Inductive learning approach for fault isolation – Application to the induction motor
Résumé
Within the diagnosis assistance framework, the supervision of a system without behavioral analytical model requires a statistical model elaborated
from the observed data analysis. This approach is based on supervised learning techniques for large databases (data mining): from the knowledge of some parameters, the value of the variable to explain is predicted. The system dynamical behavior is reinjected in the initial database to be taken
into account by learning techniques which deal with raw data. C4.5, which represents the reference algorithm based on decision-tree formalism,
is applied on a database from an induction motor in order to supervise it partially. More precisely, the problem consists in discriminating a normal
functioning state of the motor from a speed sensor failure state.