基于IPSO神经网络的风电机组主轴状态监测

Wind Turbine Spindle Condition Monitoring Based on Operational Data

风电机组主轴是叶轮和齿轮箱的连接部分,在机组传动链中具有传递转矩和能量的作用,因此对主轴进行状态监测关系到风电机组的稳定性。将改进粒子群算法(IPSO)与BP神经网络相结合构造主轴温度模型并进行预测。当主轴发生故障时,模型输入的观测向量发生异常变化,导致模型预测残差发生改变。为提高主轴异常预警的灵敏度和可靠性,文中采用基于莱依特准则的双滑动窗口对预测残差序列进行实时的统计分析,如果残差均值或标准差超出设定的故障报警阈值时,发出报警信息。

Wind turbine spindle is the connecting part of impeller and gearbox. Ithas the function of transmitting torque and energy in the transmission chain of the unit. It need to bear the bending moment and thrust of the wind wheel,so the failure rate of spindle is high. The spindle temperature model is established and used to predict by Improved Particle Swarm Optimization（ IPSO） and the back-propagation（ BP） neural network under the normal operating condition of the spindle. When the spindle fails,the observation vector of the model input changes obviously. If the residual mean or standard deviation exceeds the set fault alarm threshold,an alarm message will be issued.