US 11,835,030 B2
Methods and systems for predicting risk of observable damage in wind turbine gearbox components
Vijayant Kumar, Andover, MA (US); Nathan Bolander, Idaho Falls, ID (US); Gunther Auer, Irun (ES); Inigo Zalacain, Mutilva (ES); Mercedes Irujo, Pamplona (ES); and Enrique Iriarte, Sarriguren (ES)
Assigned to Sentient Science Corporation, Buffalo, NY (US); and Acciona Energia, Sarriguren (ES)
Appl. No. 17/420,064
Filed by SENTIENT SCIENCE CORPORATION, Buffalo, NY (US); and ACCIONA ENERGIA, Navarra (ES)
PCT Filed Dec. 31, 2019, PCT No. PCT/US2019/069140
§ 371(c)(1), (2) Date Jun. 30, 2021,
PCT Pub. No. WO2020/142542, PCT Pub. Date Jul. 9, 2020.
Claims priority of provisional application 62/786,817, filed on Dec. 31, 2018.
Prior Publication US 2022/0082090 A1, Mar. 17, 2022
Int. Cl. F03D 17/00 (2016.01); F16H 57/01 (2012.01)
CPC F03D 17/00 (2016.05) [F16H 57/01 (2013.01); F05B 2260/80 (2013.01); F05B 2260/83 (2013.01); F05B 2270/32 (2013.01); F05B 2270/321 (2013.01); F05B 2270/334 (2013.01); F05B 2270/335 (2013.01); F16H 2057/012 (2013.01)] 24 Claims
OG exemplary drawing
 
1. A method for determining a damage state of a wind turbine gearbox of a wind turbine, comprising:
producing a damage state diagnostic, comprising:
obtaining a measurement dataset from the wind turbine;
integrating field-operator-provided field intelligence into the measurement dataset;
normalizing the measurement dataset with respect to a known failure behavior for the wind turbine gearbox to produce a normalized measurement dataset;
combining the normalized measurement dataset with the known failure behavior to produce the damage state diagnostic;
producing a damage progression model for the wind turbine gearbox using operational data and a state transition function; and
combining the damage state diagnostic with the damage progression model using a hybrid prognostics model to produce a probability distribution for a current damage state estimate.