Cluster analysis of mineral process data with autoassociative neural networks

Experimental results indicate that autoassociative neural networks provide a robust method for the identification of clusters in process data. Cluster identification is accomplished by extracting a single feature from each mu ltivariate data vector. The ranked features can be used to construct a feat ure curve, which is subsequently used as a basis for partitioning of the da ta space. In three case studies, involving two sets of ore samples, and a s et of flotation froth features, with 11, 13 and 5 variables respectively, t he clusters identified with the neural network appeared to be better than t hose obtained by conventional means.