An XGBoost-Based Method for Predicting the Location of MIV Open Fault

With the fast development trend of highly integrated electronic products, as the key technology of 3-D interconnects circuits, the research on monolithic intertier via (MIV) testing technology is particularly critical. Due to the high integration density, the MIV itself is very prone to manufacturing fault; moreover, the uncertainty of fault location and the complexity of fault type will have a greater impact on the signal transmission performance of the MIV. Therefore, in order to effectively isolate the fault and reduce the loss of assembly yield. This article proposes an EXtreme Gradient Boosting (XGBoost)-based method for predicting the location of MIV open fault. This method adopts the XGBoost prediction model optimized based on the grid search (GS) algorithm and takes the S-parameters as the training dataset. The S-parameters are used as the training dataset to train and evaluate the prediction model. This method can effectively solve the problem that the traditional MIV test method makes it difficult to accurately locate the MIV open fault. Simulation results show that the prediction model proposed in this article can accurately predict the location of open faults.