Fault Detection and Diagnosis using Qualitative Modelling and Interpretation
| Autor: | Lyle H. Ungar, J.M. Vinson |
|---|---|
| Rok vydání: | 1992 |
| Předmět: |
Engineering
Interpretation (logic) business.industry Noise (signal processing) Real-time computing Chemical plant computer.software_genre Fault detection and isolation Identification (information) Range (statistics) Data mining Sensitivity (control systems) business computer Reliability (statistics) |
| Zdroj: | IFAC Proceedings Volumes. 25:121-126 |
| ISSN: | 1474-6670 |
| DOI: | 10.1016/s1474-6670(17)50227-x |
| Popis: | The Qualitative Modelling and Interpretation (QMI) system translates noisy sensor data into a qualitative description of the underlying behavior of a chemical plant and uses this information together with qualitative models to identify faults and operating regimes. Qualitative models of normal and faulty equipment are simulated to describe the range of possible behaviors in a chemical plant without the need for exact numeric models which are unavailable for many faults. Sensor data are then used to select between different models. Simultaneously using interpretations from multiple sensors reduces sensitivity to sensor noise, increasing diagnosis reliability. QMI has been implemented on a simulated propylene glycol reactor with good results. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|