To meet the projected energy demand in the next 30 years, advanced reactor designers are looking to maximize system capacity factor to increase economic competitiveness. To maximize capacity factor, operators must minimize the system downtime due to forced shutdowns from transients. To accomplish this, the objective of this work is to develop a System level Diagnostic/Prognostic (SDP) framework based on state-of-the-art Machine Learning Models (MLM) to support operators by detecting and diagnosing anomalous behaviors and predicting the onset of exceeding safety limits. This Accident Management Support Tool (AMST) consists of a Long Short Term Memory Autoencoder (LSTM-AE) model to identify if an anomaly is present, a Convolutional Neural Network (CNN) diagnostic model to characterize that anomaly, and a Long Short Term Memory Dense layered (LSTM-D) model to provide Remaining Useful Life (RUL) predictions. These models were trained on data from various system wide transients that occur at different power levels and at different rates using a digital twin of the Xe-100 Pebble-Bed High Temperature Gas Reactor (PB-HTGR) developed in SimuPACT. This framework’s capability is showcased with a water ingress constant reactivity insertion event that caused the reactor outlet temperature to exceed its safety threshold. This study showed that as the transient progresses, the LSTM-AE detects an anomaly within 20 s of event initiation, the CNN characterization stays steady throughout the transient with a 60 s delay, and the LSTM-D is able to accurately predict the time to threshold as the reactor outlet temperature approaches its safety threshold 720 s after fault initiation.