SOx monitoring and neural net classification in the power plant

Abstract

In this paper, we propose a prediction method of the pollutant and a synchronous classification of the current state of SOx emission in the power plant. We use the autoregressive with exogeneous (ARX) model as a predictor of SOx emission and use the neural network (NN) as a pattern classifier. The ARX modeling scheme is implemented using the recursive least-squares method to update the model parameters adaptively. The capability of SOx emission monitoring is utilized with the application of the NN classifier, where genetic algorithms are used to decide the structure such as the number of hidden nodes of a NN classifier. Experimental results show that the ARX model can predict the SOx emission concentration well and the ARX modeling parameters can be a good feature for the state monitoring. In addition, its validity has been verified through the power spectrum analysis. Consequently, the NN classifier in combination with the ARX model is quite adequate for monitoring the state of SOx emission.