Improving feedwater cross-correlation flow measurements in nuclear power plants with artificial neural networks

One of the primary objectives of the power plant industry has long been the efficient operation of plant systems, thus reducing the cost of electricity production. The operating thermal power of a nuclear reactor is limited by the Nuclear Authority licensing requirements. Therefore, the thermal power of the plant should be determind very accurately. The feedwater flow rate is one of the major quantities used in determining the thermal power, and Venturi meters are traditionally used to measure this flow rate. Venturi flow meters are subject to known accuracy problems, mainly originating from the gradual build-up of fouling in the Venturi constriction, which leads to an overestimation of the produced thermal power, and a consequenct forced "derating" of the plant in order to stay within authority limits. This paper reports on early progress of a feasibility study of a computational intelligence approach to the enhancement of the accuracy of cross-correlation flow measurements as a potential solution to the problem of Venturi fouling.