General Electric Company

Ge Infrastructure Technology, LLC

General Electric Renovables Espana, S.l.

John Joseph Mihok

Michael James Rizzo

Frederick Wilson Wheeler

Zhanpan Zhang

Guangliang Zhao

David Charles Korim

Frank William Ripple, Jr

Kyle Raymond Barden

Jin Xia

Radislav Alexandrovich Potyrailo

Sameh Ramadan Salem

Suryarghya Chakrabarti

Peter Alan Gregg

Ameet Shridhar Deshpande

Dayu Huang

Liwei Hao

Lijun He

Michael Garry

Bouchra Bouqata

Ashley Simone Wilford

Dhaval Ramesh Bhalodia

Alvaro Enrique Gil

Youngwon Shin

Santiago Murcia

Christopher Albert Jordan

Inderdeep Kaur

Robert Mcleod

Waad Hussain Subber

Jr Frank William Ripple

Subhankar Ghosh

Jeremy Canary

Srinivas Kannepalli

Joshua Potter

Sridhar Dasaratha

Dhaval Bhalodia

A system and method are provided for operating a power generating asset. Accordingly, a plurality of operational data sets are received by a controller. The operational data sets include at least one indication of a performance anomaly. A plurality of predictive models are implemented by the controller to determine a plurality of potential root causes of the performance anomaly and a plurality of corresponding probabilities for each of the potential root causes. A consolidation model is generated for classifying the plurality of potential root causes and corresponding probabilities. The consolidation model is trained via a training data set to correlate the plurality of potential root causes to an actual root cause for the performance anomaly. The consolidation model is implemented by the controller to determine the actual root cause of the performance anomaly based on the plurality of potential root causes and corresponding probabilities.

Systems and methods for operating a power generating asset

A method for preventing a pitch bearing failure of a pitch system of a wind turbine includes monitoring, via at least one sensor, one or more electrical signals of a pitch motor of a pitch drive mechanism of the pitch system that drives a pitch bearing of the pitch system. The method also includes analyzing, via the controller, the one or more electrical signals of the pitch motor so as to remove noise and amplify outliers. Moreover, the method includes estimating bearing friction of the pitch bearing using the analyzed one or more electrical signals of the pitch motor. As such, the method includes implementing, via the controller, a control action when the estimated bearing friction of the pitch bearing indicates an anomaly in the pitch bearing.

System and method for preventing pitch bearing failures in a wind turbine using pitch motor signals

A method for detecting anomalies during operation of an asset to improve performance of the asset includes collecting, via a server, data relating to operation of the asset or a group of assets containing the asset. The data includes normal and abnormal asset behavior of the asset or the group of assets containing the asset. Further, the method includes automatically removing, via an iterative algorithm programmed in the server that utilizes one or more inputs or outputs of an anomaly detection analytic, portions of the data containing the abnormal asset behavior to form a dataset containing only the normal asset behavior. The method also includes training, via a computer-based model programmed in the server, the anomaly detection analytic using, at least, the dataset containing only the normal asset behavior. Moreover, the method includes applying, via the server, the anomaly detection analytic to the asset so as to monitor for anomalies during operation thereof.

System and method for training anomaly detection analytics to automatically remove outlier data

A method for detecting a fault in a direct current (DC) battery of a pitch system includes receiving, via a server, a plurality of voltage signals of the battery over at least one time period. The method also includes storing, via a database of the server, the plurality of voltage signals of the battery for the predetermined time period. Further, the method includes determining, via the server, a state of the battery as a function of the plurality of voltage signals. When the state of the battery is indicative of a battery fault, the method includes implementing a corrective action for the battery.

System and method for detecting battery faults in a pitch system of a wind turbine

A system and method for monitoring a pitch system of a wind turbine includes monitoring, via one or more first sensors, at least one electrical condition of the pitch system. The method also includes monitoring, via one or more second sensors, at least one mechanical condition of the pitch system. Further, the method includes receiving, via a controller communicatively coupled to the one or more first and second sensors, sensor signals representing the at least one electrical condition and the at least one mechanical condition of the pitch system. Thus, the method includes determining, via the controller, a bearing condition of a pitch bearing of the pitch system based on the at least one electrical condition and the at least one mechanical condition of the pitch system.

System and method for monitoring a wind turbine pitch bearing

A method for detecting damage in a bearing coupled to a rotating shaft of a rotary machine includes receiving one or more measurement signals from one or more first sensors for monitoring movement of the rotating shaft in one or more directions over a time period. The method also includes removing an effect of one or more environmental and/or operating conditions of the rotary machine from the one or more measurement signals over the time period. After removing, the method includes analyzing changes in the one or more measurement signals from the one or more first sensors, wherein changes in the one or more measurement signals above a predetermined threshold or of a certain magnitude are indicative of a damaged bearing. Moreover, the method includes implementing a corrective action when the changes in the one or more measurement signals are above the predetermined threshold.

Systems and methods for detecting damage in rotary machines

A method of correcting turbine underperformance includes calculating a power production curve using monitored data, detecting changes between the monitored data and a baseline power production curve, generating operability curves for paired operational variables from the monitored data, detecting changes between the operability curves and corresponding baseline operability curves, comparing the changes to a respective predetermined metric, and if the change exceeds the metric, providing feedback to a turbine control system identifying at least one of the paired operational variables for each paired variable in excess of the metric. A system and a non-transitory computer-readable medium are also disclosed.

System and method for detecting turbine underperformance and operation anomaly

A system and method are provided for operating and maintaining a wind turbine. Accordingly, a plurality of data inputs are received. The plurality of data inputs represent a plurality of monitored attributes of a component of the wind turbine. A consolidated risk index for the component is determined using the plurality of monitored attributes, and a range of potential risk indices is forecasted. A remaining-useful-life distribution is determined based on the damage potential and an end-of-life damage threshold. The wind turbine is shut down or idled if the remaining-useful-life distribution is below a shutdown threshold.

System and method for operating a wind turbine

A method for mitigating damage in a rotor blade of a plurality of rotor blades of a wind turbine includes receiving a plurality of acceleration signals from the plurality of the rotor blades in at least one direction. The method also includes generating a spectral density for each of the plurality of acceleration signals. Further, the method includes determining blade energies for each of the plurality of rotor blades based on the spectral densities for each of the plurality of acceleration signals for at least one predetermined frequency range. Moreover, the method includes comparing the blade energies to at least one of each other or a predetermined damage threshold. In addition, the method includes implementing a control action when one or more of the blade energies vary from each other by a predetermined amount or one or more of the blade energies exceed the predetermined damage threshold.

System and method for mitigating damage in a rotor blade of a wind turbine

A system includes a resonant sensor in contact with oil within a gearbox of a rotor system, such as a wind turbine, and one or more processors. The sensor includes electrodes and a sensing circuit that generates electrical stimuli having frequencies applied to the oil at different times during a life of the gearbox. The processors receive electrical signals from the resonant sensor representative of impedance responses of the oil to the electrical stimuli. The processors analyze the impedance responses and determine a concentration of a polar analyte in the oil at different times. The processors calculate a degradation value for the gearbox based on the concentration of the polar analyte. Responsive to the degradation value exceeding a designated threshold, the processors at least one of schedule maintenance for the rotor system, provide an alert to schedule maintenance, or prohibit operation of the rotor system until maintenance is performed.

Sensing system and method

A device and method for use in detecting anomalies in wind turbines is provided. The method includes monitoring data acquired by at least one sensor in a first wind turbine, wherein the data is calculated to produce a value for a predetermined amount of time, monitoring data acquired by at least one sensor in a grouping of wind turbines similar to the first wind turbine, wherein the monitored data corresponds to the monitored data of the first wind turbine and is combined for a predetermined amount of time, and comparing the monitored data of the first wind turbine with the monitored data of the grouping of wind turbines. The method also includes generating a sensor error if the monitored data of the first wind turbine deviates more than a predetermined amount from the monitored data of the grouping of wind turbines, and displaying the results of the comparison of the monitored data.

System and method for detecting anomalies in wind turbines

Growing community of inventors

Schenectady, NY, United States of America

John Joseph Mihok