Independent monitoring system for a wind turbine
The invention relates to a system for monitoring wind turbine components including an independent data processing environment adapted to: receive a first category of data input related to operation of the wind turbine, process the received data input by one or more component specific monitoring algorithms adapted to establish an estimated component value related to a component to be monitored based on received first category data input having at least indirectly impact on the component, wherein the component specific monitoring algorithm is adapted to establish a component residual as the difference between the estimated component value and received first category of data input of the component to be monitored, and wherein the component specific monitoring algorithm furthermore is adapted to establish a component specific health value of the component to be monitored based on the established residual and put the health value at disposal for data processors outside the environment.
1. A system for monitoring of wind turbine components, wherein the system comprises:
a data processing environment external to a wind turbine; and
a wind turbine component to communicate with a data processor of the wind turbine,
wherein the data processing environment is adapted to:
receive, using an environment data interface, sensor data that are monitoring components of the wind turbine,
process the received sensor data using one or more component specific monitoring algorithms which have been developed at least partly based on results of simulation of the wind turbine components to be monitored,
wherein the one or more component specific monitoring algorithms estimates a component value related to one of the wind turbine components to be monitored based on received sensor data having at least indirectly an impact on the component, wherein the estimated component value refers to an estimated value of one of the parameters associated with the component,
wherein the one or more component specific monitoring algorithms estimates a component residual as the difference between the estimated component value and received sensor data of the one of the wind turbine components to be monitored, and
wherein the one or more component specific monitoring algorithms estimates a component specific health value of the one of the wind turbine components to be monitored based on the estimated component residual, and
the environment data interface communicates the estimated component specific health value to the data processor of the wind turbine, a monitoring system, and/or a data storage system, wherein
the environment data interface receives a failure rate of the one of the wind turbine components to be monitored, and
the one or more component specific monitoring algorithms updates the component specific health value based on the received failure rate and the estimated component specific health value.
2. The system according to claim 1 , wherein the weight of the received failure rate information is dynamic so that if a pattern in the received sensor data is recognised as a pattern that has previously lead to derate or shut down of the wind turbine, the updated component specific health value value is determined solely based on the received failure rate information.
3. The system according to claim 1 , wherein the updated component specific health value is determined solely based on the received failure rate information if from the received failure rate information it is estimated that based on comparison with the received sensor data, the failure rate of the wind turbine component to be monitored is 50% or above.
4. The system according to claim 1 , wherein the one or more component specific monitoring algorithms comprises a component specific residual scale established based on the results of the simulations of the wind turbine components to be monitored or based on historic data acquired relating to the wind turbine components to be monitored.
5. The system according to claim 1 , wherein the component specific health value is established by comparing the residual to a component specific residual scale.
6. The system according to claim 1 , wherein the estimated component specific health value is decreased if the residual changes between a plurality of executions of the one or more component specific monitoring algorithms.
7. The system according to claim 1 , wherein the estimated component specific health value of the wind turbine component is converted to a health status of the wind turbine component wherein the health status is established based on a plurality of sub-ranges in the range of possible health values of the wind turbine component.
8. The system according to claim 1 , wherein the estimated component specific health value is a value in the range between X-X and X/1, wherein immediate action is required if the estimated component specific health value is in the sub-range of X-X and X/4, wherein action is required if the estimated component specific health value is in the sub-range of X/4 and X/2, and wherein no action is required if the estimated component specific health value is in the sub-range of X/2 and X/1.
9. The system according to claim 1 , wherein the data processing environment operates parallel to and independent of existing monitoring and control systems of the wind turbine.
10. The system according to claim 1 , wherein the data processing environment is a cloud based environment.
11. The system according to claim 1 , wherein algorithms of the environment data interface and the one or more component specific monitoring algorithms are executed by the same data processor.
12. The system according to claim 1 , wherein the environment data interface facilitates communication of the estimated component specific health value, component specific health status or alarms established based on the estimated component specific health value to a data receiver external to the data processing environment.
13. The system according to claim 1 , wherein the environment data interface facilitates providing control input to the data processor dependent on the component specific health status.
14. The system according to claim 1 , wherein the sensor data is received from existing sensors of the wind turbine or from retrofitted sensors.
15. The system according to claim 1 , wherein one or more data input of the received sensor data is used for establishing one other data input of the received sensor data.
16. The system according to claim 1 , wherein the received failure rate information is obtained from a database located on an external data storage.
17. The system according to claim 1 , wherein the estimated component residual is input to the data processor of the wind turbine for optimized control, and to a display for use in predictive maintenance and for updating in a database, reliability information of the one of the wind turbine components to be monitored or any combination thereof.
18. A method of estimating a health value for a specific wind turbine component, the method comprising the steps of:
by a data processing environment external to a wind turbine and the wind turbine component communicating with a data processor of the wind turbine to:
receive, from an environment data interface of the data processing environment, sensor data that monitors components of the wind turbine, and
process the received sensor data by one or more component specific monitoring algorithms, the one or more component specific monitoring algorithms having been developed at least partly based on results of simulation of the wind turbine components to be monitored, wherein the one or more component specific monitoring algorithm is configured to:
estimate a component value related to one of the wind turbine components to be monitored based on received sensor data having at least indirectly an impact on the wind turbine component, wherein the estimated component value refers to an estimated value of one of the parameters associated with the component,
estimate a component residual as the difference between the estimated component value and received sensor data of the wind turbine component, and wherein
the one or more component specific monitoring algorithms estimates a component specific health value of the wind turbine component based on the estimated component residual,
the environment data interface communicates the estimated component specific health value to the data processor of the wind turbine, a monitoring system, and/or a data storage system,
the environment data interface receives a failure rate of the one of the wind turbine components to be monitored, and
the one or more component specific monitoring algorithms updates the component specific health value based on the received failure rate and the estimated component specific health value.