Data-Driven Fault Diagnosis Techniques: Non-Linear Directional Residual vs. Machine-Learning-Based Methods
Linear dependence of variables is a commonly used assumption in most diagnostic systems for which many robust methodologies have been developed over the years. In case the system nonlinearities are relevant, fault diagnosis methods, relying on the assumption of linearity, might potentially provide u...
Main Authors: | Nicholas Cartocci, Marcello R. Napolitano, Francesco Crocetti, Gabriele Costante, Paolo Valigi, Mario L. Fravolini |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-03-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/22/7/2635 |
Similar Items
-
A Comprehensive Case Study of Data-Driven Methods for Robust Aircraft Sensor Fault Isolation
by: Nicholas Cartocci, et al.
Published: (2021-02-01) -
Integration of fault diagnosis and control based on residual decoupling
by: Kai Liu, et al.
Published: (2019-01-01) -
Two-Step Neural-Network-Based Fault Isolation for Stochastic Systems
by: Liping Yin, et al.
Published: (2022-11-01) -
Expert system for FDI of dc motor faults using structured residuals design technique
by: Antić Sanja, et al.
Published: (2023-01-01) -
Model Selection Based on Residual Dependence Measure
by: Linfeng Lyu, et al.
Published: (2023-01-01)