An application oriented guideline for choosing a prognostic tool

Prognostic is nowadays recognized as a key feature in maintenance strategies as it should allow avoiding inopportune maintenance spending. Real prognostic systems are however scarce in industry. That can be explained from different aspects, on of them being the difficulty of choosing an efficient technology: many approaches to support the prognostic process exist, whose applicability is highly dependent on industrial constraints. Thus, the objective of the paper is to dress up a guideline to choose a suitable prediction technique, i.e., to enable industrials to point out a method that fit their real applications restrictions. In this way, prognostic approaches are studied from both the academic and industrial points of view. A cross view of the prognostic problem is also given in order to establish a common perception of it. Finally, an innovative classification of prognostic approaches is proposed. A guideline to choose a prognostic tool follows from it.