中国邮电高校学报(英文) ›› 2020, Vol. 27 ›› Issue (4): 26-33.doi: 10.19682/j.cnki.1005-8885.2020.0034

• Artificial Intelligence • 上一篇    下一篇

Independently recurrent neural network for remaining useful life estimation

王锴烨 崔绍华 许方敏 赵成林   

  1. 1. 北京邮电大学
    2. 中国石油技术开发公司
    3. 北京市海淀区西土城路10号北京邮电大学科研楼618
  • 收稿日期:2018-06-04 修回日期:2020-08-18 出版日期:2020-08-31 发布日期:2020-08-31
  • 通讯作者: 王锴烨 E-mail:wangky@bupt.edu.cn

Independently recurrent neural network for remaining useful life estimation

Wang Kaiye, Cui Shaohua, Xu Fangmin, Zhao Chenglin   

  • Received:2018-06-04 Revised:2020-08-18 Online:2020-08-31 Published:2020-08-31
  • Contact: Wang Kaiye E-mail:wangky@bupt.edu.cn

摘要:

In the industrial fields, the mechanical equipment will inevitably wear out in the process of operation. With the accumulation of losses, the probability of equipment failure is increasing. Therefore, if the remaining useful life (RUL) of the equipment can be accurately predicted, the equipment can be maintained in time to avoid the downtime caused by equipment failure and greatly improve the production efficiency of enterprises. This paper aims to use independently recurrent neural network (IndRNN) to learn health degradation of turbofan engine and make accurate predictions of its RUL, which not only effectively solves the problem of gradient explosion and vanishing, but also increases the interpretability of neural networks. IndRNN can be used to process longer time series which matches the scene with high frequency sampling sensor in industrial practical applications. The results demonstrate that IndRNN for RUL estimation significantly outperforms traditional approaches, as well as convolutional neural network (CNN) and long short-term memory network (LSTM) for RUL estimation.

关键词:

multivariate time series analysis, independent recurrent neural network, remaining useful life estimation, prognostic and health management

Abstract: In the industrial fields, the mechanical equipment will inevitably wear out in the process of operation. With the accumulation of losses, the probability of equipment failure is increasing. Therefore, if the remaining useful life (RUL) of the equipment can be accurately predicted, the equipment can be maintained in time to avoid the downtime caused by equipment failure and greatly improve the production efficiency of enterprises. This paper aims to use independently recurrent neural network (IndRNN) to learn health degradation of turbofan engine and make accurate predictions of its RUL, which not only effectively solves the problem of gradient explosion and vanishing, but also increases the interpretability of neural networks. IndRNN can be used to process longer time series which matches the scene with high frequency sampling sensor in industrial practical applications. The results demonstrate that IndRNN for RUL estimation significantly outperforms traditional approaches, as well as convolutional neural network (CNN) and long short-term memory network (LSTM) for RUL estimation.

Key words: multivariate time series analysis, independent recurrent neural network, remaining useful life estimation, prognostic and health management