Supervised learning algorithm for open loop NN based control of tumbling mill

The paper proposes a new supervised training algorithm for feedforward neural networks. Instead of applying single valued input-output information at a time, multivalued information in the form of a K-dimensional vector (K>l) are applied to each node of the input output layer. Weights are adjusted using gradient decent approximation method in order to minimise the sum squared error value at each node of the-output layer. The work aims at developing feedforward neural network model meant for controlling a tumbling mill apparently in open circuit but actually perform a closed circuit operation. The data input is particle size in vector form and output is size of particle of crushed parent in band/upper triangular, matrix. The model is verified using wide range of data