Data analytics and real-time monitoring can be used to ensure that boards and systems operate as intended. This paper first describes how machine learning, statistical techniques, and information-theoretic analysis can be used to close the gap between working silicon and a working system. Next, it describes how time-series analysis can be used to analyze health status and detect anomalies in complex core router systems. Traditional techniques fail to identify abnormal or suspect patterns when the monitored data involves temporal measurements and exhibits significantly different statistical characteristics for its constituent features. This paper thus not only describes a feature-categorization-based hybrid method and a changepoint-based method to detect anomalies in time-varying features with different statistical characteristics, but also proposes a symbol-based health analyzer to obtain a full picture of the health status of monitored core routers. A comprehensive set of experimental results is presented for data collected during 30 days of field operation from over 20 core routers deployed by customers of a major telecom company.