Evolving fuzzy model based performance identification for production control

In this paper we present a fuzzy cloud-based model identification method tested on realistic input/output data signals acquired from simulated Tennessee Eastman (TE) benchmark process. The cloud-based method uses simplified antecedent (IF) part based on the local density of the clouds and functional consequent (THEN) part. Number of clouds (fuzzy rules) in the IF part evolves such that when certain criteria are satisfied a new cloud is added. In this paper we use simple density threshold complemented with protecting mechanism for outliers. The parameters of the consequent part were identified using recursive Weight Least Square method. The proposed method was tested on TE process where three models were identified for the chosen, most representative, production Performance Indicators (pPIs). The provided results (quality measures) of the proposed method were compared with the results obtained using eFuMo identification tool.