Back to Search
Start Over
Co-Design of Embeddable Diagnostics using Reduced-Order Models * *The paper has been supported by SFI grants 12/RC/2289 and 13/RC/2094
- Source :
- IFAC-PapersOnLine. 50:12222-12229
- Publication Year :
- 2017
- Publisher :
- Elsevier BV, 2017.
-
Abstract
- We develop a system for generating embedded diagnostics from an ODE model that can isolate faults given the memory and processing limitations of the embedded processor. This system trades off diagnosis isolation accuracy for inference time and/or memory in a principled manner. We use a Polynomial Regression approach for tuning the performance of an ensemble of low-fidelity ODE diagnosis models such that we achieve the target of embedded processing limits. We demonstrate our approach on a non-linear tank benchmark system.
- Subjects :
- Polynomial regression
Co-design
0209 industrial biotechnology
Engineering
business.industry
Ode
Inference
Embedded processing
02 engineering and technology
Structural engineering
01 natural sciences
Reduced order
010104 statistics & probability
020901 industrial engineering & automation
Computer engineering
Control and Systems Engineering
Benchmark (computing)
Isolation (database systems)
0101 mathematics
business
Subjects
Details
- ISSN :
- 24058963
- Volume :
- 50
- Database :
- OpenAIRE
- Journal :
- IFAC-PapersOnLine
- Accession number :
- edsair.doi...........98da6d1a0baaf47f6a80104001118683