首页|Patent Issued for Characterizing susceptibility of a machine-learning model to follow signal degradation and evaluating possible mitigation strategies (USPTO 11 921848)
Patent Issued for Characterizing susceptibility of a machine-learning model to follow signal degradation and evaluating possible mitigation strategies (USPTO 11 921848)
扫码查看
点击上方二维码区域,可以放大扫码查看
原文链接
NETL
NSTL
inventors: “Field “The disclosed embodiments generally relate to techniques for using machine-lear ning (ML) models to perform prognostic-surveillance operations based on time-ser ies sensor signals. More specifically, the disclosed embodiments relate to a tec hnique for characterizing the susceptibility of an ML model to follow signal deg radation and evaluating possible mitigation strategies. “Related Art “Large numbers of sensors are presently deployed to monitor the operational heal th of critical assets in a large variety of business-critical systems. For examp le, a medium-sized computer data center can include over 1,000,000 sensors monit oring thousands of servers, a modern passenger jet can include 75,000 sensors, a n oil refinery can include over 1,000,000 sensors, and even an ordinary car can have over 100 sensors. These sensors produce large volumes of time-series sensor data, which can be used to perform prognostic-surveillance operations to facili tate detecting incipient anomalies. This makes it possible to take remedial acti on before the incipient anomalies develop into failures in the critical assets.