Abstract
Unscheduled shutdown of nuclear power facilities for recalibration and replacement of faulty sensors can be expensive and disruptive to grid management. In this work, we present virtual (software) sensors that can replace a faulty physical sensor for a short duration thus allowing recalibration to be safely deferred to a later time. The virtual sensor model uses a Gaussian process model to process input data from redundant and other nearby sensors. Predicted data includes uncertainty bounds including spatial association uncertainty and measurement noise and error. Using data from an instrumented cooling water flow loop testbed, the virtual sensor model has predicted correct sensor measurements and the associated error corresponding to a faulty sensor.
| Original language | English |
|---|---|
| Title of host publication | 10th International Topical Meeting on Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2017 |
| Publisher | American Nuclear Society |
| Pages | 719-728 |
| Number of pages | 10 |
| ISBN (Electronic) | 9781510851160 |
| State | Published - 2017 |
| Externally published | Yes |
| Event | 10th International Topical Meeting on Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2017 - San Francisco, United States Duration: Jun 11 2017 → Jun 15 2017 |
Publication series
| Name | 10th International Topical Meeting on Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2017 |
|---|---|
| Volume | 2 |
Conference
| Conference | 10th International Topical Meeting on Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2017 |
|---|---|
| Country/Territory | United States |
| City | San Francisco |
| Period | 06/11/17 → 06/15/17 |
Funding
The work described in this report was sponsored by the Advanced Sensors and Instrumentation (ASI) technical area within the Nuclear Energy Enabling Technologies (NEET) R&D program of the U.S. Department of Energy Office of Nuclear Energy. The authors thank Dr. Jamie Coble from the University of Tennessee Knoxville, and Dr. Brent Shumaker and Dr. Hash Hashemian from AMS Corp., Knoxville, TN for their feedback on the research described here. The work described in this paper was performed at the Pacific Northwest National Laboratory, managed by Battelle for the U.S. Department of Energy under DOE contract number DE-AC06-76RLO-1830.
Keywords
- Gaussian process model
- Online monitoring (OLM)
- Virtual sensors