CAJ | 학술논문

针对风电机组传动链故障识别由风电场制定合理维修策略可减少停机时间、降低维修费用问题，将引力搜索算法用于 BP 神经网络初始权值及阈值优化，提出基于引力搜索神经网络的风电机组传动链故障识别方法。算例结果表明，所提方法精度较 BP 神经网络高，能准确识别齿轮磨损、齿轮断齿、轴承松动等风电机组传动链典型故障，验证该方法的有效性。
침대풍전궤조전동련고장식별유풍전장제정합리유수책략가감소정궤시간、강저유수비용문제，장인력수색산법용우 BP 신경망락초시권치급역치우화，제출기우인력수색신경망락적풍전궤조전동련고장식별방법。산례결과표명，소제방법정도교 BP 신경망락고，능준학식별치륜마손、치륜단치、축승송동등풍전궤조전동련전형고장，험증해방법적유효성。
Fault identification of wind turbine drivetrain is the key for wind electric power plants to work out appropriate maintenance strategies to reduce downtime and maintenance cost,and also is one of the highly discussed issues and difficulties in recent research.Here,gravitational search algorithm was applied in the optimization of initial weights and thresholds for BP neural network,a fault identification method for wind turbine drivetrain using BP neural network based on gravitational search algorithm was proposed.The results of examples showed that the proposed method can be used to precisely identify three typical wind turbine drivetrain faults induding gear wear,tooth breaking and bearing looseness,with higher average accuracy than that of BP neural network.So,the effectiveness of the proposed method was verified.