A clustering technique groups manufacturing data in clusters of similar parametric behaviour. Each cluster groups data points which satisfy a given criterion of process behaviour similarity. These data may be widely separated in time and thus need not form time ordered clusters. The technique operates in multi-dimensional parameter space and can represent process data that is characterised with multiple performance measures. The technique produces a partition of the data into the minimum number of clusters which satisfy the criterion that all data in the grouping are within a given threshold distance from a cluster nucleus. In addition, the clustering mechanism according the invention is computationally rapid.