US 12,135,009 B2
Method for estimating remaining useful life of components of an operational wind turbine
Adrijan Ribaric, Buffalo, NY (US); Juan Gallego-Calderon, Buffalon, NY (US); and Mercedes Irujo Espinosa De Monteros, Navarra (ES)
Assigned to ACCIONA GENERACIÓN RENOVABLE, S.A., Navarra (ES); and SENTIENT SCIENCE CORPORATION, Buffalo, NY (US)
Appl. No. 17/600,436
Filed by ACCIONA GENERACIÓN RENOVABLE, S.A., Navarra (ES); and SENTIENT SCIENCE CORPORATION, Buffalo, NY (US)
PCT Filed Apr. 1, 2019, PCT No. PCT/EP2019/058207
§ 371(c)(1), (2) Date Sep. 30, 2021,
PCT Pub. No. WO2020/200421, PCT Pub. Date Oct. 8, 2020.
Prior Publication US 2022/0178353 A1, Jun. 9, 2022
Int. Cl. F03D 17/00 (2016.01); F03D 7/02 (2006.01)
CPC F03D 17/00 (2016.05) [F03D 7/0292 (2013.01); F05B 2260/84 (2013.01); F05B 2270/332 (2013.01)] 12 Claims
OG exemplary drawing
 
1. A method for estimating remaining useful life of components of an operational wind turbine model executed by computational elements, wherein said computational elements are communicatively coupled to the operational wind turbine which comprises a data acquisition module configured to measure real historical data of said operational wind turbine and an additional state detection unit to identify historical states of operation, wherein said method comprises:
extracting historical data from the data acquisition module at a chosen time interval, said data comprising at least wind speed, blade pitch position and rotor speed;
identifying operational states of the wind turbine using the state detection unit for each chosen time interval, said operational states comprising at least Run, Idle, and Transition which in turn comprises: Start up, Normal Stop, and Emergency Stop;
validating the identified operational states with the data extracted from the data acquisition module at each time interval, identifying and discarding uncertain data that do not match;
identifying a number of transitory events comprising the number of times the wind turbine has changed states,
identifying a prevailing operational state comprising the state at which the longest amount of time said wind turbine has spent over the chosen time interval thereof;
identifying wind condition, said wind condition comprising at least mean wind speed and turbulence intensity at the chosen time interval;
repeat previous steps for multiple time intervals,
wherein the method further comprises performing multiple simulations for the multiple time intervals chosen to estimate a fatigue equivalent load, said simulations consisting of obtaining the loads for the wind turbine model corresponding to wind condition for:
the prevailing operational state identified and duration thereof at each time interval, and
the transitory events identified at each time interval thereof.