Fault Condition Recognition Based on Multi-scale Texture Features and Embedding Prior Knowledge K-means for Antimony Flotation Process

Abstract

The key point to achieve automatic control and optimal operation in flotation process is to recognize the flotation conditions correctly. By the fact that it's difficult to detect and identify fault conditions in antimony flotation process, a fault condition recognition method based on multi-scale texture features extraction and k-means clustering embedding prior knowledge is proposed in this paper. Firstly, wavelet transform method is applied to froth images, and sub-images at different scales are obtained. Then neighboring gray level dependence matrix of sub-images is calculated, and the novel multi-scale texture features are statistically extracted, which can reflect the statistical laws of gray level changes in froth images. Finally, an embedding priori knowledge k-means clustering algorithm is applied to offline classification of froth images under different working conditions, and the online recognition is realized as well. Simulation and real-time recognition results show that the proposed method can achieve satisfactory performance on the fault condition recognition for antimony flotation process.