Prediction Interval Estimation of Aeroengine Remaining Useful Life Based on Bidirectional Long Short-Term Memory Network

预言 计算机科学 聚类分析 区间(图论) 数据挖掘 航空发动机 期限(时间) 模糊逻辑 钥匙(锁) 人工神经网络 人工智能 可靠性工程 工程类 数学 机械工程 组合数学 物理 量子力学 计算机安全
作者
Chuang Chen,Ningyun Lu,Bin Jiang,Yin Xing,Zheng Zhu
出处
期刊:IEEE Transactions on Instrumentation and Measurement [Institute of Electrical and Electronics Engineers]
卷期号:70: 1-13 被引量:59
标识
DOI:10.1109/tim.2021.3126006
摘要

Reliable and accurate aero-engine remaining useful life (RUL) prediction plays a key role in aero-engine prognostics and health management (PHM) system. However, due to the epistemic uncertainties associated with aero-engine systems, prediction errors are unavoidable and sometimes significant in traditional deterministic point prediction methods. To improve the accuracy and credibility of RUL prediction, a novel prediction interval (PI) estimation method is proposed to quantify the uncertainties in RUL prediction. The proposed method involves the data clustering, mathematical statistical analysis and deep learning techniques, and is achieved through offline and online phases. In the offline phase, an enhanced fuzzy c-means algorithm (FCM) is proposed to divide the aero-engine health status into several discrete states. After labeling the health state of each sampling point, PIs are computed for them. This step is achieved by the empirical distributions of errors associated with all instances belonging to the health state under consideration. In the online phase, a bidirectional long short-term memory (Bi-LSTM) network is employed to estimate the boundaries of point prediction, and thus the PI of aero-engine RUL is generated. The aero-engine degradation dataset from NASA is used to validate the proposed RUL PI estimation method. The results obtained indicate that the proposed method is a promising tool for providing reliable aero-engine RUL interval estimates, which can inform maintenance-related decisions.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
1秒前
ppppp完成签到,获得积分10
2秒前
是然宝啊完成签到,获得积分10
3秒前
鄂百川发布了新的文献求助10
4秒前
自然紫山完成签到,获得积分10
5秒前
维尼发布了新的文献求助10
6秒前
Lowman完成签到,获得积分10
7秒前
wanci应助houchengru采纳,获得50
7秒前
苏卿应助迅速的鹤采纳,获得10
8秒前
kevindm完成签到,获得积分10
8秒前
mjl完成签到,获得积分20
8秒前
JM完成签到,获得积分10
9秒前
老实黄蜂应助Agoni采纳,获得10
10秒前
10秒前
科研通AI2S应助闪闪的山槐采纳,获得10
12秒前
努力发一区完成签到 ,获得积分10
12秒前
充电宝应助小于采纳,获得10
13秒前
饱满的海秋完成签到,获得积分10
13秒前
一丢丢完成签到,获得积分10
13秒前
失眠的煎饼完成签到,获得积分20
13秒前
青耕完成签到 ,获得积分10
14秒前
orixero应助yangxin614采纳,获得10
14秒前
医痞子发布了新的文献求助10
15秒前
慕青应助小酒窝采纳,获得10
15秒前
科研通AI2S应助小鱼采纳,获得10
17秒前
17秒前
17秒前
科研完成签到,获得积分10
18秒前
丘比特应助勇往直前采纳,获得10
18秒前
科研通AI2S应助Agoni采纳,获得10
18秒前
华仔应助ddffgz采纳,获得10
19秒前
受伤凌蝶完成签到,获得积分10
20秒前
Maneuvers完成签到,获得积分10
20秒前
21秒前
21秒前
JamesPei应助达达利亚采纳,获得10
23秒前
23秒前
66发布了新的文献求助10
24秒前
文献文献文献完成签到,获得积分10
25秒前
26秒前
高分求助中
Evolution 10000
Sustainability in Tides Chemistry 2800
юрские динозавры восточного забайкалья 800
English Wealden Fossils 700
A new species of Coccus (Homoptera: Coccoidea) from Malawi 500
A new species of Velataspis (Hemiptera Coccoidea Diaspididae) from tea in Assam 500
Diagnostic immunohistochemistry : theranostic and genomic applications 6th Edition 500
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3156020
求助须知:如何正确求助?哪些是违规求助? 2807409
关于积分的说明 7872961
捐赠科研通 2465760
什么是DOI,文献DOI怎么找? 1312375
科研通“疑难数据库(出版商)”最低求助积分说明 630083
版权声明 601905