A Machine Learning Model for the Detection of Solder Voids with Adjacent Sensors

In this work, a machine-learning model is trained for the detection of voids in the solder layer underneath a power semiconductor based on the readings of temperature sensors adjacent to the device. For this, multiple con.gurations of a nearest-neighbor classi.cation model are trained and tested with data obtained from the measurement and simulation of a test arrangement with arti.cial faults. A grid search with cross-validation is used to propose an optimized model for the given task, based on di.erent scoring metrics. Additionally, the success of the classi.cation is evaluated in the context of the application case.