SCIENCE@home

Fault diagnosis for complex systems based on reliability analysis and sensors data considering epistemic uncertainty

R. Duan,Yanni Lin,Yining Zeng

Published 2018 in Eksploatacja i Niezawodnosc - Maintenance and Reliability

ABSTRACT

With the rapid development of science and technology, application of high dependability safeguard techniques have improved the performance of modern systems greatly on the one hand, but increased the complexity of these systems on the other hand, which significantly raises some challenges in fault diagnosis. These challenges are failure dependency of components and epistemic uncertainty. Usually, some methods of fault tolerance are used to improve the system reliability. The behaviours of components in this system, such as failure priority, functional dependent failures, and sequentially dependent failures should be taken into account. In addition, high reliability makes it extremely difficult to obtain complete fault data because these systems may still be in the early life cycle, which results in the epistemic uncertainty. Thus, the work of fault diagnosis has attracted more attention than before. The aim of a fault diagnosis system is to quickly detect and identify the root causes of these failures based on some information such as sensors data and operator experience by using some models and algorithms. Several efficient fault diagnosis approaches have been proposed for a variety of systems over the last few decades. Doguc et al. proposed a new fault diagnosis method based on the realtime reliability analysis [7]. Bayesian network (BN) was used to calculate the system reliability, and the real-time system reliability was monitored and compared with the previous values. If the deviations exceeded the set threshold, a heuristic efficient algorithm was used to locate the failed component which had the greatest changes between the prior probability and posterior probability. In the literature [3], a real-time fault diagnosis method for complex systems using objectoriented BN was proposed. It included an off-line BN construction phase and an on-line fault diagnosis phase. However, the construction of BN model requires a large amount of fault data. In [5], a fault diagnosis approach based on the fuzzy neural network and fault tree was proposed. Fuzzy neural network was used to train the relationDUAN R, LIN Y, ZENG Y. Fault diagnosis for complex systems based on reliability analysis and sensors data considering epistemic uncertainty. Eksploatacja i Niezawodnosc – Maintenance and Reliability 2018; 20 (4): 558–566, http://dx.doi.org/10.17531/ein.2018.4.7.

PUBLICATION RECORD

  • Publication year

    2018

  • Venue

    Eksploatacja i Niezawodnosc - Maintenance and Reliability

  • Publication date

    2018-09-18

  • Fields of study

    Computer Science, Engineering

  • Identifiers
    DOI 10.17531/EIN.2018.4.7
  • External record

    Open on Semantic Scholar

  • Source metadata

    Semantic Scholar

CITATION MAP

EXTRACTION MAP

CLAIMS

  • No claims are published for this paper.

CONCEPTS

  • No concepts are published for this paper.

REFERENCES

Showing 1-28 of 28 references · Page 1 of 1

CITED BY

Showing 1-17 of 17 citing papers · Page 1 of 1