In this paper a modem methodology of biplots is introduced as a means for monitoring the behaviour of process systems. This sophisticated methodology allows for the projection of high-dimensional data to a low-dimensional subspace that can be visualised by a human operator. The projections are highly graphical in nature, and rich in information regarding variation in process variables, correlations among these variables, as well as class separation, taking into account the multivariate character of the data. Moreover, as is shown by way of two case studies, process disturbances can be visualised and explored quantitatively by superimposing alpha-bags on biplots. (c) 2005 Elsevier Ltd. All rights reserved.