1 Neural Network for Evaluating Boiler Behaviour Luis M. Romeo * Renewable energy sources are essential paths towards sustainable development and CO 2 emission reduction. For example, the European Union has set the target of achieving 22% of electricity generation from renewable sources by 2010. Therefore, intensive research is carrying out in order to take advantage of biomass potential. Biomass characterization has been analysed in detail, and there is a great number of comprehensive studies of biomass combustion behaviour. and Raquel Gareta Centro de Investigación de Recursos y Consumos Energéticos (CIRCE). Universidad de Zaragoza. Centro Politécnico Superior. María de Luna, 3, 50018 Zaragoza. Abstract Fouling and slagging are some difficulties for the development of biomass as energy potential and to achieve the targets of renewable energy sources utilization. The proper technique to analyze the influence of fouling in a biomass boiler is to monitorize the evolution of heat absorption in heat transfer equipment. Traditional equation-based monitoring techniques have problems to tackle with this complex phenomenon. The objective of this paper is to present the methodology of Neural Network (NN) design and application for a biomass boiler monitoring and point out the advantages of NN in these situations. A combination of traditional methods aided with a NN structure to monitorize the boiler could completely solve the problem. NN monitorizing results show an excellent agreement with real data. It is also concluded that NN is a stronger tool for monitoring than equation-based monitoring. This work will be the basis of a future development in order to control and minimize the effect of fouling in biomass boilers. Keywords: Monitorizing; Biomass Boiler; Simulation; Neural Network; Boiler Fouling. 1. INTRODUCTION * Corresponding author (e-mail: luismi@unizar.es ). Phone +34 976 762570 Fax +34 976 732078