Anomaly detection in rolling element bearings via two-dimensional Symbolic Aggregate Approximation

Symbolic dynamics is a current interest in the area of anomaly detection, especially in mechanical systems. Symbolic dynamics reduces the overall dimensionality of system responses while maintaining a high level of robustness to noise. Rolling element bearings are particularly common mechanical components where anomaly detection is of high importance. Harsh operating conditions and manufacturing imperfections increase vibration innately reducing component life and increasing downtime and costly repairs. This thesis presents a novel way to detect bearing vibrational anomalies through Symbolic Aggregate Approximation (SAX) in the two-dimensional time-frequency domain. SAX reduces computational requirements by partitioning high-dimensional sensor data into discrete states. This analysis specifically suits bearing vibration data in the time-frequency domain, as the distribution of data does not greatly change between normal and faulty conditions. Under ground truth synthetically-generated experiments, two-dimensional SAX in conjunction with Markov model feature extraction is successful in detecting anomalies (> 99%) using short time spans (< 0.1 seconds) of data in the time-frequency domain with low false alarms (< 8%). Analysis of real-world datasets validates the performance over the commonly used one-dimensional symbolic analysis by detecting 100% of experimental anomalous vibration with 0 false alarms in all fault types using less than 1 second of data for the basis of 'normality'. Two-dimensional SAX also demonstrates the ability to detect anomalies in predicative monitoring environments earlier than previous methods, even in low Signal-to-Noise ratios.

Name thesis:degree_name

Master of Science

Level thesis:degree_level

masters

Discipline thesis:degree_discipline

Mechanical Engineering

Department dc:contributor.department

Mechanical Engineering

Grantor dc:publisher

Virginia Tech

Year dc:date.issued

2013

Author dc:creator

• Harris, Bradley William

Chair dc:contributor.committeechair

• Roan, Michael J.

Committee members dc:contributor.committeemember

• West, Robert L.
• Leonessa, Alexander

• Symbolic dynamics
• Rolling element bearings
• Anomaly detection
• Predicative maintenance
• Digital signal processing
• Bayesian sta

Statement dc:rights

• In Copyright

Licence dc:rights.uri

• http://rightsstatements.org/vocab/InC/1.0/

Dc Identifier Other

vt_gsexam:996

OAI identifier oai:identifier

oai:vtechworks.lib.vt.edu:10919/23103