US 11,599,815 B1Granted

Scalable and bottom-up approach to automated anomaly detection

AssigneeProgress Software Corporation

InventorsAshutosh Mani, Shyamantak Gautam, Ruban Phukan, Santosh Kumar

Life of this patent

Estimating the term…

Loading patent…

Abstract

A system and method are disclosed for bottom-up modeling and prediction of asset anomalies. In one embodiment, the system receives first sensor data from a first sensor, the first sensor associated with a first asset; smooths the first sensor data; determines a first stage within sensor data, the sensor data including the first sensor data; determines a first set of anomalies within the first stage; generates a first asset state space associated with the first asset; trains a base model describing a first group of one or more assets, the first group of one or more assets including the first asset; and trains, using the base model, a final model particular to the first asset.

Claims18

Dependent claims

A method comprising:

receiving, using one or more processors, first sensor data from a first sensor, the first sensor associated with a first asset;
smoothing, using the one or more processors, the first sensor data;
determining, using the one or more processors, a first set of change points within the first sensor data;
dividing, using the one or more processors, based on the first set of change points, the first sensor data into a first stage of the first sensor data and a second stage of the first sensor data;
determining, using the one or more processors, a first probability density distribution of the first stage of the first sensor data;
determining, using the one or more processors, a second probability density distribution of the second stage of the first sensor data;
determining, using the one or more processors, that the first probability density distribution and the second probability density distribution are statistically similar;
responsive to determining that the first probability density distribution and the second probability density distribution are statistically similar, merging, using the one or more processors, the second stage of the first sensor data into the first stage of the first sensor data;
determining, using the one or more processors, a first set of anomalies within the first stage;
generating, using the one or more processors, a first asset state space associated with the first asset;
training, using the one or more processors, a base model describing a first group of one or more assets, the first group of one or more assets including the first asset;
and
training, using the one or more processors and the base model, a final model particular to the first asset.

10 more elements

A system comprising:

one or more processors;
and
a memory storing instructions that, when executed by the one or more processors, cause the system to:
receive first sensor data from a first sensor, the first sensor associated with a first asset;
smooth the first sensor data;
determine a first set of change points within the first sensor data;
divide, based on the first set of change points, the first sensor data into a first stage of the first sensor data and a second stage of the first sensor data;
determine a first probability density distribution of the first stage of the first sensor data;
determine a second probability density distribution of the second stage of the first sensor data;
determine that the first probability density distribution and the second probability density distribution are statistically similar;
responsive to determining that the first probability density distribution and the second probability density distribution are statistically similar, merge the second stage of the first sensor data into the first stage of the first sensor data;
determine a first set of anomalies within the first stage;
generate a first asset state space associated with the first asset;
train a base model describing a first group of one or more assets, the first group of one or more assets including the first asset;
and
train, using the base model, a final model particular to the first asset.

13 more elements

Dependencies are inferred from the claim text.