In power converters, power semiconductor devices, mainly Insulated-Gate Bipolar Transistor (IGBT), are generally used as they are less costly and capable of converting electrical energy into high frequency and voltage. It is critical to accurately determine the switching and conduction losses of power devices before they are assembled into an electronic system. The accurate values help to minimize power loss in a power converter system. With the aid of simulation, design problems are identified to help eliminate device destruction, and critical parameters are monitored. In addition, costly equipment for measuring purposes and testing prototypes is not required at the initial design stage. This research uses simulation work in a power converter system to predict IGBT and diode losses with varied frequencies and voltages. The predictive modelling is produced using regression analysis. The models have been validated by R square (R2) and Mean Absolute Percentage Error (MAPE) techniques. This work is aimed at providing a supervised learning technique mainly used in a machine learning environment, in line with the technological development in the semiconductor industry. With the simulation performed in this work, the efficiency of a boost converter system is enhanced as it shows the models have a good fit with an R2 value of almost 1, and MAPE values are noticed to be less than 5%.
Read full abstract