Slow-Varying Dynamics-Assisted Temporal Capsule Network for Machinery Remaining Useful Life Estimation

被引:0
|
作者
Qin, Yan [1 ]
Yuen, Chau [1 ]
Shao, Yimin [2 ]
Qin, Bo [3 ]
Li, Xiaoli [4 ]
机构
[1] Singapore Univ Technol & Design, Engn Prod Dev Pillar, Singapore 487372, Singapore
[2] Chongqing Univ, Key Lab Mech Transmiss, Chongqing 400044, Peoples R China
[3] Inner Mongolia Univ Sci & Technol, Sch Mech Engn, Baotou 014010, Peoples R China
[4] ASTAR, Inst Infocomm Res, Singapore 138632, Singapore
基金
中国国家自然科学基金; 新加坡国家研究基金会;
关键词
Estimation; Degradation; Time series analysis; Machinery; Tuning; Correlation; Indexes; Capsule network (CapsNet); deep dynamics analysis; intelligent manufacturing; remaining useful life (RUL) estimation; SYSTEMS;
D O I
10.1109/TCYB.2022.3164683
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Capsule network (CapsNet) acts as a promising alternative to the typical convolutional neural network, which is the dominant network to develop the remaining useful life (RUL) estimation models for mechanical equipment. Although CapsNet comes with an impressive ability to represent entities' hierarchical relationships through a high-dimensional vector embedding, it fails to capture the long-term temporal correlation of run-to-failure time series measured from degraded mechanical equipment. On the other hand, the slow-varying dynamics, which reveals the low-frequency information hidden in mechanical dynamical behavior, is overlooked in the existing RUL estimation models (including CapsNet), limiting the utmost ability of advanced networks. To address the aforementioned concerns, we propose a slow-varying dynamics-assisted temporal CapsNet (SD-TemCapsNet) to simultaneously learn the slow-varying dynamics and temporal dynamics from measurements for accurate RUL estimation. First, in light of the sensitivity of fault evolution, slow-varying features are decomposed from normal raw data to convey the low-frequency components corresponding to the system dynamics. Next, the long short-term memory (LSTM) mechanism is introduced into CapsNet to capture the temporal correlation of time series. To this end, experiments conducted on an aircraft engine and a milling machine verify that the proposed SD-TemCapsNet outperforms the mainstream methods. In comparison with CapsNet, the estimation accuracy of the aircraft engine with four different scenarios has been improved by 10.17%, 24.97%, 3.25%, and 13.03% about the index root mean squared error, respectively. Similarly, the estimation accuracy of the milling machine has been improved by 23.57% compared to LSTM and 19.54% compared to CapsNet.
引用
收藏
页码:592 / 606
页数:15
相关论文
共 28 条
  • [21] Remaining Useful Life Estimation of Aircraft Engines Based on Deep Convolution Neural Network and LightGBM Combination Model
    Liu, Lijun
    Wang, Lan
    Yu, Zhen
    INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS, 2021, 14 (01)
  • [22] Remaining Useful Life Estimation of BLDC Motor Considering Voltage Degradation and Attention-Based Neural Network
    Shifat, Tanvir Alam
    Jang-Wook, Hur
    IEEE ACCESS, 2020, 8 : 168414 - 168428
  • [23] Remaining useful life estimation for deteriorating systems with time-varying operational conditions and condition-specific failure zones
    Li Qi
    Gao Zhanbao
    Tang Diyin
    Li Baoan
    CHINESE JOURNAL OF AERONAUTICS, 2016, 29 (03) : 662 - 674
  • [24] Spatio-Temporal Propagation: An Extended Message-Passing Graph Neural Network for Remaining Useful Life Prediction
    Kong, Ziqian
    Jin, Xiaohang
    Wang, Feng
    Xu, Zhengguo
    IEEE SENSORS JOURNAL, 2024, 24 (20) : 32468 - 32479
  • [25] Remaining useful life estimation for deteriorating systems with time-varying operational conditions and condition-specific failure zones
    Li Qi
    Gao Zhanbao
    Tang Diyin
    Li Baoan
    Chinese Journal of Aeronautics , 2016, (03) : 662 - 674
  • [26] Temporal Convolution-Based Long-Short Term Memory Network With Attention Mechanism for Remaining Useful Life Prediction
    Hsu, Chia-Yu
    Lu, Yi-Wei
    Yan, Jia-Hong
    IEEE TRANSACTIONS ON SEMICONDUCTOR MANUFACTURING, 2022, 35 (02) : 220 - 228
  • [27] Remaining Useful Life Prediction Under Multiple Operating Conditions Based on a Novel Dual-Layer Temporal Convolutional Network
    Yang, Xu
    Chen, Dandan
    Huang, Jian
    Wu, Xia
    Chen, Zhiwen
    Li, Qing
    IEEE SENSORS JOURNAL, 2025, 25 (01) : 1900 - 1911
  • [28] An adaptive data-driven approach for two-timescale dynamics prediction and remaining useful life estimation of Li-ion batteries
    Bhadriraju, Bhavana
    Kwon, Joseph Sang-Il
    Khan, Faisal
    COMPUTERS & CHEMICAL ENGINEERING, 2023, 175