Track: Artificial Intelligence

Abstract

Machine learning techniques inspired by the structure and function of the human brain are known as artificial neural networks (ANNs). Their popularity has grown in recent years due to their ability to learn and improve via training, allowing them to be used in a variety of applications. The ANN approach has the appealing advantage of providing an accurate representation of the process input/output data and due to this reason, their application in the extraction metallurgy field have increased over the years. This systematic review aims to investigate the application and efficacy of ANN for facilitating and upgrading mineralogical data processing in the extraction metallurgical field. In this study, 112 research papers, published over years, that discuss ANN application were retrieved and 49 research papers were systematically reviewed. Research trends, ANN algorithms models, and evaluation methods primarily discussed in the 49 papers were discussed. From the review, it was discovered that the main justification to the increase application of ANN in the extraction metallurgy field is due to the ore grade decline which makes extraction processes complex demanding a need for a predicting and optimising tool. The frequently used ANN algorithm was found to Levenberg- Marquardt algorithm (LMA) which was due to its ability to process a lot of data in a short period of time. It was further concluded that the applicability of ANN in metallurgical field diverse from processes optimisation using operational to equipment parameters with least error and high efficiency.