Hierarchical fault classification for resource constrained systems

•Using hierarchical classification to minimize resource consumption of fault classification algorithms.•Using reinforcement learning to select the classifier at each node in the hierarchy.•The method is demonstrated on a hydraulic actuator fault diagnostic data set where the objective is to minimize...

Full description

Saved in:
Bibliographic Details
Published in:Mechanical systems and signal processing 2019-12, Vol.134, p.106266, Article 106266
Main Authors: Adams, Stephen, Meekins, Ryan, Beling, Peter A., Farinholt, Kevin, Brown, Nathan, Polter, Sherwood, Dong, Qing
Format: Article
Language:English
Subjects:
Actuators
Algorithms
Classification
Classifiers
Condition monitoring
Constraints
Consumption
Decision making
Diagnostic systems
Energy-efficient classification
Fault diagnostics
Hierarchical classification
Limiting factors
Maintenance
Prognostics and health management
Resource management
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•Using hierarchical classification to minimize resource consumption of fault classification algorithms.•Using reinforcement learning to select the classifier at each node in the hierarchy.•The method is demonstrated on a hydraulic actuator fault diagnostic data set where the objective is to minimize power consumption of the predictive algorithm. Prognostics and health management (PHM) is the study of using health information to support decision making to improve maintenance and operations. There are many existing methods for PHM but most solely focus on predictive accuracy and ignore resource constraints. In a real-world application of a PHM system, resources consumed by the predictive algorithm at the core of the PHM system could be a limiting factor. In this study, we propose using a hierarchical classification scheme to break the conventional classification problem into many sub-problems arranged in a hierarchy. By splitting the diagnostic task into many sub-problems, the hierarchical classifier can be constructed to maximize accuracy while minimizing resource consumption. Reinforcement learning is proposed to select the classifiers for each sub-problem. The proposed methodology is applied to condition monitoring of a hydraulic actuator where power is a limiting resource. Numerical experiments demonstrate that the proposed hierarchical classification method can reduce resource consumption compared to a traditional flat classification approach.
ISSN:0888-3270
1096-1216
DOI:10.1016/j.ymssp.2019.106266