A Clustering-analysis-based membership functions formation method for fuzzy controller of ball mill pulverizing system

► We propose a clustering-analysis-based membership functions formation method for fuzzy controller of ball mill pulverizing system. ► The fuzzy set and the membership functions of the fuzzy controller could be automatically generated by the proposed method on the field database. ► The proposed method using a hybrid density-based clustering algorithm is more suitable for clustering analysis on the industrial process database. ► The experiments results verify the effectiveness of our method and the fuzzy controller has been put into practice successfully.