基于SSAE和相似性匹配的航空发动机剩余寿命预测

Remaining useful life prediction of aeroengine based on SSAE and similarity matching

航空发动机作为高度复杂的热力机械,其剩余寿命(RUL)预测往往作为提高安全性和经济性的重要保障。为了提高航空发动机剩余寿命预测精度,提出一种基于堆栈稀疏自编码器(SSAE)及相似性匹配的剩余寿命预测方法。以Spearman秩相关系数(SRCC)作为适应度函数,利用遗传算法(GA)对融合参数候选集进行寻优;采用SSAE的结构融合最优参数集,生成特征融合指标;采用相似性匹配的方法在历史数据库内全局搜索最优匹配的历史轨迹,得到寿命预测结果;采用美国国家航空航天局(NASA)公布的C-MAPSS数据集验证该融合指标和方法的有效性。

As a highly complex thermal machinery,the prognosis of the remaining useful life(RUL)of an aero-engine is often used as an important guarantee to improve safety and economy.In order to increase the engine’s remaining usable life prediction accuracy,a strategy based on stacked sparse autoencoders(SSAE)and similarity matching is proposed in this study.Firstly,Spearman’s rank correlation coefficient(SRCC)is utilized as a fitness function and optimizes the candidate set of fusion parameters through a genetic algorithm(GA).The SSAE fuses the optimal parameter set in order to generate the feature comprehensive index.The results of the life prediction are then obtained by using the similarity matching approach to search the history database worldwide for the best matching trajectory.Finally,the C-MAPSS dataset published by the National Aeronautics and Space Administration(NASA)is obtained to verify the validity of the fusion index and method.