Abstract: A device for early warning of a device under test (DUT) failure during an electromagnetic susceptibility (EMS) test is provided. The device is configured to gradually increase perturbation of a DUT during the EMS test. The device is further configured to receive a monitoring result from the DUT being exposed to the increased perturbation, and to determine, by a machine learning (ML) model evaluating the monitoring result, a probability value of the monitoring result corresponding to a faultless operation mode of the DUT. The ML model was trained based on monitoring results obtained during undisturbed operation of the DUT.

Abstract: A device for early warning of a device under test (DUT) failure during an electromagnetic susceptibility (EMS) test is provided. The device is configured to gradually increase perturbation of a DUT during the EMS test. The device is further configured to receive a monitoring result from the DUT being exposed to the increased perturbation, and to determine, by a machine learning (ML) model evaluating the monitoring result, a probability value of the monitoring result corresponding to a faultless operation mode of the DUT. The ML model was trained based on monitoring results obtained during undisturbed operation of the DUT.