公开(公告)号：US20180159879A1

公开(公告)日：2018-06-07

申请号：US15484282

申请日：2017-04-11

Applicant: General Electric Company

Inventor： Lalit Keshav MESTHA ,  Justin Varkey JOHN ,  Weizhong YAN ,  David Joseph HARTMAN

IPC: H04L29/06 ,  G06N99/00 ,  G06F17/16 ,  G06N3/04

CPC classification number: H04L63/1425 ,  G06N3/0454 ,  G06N3/084 ,  G06N7/005 ,  G06N20/00 ,  G06N20/10

Abstract: A threat detection model creation computer receives normal monitoring node values and abnormal monitoring node values. At least some received monitoring node values may be processed with a deep learning model to determine parameters of the deep learning model (e.g., a weight matrix and affine terms). The parameters of the deep learning model and received monitoring node values may then be used to compute feature vectors. The feature vectors may be spatial along a plurality of monitoring nodes. At least one decision boundary for a threat detection model may be automatically calculated based on the computed feature vectors, and the system may output the decision boundary separating a normal state from an abnormal state for that monitoring node. The decision boundary may also be obtained by combining feature vectors from multiple nodes. The decision boundary may then be used to detect normal and abnormal operation of an industrial asset.