US 10,685,159 B2 · Analog functional safety with anomaly detection

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.

Claims22

Dependent claims

A system for detecting anomalies in an analog circuit, comprising:

memory to store instructions to operate an anomaly detection model running one or more machine learning models;
a processor coupled to the memory to execute the instructions to cause the anomaly detection model to:
access a runtime signal data from an in-field detector on an analog component, wherein the runtime signal data is functional signal data or design for feature (DFx) signal data, the functional signal data or the DFx signal data collected based on functional input or test control signals to the analog component;
analyze the functional signal data or the DFx signal data using at least one of a point anomaly detector, a contextual anomaly detector, or a collective anomaly detector;
generate an anomaly score based on results of the analyzing;
compare the anomaly score to a pre-selected threshold;
and
trigger a functional safety action for the analog component in response to a result of the comparison indicating that the anomaly score traverses the threshold.

5 more elements

A computer implemented method for detecting anomalies in an analog circuitry, comprising:

accessing a runtime signal data from an in-field detector on an analog component, wherein the runtime signal data is functional signal data or design for feature (DFx) signal data, the functional signal data or the DFx signal data collected based on functional input or test control signals to the analog component;
analyzing the functional signal data or the DFx signal data using at least one of a point anomaly detector, a contextual anomaly detector, or a collective anomaly detector;
generating an anomaly score based on results of the analyzing;
comparing the anomaly score to a pre-selected threshold;
and
triggering a functional safety action for the analog component in response to a result of the comparison indicating that the anomaly score traverses the threshold.

3 more elements

At least one non-transitory machine-readable medium including instructions for detecting anomalies in an analog circuitry, which, when executed by a processor, cause the processor to perform operations to:

access a runtime signal data from an in-field detector on an analog component, wherein the runtime signal data is functional signal data or design for feature (DFx) signal data, the functional signal data or the DFx signal data collected based on functional input or test control signals to the analog component;
analyze the functional signal data or the DFx signal data using at least one of a point anomaly detector, a contextual anomaly detector, or a collective anomaly detector;
generate an anomaly score based on results of the analyzing;
compare the anomaly score to a pre-selected threshold;
and
trigger a functional safety action for the analog component in response to a result of the comparison indicating that the anomaly score traverses the threshold.

3 more elements

Dependencies are inferred from the claim text.

Analog functional safety with anomaly detection

Life of this patent

Analog functional safety with anomaly detection

Life of this patent

Abstract

Claims22