|
|
Publications
Sobral, J. and Guedes Soares, C. (2018), “Identification of Outliers in Failure Data”, 3rd International Conference on Maintenance Engineering (IncoME 2018), 6-7 September, Coimbra, Portugal, pp. 247-261.
A review of tests that can be used to identify outliers from failure data allowing performing a more accurate analysis of maintenance related data, as required to define the best maintenance strategies. This is important for condition based maintenance in particular for predictive analytics. On the other hand, the increasing use of Big Data and the necessity to select only the “good data” through the implementation of intelligent algorithms brings up the importance of these methodologies. Tests like the Simple Test, the Grubbs Outlier Test, the Natrella-Dixon Outlier Test, the Rank Limits Test or the Modified Thompson Tau Test are presented showing inherent characteristics and describing how to apply them. Based on these tests it is possible to clean erroneous data usually mixed with important failure data and understand their influence on the accuracy of the estimation of reliability and life characteristics.
If you did not manage to obtain a copy of this paper: Request a copy of this article
For information about all CENTEC publications you can download: Download the Complete List of CENTEC Publications
|