US 11,868,906 B2
System and method for fault detection of components using information fusion technique
Guruprasad Srinivasan, Bangalore (IN); Younghun Kim, Pleasantville, NY (US); and Tarun Kumar, Chappaqua, NY (US)
Assigned to Utopus Insights, Inc., Valhalla, NY (US)
Filed by UTOPUS INSIGHTS, INC., Valhalla, NY (US)
Filed on Dec. 15, 2020, as Appl. No. 17/122,943.
Application 17/122,943 is a continuation of application No. 16/234,465, filed on Dec. 27, 2018, granted, now 10,867,250.
Prior Publication US 2021/0216883 A1, Jul. 15, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G06N 5/02 (2023.01); G06N 3/08 (2023.01); G06N 20/00 (2019.01)
CPC G06N 5/02 (2013.01) [G06N 3/08 (2013.01); G06N 20/00 (2019.01)] 18 Claims
OG exemplary drawing
 
1. A non-transitory computer readable medium comprising executable instructions, the executable instructions being executable by one or more processors to perform a method, the method comprising:
receiving historical sensor data of a first time period, the historical sensor data including sensor data from one or more sensors of a renewable energy asset;
extracting features from the historical sensor data;
performing a unsupervised anomaly detection technique on the historical sensor data to generate a first set of labels associated with the historical sensor data, the performing comprises:
generating an anomaly score based on an output of the unsupervised anomaly detection technique;
comparing the anomaly score to a threshold; and
generating a label of the first set of labels based on the comparison;
performing at least one dimensionality reduction technique to generate a second set of labels associated with the historical sensor data, the dimensionality reduction technique reducing a second number of dimensions of the extracted features when compared to a first number of dimensions of the extracted features analyzed using the unsupervised anomaly detection;
combining at least the label of the first set of labels and one or more labels of the second set of labels to generate combined labels;
generating one or more models based on supervised machine learning and the combined labels;
receiving current sensor data of a second time period, the current sensor data including sensor data from at least a subset of the one or more sensors of the renewable energy asset;
extracting features from the current sensor data;
applying the one or more models to the extracted features of the current sensor data to create a prediction of a future fault in the renewable energy asset,
comparing the prediction of the future fault against one or more criteria to determine significance of the future fault, the one or more criteria including a number of failures in close proximity to each other, a total number of failures, significance of risk to the renewable energy asset as a whole, impact to other assets, impact to an electrical network, or impact the future fault has to important service; and
generating an alert based on the comparison, the alert including the prediction of the future fault in the renewable energy asset.