Control of Combustion based on euro- ybrid Model

In this paper, we describe our application of a neuro-controller based on hybrid system to optimize the combustion-process for an industrial waste incineration plant. This controller originally was designed for online controlling. It is difficult to achieve effective control of time variable and nonlinear plants such a waste combustion. Therefore a modified network topologies and training regimes have been suggested. This paper demonstrated the efficacy of our new hybrid system based on a combination of self organizing maps (SOM) and a back propagation nets. The control system has been validated on experiment data obtained from a real installation of waste combustion. The results have shown that the system is able to detect different situations