Artificial Neural Network Application for a Predictive Task in Mining (Department of Mining Engineering University of Kentucky)

Artificial Intelligence research has produced several tools for commercial application. Neural Networks, Fuzzy Logic and Expert Systems are some of the techniques that are widely used today. Artificial Neural Networks (ANNs) are excellent predictive, pattern recognition, and data analysis tools. In the mining industry, ANN techniques are being used commercially for real-time process control applications. Modeling of spatial data, ore reserve estimation, tunnel design, longwall stability prediction, and geologic roof classification are additional application areas in which neural networks have been applied successfully. A standard back-propagation algorithm was used to train a series of neural networks for a real-world predictive task. After training and optimizing the neural network architecture, performance of the network is measured on an independent validation set. Results indicate a correlation coefficient of up to 84 % between the actual and predicted values. A neural network model is developed for learning the spatial continuity of a mineral field and, consequently, for predicting sulfur values given coordinate values. The neural network performed not only satisfactorily, but in some cases performed better than the kriging model.