Implementation of Artificial Neural network into the copper and cobalt leaching process

Abstract

In this paper, the leaching laboratory experiment is described using the artificial neural network (ANN) to predict the copper and cobalt recovery. The ANN Multi-layer, feedforward, and back-propagation learning algorithm is trained to optimize the leaching process parameters such as acid concentration, leaching time, temperature, pulp density, and sodium metabisulfite. These parameters are responsible for the high recovery of cobalt by reducing sulphuric acid leaching process. The ANN algorithm was built with two neurons as output layers corresponding to copper and cobalt leaching recovery, 15 hidden layers, and 5 input variables defining the leaching parameters. The optimized trained neural network depicts the testing and training step with R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> about 0.8429 and 1, respectively, and corresponding to 94.98 % of copper recovery and 98.43 % or cobalt recovery.