Generalized Dynamic Feature Extraction Method for Rotary Kiln Sintering Condition Recognition

Maintaining a normal sintering condition is vital to ensuring the quality of nonferrous metals in a rotary kiln. Identification of the sintering conditions is a crucial component of a condition control system. In order to exploit the dynamic information of the flame combustion process, i.e., multiview of flame. This article presents a generalized dynamic feature extraction method to improve the sintering condition identification accuracy. Compared to most of the current methods, our approach introduces the concept of multiview subspace clustering that reveals the manifold structure of the data through the symmetric positive definite (SPD) manifold termed invariant SPD manifold representation multiview subspace clustering (IMMSC). Moreover, our method is generalized to extract dynamic features for most static features. With the manifold metric's affine invariance property, we demonstrate that IMMSC can extract dynamic features to enhance classification accuracy. The proposed method can be efficiently optimized by manifold optimization. Experimental results using real datasets and coil-20-proc dataset demonstrate that the proposed method for recognizing sintering condition are effective and robust.