Prediction of liquid bridge rupture between two plates combining artificial neural network with grey wolf optimization algorithm

The liquid bridge rupture has attracted much attention in various fields such as powder technology, micro gripping, and wet agglomeration. In present study, an artificial neural network (ANN) model was developed to predict the liquid bridge rupture between two plates, focusing on the rupture distance and the transfer ratio. The initial weights and biases of the ANN model were optimized by the grey wolf optimization algorithm (GWO). The GWO-ANN model prediction is compared with the BP-ANN model prediction. Based on the testing dataset, the mean square error (MSE) and correlation coefficient (R²) of the rupture distance for the optimized GWO-ANN model were calculated as 4.65 × 10^− 4 and 0.9586, and that of the transfer ratio was 2.15 × 10^− 4 and 0.975, respectively. The effectiveness of the constructed GWO-ANN model for the liquid bridge rupture prediction was verified by experimental investigations. The effect of input parameters including contact angles, stretching speed, liquid volume and liquid viscosity on the rupture was discussed in detail.