公开(公告)号：US10929337B2

公开(公告)日：2021-02-23

申请号：US16422714

申请日：2019-05-24

Applicant: Intel Corporation

Inventor： Rahul Kundu ,  Fei Su ,  Prashant Goteti

IPC: G06F15/78 ,  G06F30/34 ,  G06F30/327 ,  G06F11/34 ,  G06F11/07 ,  G06F11/30

Abstract: Methods, systems and apparatuses may provide for technology that detects, by a first monitor in a first domain of a system, a presence of a first anomaly in the first domain and encodes, by the first monitor, the presence of the first anomaly and a weight of the first anomaly into a multi-level data structure. In one example, the technology also sends, by the first monitor, the multi-level data structure to a second monitor in a second domain of the system, wherein the second domain is located at a different hierarchical level in the system than the first domain.

公开(公告)号：US10685159B2

公开(公告)日：2020-06-16

申请号：US16020396

申请日：2018-06-27

Applicant: Intel Corporation

Inventor： Fei Su ,  Prashant Goteti

IPC: G06F11/00 ,  G06F30/367 ,  G01R31/3163 ,  G06N20/00 ,  G01R31/00 ,  G06F30/15

Abstract: In some examples, systems and methods may be used to improve functional safety of analog or mixed-signal circuits, and, more specifically, to anomaly detection to help predict failures for mitigating catastrophic results of circuit failures. An example may include using a machine learning model trained to identify point anomalies, contextual or conditional anomalies, or collective anomalies in a set of time-series data collected from in-field detectors of the circuit. The machine learning models may be trained with data that has only normal data or has some anomalous data included in the data set. In an example, the data may include functional or design-for-feature (DFx) signal data received from an in-field detector on an analog component. A functional safety action may be triggered based on analysis of the functional or DFx signal data.

公开(公告)号：US20190050515A1

公开(公告)日：2019-02-14

申请号：US16020396

申请日：2018-06-27

Applicant: Intel Corporation

Inventor： Fei Su ,  Prashant Goteti

IPC: G06F17/50 ,  G06N99/00 ,  G01R31/3163

Abstract: In some examples, systems and methods may be used to improve functional safety of analog or mixed-signal circuits, and, more specifically, to anomaly detection to help predict failures for mitigating catastrophic results of circuit failures. An example may include using a machine learning model trained to identify point anomalies, contextual or conditional anomalies, or collective anomalies in a set of time-series data collected from in-field detectors of the circuit. The machine learning models may be trained with data that has only normal data or has some anomalous data included in the data set. In an example, the data may include functional or design-for-feature (DFx) signal data received from an in-field detector on an analog component. A functional safety action may be triggered based on analysis of the functional or DFx signal data.