Failure rate prediction with artificial neural networks

被引:17
|
作者
Bevilacqua, Maurizio [1 ]
Braglia, Marcello [2 ]
Frosolini, Marco [2 ]
Montanari, Roberto [3 ]
机构
[1] Univ Bologna, Dipartimento Ingn Costruzioni Mecc Nucl Aeronaut, Bologna, Italy
[2] Univ Pisa, Dipartimento Ingn Meccan Nucl Prod, Pisa, Italy
[3] Univ Parma, Dipartimento Ingn Ind, Parma, Italy
关键词
Neural nets; Preventive maintenance; Failure (mechanical);
D O I
10.1108/13552510510616487
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Purpose - To suggest that a multi layer perception based artificial neural network (MLP-ANN) is a practical instrument to evaluate the expected failure rates of 143 centrifugal pumps used in an oil refinery plant. Design/methodology/approach - A MLP is adopted to weigh up the correlation existing among the failure rates and the several different operating conditions which have some influence in the occurrence. Findings - During the training phase, it is possible to discriminate among those variables closely significant for the final outcome and those which can be kept off from the analysis. In particular, the neural network automatically calculates and classifies the centrifugal pumps in terms of both the failure probability and its variability degree, giving a better analysis instrument to take decisions and to justify them, in order to optimise and fully support an eventual preventive maintenance (PM) program. Originality/value - Aids in decision-making to reduce the necessity of reactive maintenance activities and to simplify the planning of PM ones.
引用
收藏
页码:279 / +
页数:17
相关论文
共 50 条
  • [1] Application of artificial neural networks to the prediction of sewing performance of fabrics
    Hui, Patrick C. L.
    Chan, Keith C. C.
    Yeung, K. W.
    Ng, Frency S. F.
    INTERNATIONAL JOURNAL OF CLOTHING SCIENCE AND TECHNOLOGY, 2007, 19 (05) : 291 - 318
  • [2] Prediction of quality performance using artificial neural networks Evidence from Indian construction projects
    Jha, K. N.
    Chockalingam, C. T.
    JOURNAL OF ADVANCES IN MANAGEMENT RESEARCH, 2009, 6 (01) : 70 - U94
  • [3] Remaining Useful Life (RUL) Prediction of Equipment in Production Lines Using Artificial Neural Networks
    Kang, Ziqiu
    Catal, Cagatay
    Tekinerdogan, Bedir
    SENSORS, 2021, 21 (03) : 1 - 20
  • [4] A flexible multicomputer algorithm for artificial neural networks
    Ostermark, R
    NEURAL NETWORKS, 1996, 9 (01) : 169 - 178
  • [5] APPROXIMATION AND ESTIMATION BOUNDS FOR ARTIFICIAL NEURAL NETWORKS
    BARRON, AR
    MACHINE LEARNING, 1994, 14 (01) : 115 - 133
  • [6] ARTIFICIAL NEURAL NETWORKS IN PROCESS ESTIMATION AND CONTROL
    WILLIS, MJ
    MONTAGUE, GA
    DIMASSIMO, C
    THAM, MT
    MORRIS, AJ
    AUTOMATICA, 1992, 28 (06) : 1181 - 1187
  • [7] Neural network-based failure rate prediction for De Havilland Dash-8 tires
    Al-Garni, Ahmed Z.
    Jamal, Ahmad
    Ahmad, Abid M.
    Al-Garni, Abdullah M.
    Tozan, Mueyyet
    ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2006, 19 (06) : 681 - 691
  • [8] PATTERN-RECOGNITION OF THE ELECTROENCEPHALOGRAM BY ARTIFICIAL NEURAL NETWORKS
    JANDO, G
    SIEGEL, RM
    HORVATH, Z
    BUZSAKI, G
    ELECTROENCEPHALOGRAPHY AND CLINICAL NEUROPHYSIOLOGY, 1993, 86 (02): : 100 - 109
  • [9] Forecasting of ozone pollution using artificial neural networks
    Ettouney, Reem S.
    Mjalli, Farouq S.
    Zaki, John G.
    El-Rifai, Mahmoud A.
    Ettouney, Hisham M.
    MANAGEMENT OF ENVIRONMENTAL QUALITY, 2009, 20 (06) : 668 - 683
  • [10] Hybrid Ensembles of Decision Trees and Artificial Neural Networks
    Hsu, Kuo-Wei
    2012 IEEE INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND CYBERNETICS (CYBERNETICSCOM), 2012, : 25 - 29