Modeling of Wet Grinding Operation using Artificial Intelligence based Techniques
| Authors: | Mitra Kishalay, Tata Consultancy Services, India
Ghivari Mahesh, Tata Consultancy Services, India |
|---|
| Topic: | 6.2 Mining, Mineral & Metal Processing |
|---|
| Session: | Technology in Mining and Metal Processing Industry |
|---|
| Keywords: | Process identification, process models, simulation, artificial intelligence, neural network, wavelet |
|---|
Abstract
The Artificial Intelligence (AI) based modeling techniques applied to the industrial grinding operation of a lead-zinc ore-beneficiation plant to predict the key performance indicators (KPIs) for the circuit. As system identification of the non-linear process is a must in advanced control, AI based techniques are applied to predict the KPIs within some acceptable limits. The nonparametric model for these KPIs is constructed using Feed-Forward Neural Networks (FNN), and wavelet-frames. A well-validated hybrid-model, using physico-empirical methodologies, is used to approximate the actual behaviour of the plant. Merits and demerits of each of these techniques are presented.
