Soft computing for overflow particle size in grinding process based on hybrid case based reasoning

Abstract

The overflow particle size of cyclone is one of the most significant performance indices in the process of ore grinding. Given the measuring difficulty under the current industrial conditions, a hybrid method, which combines community finding (CF) of a complex network with case-based reasoning (CBR) is proposed in this study. The CF method with a new evaluation criterion for the vertex combination degree is designed to select the typical cases from the constructed communities, and a k-nearest neighbors (k-NN) based strategy with multi-similarity threshold is proposed in the case retrieval process. To verify the effectiveness of the proposed method, a number of comparative simulations by using the real-world data coming from a copper–molybdenum concentration plant are carried out, and the results indicate that the proposed method can provide a good measure quality for the industrial application.