Inferential estimation of viscosity index on a lubricant production plant

A multi-rate adaptive inferential estimation technique is briefly presented. The methodology is used to infer infrequently measured viscosity index on an industrial lubricant production plant. The inference is obtained using more frequently sampled secondary outputs and manipulated inputs. The techniques employed in the selection of the appropriate variables for use in the algorithm are described. The results demonstrate the ability of the algorithm to accurately estimate the `quality variable´ at a rate at which the more easily measured information is available