Advances on Prognostics for Intelligent Maintenance Systems
| Authors: | Qiu Hai, University of Wisconsin-Milwaukee, United States
Lee Jay, University of Wisconsin-Milwaukee, United States
Djudjanovic Dragan, University of Michigan, United States
Ni Jun, University of Michigan, United States |
|---|
| Topic: | 5.1 Manufacturing Plant Control |
|---|
| Session: | Advanced Manufacturing Plant Control |
|---|
| Keywords: | Prediction, Intelligent Manufacturing Systems, Fault Diagnosis, Sensor Fusion |
|---|
Abstract
An increasing number of manufacturers are beginning to realize the importance of adopting new maintenance technologies to enable products and systems to achieve near-zero downtime. Prognostic technology enables this paradigm shift from the traditional fail and fix maintenance practices to a predict and prevent paradigm. This paper addresses the current issues of prognostic applications in machinery maintenance, and presents an overall prognostic architecture called Intelligent Maintenance Systems (IMS). Discussion is focused on four aspects, including the relationship between diagnostics and prognostics, feature extraction methods, performance assessment techniques, and prediction algorithms.
