Learning of physical health timestep using the LSTM network for remaining useful life estimation

Bae J.; Xi Z.

首页> 外文期刊>Reliability engineering & system safety >Learning of physical health timestep using the LSTM network for remaining useful life estimation

【24h】

Learning of physical health timestep using the LSTM network for remaining useful life estimation

机译：Learning of physical health timestep using the LSTM network for remaining useful life estimation

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相关主题

摘要

? 2022Remaining useful life (RUL) estimation is a key task in prognostics and health management. Due to the complexity of engineering systems, data-driven methods for the RUL estimation have been widely applied and developed through machine learning and artificial intelligence techniques. To enhance performance of these methods, improving data quality is as much important as developing sophisticated algorithms. This paper proposes learning of physical health timestep (PHT) using the long short-term memory (LSTM) network to replace the labeled timestep (LT) of a test unit. While the LT mainly records the timestep as an operation or observation index of the unit, the PHT estimates the unit's physical health from available sensory measurements. With the PHT, RUL estimation can be more accurate considering the unit's loading history. Effectiveness of the proposed methodology has been verified through experiments on lithium-ion battery and C-MAPSS engine datasets.

著录项

来源
《Reliability engineering & system safety》 |2022年第10期|108717.1-108717.13|共13页
作者
Bae J.; Xi Z.;
展开▼
作者单位

Rutgers University New Brunswick;

展开▼
收录信息美国《科学引文索引》(SCI);美国《工程索引》(EI);
原文格式 PDF
正文语种英语
中图分类
关键词
Data quality; Long short-term memory neural network; Physical health timestep; Prognostics and health management; Remaining useful life;

Learning of physical health timestep using the LSTM network for remaining useful life estimation

摘要

著录项

相关主题

期刊订阅