基于非线性Wiener过程航空发动机性能退化预测

针对线性随机过程航空发动机剩余使用寿命预测精度不高的问题,提出一种漂移系数为指数形式的非线性Wiener过程发动机性能退化建模,进而预测航空发动机的剩余寿命。基于直接监测发动机性能退化数据,构建发动机性能退化模型,根据Wiener过程首达阈值时间的数学性质,推导出剩余寿命的概率分布。通过极大似然估计构建退化模型中未知参数的似然函数,利用遗传算法得到发动机总体模型参数的离线估计值。考虑到不同发动机个体间的差异性,采用贝叶斯公式,结合发动机的实时监测数据与总体模型参数的先验分布对模型中随机参数进行实时更新,从而对个体发动机的剩余寿命实时预测。最后,选择商用航空发动机仿真数据集(C-MAPSS)进行实验,结果表明：针对个体发动机基于非线性随机过程方法,实时更新非线性Wiener方法能够提高航空发动机循环中期剩余寿命预测的准确性,提供更加可靠的预防性维修决策。

Performance Degradation Prediction of Aero-Engine Based on Nonlinear Wiener Process

Aiming at the problem of low accuracy of in predicting the remaining useful life of aero-engine with linear Wiener process, a nonlinear Wiener process engine performance degradation model with drift coefficient in exponential form is proposed to predict the remaining life of aero-engine. Based on the direct monitoring of engine performance degradation data, the engine performance degradation model was constructed, and the probability distribution of remaining life was deduced according to the mathematical properties of the first threshold time of Wiener process. The likelihood function of unknown parameters in the regression model is constructed by maximum likelihood estimation, and the off-line estimation of the overall model parameters of the engine is obtained by genetic algorithm. Considering the differences among different engine individuals, the Bayesian formula is used to update the random parameters in the model in real time by combining the real-time monitoring data of the engine with the prior distribution of the overall model parameters, so as to update the residual life prediction of the individual engine in real time. Finally, the commercial aero-engine simulation data set (C-MAPSS) was selected for the experiment. The results showed that the real-time updating of nonlinear Wiener method based on the nonlinear random process method for individual engines could improve the accuracy of the prediction of the remaining life of aero-engines in the middle cycle and provide more reliable preventive maintenance decisions.