Data-driven bearing fault detection using hybrid autoencoder-LSTM deep learning approach

被引:4
|
作者
Kamat, Pooja [1 ,2 ]
Sugandhi, Rekha [2 ]
Kumar, Satish [1 ]
机构
[1] Symbiosis Int Deemed Univ, Symbiosis Inst Technol, Pune, Maharashtra, India
[2] MIT ADT Univ, MIT Sch Engn, Pune, Maharashtra, India
关键词
bearings; fault detection; deep learning; autoencoder; long-short-term memory; LSTM; K-means; DIAGNOSIS; SPECTRUM;
D O I
10.1504/IJMIC.2021.122471
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Artificial intelligence (AI) and its sub-domains of machine learning and deep learning have kindled the interests of both industry practitioners and academicians. Its contribution to the manufacturing industry in making intelligent predictions about a machinery's health and its working has seen a huge surge in the research carried in recent years. Nowadays, AI in manufacturing is popularly applied for the efficient fault detection of machinery using data analytics. Traditional fault predictive classification and further diagnosis have pitfalls such as low prediction accuracy, poor feature extraction and susceptibility to noise. To overcome these disadvantages, this paper proposes the deep-learning-based hybrid autoencoders (AE) - long-short-term memory (LSTM) framework for fault detection. The dimensionality reduction with automatic latent feature extraction by autoencoders and temporal feature consideration by LSTM help to achieve high fault diagnosis accuracy. The empirical results show that fault detection of roll bearings based on the proposed hybrid AE-LSTM deep learning technique achieved superior results in comparison to the traditional K-means clustering technique.
引用
收藏
页码:88 / 103
页数:16
相关论文
共 50 条
  • [1] Data-Driven Day-Ahead PV Estimation Using Autoencoder-LSTM and Persistence Model
    Zhang, Yue
    Qin, Chuan
    Srivastava, Anurag K.
    Jin, Chenrui
    Sharma, Ratnesh K.
    [J]. IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS, 2020, 56 (06) : 7185 - 7192
  • [2] Forecasting Foreign Exchange Volatility Using Deep Learning Autoencoder-LSTM Techniques
    Jung, Gunho
    Choi, Sun-Yong
    [J]. COMPLEXITY, 2021, 2021
  • [3] Data-driven fault detection for chemical processes using autoencoder with data augmentation
    Lee, Hodong
    Kim, Changsoo
    Jeong, Dong Hwi
    Lee, Jong Min
    [J]. KOREAN JOURNAL OF CHEMICAL ENGINEERING, 2021, 38 (12) : 2406 - 2422
  • [4] Data-driven fault detection for chemical processes using autoencoder with data augmentation
    Hodong Lee
    Changsoo Kim
    Dong Hwi Jeong
    Jong Min Lee
    [J]. Korean Journal of Chemical Engineering, 2021, 38 : 2406 - 2422
  • [5] A Data-Driven Approach for Bearing Fault Prognostics
    Jin, Xiaohang
    Que, Zijun
    Sun, Yi
    Guo, Yuanjing
    Qiao, Wei
    [J]. IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS, 2019, 55 (04) : 3394 - 3401
  • [6] A Data-Driven Approach for Bearing Fault Prognostics
    Jin, Xiaohang
    Que, Zijun
    Sun, Yi
    Guo, Yuanjing
    Qiao, Wei
    [J]. 2018 IEEE INDUSTRY APPLICATIONS SOCIETY ANNUAL MEETING (IAS), 2018,
  • [7] Data-Driven Intelligent Condition Adaptation of Feature Extraction for Bearing Fault Detection Using Deep Responsible Active Learning
    Mahesh, T. R.
    Chandrasekaran, Saravanan
    Ram, V. Ashwin
    Kumar, V. Vinoth
    Vivek, V.
    Guluwadi, Suresh
    [J]. IEEE ACCESS, 2024, 12 : 45381 - 45397
  • [8] Data-Driven Hybrid Approach for Early Fault Detection of AHU using Electrical Signals
    Malik, Hasmat
    Panda, Sanjib Kumar
    Poolla, Kameshwar
    Spanos, Costas J.
    [J]. 2022 INTERNATIONAL POWER ELECTRONICS CONFERENCE (IPEC-HIMEJI 2022- ECCE ASIA), 2022, : 1365 - 1371
  • [9] Sensor Data-Driven UAV Anomaly Detection using Deep Learning Approach
    Galvan, Julio
    Raja, Ashok
    Li, Yanyan
    Yuan, Jiawei
    [J]. 2021 IEEE MILITARY COMMUNICATIONS CONFERENCE (MILCOM 2021), 2021,
  • [10] Data-driven fault detection and isolation of nonlinear systems using deep learning for Koopman operator
    Bakhtiaridoust, Mohammadhosein
    Yadegar, Meysam
    Meskin, Nader
    [J]. ISA TRANSACTIONS, 2023, 134 : 200 - 211