基于LSTM-CAPF框架的岸桥起升减速箱轴承寿命预测方法

doi:10.16183/j.cnki.jsjtu.2022.440

上海交通大学学报 ›› 2024, Vol. 58 ›› Issue (3): 352-360.doi: 10.16183/j.cnki.jsjtu.2022.440

基于LSTM-CAPF框架的岸桥起升减速箱轴承寿命预测方法

孙志伟¹, 胡雄¹(), 董凯¹, 孙德建¹, 刘洋²

1.上海海事大学物流工程学院,上海 201306
2.中国船舶集团有限公司第七一一研究所,上海 201108

收稿日期:2022-11-04 修回日期:2023-02-10 接受日期:2023-03-03 出版日期:2024-03-28 发布日期:2024-03-28
通讯作者: 胡雄,博士,教授;E-mail:huxiong@shmtu.edu.cn.
作者简介:孙志伟(1994-),博士生,研究方向为港航设备自动检测与智能信息处理.
基金资助:
国家自然科学基金(62073213)

RUL Prediction Method for Quay Crane Hoisting Gearbox Bearing Based on LSTM-CAPF Framework

SUN Zhiwei¹, HU Xiong¹(), DONG Kai¹, SUN Dejian¹, LIU Yang²

1. Logistics Engineering College, Shanghai Maritime University, Shanghai 201306, China
2. Shanghai Marine Diesel Engine Research Institute, China State Shipbuilding Co., Ltd., Shanghai 201108, China

Received:2022-11-04 Revised:2023-02-10 Accepted:2023-03-03 Online:2024-03-28 Published:2024-03-28

摘要/Abstract

摘要：

岸桥起升减速箱轴承的健康状况对港口生产安全具有重要意义.针对岸桥变工况的工作条件,提出一种起升减速箱轴承的剩余使用寿命(RUL)预测框架.首先,对工作载荷进行离散化,并确定工况边界.然后,利用长短时记忆(LSTM)网络模型预测载荷和相应的运行工况.其次,以维纳过程为基础,建立了考虑不同工况下退化率和跳变系数的状态退化函数.最后,利用工况激活粒子滤波(CAPF)方法预测轴承退化状态和RUL.采用NetCMAS系统采集的上海某港口起升减速箱轴承全寿命数据验证了所提出的预测框架.与其他3种预测模式比较表明,所提出的框架能够在变工况条件下获得更准确的退化状态和RUL预测.

关键词: 岸桥轴承, 剩余寿命预测, 长短时记忆网络, 工况激活粒子滤波, 时变工况

Abstract:

The health condition of hoisting gearbox bearings of quay cranes is of great importance for the safety of port production. A remaining useful life (RUL) predicting framework for lifting gearbox bearings of quay crane under time-varying operating conditions is proposed. First, the working load is discretized and the condition boundaries are determined. Then, the long short-term memory (LSTM) network model is adopted to predict the load and the corresponding operating conditions. Afterwards, considering the degradation rates and jump coefficients under different operating conditions, the state degradation function is established based on the Wiener process. Finally, the condition-activated particle filter (CAPF) is used to predict the degradation state and RUL of bearings. The proposed prediction framework is verified by the full-life data of the hoisting gearbox bearings in a port in Shanghai collected by the NetCMAS system. A comparison with the other three prediction methods shows that the proposed framework is able to obtain more accurate degradation states and RUL predictions under time-varying operating conditions.

Key words: quay crane bearing, remaining useful life (RUL) prediction, long and short-term memory network (LSTM), condition-activated particle filter (CAPF), time-varying operating conditions

中图分类号:

TH215

孙志伟, 胡雄, 董凯, 孙德建, 刘洋. 基于LSTM-CAPF框架的岸桥起升减速箱轴承寿命预测方法[J]. 上海交通大学学报, 2024, 58(3): 352-360.

SUN Zhiwei, HU Xiong, DONG Kai, SUN Dejian, LIU Yang. RUL Prediction Method for Quay Crane Hoisting Gearbox Bearing Based on LSTM-CAPF Framework[J]. Journal of Shanghai Jiao Tong University, 2024, 58(3): 352-360.

图/表 12

图1

图2

图3

图4

图5

表1

图6

表2

图7

表3

表4

图8

参考文献 23

[1]	侯美慧, 胡雄, 王冰, 等. 基于Weibull分布的岸桥铰点退化特征提取方法研究[J]. 振动与冲击, 2019, 38(22): 198-203.
	HOU Meihui, HU Xiong, WANG Bing, et al. Degradation feature extraction for the ship-to-shore crane turning point based on Weibull distribution[J]. Journal of Vibration and Shock, 2019, 38(22):198-203.
[2]	SINGLETON R K, STRANGAS E G, AVIYENTE S. The use of bearing currents and vibrations in lifetime estimation of bearings[J]. IEEE Transactions on Industrial Informatics, 2016, 13(3): 1301-1309. doi: 10.1109/TII.2016.2643693 URL
[3]	唐刚, 李建霞, 胡雄. 准确近似聚类算法及其在岸桥拉杆状态监测中的应用[J]. 东华大学学报(自然科学版), 2018, 44(4): 590-594.
	TANG Gang, LI Jianxia, HU Xiong. Accurate approximate clustering algorithm and its application in the state monitoring of crane[J]. Journal of Donghua University (Natural Science), 2018, 44(4): 590-594.
[4]	CHEN D, QIN Y, WANG Y, et al. Health indicator construction by quadratic function-based deep convolutional auto-encoder and its application into bearing RUL prediction[J]. ISA Transactions, 2021, 114: 44-56. doi: 10.1016/j.isatra.2020.12.052 pmid: 33402262
[5]	BAE J, XI Z. Learning of physical health timestep using the LSTM network for remaining useful life estimation[J]. Reliability Engineering & System Safety, 2022, 226: 108717. doi: 10.1016/j.ress.2022.108717 URL
[6]	LEI Y, LI N, GONTARZ S, et al. A model-based method for remaining useful life prediction of machinery[J]. IEEE Transactions on Reliability, 2016, 65(3): 1314-1326. doi: 10.1109/TR.2016.2570568 URL
[7]	QIAN Y, YAN R, 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. doi: 10.1016/j.ymssp.2016.06.031 URL
[8]	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: 485-498. doi: 10.1016/j.ymssp.2016.07.039 URL
[9]	WANG Q, XU K, KONG X, et al. A linear mapping method for predicting accurately the RUL of rolling bearing[J]. Measurement, 2021, 176: 109127. doi: 10.1016/j.measurement.2021.109127 URL
[10]	ALI J B, CHEBEL-MORELLO B, SAIDI L, et al. Accurate bearing remaining useful life prediction based on Weibull distribution and artificial neural network[J]. Mechanical Systems and Signal Processing, 2015, 56: 150-172.
[11]	BIAN L, GEBRAEEL N, KHAROUFEH J P. Degradation modeling for real-time estimation of residual lifetimes in dynamic environments[J]. Iie Transactions, 2015, 47(5): 471-486. doi: 10.1080/0740817X.2014.955153 URL
[12]	LIAO H, TIAN Z. A framework for predicting the remaining useful life of a single unit under time-varying operating conditions[J]. Iie Transactions, 2013, 45(9): 964-980. doi: 10.1080/0740817X.2012.705451 URL
[13]	PENG W, LI Y F, YANG Y J, et al. Bayesian degradation analysis with inverse Gaussian process models under time-varying degradation rates[J]. IEEE Transactions on Reliability, 2017, 66(1): 84-96. doi: 10.1109/TR.2016.2635149 URL
[14]	KUNDU P, DARPE A K, KULKARNI M S. Weibull accelerated failure time regression model for remaining useful life prediction of bearing working under multiple operating conditions[J]. Mechanical Systems and Signal Processing, 2019, 134: 106302. doi: 10.1016/j.ymssp.2019.106302 URL
[15]	LI N, GEBRAEEL N, LEI Y, et al. Remaining useful life prediction of machinery under time-varying operating conditions based on a two-factor state-space model[J]. Reliability Engineering & System Safety, 2019, 186: 88-100. doi: 10.1016/j.ress.2019.02.017 URL
[16]	SUN Z, HU X, DONG K. Remaining useful life prediction of quay crane hoist gearbox bearing under dynamic operating conditions based on ARIMA-CAPF framework[J]. Shock and Vibration, 2021, 2021: 9403401.
[17]	WANG Y, WANG Z, HE S, et al. A practical chiller fault diagnosis method based on discrete Bayesian network[J]. International Journal of Refrigeration, 2019, 102: 159-167. doi: 10.1016/j.ijrefrig.2019.03.008 URL
[18]	HUANG Q, LI J, ZHU M. An improved convolutional neural network with load range discretization for probabilistic load forecasting[J]. Energy, 2020, 203: 117902. doi: 10.1016/j.energy.2020.117902 URL
[19]	王玉静, 李少鹏, 康守强, 等. 结合CNN和LSTM的滚动轴承剩余使用寿命预测方法[J]. 振动、测试与诊断, 2021, 41(3): 439-446.
	WANG Yujing, LI Shaopeng, KANG Shouqiang, et al. Method of predicting remaining useful life of rolling bearing combining CNN and LSTM[J]. Journal of Vibration, Measurement & Diagnosis, 2021, 41(3): 439-446.
[20]	LI Y, HUANG X, DING P, et al. Wiener-based remaining useful life prediction of rolling bearings using improved Kalman filtering and adaptive modification[J]. Measurement, 2021, 182: 109706. doi: 10.1016/j.measurement.2021.109706 URL
[21]	侯美慧, 胡雄, 王冰, 等. 基于Weibull和GG模糊聚类的岸桥减速箱健康状态识别方法[J]. 机械强度, 2019, 41(5): 1023-1028. doi: 10.16579/j.issn.1001.9669.2019.05.002
	HOU Meihui, HU Xiong, WANG Bing, et al. Health condition recognition for quayside container crane reducer based on Weibull and GG fuzzy clustering[J]. Journal of Mechanical Strength, 2019, 41(5): 1023-1028.
[22]	LI N, LEI Y, LIN J, et al. An improved exponential model for predicting remaining useful life of rolling element bearings[J]. IEEE Transactions on Industrial Electronics, 2015, 62(12): 7762-7773. doi: 10.1109/TIE.2015.2455055 URL
[23]	WANG Y, YANG C, XU D, et al. Evaluation and prediction method of rolling bearing performance degradation based on attention-LSTM[J]. Shock and Vibration, 2021, 2021: 6615920.

超参数	取值
LSTM层数	2
初始学习率	0.005
学习率衰减系数	0.2
隐藏层神经元个数	200
输入序列长度	20
输出序列长度	30
迭代次数	500
训练优化算法	Adam

预测步长	I_MAE	工况准确率/%
1	0.085 48	95.8
5	0.265 87	91.3
10	0.315 39	89.8
20	0.367 99	87.3
30	0.598 95	70.6

预测步长	M1	M2	M3	M4
1	0.37	0.72	0.96	0.68
5	0.42	1.33	1.77	1.29
10	1.08	2.11	2.44	2.01
20	1.50	2.44	3.56	2.21
30	2.01	3.86	7.63	3.47

方法	平均方差×10³
M1	1.972
M2	1.039
M3	3.159
M4	1.028

基于LSTM-CAPF框架的岸桥起升减速箱轴承寿命预测方法

RUL Prediction Method for Quay Crane Hoisting Gearbox Bearing Based on LSTM-CAPF Framework

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 23

相关文章 6

编辑推荐

Metrics

本文评价

[1]	王汉禹, 陈震, 周笛, 陈兆祥, 潘尔顺. 基于核函数-Wiener过程的轧辊非线性退化建模与剩余寿命预测[J]. 上海交通大学学报, 2023, 57(8): 1037-1045.
[2]	钟智伟, 王誉翔, 黄亦翔, 肖登宇, 夏鹏程, 刘成良. 基于概率稀疏自注意力的IGBT模块剩余寿命跨工况预测[J]. 上海交通大学学报, 2023, 57(8): 1005-1015.
[3]	詹可, 朱仁传. 一种CNN-LSTM船舶运动极值预报模型[J]. 上海交通大学学报, 2023, 57(8): 963-971.
[4]	曹现刚1, 2，雷卓1，李彦川1，张梦园1，段欣宇1. 基于Self-Attention-LSTM神经网络的设备剩余寿命预测方法[J]. J Shanghai Jiaotong Univ Sci, 2023, 28(5): 652-664.
[5]	王者蓝, 赵宏杰, 赵凡, 沈晨晨, 吴佳伟. 基于卷积神经网络与滤波融合算法的某惯导系统剩余寿命预测模型建立[J]. 空天防御, 2023, 6(1): 70-77.
[6]	倪扬帆, 杨媛媛, 谢哲, 郑德重, 王卫东. 基于LSTM与注意力结构的肺结节多特征抽取方法[J]. 上海交通大学学报, 2022, 56(8): 1078-1088.