Selective transport of attached particles across the pulp-froth interface

A technique for determining the recovery of attached particles across the froth phase in flotation that relies on measuring the rate at which bubble-particle aggregates enter the froth is used to investigate the selectivity of attached particles across the froth phase. Combining these measurements with those of other techniques for determining the froth recovery of attached particles provides an insight into the different subprocesses of particle rejection in the froth phase. The results of experiments conducted in a 3 m3 Outokumpu tank cell show that the detachment of particles from aggregates in the froth phase occurs largely at the pulp-froth interface. In particular it is shown that the pulp-froth interface selectively detaches particles from aggregates according to their physical attributes.

Tracking the states of a nonlinear system in the weight-space of a feed-forward neural network

Nonlinear, non-stationary signals are commonly found in a variety of disciplines such as biology, medicine, geology and financial modeling. The complexity (e.g. nonlinearity and non-stationarity) of such signals and their low signal to noise ratios often make it a challenging task to use them in critical applications. In this paper we propose a new neural network based technique to address those problems. We show that a feed forward, multi-layered neural network can conveniently capture the states of a nonlinear system in its connection weight-space, after a process of supervised training. The performance of the proposed method is investigated via computer simulations.