RBF Neural Networks Modeling Methodology Compared to Non-Parametric Auto-Associative Models for Condition Monitoring Applications

This work presents the use of radial basis function artificial neural network to estimate the sensors readings, exploring the analytical redundancy via auto association. However, in order to guarantee good performance of the network the training and optimization process was modified. In the conventional training algorithm, although the stop criteria, such as summed squared error, is reached, one or more of the individual performance metrics, including: i) accuracy; ii) robustness; iii) spillover and iv) filtering matrix of the neural network may not be satisfactory. The paper describes the proposed algorithm including all the mathematical foundation. A dataset of a petroleum refinery is used to train a RBF network using the conventional and the modified algorithm and the performance of both will be evaluated. Furthermore, AAKR model is used to the same dataset. Finally, a comparison study of the developed models will be done for each of the performance metrics, as well as for the overall effectiveness in order to demonstrate the superiority of the proposed approach.