基于残差NLSTM网络和注意力机制的航空发动机剩余使用寿命预测  

Prediction of remaining useful life of aero-engine based on residual NLSTM neural network and attention mechanism

作　　者：陈保家 郭凯敏 陈法法 肖文荣[1] 李公法 陶波[3] CHEN Baojia;GUO Kaimin;CHEN Fafa;XIAO Wenrong;LI Gongfa;TAO Bo(Hubei Key Laboratory of Hydroelectic Machinery Design and Maintenance,China Three Gorges University,Yichang Hubei 443002,China;State Key Laboratory of Mechanical Transmissions,Chongqing University,Chongqing 400030,China;Key Laboratory of Metallurgical Equipment and Control Units,Ministry of Education,Wuhan University of Science and Technology,Wuhan 430081,China)

机构地区：[1]三峡大学水电机械设备设计与维护湖北省重点实验室,湖北宜昌443002 [2]重庆大学机械传动国家重点实验室,重庆400030 [3]武汉科技大学冶金装备及其控制省部共建教育部重点实验室,武汉430081

出　　处：《航空动力学报》2023年第5期1176-1184,共9页Journal of Aerospace Power

基　　金：国家自然科学基金(51975324,52075292);机械传动国家重点实验室开放基金(SKLMT-MSKFKT-202020);水电机械设备设计与维护湖北省重点实验室(三峡大学)开放基金(2020KJX02,2021KJX02,2021KJX13);武汉科技大学冶金装备及其控制教育部重点实验室开放基金(MECOMF2021B04)。

摘　　要：针对长短期记忆(LSTM)网络对于多维数据特征识别和提取上存在不足的问题,在其改进模型嵌套式长短期记忆(NLSTM)网络的基础上,提出了一种基于注意力机制和残差NLSTM网络的剩余使用寿命预测方法。该方法将双层NLSTM网络代替残差块中的主网络,保留捷径连接中的卷积神经网络结构,既能充分提取时序特征又能保证有用数据在网络层中的跳层传递,并融入注意力机制构建多层残差网络,注意力机制的使用能够选择出对预测结果有重要影响的信息,有效提高预测的准确率。在航空发动机退化实验数据集上进行实验分析,结果表明:所述方法能有效建立监测数据与发动机健康状态之间的关系,剩余使用寿命预测误差较未改进残差结构方法平均降低10.8%,比未融入注意力机制方法平均降低18.9%,有效提高了预测精度。The remaining useful life prediction method based on attention mechanism and residual nested long-short-term memory(NLSTM)neural network was employed to address the shortcomings of traditional long-short-term memory(LSTM)neural network in the recognition and extraction of multi-dimensional data features.Two NLSTM neural network layers were used to replace the main structure of the residual block,and the shortcut connection of the one-dimensional convolutional network in the residual block was retained,which can fully extract the temporal feature and use the jump layer to transfer useful data in the network layer.The method also added the attention mechanism to construct multilayer network,and the important information influencing the result of prediction can be chosen to improve the prediction accuracy by the attention mechanism.The proposed method was verified by experiments in the aero-engines degradation dataset.The results showed that the method can effectively establish the relationship between the monitoring data and the engines health.The prediction error was reduced by 10.8%compared with the method without residual structure and reduced 18.9%compared with the method without attention mechanism,which improved the prediction accuracy effectively.

关 键 词：残差网络 剩余使用寿命 注意力机制 预测模型 嵌套式长短期记忆神经网络 

分 类 号：V240.2[航空宇航科学与技术—飞行器设计]