Clustering of a Greenhouse Fuzzy Model
Paulo Salgado, Paulo Afonso, José Boaventura‐Cunha · 2005
This paper describes the identification of greenhouse climate processes with multiple fuzzy models, derived from an organization of information of one global (flat) fuzzy model. This concept is called Separation of Linguistic Information Methodology - SLIM, and it is based on a new concept of relevance, which has been proposed to measure the relative importance of sets of rules. It allows the automatic organization of the sets of fuzzy IF … THEN rules of one fuzzy system into a multimodel Hierarchical Structure. This task is accomplished by a new Fuzzy Clustering of Fuzzy Rules Algorithm (FCFRA), which is a generalization of the well-known Fuzzy c-means, applied to a cluster of fuzzy rules instead of data points. This organizational structure makes the fuzzy greenhouse climate model interpretable, as in the case of the physical model. This new methodology was tested to split the inside greenhouse air temperature and humidity flat fuzzy models into fuzzy sub-models, which have alike counterparts on the physical sub-models.