Computational intelligence approaches for parametric estimation and feature extraction of power spectral density

This paper reports an early progress of a feasibility study of a computational intelligence approach to the enhancement of the accuracy of flow measurements in the framework of a current cooperation between Tecnatom s.a. in Madrid and the OECD Halden Reactor Project in Halden. The aim of this research project is to contribute to the development and validation of a flow sensor in a nuclear power plant (NPP). The basic idea of the current project is to combine the use of applied computational intelligence approaches (noise analysis, neural networks, fuzzy systems, and wavelet etc.) with existing traditional flow measurements, and in particular with cross correlation flowmeter concepts. The design of possible algorithms based on computational intelligence approaches will be modified during the tests of a real NPP.

• Type: Conference
• Year: 2001
• Where: EUSFLAT
• Authors: Da Ruan, Davide Roverso, Paolo F. Fantoni
• Keywords: Computational Intelligence, Computational Intelligence Approaches, EUSFLAT 2001, EUSFLAT 2007, Flow Measurements