August 24-27, 2011, Starhotels Savoia Excelsior Palace, Trieste, Italy.
  

CASE 2011 Paper Abstract

Close

Paper ThB1.2

Broderick, John (University of Michigan), Allen, Lindsay V. (University of Michigan), Tilbury, Dawn (University of Michigan)

Anomaly Detection without a Pre-Existing Formal Model: Application to an Industrial Manufacturing System

Scheduled for presentation during the Regular Session "Diagnosis of discrete event systems" (ThB1), Thursday, August 25, 2011, 14:20−14:40, Excelsior

2011 IEEE International Conference on Automation Science and Engineering, August 24-27, 2011, Starhotels Savoia Excelsior Palace, Trieste, Italy

This information is tentative and subject to change. Compiled on April 21, 2014

Keywords Fault Analysis and Recovery, Discrete Event Systems

Abstract

Some faults in manufacturing systems that are evident in event-based data cannot be detected by existing solutions, including systems for which limited information is known. An anomaly detection solution that identifies anomalies in eventbased data using model generation is presented. The solution is based on knowledge of events and resources of the system and generates a set of Petri Net models to detect the anomalies. An example application of this solution is presented for a Ford machining cell that has been experiencing a gantry waiting problem. The anomaly detection solution is able to accurately identify the gantry waiting anomaly and another anomaly that occurred right before the gantry waiting issue, indicating a possible cause.

 

 

Technical Content © IEEE Robotics & Automation Society

This site is protected by copyright and trademark laws under US and International law.
All rights reserved. © 2002-2014 PaperCept, Inc.
Page generated 2014-04-21  00:04:27 PST  Terms of use