SAG mill system diagnosis using multivariate process variable analysis

Abstract

Semi-autogenous grinding (SAG) of ore plays a critical role in a mineral processing plant. In SAG operations, abnormal conditions, such as overload or insufficient ore holdup, often result in inefficient production and unstable operation. It is, therefore, essential to monitor the process using effective technology so that abnormal or faulty conditions can be detected and addressed in a timely manner. In this study, investigation is focused on applying multivariate analysis in the monitoring and diagnosing of an industrial SAG operation. The results show that principal component analysis provides an effective methodology for on-line monitoring and diagnosis. The detection and removal of faulty conditions will help to provide stable and cost-efficient operation.Le broyage semi-autogène (BSA) du minerai joue un rôle essentiel dans une usine de traitement des minéraux. Dans les activités de BSA, des conditions anormales, comme une surcharge ou une retenue du minerai insuffisante, mènent souventà une production inefficace et un fonctionnement instable. Il est, par conséquent, essentiel de surveiller le processusà l'aide d'une technologie efficace pour que les conditions anormales soient détectées et abordées de manière opportune. Dans ce document, l'enquête est axée sur l'utilisation d'une analyse multivariée dans le suivi et le diagnostic d'une activité de BSA industrielle. Les résultats indiquent que l'analyse des principaux composants fournit une méthodologie efficace pour le suivi et le diagnostic en ligne. La détection et le retrait de ses conditions anormales aiderontà procurer un fonctionnement stable et economique.

Performance Audit of a Semi-autogenous Grinding Mill Circuit

“…This view and these statistics can be used to determine whether a fault may have occurred and offer a starting point for root cause analyses. The application to SAG mill monitoring with PCA has also been considered by Ko and Shang (2011). Their study indicated that PCA is a suitable approach to visualize overall mill process performance, as well as to detect abnormal process conditions.…”

Nonlinear Process Monitoring Using Supervised Locally Linear Embedding Projection

“…PCA, using the Q and T 2 test statistics, is also trained as a process monitoring method for comparison to SLLEP-LDA. Ko and Shang introduce this technique for SAG monitoring and demonstrate its ability to detect process abnormalities for SAG mill operation. However, this study does not identify which abnormalities are overload events.…”

“…We apply SLLEP to detect the early onset of a semiautogenous grinding (SAG) mill overload. We show that SLLEP with linear discriminant classification beats the best-in-class technique in the industry, PCA with T 2 and Q test statistics, 13 for monitoring a SAG mill overload. Furthermore, we discuss a simple method to interpret the classification output of the SLLEP feature space to estimate the severity of a process abnormality and provide operators with an information-rich univariate measurement.…”