Calibration Of On-Line Ash Analyzers Using Neural Networks

A novel form of calibration of on-line analyzers was implemented. Rather than simple equations, a neural network was used to model the relationship between the scintillation counts (Am and Cs) of an analyzer, and the measured ash for improved on-line analysis of run-of-mine (r.o.m.) coal. Also, a new approach was followed to better evaluate neural network performance. Samples were first divided into various statistically different groups using a Kohonen network. Data was then selected for the training, calibration and prediction subsets, using criteria developed in this paper for sparse data, with representation from each group. A backpropagation based neural network architecture was used in conjunction with quick stop training. Due to noise in the data, the predictions were very good on average, but not individually.