NOx and CO prediction in fossil fuel plants by time delay neural networks

This paper presents a time delay neural network (TDNN) model designed for t he prediction of nitrogen oxides (NOx) and carbon monoxide (CO) emissions f rom a fossil fuel power plant. NOx and CO emissions of the plant are determ ined as a function of other related time-series such as air flow rates and oxygen levels that are measured during the system operation. Correlation an alysis is performed on the data to determine the location and the spread of cross-correlation between pairs of variables and this information is used to form a variable tapped delay line at the input of the network. We also i ntroduce a neural network based preprocessor which employs an iterative reg ularization scheme to recover missing portions of CO data that are censored due to saturation of the measuring device. Prediction after training with the restored data set is observed to be significantly more accurate.