Adverse environmental conditions have combined cumulative effects leading to performance degradation and failures of avionics. Classical reliability addresses statistically-generic devices and is less suitable for the situations when failures are not traced to manufacturing but rather to unique operational conditions of particular hardware units. An approach aimed at the accurate assessment of the probability of failure of any avionics unit utilizing the known history-of-abuse from environmental and operational factors is presented herein. The suggested prognostic model utilizes information downloaded from dedicated monitoring systems of flight-critical hardware and stored in a database. Such a database can be established from the laboratory testing of hardware and supplemented with real operational data. This approach results in a novel knowledge discovery from data technology that can be efficiently used in a wide area of applications and provide a quantitative basis for the modern maintenance concept known as service-when-needed. An illustrative numerical example is provided.
Data mining technology for failure prognostic of avionics
IEEE Transactions on Aerospace and Electronic Systems ; 38 , 2 ; 388-403
2002-04-01
1291046 byte
Article (Journal)
Electronic Resource
English
PAPERS - Data Mining Technology for Failure Prognostic of Avionics
Online Contents | 2002
|Prognostic and health management for avionics
IEEE | 2004
|11.0202 Prognostic and Health Management for Avionics
British Library Conference Proceedings | 2004
|Wiley | 2013
|Wiley | 2008
|