Soft measurement of ball mill load based on multi-classifier ensemble modelling and multi-sensor fusion with improved evidence combination

Abstract

Abstract Aiming at the problem that the traditional Dempster–Shafer (D–S) evidence theory obtains counter-intuitive results when dealing with conflicting evidences, a new index of evidence dissimilarity measure and an improved evidence combination method are proposed in this paper, which are verified through numerical examples and UCI datasets by comparing with other methods. Then, based on the improved evidence combination method, an improved multi-classifier ensemble modelling is proposed in this paper, which is applied to the soft measurement of ball mill load. Experiments are performed with a laboratory ball mill, and the vibration signals of bearing seats are used as auxiliary variables for the mill load. The recognition results of multiple classifiers and multiple sensors are fused in turn. The recognition accuracy of the proposed method in multi-sensor fusion is significantly higher than that of a single sensor, and the overall classification accuracy is higher than that of other combination methods, which can be found that the proposed method effectively improves the accuracy of soft measurement of ball mill load.