Huang, Y.; Chen, J., and Wang, C., 2019. Algorithm for predicting flocculation rate of particulate minerals in water under different influencing factors. In: Guido-Aldana, P.A. and Mulahasan, S. (eds.), Advances in Water Resources and Exploration. Journal of Coastal Research, Special Issue No. 93, pp. 61–69. Coconut Creek (Florida), ISSN 0749-0208.

The flocculation rate of particulate minerals in water affects the separation efficiency of particulate minerals. The flocculation rate of particulate minerals in water is influenced by factors such as the consumption of flocculants and the concentration of particulate minerals. Therefore, when predicting the flocculation rate of particulate minerals in water, the factors such as the consumption of flocculants and the concentration of particulate minerals should be taken into account. Firstly, support vector regression prediction algorithm is used to predict the flocculation rate, flocculant consumption and particle mineral concentration are the input variables and flocculation rate is the output variables. The penalty factor and kernel function parameters of the prediction algorithm are optimized by using particle swarm optimization algorithm based on swarm energy conservation, and the parameter combination of the optimal prediction algorithm is obtained. Experiments are carried out to verify the predictive performance of the algorithm. The results show that when the flocculant consumption is 8 g/t^-1 and the particle mineral concentration is 7%, the predicted flocculation rate can reach 1.208 m/h^-1, which is in good agreement with the measured flocculation rate. Therefore, the algorithm is a reliable method for predicting the flocculation rate of particulate minerals in water.