 深度强化学习, 多尺度特征, 通道注意力

Abstract: Given the difference in fault characterization of the planetary gearbox under multiple working conditions, the existing methods have problems of insufficient feature extraction, low generalization, and diagnosis accuracy, an intelligent diagnosis method using multiscale deep attention Q network (MSDAQN) of deep reinforcement learning for planetary gearboxes under multi-working condition is proposed. Classification Markov decision process is defined to describe the diagnosis process and establish the simulation environment of fault diagnosis. The structure of an MSDAQN deep reinforcement learning agent is designed, which extracts multi-scale fault features by a multi-scale convolutional neural network and uses adaptive channel attention to reweight them and highlight key fault information. Finally, using the interaction experience between the developed agent and diagnosis simulation environment, the optimal diagnosis strategy is learned autonomously. The test and analysis of planetary gearbox's multi-working condition test and actual cases show that the proposed method has higher diagnostic accuracy and strong adaptability.

Key words: planetary gearbox, fault diagnosis, deep reinforcement learning, multi-scale features, channel attention

中图分类号:

TH165
TH17

王辉, 徐佳文, 严如强. 基于多尺度注意力深度强化学习网络的行星齿轮箱智能诊断方法[J]. 机械工程学报, 2022, 58(11): 133-142.

WANG Hui, XU Jiawen, YAN Ruqiang. Multi-Scale Attention Based Deep Reinforcement Learning for Intelligent Fault Diagnosis of Planetary Gearbox[J]. Journal of Mechanical Engineering, 2022, 58(11): 133-142.

参考文献

[1] CHEN Xuefeng, LI Jimeng, CHENG Hang, et al. Research and application of condition monitoring and fault diagnosis technology in wind turbines[J]. Journal of Mechanical Engineering, 2011, 47(9):45-52. 陈雪峰, 李继猛, 程航, 等. 风力发电机状态监测和故障诊断技术的研究与进展[J]. 机械工程学报, 2011, 47(9):45-52.
[2] LI T, ZHAO Z, SUN C, et al. Adaptive channel weighted CNN with multisensor fusion for condition monitoring of helicopter transmission system[J]. IEEE Sensors Journal, 2020, 20(15):8364-8373.
[3] ZHAO M, ZHONG S, FU X, et al. Deep residual networks with adaptively parametric rectifier linear units for fault diagnosis[J]. IEEE Transactions on Industrial Electronics, 2020, 68(3):2587-2597.
[4] HINTON G E, SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786):504-507.
[5] LEI Yaguo, JIA Feng, KONG Detong, et al. Opportunities and challenges of machinery intelligent fault diagnosis in big data era[J]. Journal of Mechanical Engineering, 2018, 54(5):94-104. 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.
[6] 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.
[7] SAUFI S R, AHMAD Z A B, LEONG M S, et al. Gearbox fault diagnosis using a deep learning model with limited data sample[J]. IEEE Transactions on Industrial Informatics, 2020, 16(10):6263-6271.
[8] ZHOU Xingkang, YU Jianbo. Gearbox fault diagnosis based on one-dimension residual convolutional auto- encoder[J]. Journal of Mechanical Engineering, 2020, 56(7):96-108. 周兴康, 余建波. 基于深度一维残差卷积自编码网络的齿轮箱故障诊断[J]. 机械工程学报, 2020, 56(7):96-108.
[9] 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.
[10] WANG L H, ZHAO X P, WU J X, et al. Motor fault diagnosis based on short-time Fourier transform and convolutional neural network[J]. Chinese Journal of Mechanical Engineering, 2017, 30(6):1357-1368.
[11] ZHANG W, PENG G, LI C, 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.
[12] YE Zhuang, YU Jianbo. Feature extraction of gearbox vibration signals based on multi-channels weighted convolutional neural network[J]. Journal of Mechanical Engineering, 2021, 57(1):110-120. 叶壮, 余建波. 基于多通道加权卷积神经网络的齿轮箱振动信号特征提取[J]. 机械工程学报, 2021, 57(1):110-120.
[13] LIU R, WANG F, YANG B, et al. Multiscale kernel based residual convolutional neural network for motor fault diagnosis under nonstationary conditions[J]. IEEE Transactions on Industrial Informatics, 2019, 16(6):3797- 3806.
[14] TANG Si, CHEN Xinchu, ZHENG Song. Fault diagnosis method of motor bearing based on attention and multi- scale convolution neural network[J]. Electrical Engineering, 2020, 21(11):32-38. 唐斯, 陈新楚, 郑松. 基于注意力与多尺度卷积神经网络的电机轴承故障诊断[J]. 电气技术, 2020, 21(11):32-38.
[15] MNIH V, KAVUKCUOGLU K, SILVER D, et al. Human-level control through deep reinforcement learning[J]. Nature, 2015, 518(7540):529-533.
[16] SILVER D, HUANG A, MADDISON C J, et al. Mastering the game of Go with deep neural networks and tree search[J]. Nature, 2016, 529(7587):484-489.
[17] LIU Zhaoyng, MU Chaoxu, SUN Changyin. An overview on algorithms and applications of deep reinforcement learning[J]. Chinese Journal of Intelligent Science and Technology, 2020, 2(4):314-326. 刘朝阳, 穆朝絮, 孙长银. 深度强化学习算法与应用研究现状综述[J]. 智能科学与技术学报, 2020, 2(4):314- 326.
[18] DING Y, MA L, MA J, et al. Intelligent fault diagnosis for rotating machinery using deep Q-network based health state classification:A deep reinforcement learning approach[J]. Advanced Engineering Informatics, 2019, 42:100977.
[19] WANG H, XU J, SUN C, et al. Intelligent fault diagnosis for planetary gearbox using time-frequency representation and deep reinforcement learning[J]. IEEE/ASME Transactions on Mechatronics, 2021. doi:10.1109/TMECH.2021.3076775.
[20] LIN E, CHEN Q, QI X. Deep reinforcement learning for imbalanced classification[J]. Applied Intelligence, 2020, 50(8):2488-2502.
[21] SUTTON R S, BARTO A G. Reinforcement learning:An introduction[M]. MIT Press, 2018.
[22] WANG Q, WU B, ZHU P, et al. ECA-Net:Efficient channel attention for deep convolutional neural networks, 2020 IEEE[C]//CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE. 2020.
[23] LIU L, JIANG H, HE P, et al. On the variance of the adaptive learning rate and beyond[J]. arXiv preprint arXiv:1908.03265, 2019.
[24] WU P, NIE X, XIE G. Multi-sensor signal fusion for compound fault diagnosis method with strong generaliza- tion and anti-noise performance[J]. Measurement Science and Technology, 2020, 32(3):035108.
[25] LAURENS V D M, HINTON G. Visualizing data using t- SNE[J]. Journal of Machine Learning Research, 2008, 2605(9):2579-2605.

基于多尺度注意力深度强化学习网络的行星齿轮箱智能诊断方法

Multi-Scale Attention Based Deep Reinforcement Learning for Intelligent Fault Diagnosis of Planetary Gearbox

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	向东, 韦尧中, 沈银华, 孙欣宇. 面向风电齿轮箱油温超限故障的热网络模型及其节点温度计算方法研究[J]. 机械工程学报, 2022, 58(9): 119-135.
[2]	李奕璠, 杨杰, 陈再刚, 易彩, 林建辉. 基于分层算子形态小波的轮对轴承复合故障检测[J]. 机械工程学报, 2022, 58(10): 1-11.
[3]	宋立业, 范抑伶, 王燚增. 基于KPCA与IHHO-LSSVM的电力变压器故障诊断方法研究^*[J]. 电气工程学报, 2022, 17(1): 95-103.
[4]	苗宝权, 陈长征, 罗园庆, 赵思雨. 基于自适应增强差分积形态滤波器的滚动轴承故障特征提取方法[J]. 机械工程学报, 2021, 57(9): 78-88.
[5]	黄包裕, 张永祥, 赵磊. 基于布谷鸟搜索算法和最大二阶循环平稳盲解卷积的滚动轴承故障诊断方法[J]. 机械工程学报, 2021, 57(9): 99-107.
[6]	黄伟国, 李仕俊, 毛磊, 马玉强, 王俊, 沈长青, 阙红波, 朱忠奎. 多源稀疏优化方法研究及其在齿轮箱复合故障检测中的应用[J]. 机械工程学报, 2021, 57(7): 87-99.
[7]	周亚波, 池茂儒, 蔡吴斌, 孙建锋, 肖新标. 铁道车辆异常振动噪声的原因分析[J]. 机械工程学报, 2021, 57(4): 148-155.
[8]	孟宗, 关阳, 潘作舟, 孙登云, 樊凤杰, 曹利宵. 基于二次数据增强和深度卷积的滚动轴承故障诊断研究[J]. 机械工程学报, 2021, 57(23): 106-115.
[9]	谯自健, 束学道. 非对称势诱导随机共振增强机械重复瞬态提取[J]. 机械工程学报, 2021, 57(23): 160-168.
[10]	唐小林, 陈佳信, 刘腾, 李佳承, 胡晓松. 基于深度强化学习的混合动力汽车智能跟车控制与能量管理策略研究[J]. 机械工程学报, 2021, 57(22): 237-246.
[11]	陈祝云, 钟琪, 黄如意, 廖奕校, 李霁蒲, 李巍华. 基于增强迁移卷积神经网络的机械智能故障诊断[J]. 机械工程学报, 2021, 57(21): 96-105.
[12]	叶楠, 常佩泽, 张露予, 王嘉. 基于改进后半监督深度信念网络的多工况轴承故障诊断研究[J]. 机械工程学报, 2021, 57(15): 80-90.
[13]	王震坡, 李晓宇, 袁昌贵, 黎小慧. 大数据下电动汽车动力电池故障诊断技术挑战与发展趋势[J]. 机械工程学报, 2021, 57(14): 52-63.
[14]	孙振宇, 王震坡, 刘鹏, 张照生, 陈勇, 曲昌辉. 新能源汽车动力电池系统故障诊断研究综述[J]. 机械工程学报, 2021, 57(14): 87-104.
[15]	陈超逸, 鲁娟, 陈楷, 黎宇嘉, 马俊燕, 廖小平. 车削表面粗糙度解析模型与DDQN-SVR预测模型研究[J]. 机械工程学报, 2021, 57(13): 262-272.