Method and system for performing condition monitoring of wind turbine components
A technique for performing condition monitoring of a plurality of components of a plurality of wind turbines is disclosed. The technique includes, for each of the plurality of wind turbines, measuring at least one time-series electrical output signal of the wind turbine generator, each time-series electrical output signal representing an aggregate of a plurality of subset signals. Such condition monitoring further includes mathematically extracting one or more such subset signals from the at least one time-series electrical output signal of the generator, and associating one or more such subset signals with one or more wind turbine components. A fault threshold value for each such one or more subset signals may be determined, and the one or more such subset signals are compared to such fault threshold value. Based on such association and comparison, the condition of such a wind turbine component of the plurality of wind turbines is determined.
1 . A method for performing condition monitoring of a plurality of components of a plurality of wind turbines, the method comprising:
for each of the plurality of wind turbines, measuring, using a sensing device, at least one time-series electrical output signal of a generator of the wind turbine, each time-series electrical output signal representing an aggregate of a plurality of subset signals;
sampling the at least one time series electrical output signal to generate sampled values, and extracting one or more such subset signals from the at least one time-series electrical output signal of the generator based on the sampled values;
associating one or more of the plurality of subset signals with one or more wind turbine components, wherein associating one or more subset signals with one or more wind turbine components includes calculating at least one of a product and a ratio between a frequency of a subset signal and a measure of physical motion of one or more moving elements within a drivetrain of the wind turbine;
comparing the one or more such subset signals to fault criteria, wherein the fault criteria comprises a fault threshold level and at least one mean historical value for each of the one or more such subset signals, wherein the comparing includes generating a first comparison value based on a first comparison of at least one of the one or more such subset signals to the at least one mean historical value, and a second comparison value based on a second comparison of the first value and the fault threshold level;
determining a condition of such at least one wind turbine component of the plurality of wind turbines based on the second comparison value including
determining that the second comparison value meets the corresponding fault threshold level; and
in response to determining that the second value meets the corresponding fault threshold level, outputting an alert comprising at least one of a control signal and a user notification.
2 . The method according to claim 1 wherein the alert is the control signal, and wherein the control signal modifies at least one operating condition of the wind turbine to reduce the at least one time-series electrical output signal.
3 . The method according to claim 1 wherein the alert is the user notification, and wherein the user notification is an alarm notification.
4 . A condition monitoring system for a wind turbine, the condition monitoring system operationally coupled to a plurality of wind turbines in a wind farm, the condition monitoring system is configured to:
for each wind turbine of the plurality of wind turbines, measure, using a sensing device, at least one time-series electrical output signal of a generator of the wind turbine, each time-series electrical output signal representing an aggregate of a plurality of subset signals;
sample the at least one time-series electrical output signal to generate sampled values, and extract one or more such subset signals from the at least one time-series electrical output signal of the generator based on the sampled values;
associate one or more of the plurality of subset signals with one or more wind turbine components, wherein associating one or more subset signals with one or more wind turbine components, includes calculating at least one of a product and a ratio between a frequency of a subset signal and a measure of physical motion of one or more moving elements within a drivetrain of the wind turbine;
compare the one or more such subset signals to fault criteria, wherein the fault criteria comprises a fault threshold level and at least one mean historical value for each of the one or more such subset signals, wherein comparison includes a generation of a first comparison value based on a first comparison of at least one of the one or more such subset signals to the at least one mean historical value, and a second comparison value based on a second comparison of the first value and the fault threshold level;
determine a condition of such at least one wind turbine component of the plurality of wind turbines based on the second comp value including a determination that the second comparison value meets the corresponding fault threshold level; and
in response to the determination that the second value meets the corresponding fault threshold level, output an alert comprising at least one of a control signal and a user notification.
5 . The system according to claim 4 wherein the alert is the control signal, and wherein the control signal modifies at least one operating condition of the wind turbine to reduce the at least one time-series electrical output signal.
6 . The system according to claim 4 wherein the alert is the user notification, and wherein the user notification is an alarm notification.