LAUSR

This paper proposed a non-contact froth depth estimation approach based on machine vision. Firstly, the froth images collected from sulphur flotation process under different working conditions are processed to obtain froth features. Secondly, the working condition recognition model based on froth features of flotation process is built to recognize working conditions. Moreover, the key froth features are selected by correlation analysis for various operating modes, which are the inputs of the estimation models for froth depth. Finally, the estimation models of froth depth for different working conditions are established based on the low dimensional process features, which are composed of the deep froth image features under current working condition, and crucial process operating parameters, e.g., flow rates of air, tailing and feeding. Experimental results demonstrate that the proposed method can significantly improve the measuring accuracy, compared with traditional measuring method using physical liquid level meter.