Features Selection Procedure for Prognostics: An Approach Based on Predictability

Abstract

Prognostic aims at estimating the remaining useful life (RU L) of a degrading equipment, i.e at predicting the life time at which a component or a system will be unable to perform a desired function. This task is achieved through essential steps of data acquisition, feature extraction and selection, and prognostic modeling. This paper emphasizes on the selection phase and aims at showing that it should be performed according to the predictability of features: as there is no interest in retaining features that are hard to be predicted. Thereby, predictability is defined and a feature selection procedure based on this concept is proposed. The effectiveness of the approach is judged by applying it on a real-world case: through comparison is made in order to show that the better predictable features lead to better RU L estimation.

Comparison of Computational Prognostic Methods for Complex Systems Under Dynamic Regimes: A Review of Perspectives

“…For complex systems under dynamic regimes, the use of neural networks for RUL estimation is extended for higher performance levels of the learning methodology [95,96]. Particularly, the feature selection procedure is applied within the he neural network based prognostics and it is shown that it should be performed according to the predictability of features [97]. For multi-step estimations, the network structures such as non-linear autoregressive ANN models form dynamic filtering frameworks in which past monitoring information is used to predict the future values [98].…”

A New Multivariate Approach for Prognostics Based on Extreme Learning Machine and Fuzzy Clustering

“…Describing the problem of prognostics by means of continuous predictions and discrete state estimations is new in PHM community and its only addressed in few publications [14], [16], [18]. Obviously, for prognostics part, the prediction phase is critical and must be dealt in an accurate manner for timely decisions.…”

Degradation Feature Selection for Remaining Useful Life Prediction of Rolling Element Bearings

“…divided a degradation feature into segments and the average separability of all segments was defined for feature selection, and optimal degenerative features were outstood. Predictability accounts for prediction horizon, tolerate accuracy and prognostic model error was formulated by Javed et al . for prognostic feature selection.…”

“…Camci et al 26 divided a degradation feature into segments and the average separability of all segments was defined for feature selection, and optimal degenerative features were outstood. Predictability accounts for prediction horizon, tolerate accuracy and prognostic model error was formulated by Javed et al 27 for prognostic feature selection. Although feature evaluation for diagnostics has been much studied with indices based on intraclass closeness and interclass separability, it is not trivial to define goodness metrics for prognostic feature evaluation and selection.…”