Silicon carbide power device ion implantation optimization method based on machine learning

The invention belongs to the technical field of silicon carbide power device manufacture procedures, and particularly relates to a silicon carbide power device ion implantation optimization method based on machine learning. The method comprises the following steps: acquiring historical silicon carbide power device ion implantation process data, and making an ion implantation process optimization sample data set; dividing the sample data set into a training set A1, a training set A2 and a test set; training an SVM prediction model by using the training set A1 to obtain an initial SVM prediction model; according to the training set A2, training and verifying the initial SVM prediction model by using a network-based transfer learning method to obtain a trained SVM prediction model; and testing the test set by using the trained SVM prediction model. According to the method, the process optimization rate and accuracy can be improved, the cost is reduced, and the rejection rate is reduced; the method can efficientl