Fault Detection and Localization with Neural Principal Component Analysis

Khaled Ouni , Lotfi Nabli , Zineb Simeu-Abazi (1)

1 G-SCOP_GCSP - Gestion et Conduite des Systèmes de Production

This paper presents a detection and diagnosis fault based on Neural Non Linear Principal Component Analysis (NNLPCA) and a Partial Least Square (PLS). This method is applied on a manufactured system, and the NNLPCA approach is used to estimate the non linear component. This NNLPCA model helps to estimate the prediction error and to define data classes with and without faults. The classes associated to data with faults are isolated by applying a PLS-2. Detecting faults is realized by SPE (square prediction error) statistics method, while locating them is realized by calculating contributions.

Mots clés: NIPALS algorithm.; PLS-2; NIPALS algorithm; Fault diagnosis; Neural Principal Component Analysis; Partial Least Square

Domaines: Automatique / Robotique

Khaled Ouni, Lotfi Nabli, Zineb Simeu-Abazi. Fault Detection and Localization with Neural Principal Component Analysis. International Conference on Communications, Computing and Control Applications, Sep 2011, Hammamet, Tunisia. pp.20-27. ⟨hal-00684238⟩