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.