The aim of the article is to numerically model a two-dimensional multiphase flow based on the volume of fluid method (VOF) in a pulsating heat pipe (PHP). The current state of knowledge regarding the modeling of these devices was studied and summarised. The proposed model is developed within open source software, OpenFOAM, based on the predefined solver called interPhaseChangeFoam. The analyses were carried out in terms of the influence of four different mass transfer models between the phases, proposed by Tanasawa, Lee, Kafeel and Turan, and Xu et al. on the shape and dynamics of the internal flow structures. The numerical models were validated against data obtained from a specially designed experimental setup, consisting of three bends of pulsating heat pipes. The numerical calculations were carried out with ethanol being treated as a working medium and the initial and boundary conditions taken directly from the measurement procedures. The variable input parameter for the model was the heat flux implemented in the evaporation section and a fixed temperature applied to the condensation section. The flow structures obtained from the numerical analyses were compared and discussed with the flow structures gained from experimental studies by employing a high speed camera. In addition, to verify the quantitative results obtained from the numerical analyses with the experimental data, a technique called particle image velocimetry (PIV) was used for the velocity vector field. For the analysed velocity ranges, the relative error obtained was reached at the level of 10%.

Conveyor belts are vital for material transportation in coal mines due to their cost-effectiveness and versatility. These belts endure significant wear from harsh operating conditions, risking substantial financial losses if they fail. This study develops five artificial neural network (ANN) models to predict conveyor belt damage using 11 parameters from the Belchatow brown coal mine in Poland. The models target five outputs: number of repairs and cable cuts, cumulative number of repairs and cable cuts, and their ages. Various optimizers (Adam, Nadam, RMSprop, Adamax, and stochastic gradient descent or SGD) and activation functions (ReLU, Swish, sigmoid, tanh, Leaky ReLU, and softmax) were tested to find the optimal configurations. The predictive performance was evaluated using three error indicators against actual mine data. Superior models can forecast belt behavior under specific conditions, aiding proactive maintenance. The study also advocates for the Diagbelt+ system over human inspections for failure detection. This modeling approach enhances proactive maintenance, preventing total system breakdowns due to belt wear.