基于条件深度循环生成对抗网络和动作探索的行星轮轴承剩余寿命预测

doi:10.3969/j.issn.1000-1093.2020.11.003

兵工学报 ›› 2020, Vol. 41 ›› Issue (11): 2170-2178.doi: 10.3969/j.issn.1000-1093.2020.11.003

基于条件深度循环生成对抗网络和动作探索的行星轮轴承剩余寿命预测

于军^1,2，3，刘可^1,3，郭帅⁴，于广滨¹，郭振宇²

(1.哈尔滨理工大学先进制造智能化技术教育部重点实验室, 黑龙江哈尔滨 150080；2.矿冶过程自动控制技术国家重点实验室，北京 100089；3.哈尔滨理工大学自动化学院，黑龙江哈尔滨 150080；4.中国船舶重工集团公司第703研究所蒸汽轮机事业部，黑龙江哈尔滨 150078)

上线日期:2020-12-04
通讯作者: 于广滨(1978—)，男，教授，博士生导师 E-mail:yu_ccna@163.com
作者简介:于军(1984—)，男，讲师，硕士生导师，博士。E-mail: shengda1302@126.com
基金资助:
国家重点研发计划项目(2019YFB2006400)；矿冶过程自动控制技术国家重点实验室开放基金项目（BGRIMM-2020-06）；国家自然科学基金项目(61806060)；黑龙江省科技重大专项项目(2019ZX03A02)；黑龙江省杰出青年基金项目(JC2014020)；哈尔滨市杰出青年人才基金项目(2017RAYXJ011)

Remaining Useful Life Prediction of Planet Bearings Based on Conditional Deep Recurrent Generative Adversarial Network and Action Discovery

YU Jun^1,2,3， LIU Ke^1,3， GUO Shuai⁴, YU Guangbin¹， GUO Zhenyu²

(1.Key Laboratory of Advanced Manufacturing and Intelligent Technology, Ministry of Education, Harbin University of Science and Technology, Harbin 150080, Heilongjiang, China; 2.State Key Laboratory of Process Automation in Mining & Metallurgy, Beijing 100089, China; 3.School of Automation, Harbin University of Science and Technology, Harbin 150080, Heilongjiang, China; 4.Division of Steam Turbine, The No. 703 Research Institute, China State Shipbuilding Corporation Limited, Harbin 150078, Heilongjiang, China)

Online:2020-12-04

摘要/Abstract

摘要： 为解决小样本和变工况下行星轮轴承剩余寿命预测准确率低的问题，提出一种基于条件深度循环生成对抗网络(C-DRGAN)和动作探索(AD)的行星轮轴承剩余寿命预测方法。将门控循环单元神经网络与条件生成对抗网络相结合，构建C-DRGAN，从非静态和非线性信号中提取故障特征，实现小样本和变工况下行星轮轴承的剩余寿命预测；采用基于AD的训练算法训练C-DRGAN，提高收敛速度，降低训练时间；根据训练后的C-DRGAN，利用多元线性回归分类器预测测试样本中行星轮轴承的剩余寿命。通过行星轮轴承加速疲劳寿命试验验证该方法的有效性。结果表明，该方法具有较强的非静态和非线性信号处理能力，并能在小样本情况下取得出色的行星轮轴承剩余寿命预测效果。

关键词: 行星轮轴承, 剩余寿命预测, 门控循环单元神经网络, 条件生成对抗网络, 动作探索, 小样本

Abstract: In order to address the problem about the remaining useful life (RUL) prediction of planet bearings under small samples and varying operating conditions, a RUL prediction method of planet bearings based on conditional deep recurrent generative adversarial network (C-DRGAN) and action discovery (AD) is presented. The gated recurrent unit neural network is integrated with conditional generative adversarial network to construct the C-DRGAN, which extracts the fault features from the nonlinear and non-stationary signals so as to realize the RUL prediction of planet bearings under small samples and varying operating conditions conditions. Then the training algorithm based on AD is employed to train the C-DRGAN to enhance the convergence speed and reduce the training time. Finally, according to the C-DRGAN after training, a multiple linear regression classifier is employed to predict the RUL of planet bearings in test samples. The effectiveness of the proposed method is validated through an accelerated fatigue life experiment of planet bearings. The results show that the proposed method processes strong processing adaptability to the nonlinear and non-stationary signals and obtains the excellent performance in the case of small samples.

Key words: planetbearing, remainingusefullifeprediction, gatedrecurrentunitneuralnetwork, conditionalgenerativeadversarialnetwork, actiondiscovery, smallsample

中图分类号:

TJ810.3⁺21

于军，刘可，郭帅，于广滨，郭振宇. 基于条件深度循环生成对抗网络和动作探索的行星轮轴承剩余寿命预测[J]. 兵工学报, 2020, 41(11): 2170-2178.

YU Jun， LIU Ke， GUO Shuai, YU Guangbin， GUO Zhenyu. Remaining Useful Life Prediction of Planet Bearings Based on Conditional Deep Recurrent Generative Adversarial Network and Action Discovery[J]. Acta Armamentarii, 2020, 41(11): 2170-2178.

参考文献

［1］ WANG T Y, HAN Q K, CHU F L, et al. Vibration based condition monitoring and fault diagnosis of wind turbine planetary gearbox: a review[J]. Mechanical Systems and Signal Processing, 2019, 126: 662-685.
[2］吴春志, 冯辅周, 吴守军, 等. 一种有效的不均衡样本生成方法及其在行星变速箱故障诊断中的应用[J]. 兵工学报, 2019, 40(7): 1349-1357.
WU C Z, FENG F Z, WU S J, et al. An effective method for imbalanced sample generation and its application in fault diagnosis of planetary gearbox[J]. Acta Armamentarii, 2019, 40(7): 1349-1357. (in Chinese)
[3］ WANG T Y, CHU F L, FENG Z P. Meshing frequency modulation (MFM) index-based kurtogram for planet bearing fault detection[J]. Journal of Sound and Vibration, 2018, 432: 437-453.
[4］ LEI Y G, LI N P, GUO L, et al. Machinery health prognostics: a systematic review from data acquisition to RUL prediction[J]. Mechanical Systems and Signal Processing, 2018, 104: 799-834.
[5］ QIAN Y N, YAN R Q, GAO R X. A multi-time scale approach to remaining useful life prediction in rolling bearing[J]. Mechanical Systems and Signal Processing, 2017, 83: 549-567.
[6］ AHMAD W, KHAN S A, KIM J M. A hybrid prognostics technique for rolling element bearings using adaptive predictive models[J]. IEEE Transactions on Industrial Electronics, 2018, 65(2): 1577-1584.
[7］ LIU X J, SONG P, YANG C, et al. Prognostics and health management of bearings based on logarithmic linear recursive least- squares and recursive maximum likelihood estimation[J]. IEEE Transactions on Industrial Electronics, 2018, 65(2): 1549-1558.
[8］ HU Y G, LI H, SHI P P, et al. A prediction method for the real-time remaining useful life of wind turbine bearings based on the Wiener process[J]. Renewable Energy, 2018, 127: 452-460.
[9］ BOUMAHDI M, RECHAK S, HANINI S. Analysis and prediction of defect size and remaining useful life of thrust ball bearings:modelling and experiment procedures[J]. Arabian Journal for Science and Engineering, 2017, 42(11): 4535-4546.
[10］ RAI A, UPADHYAY S H.The use of MD-CUMSUM and NARX neural network for anticipating the remaining useful life of bearings[J]. Measurement, 2017, 111: 397-410.
[11］于震梁, 孙志礼, 曹汝男, 等. 基于支持向量机和卡尔曼滤波的机械零件剩余寿命预测模型研究[J]. 兵工学报, 2018, 39(5): 991-997.
YU Z L, SUN Z L, CAO R N, et al. Research on remaining useful life predictive model of machine parts based on SVM and Kalman filter[J]. Acta Armamentarii, 2018, 39(5): 991-997.(in Chinese)
[12］ AYE S A, HEYNS P S.An integrated Gaussian process regression for prediction of remaining useful life of slow speed bearings based on acoustic emission[J]. Mechanical Systems and Signal Processing, 2017, 84(Part A): 485-498.
[13］ RUMELHART D E, HINTON G E, WILLIAMS R J.Learning representations by back-propagating errors[J]. Nature, 1986, 323: 533-536.
[14］ CHUNG J, GULCEHRE C, CHO K, et al. Empirical evaluation of gated recurrent neural networks on sequence modeling[C]∥Proceedings of Deep Learning and Representation Learning Workshop at NIPS'2014. Montreal, Canada: [s.n.], 2014.
[15］ GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial networks[C]∥Proceedings of the 27th International Conference on Neural Information Processing Systems. Montreal, Canada: [s.n.］,2014: 2672-2680.
[16］ MIRZA M, OSINDERO S. Conditional generative adversarial nets: arXiv1411.1784[R/OL]. Ithaca, NY, US: Cornell University, 2014 (2014-11-06)［2019-12-05］. https:∥arxiv.org/abs/1411.1784.
[17］ SUTTON R S, BARTO A G, Reinforcement learning: An introduction[M]. Cambridge, MA, US: MIT Press, 1998.
[18］ LI Y, PAN Q, WANG S H,et al. A generative model for category text generation[J]. Information Sciences, 2018, 450: 301-315.
[19］ BANERJEE B, KRAEMER L, Reinforcement learning with action discovery[C]∥Proceedings of Adaptive and Learning Agents Workshop. Toronto, Canada: International Foundation for Autonomous Agents and Multiagent Systems, 2010: 30-37.
[20］ BANERJEE B, KRAEMER L. Action discovery for single and multi-agent reinforcement learning[J]. Advances in Complex Systems, 2011, 14(2): 279-305.
[21］ KHASHEI M, HAMADANI A Z, BIJARI M. A novel hybrid classification model of artificial neural networks and multiple linear regression models[J]. Expert Systems with Applications, 2012, 39(3): 2606-2620.
[22］王健, 孙志礼, 于震梁, 等. 基于支持向量机的机械零件剩余寿命区间估计[J]. 东北大学学报(自然科学版), 2016, 37(7): 974-978.
WANG J, SUN Z L, YU Z L, et al. Remaining useful life interval estimation for machine parts based on SVM and Kalman filter[J]. Journal of Northeastern University (Natural Science), 2016, 37(7): 974-978.(in Chinese)

[1]	许晓东，唐圣金，谢建，于传强，王凤飞，韩洋洋. 随机退化应力作用下设备剩余寿命预测方法[J]. 兵工学报, 2022, 43(3): 712-719.
[2]	张磊, 李世民，康淑瑰，王铁宁，郭猛超. 装甲装备维修器材需求数据模拟[J]. 兵工学报, 2022, 43(3): 720-728.
[3]	薛灵芝, 曾向阳, 杨爽. 基于生成对抗网络的水声目标识别算法[J]. 兵工学报, 2021, 42(11): 2444-2452.
[4]	牛跃听，赵晖，李妍，穆希辉，张国志. 寿命服从Weibull分布时高价值弹药导弹抽样方法[J]. 兵工学报, 2020, 41(7): 1434-1440.
[5]	程立，董海平，穆慧娜，温玉全，张浩宇，汪靖程. 基于感度分布均值的火工品发火可靠性小样本评估方法[J]. 兵工学报, 2020, 41(12): 2444-2450.
[6]	柯肇捷，周文雅. 基于灰自助和未确知有理数的小样本试验数据估计[J]. 兵工学报, 2019, 40(4): 874-879.
[7]	张领科，赵峰，余永刚. 一种小子样情况下的弹道一致性评定方法[J]. 兵工学报, 2014, 35(12): 2124-2128.
[8]	董海平, 赵霞, 蔡瑞娇. 基于信息量等值的火工品可靠性评估小样本方法[J]. 兵工学报, 2011, 32(5): 554-558.
[9]	孙群，赵颖，孟晓风. 基于动态修正贝叶斯模型的自动测试系统量值稳定性监控方法[J]. 兵工学报, 2008, 29(8): 990-994.
[10]	徐军辉，汪立新，钱培贤. 基于贝叶斯方法的捷联惯性测量组合历次测试数据分布研究[J]. 兵工学报, 2007, 28(7): 859-862.
[11]	王玮，王军波，黄景德. 一个可靠性二次抽样方案的分析及改进[J]. 兵工学报, 2006, 27(2): 360-362.

基于条件深度循环生成对抗网络和动作探索的行星轮轴承剩余寿命预测

Remaining Useful Life Prediction of Planet Bearings Based on Conditional Deep Recurrent Generative Adversarial Network and Action Discovery

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 11

编辑推荐

Metrics

本文评价