Machine Learning and Convolutional Neural Networks – Systems Based on Identification of Silicon Carbide Defects

Silicon carbide, which is a material we all call third-generation semiconductors, has special potential in 5G base stations and new energy vehicle charging.To make a better quality silicon carbide crystal, the key is to find out what defects it has.But now the factory mainly relies on manual inspection of these defects, this method is not reliable, often in the case of inequality or leakage.Better yet, we combine the method of the model that has been trained with incremental training, which can make the model more accurate and stable.Experiments have found that this method is particularly good, especially when classifying crystal defects, and even those small structural problems can be found.This method should be of great use in the fields of semiconductor production and optoelectronics.If the factory can use this automatic detection system, it can greatly improve the detection speed, reduce the error caused by manual operation, and reduce the production cost.It will be particularly easy to use in production, both flexible and accurate.