Because of the availability of powerful industrial computers which col
lect huge amounts of real-time data in mineral processing plants, ther
e is a need for efficient methods to extract relevant information from
them. Multivariate statistical techniques, such as principal componen
ts analysis (PCA) and projection to latent structures (PLS), are well
suited to analyze these large sets of noisy and ill-conditioned data.
The power of PCA and PLS is illustrated on historical data from a grin
ding and flotation plant. Three hundred and fifty observations of fort
y-four process variables are used to show the capacity of these techni
ques for preliminary data analysis, classification of operating regime
s, process monitoring, and process empirical modelling