Nuclear power plants fuel production is very crucial and highly complex processes, involving numerous variables. For the safety used in the Light Water Nuclear Reactor, the cylindrical uranium dioxide pellets as the main fuel element should shows uniform shape, uniform quality and a high density profile. Therefore, the assesment of the quality classification of these pellets is important for improving the efficiency of the production process. The quality of green pellets is conventionally monitored through a laboratory measurement of the physical pellets characteristics followed by a graphical chart classification technique. This method, however, is difficult to use and shows low accuracy and time consuming, since its lack of the ability to adress the non-linearity and the complexity of the relationship between the pellet’s quality variables and the pellett’s quality. In this paper, an intelligent technique is develop to classify the pellets quality by using a computational intelligence methods. Instead of a Single Back Propagation neural networks that ussualy used, an Ensemble Back Propagation neural networks is proposed. It is proved in the experimental results that the Ensemble Back Propagation neural networks show higher classification rate compare with that of Single Back Propagation neural networks, showing that this system could be applied effectively for classification of pellet quality in its fabrication process.
Classification of Camellia species from 3 sections using leaf anatomical data with back-propagation neural networks and support vector machines