Time-series-based Equipment Failure Diagnosis Mechanism in the Context of Minority Failure Samples

被引:0
|
作者
Chen, Cheng-Hui [1 ]
Chan, Yung-Kuan [2 ]
Yu, Shyr-Shen [1 ]
机构
[1] Natl Chung Hsing Univ, Dept Comp Sci & Engn, Taichung 407224, Taiwan
[2] Natl Chung Hsing Univ, Dept Management Informat Syst, Taichung 407224, Taiwan
关键词
time-series data; equipment failure diagnosis; minority failure samples; hybrid generation; WGAN; PREDICTION; GAN;
D O I
10.18494/SAM4579
中图分类号
TH7 [仪器、仪表];
学科分类号
0804 ; 080401 ; 081102 ;
摘要
Industrial environments frequently encounter complex time-series data such as machine vibration patterns, motor thermal imaging, and sensor pressure metrics. Equipment failure prediction grapples with the temporal nature of the data and the challenge posed by minority failure instances. In this paper, we introduce a refined generative mechanism, building on the foundation of the Wasserstein generative adversarial network (WGAN) and the borderline synthetic minority oversampling technique (Borderline-SMOTE). By utilizing time-series features, the proposed method effectively addresses the intricacies of predictive modeling. To demonstrate its efficacy, we used a complex and multisensor hydraulic system dataset for validation. Experimental results indicate that the proposed method outperforms existing strategies, enhancing the F1 score by at least 2.21% and achieving a recall rate of 95.51%. This suggests a promising direction for enhancing fault prediction in complex industrial settings.
引用
收藏
页码:3537 / 3550
页数:14
相关论文
共 50 条
  • [41] Data-driven multivariate time series prediction of in-vehicle equipment failure rates
    Guo, Yongfei
    Chen, Yonggang
    Wang, Haiyong
    Liu, Yang
    Journal of Engineering and Applied Science, 2024, 71 (01):
  • [42] Financial time series and neural networks in a minority game context
    Grilli, Luca
    Russo, Massimo Alfonso
    Sfrecola, Angelo
    MATHEMATICAL AND STATISTICAL METHODS FOR ACTUARIAL SCIENCES AND FINANCE, 2010, : 153 - 162
  • [43] On the application of Durbin-Watson statistics to time-series-based regression models
    Fahidy, Thomas Z.
    Chemical Engineering Education, 2004, 38 (01): : 22 - 25
  • [44] Die crack failure mechanism investigations depending on the time of failure
    Zirilli, T.
    MICROELECTRONICS RELIABILITY, 2015, 55 (9-10) : 1600 - 1606
  • [45] Time-Series-Based Spatiotemporal Fusion Network for Improving Crop Type Mapping
    Zhan, Wenfang
    Luo, Feng
    Luo, Heng
    Li, Junli
    Wu, Yongchuang
    Yin, Zhixiang
    Wu, Yanlan
    Wu, Penghai
    REMOTE SENSING, 2024, 16 (02)
  • [46] Parameter determination and performance evaluation of time-series-based leakage detection method
    Zhang, Tuqiao
    Li, Xin
    Chu, Shipeng
    Shao, Yu
    URBAN WATER JOURNAL, 2021, 18 (09) : 750 - 760
  • [47] A Failure Prediction Method for Spacecraft Loads Based on Time Series Model
    Zhang, Yuanhang
    Shao, Yinghua
    12TH INTERNATIONAL CONFERENCE ON RELIABILITY, MAINTAINABILITY, AND SAFETY (ICRMS 2018), 2018, : 277 - 281
  • [48] ANALYSIS METHOD OF FAILURE LIKELIHOOD ON PRESSURE EQUIPMENT WITH COMBINED ACTION OF MULTI-FAILURE MECHANISM
    Chen, Xuedong
    Ai, Zhibin
    Yang, Tiecheng
    Hu, Jiushao
    Cheng, Chuanqing
    PROCEEDINGS OF THE ASME PRESSURE VESSELS AND PIPING CONFERENCE 2010, VOL 1: CODES AND STANDARDS, 2010, : 499 - 504
  • [49] Time Series Mechanism of LCC-HVDC Commutation Failure in Single Phase Grounding
    Dai S.
    He Q.
    Wang J.
    Li H.
    Dianwang Jishu/Power System Technology, 2023, 47 (09): : 3770 - 3780
  • [50] Time-series-based damage alarming method and its application in experimental benchmark studies
    Liu, Yi
    Li, Ai-Qun
    Gongcheng Lixue/Engineering Mechanics, 2008, 25 (10): : 44 - 49