Crack Size Identification for Bearings Using an Adaptive Digital Twin

被引:19
作者
Piltan, Farzin [1 ]
Kim, Jong-Myon [1 ]
机构
[1] Univ Ulsan, Dept Elect Elect & Comp Engn, Ulsan 44610, South Korea
关键词
rotating machine; bearing; digital twin; gaussian process regression; Laguerre filter; fuzzy logic; proportional integral observer; Lyapunov robust algorithm; adaptive technique; support vector machine; fault diagnosis; CLASSIFICATION;
D O I
10.3390/s21155009
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
In this research, the aim is to investigate an adaptive digital twin algorithm for fault diagnosis and crack size identification in bearings. The main contribution of this research is to design an adaptive digital twin (ADT). The design of the ADT technique is based on two principles: normal signal modeling and estimation of signals. A combination of mathematical and data-driven techniques will be used to model the normal vibration signal. Therefore, in the first step, the normal vibration signal is modeled to increase the reliability of the modeling algorithm in the ADT. Then, to help challenge the complexity and uncertainty, the data-driven method will solve the problems of the mathematically based algorithm. Thus, first, Gaussian process regression is selected, and then, in two steps, we improve its resistance and accuracy by a Laguerre filter and fuzzy logic algorithm. After modeling the vibration signal, the second step is to design the data estimation for ADT. These signals are estimated by an adaptive observer. Therefore, a proportional-integral observer is then combined with the proposed technique for signal modeling. Then, in two stages, its robustness and reliability are strengthened using the Lyapunov-based algorithm and adaptive technique, respectively. After designing the ADT, the residual signals that are the difference between original and estimated signals are obtained. After that, the residual signals are resampled, and the root means square (RMS) signals are extracted from the residual signals. A support vector machine (SVM) is recommended for fault classification and crack size identification. The strength of the proposed technique is tested using the Case Western Reserve University Bearing Dataset (CWRUBD) under diverse torque loads, various motor speeds, and different crack sizes. In terms of fault diagnosis, the average detection accuracy in the proposed scheme is 95.75%. In terms of crack size identification for the roller, inner, and outer faults, the proposed scheme has average detection accuracies of 97.33%, 98.33%, and 98.33%, respectively.
引用
收藏
页数:24
相关论文
共 50 条
  • [21] Substructural damage identification in a digital twin framework using heterogeneous response reconstruction
    Zhang, Guangcai
    Zhou, Zhenwei
    Wan, Chunfeng
    Ding, Zhenghao
    Wu, Zhishen
    Xie, Liyu
    Xue, Songtao
    ADVANCES IN STRUCTURAL ENGINEERING, 2025, 28 (01) : 68 - 88
  • [22] Research on gas pipeline leakage model identification driven by digital twin
    Wang, Dongmei
    Shi, Shaoxiong
    Lu, Jingyi
    Hu, Zhongrui
    Chen, Jing
    SYSTEMS SCIENCE & CONTROL ENGINEERING, 2023, 11 (01)
  • [23] Adaptive Controllers and Digital Twin for Self-Adaptive Robotic Manipulators
    Edrisi, Farid
    Perez-Palacin, Diego
    Caporuscio, Mauro
    Giussani, Samuele
    2023 IEEE/ACM 18TH SYMPOSIUM ON SOFTWARE ENGINEERING FOR ADAPTIVE AND SELF-MANAGING SYSTEMS, SEAMS, 2023, : 56 - 67
  • [24] Prediction of fault evolution and remaining useful life for rolling bearings with spalling fatigue using digital twin technology
    Weiying Meng
    Yutong Wang
    Xiaochen Zhang
    Sihui Li
    Xu Bai
    Lingling Hou
    Applied Intelligence, 2023, 53 : 28611 - 28626
  • [25] Prediction of fault evolution and remaining useful life for rolling bearings with spalling fatigue using digital twin technology
    Meng, Weiying
    Wang, Yutong
    Zhang, Xiaochen
    Li, Sihui
    Bai, Xu
    Hou, Lingling
    APPLIED INTELLIGENCE, 2023, 53 (23) : 28611 - 28626
  • [26] A digital twin-based framework for load identification using odd harmonic current plotsA digital twin-based framework for load identification using odd harmonic current plotsMylona and Bouhouras
    Dimitra N. Mylona
    Aggelos S. Bouhouras
    Applied Intelligence, 2025, 55 (7)
  • [27] Deep Learning-Based Adaptive Neural-Fuzzy Structure Scheme for Bearing Fault Pattern Recognition and Crack Size Identification
    Piltan, Farzin
    Duong, Bach Phi
    Kim, Jong-Myon
    SENSORS, 2021, 21 (06) : 1 - 24
  • [28] A strain-interfaced digital twin solution for corner fatigue crack growth using Bayesian inference
    Cheok, Evan Wei Wen
    Qian, Xudong
    Kaps, Arne
    Quek, Ser Tong
    Si, Michael Boon Ing
    INTERNATIONAL JOURNAL OF FATIGUE, 2025, 191
  • [29] A model-data combination driven digital twin model for few samples fault diagnosis of rolling bearings
    Shi, Huaitao
    Yang, Tianyi
    Hu, Yunjian
    Song, Zelong
    MEASUREMENT SCIENCE AND TECHNOLOGY, 2024, 35 (09)
  • [30] Health management method of crack propagation structures based on digital twin
    Chang Q.
    Chen L.
    Zhao H.
    Xie F.
    Gao H.
    Zhendong yu Chongji/Journal of Vibration and Shock, 2023, 42 (09): : 253 - 260+303