Visualization detection of slurry transportation pipeline based on electrical capacitance tomography in mining filling

In the long distance transportation of slurry filled for mining filling, there exist complex variation rules of pressure and flow velocity, pipe distribution location and other influencing factors. Electrical capacitance tomography (ECT) is a technique for visualizing two-phase flow in a pipe or closed container. In this paper, a visual detection method was proposed by image reconstruction of core, laminar, bubble and annular flow based on ECT technology, which reflects distribution of slurry in deep filling pipeline and measures the degree of blockage. There is an error between the measured and the real two-phase flow distribution due to two factors, which are immature image reconstruction algorithm of ECT and difference of flow patterns leading to degrees of error. In this paper, convolutional neural networks (CNN) is used to recognize flow patterns, and then the optimal image is calculated by the improved particle swarm optimization (PSO) algorithm with weights using simulated annealing strategy, and the fitness function is improved based on the results of the shallow neural network. Finally, the reconstructed binary image is further processed to obtain the position, size and direction of the blocked pipe. The realization of this method provides technical support for pipeline detection technology.