Publication detail

Neural Network Time Series Classification of Changes in Nuclear Power Plant Processes

Authors: Kupka Karel | Meloun Milan

Year: 2009

Type of publication: ostatní - přednáška nebo poster

Name of source: Joint Statistical Meeting Proceedings (Sborník konference)

Publisher name: American Statistical Association, 732 North Washington Street, Alexandria, VA 22314-1943

Page from-to: nestránkováno

Titles:

Language	Name	Abstract	Keywords
cze	Klasifikace časových řad pomoci sítí a změny v jaderných procesech	PLSAR parciální regresní metody lineární regresní autoregresní metody byly užity ve víceparametrické regresní predikci.	časové řady, neurální sítě, klasifikace, SVM, QCEXPERT
eng	Neural Network Time Series Classification of Changes in Nuclear Power Plant Processes	Time series are typical data output from technological processes. Diagnostics of process data such as model change detection, outlier detection are often of primary interest for quality management. For autocorrelated processes, many models and procedures have been suggested, many of them based on uni- and multivariate EWMA, AR, ARIMA, CUSUM. Two types of models for stationary univariate series were tested: linear partial least squares autoregresison (PLSAR) and nonlinear perceptron-type feed-forward neural network autoregression (ANNAR) with multistep prediction.	model change detection; outlier detection; partial least squares; autoregression; multistep prediction

Search