›› 2019, Vol. 25 ›› Issue (第7): 1611-1619.DOI: 10.13196/j.cims.2019.07.001
Next Articles
Online:
Published:
Supported by:
宋亚1,2,夏唐斌1,2+,郑宇1,2,卓鹏程1,2,潘尔顺1,2
基金资助:
Abstract: Accurately predicting the Remaining Useful Life (RUL) of turbofan engines has important significance for developing maintenance strategies and reducing maintenance costs.Aiming at the characteristics of large sample size and high dimension of condition monitoring data,a hybrid health condition prediction model integrating the advantages of Autoencoder and Bidirectional Long Short-Term Memory (BLSTM) was proposed to improve the prediction accuracy of RUL.Autoencoder was used as a feature extractor to compress monitoring data,and BLSTM was designed to capture the bidirectional long-range dependencies of features,thus a hybrid deep learning prediction model of RUL was constructed.Through testing with a baseline dataset,the results demonstrated that the proposed Autoencoder-BLSTM hybrid model had a better prediction accuracy than existing methods,such as Multi-Layer Perceptron (MLP),Support Vector Regression (SVR),Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM).The proposed model could provide strong support for the health management and maintenance strategy development of turbofan engines.
Key words: intelligent service technology, remaining useful life, autoencoder, bidirectional long short-term memory neural networks, deep learning, fault diagnosis, turbofan engine
摘要: 准确预测涡扇发动机的剩余使用寿命,对于合理制定维护策略,降低维护成本具有重要意义。针对发动机状态监测数据样本量大、维度高的特点,提出一种整合自编码神经网络(Autoencoder)和双向长短期记忆(BLSTM)神经网络优势的混合健康状态预测模型,优化涡扇发动机的剩余使用寿命预测。首先利用Autoencoder方法作为特征提取工具,对状态监测数据进行压缩,然后利用BLSTM方法捕捉特征双向长程依赖的特性,构建剩余使用寿命的混合深度学习预测模型。基于通用数据集开展测试比较,结果表明Autoencoder-BLSTM混合模型的预测精度优于现有多层感知机、支持向量回归、卷积神经网络和长短期记忆神经网络等方法,可有力支撑涡扇发动机的健康管理与运维决策。
关键词: 智能服务技术, 剩余使用寿命, 自编码神经网络, 双向长短期记忆神经网络, 深度学习, 故障诊断, 涡扇发动机
CLC Number:
TP183
V23
宋亚,夏唐斌,郑宇,卓鹏程,潘尔顺. 基于Autoencoder-BLSTM的涡扇发动机剩余寿命预测[J]. 计算机集成制造系统, 2019, 25(第7): 1611-1619.
0 / Recommend
Add to citation manager EndNote|Ris|BibTeX
URL: http://www.cims-journal.cn/EN/10.13196/j.cims.2019.07.001
http://www.cims-journal.cn/EN/Y2019/V25/I第7/1611