Using support vector machines in the multivariate state estimation technique
One approach to validate nuclear power plant (NPP) signals makes use of pattern recognition techniques. This approach often assumes that there is a set of signal prototypes that are continuously compared with the actual sensor signals. These signal prototypes are often computed based on empirical models with little or no knowledge about physical processes. A common problem of all data-based models is their limited ability to make predictions on the basis of available training data. Another problem is related to suboptimal training algorithms. Both of these potential shortcomings with conventional approaches to signal validation and sensor operability validation are successfully resolved by adopting a recently proposed learning paradigm called the support vector machine (SVM). The work presented here is a novel application of SVM for data-based modeling of system state variables in an NPP, integrated with a nonlinear, nonparametric technique called the multivariate state estimation technique (MSET), an algorithm developed at Argonne National Laboratory for a wide range of nuclear plant applications.
- Research Organization:
- Argonne National Lab., IL (US)
- OSTI ID:
- 20005779
- Journal Information:
- Transactions of the American Nuclear Society, Journal Name: Transactions of the American Nuclear Society Vol. 81; ISSN 0003-018X; ISSN TANSAO
- Country of Publication:
- United States
- Language:
- English
Similar Records
Uncertainty analysis for multivariate state estimation in safety-critical and mission-critical maintenance applications
Randomized Sampling for Large Data Applications of SVM