Hybrid Modeling and Diagnosis in the Real World: A Case Study
Abstract
Applying model-based diagnosis techniques to systems that exhibit hybrid behavior presents an interesting set of challenges that mostly revolve around interactions of the continuous and discrete components of the system. In many real world systems, the overall physical plant is inherently continuous, but system control is performed by a supervisory controller that imposes discrete switching behaviors by reconfiguring the system components, or switching controllers. In this paper, we present a case study of an aircraft fuel system, and discuss methodologies for building system models for online tracking of system behavior and performing fault isolation and identification. Empirical studies are performed on detection and isolation for a set of pump and pipe failures.
Document Details
- Document Type
- Technical Report
- Publication Date
- May 04, 2002
- Accession Number
- ADP012687
Entities
People
- Gabor Karsai
- Gautam Biswas
- Sriram Narasimhan
- Tim Bowman
- Tivadar Szemethy
Organizations
- Vanderbilt University