New Approach for Failure Prognosis Using a Bond Graph, Gaussian Mixture Model and Similarity Techniques

被引:6
|
作者
Mebarki, Nassima [1 ]
Benmoussa, Samir [2 ]
Djeziri, Mohand [3 ]
Mouss, Leila-Hayet [1 ]
机构
[1] Univ Batna 2, Lab Automat & Mfg Engn, Batna 05000, Algeria
[2] Badji Mokhtar Annaba Univ, Lab Automat & Signaux Annaba LASA, Annaba 23000, Algeria
[3] Aix Marseille Univ, LIS UMR 7020 CNRS, F-13288 Marseille, France
关键词
remaining useful lifetime; Gaussian Mixture Model; similarity; bond graph; REMAINING USEFUL LIFE; FAULT PROGNOSIS; PREDICTION; DIAGNOSIS; SYSTEMS;
D O I
10.3390/pr10030435
中图分类号
TQ [化学工业];
学科分类号
0817 ;
摘要
This paper proposes a new approach for remaining useful life prediction that combines a bond graph, the Gaussian Mixture Model and similarity techniques to allow the use of both physical knowledge and the data available. The proposed method is based on the identification of relevant variables that carry information on degradation. To this end, the causal properties of the bond graph (BG) are first used to identify the relevant sensors through the fault observability. Then, a second stage of analysis based on statistical metrics is performed to reduce the number of sensors to only the ones carrying useful information for failure prognosis, thus, optimizing the data to be used in the prognosis phase. To generate data in the different system state, a simulator based on the developed BG is used. A Gaussian Mixture Model is then applied on the generated data for fault diagnosis and clustering. The Remaining Useful Life is estimated using a similarity technique. An application on a mechatronic system is considered for highlighting the effectiveness of the proposed approach.
引用
收藏
页数:14
相关论文
共 50 条
  • [41] A THERMOMECHANICAL ENHANCED ELASTIC MODEL: BOND GRAPH APPROACH
    Zanj, Amir
    He, Fangpo
    PROCEEDINGS OF THE 23RD INTERNATIONAL CONGRESS ON SOUND AND VIBRATION: FROM ANCIENT TO MODERN ACOUSTICS, 2016,
  • [42] Stock price prediction using a novel approach in Gaussian mixture model-hidden Markov model
    Gopinathan, Kala Nisha
    Murugesan, Punniyamoorthy
    Jeyaraj, Joshua Jebaraj
    INTERNATIONAL JOURNAL OF INTELLIGENT COMPUTING AND CYBERNETICS, 2024, 17 (01) : 61 - 100
  • [43] Gaussian Mixture Model for New Fault Categories Diagnosis
    Zhou, Jun-Hong
    Pang, Chee Khiang
    Yan, Weili
    2017 22ND IEEE INTERNATIONAL CONFERENCE ON EMERGING TECHNOLOGIES AND FACTORY AUTOMATION (ETFA), 2017,
  • [44] Wind turbine model simulation: A bond graph approach
    Sanchez, R.
    Medina, A.
    SIMULATION MODELLING PRACTICE AND THEORY, 2014, 41 : 28 - 45
  • [45] A New Algorithm for Reducing Components of a Gaussian Mixture Model
    Yokoyama, Naoya
    Azuma, Daiki
    Tsukiyama, Shuji
    Fukui, Masahiro
    IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 2016, E99A (12) : 2425 - 2434
  • [46] DGCNN: Disordered graph convolutional neural network based on the Gaussian mixture model
    Wu, Bo
    Liu, Yang
    Lang, Bo
    Huang, Lei
    NEUROCOMPUTING, 2018, 321 : 346 - 356
  • [47] Identifying hot subdwarf stars from photometric data using a Gaussian mixture model and graph neural network
    Liu, Wei
    Bu, Yude
    Kong, Xiaoming
    Yi, Zhenping
    Liu, Meng
    PUBLICATIONS OF THE ASTRONOMICAL SOCIETY OF JAPAN, 2024, 76 (03) : 329 - 339
  • [48] An efficient approach for shadow detection based on Gaussian mixture model
    Han Yan-xiang
    Zhang Zhi-sheng
    Chen Fang
    Chen Kai
    JOURNAL OF CENTRAL SOUTH UNIVERSITY, 2014, 21 (04) : 1385 - 1395
  • [49] An efficient approach for shadow detection based on Gaussian mixture model
    Yan-xiang Han
    Zhi-sheng Zhang
    Fang Chen
    Kai Chen
    Journal of Central South University, 2014, 21 : 1385 - 1395
  • [50] Deep learning based liver cancer detection using watershed transform and Gaussian mixture model techniques
    Das, Amita
    Acharya, U. Rajendra
    Panda, Soumya S.
    Sabut, Sukanta
    COGNITIVE SYSTEMS RESEARCH, 2019, 54 : 165 - 175