The fuzzy sets theory has provided a new direction to design process controls by multi-model approach. This paper proposes a new method to build operator models for process controls by means of the hyperellipsoidal clustering method that becomes the focal point of fuzzy modeling. The clustering algorithm combines hierarchical and non-hierarchical procedures, and does not require a priori assumption on the number, centroids, and volumes of clusters. An application study under consideration is the stable incineration control of a rotary kiln process treating excess sludge from a municipal wastewater treatment plant.