Name
Abstract | ||
|---|---|---|
Rotating equipment is widespread in the process industry, where pumps, compressors, and turbines are used to drive continuous manufacturing lines. This class of machinery is meant to run without interruption, but invariably experiences degradation that can lead to equipment failure. Any break in a continuous manufacturing line can halt production, so there is a pressing need to diagnose rotating equipment health before failure occurs. Existing health modeling and diagnosis strategies require supplemental tests to collect model training data, and ignore time-series behavior in machine signals that can be useful for diagnosing equipment health. This letter presents a general modeling structure to give context to historical data, which can act as a substitute for supplemental test data, and describes a methodology for assessing repair quality based on trends in signal features. A case study that uses the proposed methodology to assess the quality of repair procedures is provided. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1109/LCSYS.2020.3041214 | IEEE Control Systems Letters |
Keywords | DocType | Volume |
Manufacturing systems and automation,modeling,fault detection | Journal | 5 |
Issue | ISSN | Citations |
5 | 2475-1456 | 0 |
PageRank | References | Authors |
0.34 | 0 | 9 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Maxwell Toothman | 1 | 0 | 0.34 |
| Birgit Braun | 2 | 0 | 0.34 |
| Scott J. Bury | 3 | 0 | 0.34 |
| Michael Dessauer | 4 | 0 | 0.34 |
| Kaytlin Henderson | 5 | 0 | 0.34 |
| Ray Wright | 6 | 0 | 0.34 |
| Dawn M. Tilbury | 7 | 900 | 123.02 |
| James R. Moyne | 8 | 209 | 72.77 |
| Kira Barton | 9 | 57 | 18.97 |