Prediction of 2G HTS Tape Quench Behavior by Random Forest Model Trained on 2-D FEM Simulations

Detailed Finite Element Method (FEM) based simulations for 2G HTS tapes return high quality results, but the computation takes a long time due to non-linearity of superconducting properties and they needed mesh density. This work describes method prediction quench behavior in tape on series 2D FEM model short length many different conditions. The random forest is trained by set results from short-pieces calculations. Subsequently can be applied any with similar thermal characteristics. Comparison simulation 10 cm between detailed fully show that predicted temperatures are within 0.68%, while significantly faster: ran less than 1 s, run was 5:30 min.