4.7 Article

Remaining Useful Life Prognosis Based on Ensemble Long Short-Term Memory Neural Network

出版社

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIM.2020.3031113

关键词

Bayesian inference algorithm (BIA); ensemble learning (EL); ensemble long short-term memory neural network (ELSTMNN); remaining useful life (RUL) prognosis

资金

  1. National Key Research and Development Program of China [2018YFB1702300]
  2. National Natural Science Foundation of China [51875225]
  3. Research Grants Council of the HKSAR Government [R5020-18]
  4. Innovation and Technology Commission of the HKSAR Government [K-BBY1]

向作者/读者索取更多资源

In this article, a novel ensemble long short-term memory neural network (ELSTMNN) model is proposed for RUL prediction using a Bayesian inference algorithm to integrate multiple predictions of LSTMNNs. The effectiveness and competitive performance of the ELSTMNN-based RUL prognosis method are validated on two different turbofan engine data sets.
Remaining useful life (RUL) prognosis is of great significance to improve the reliability, availability, and maintenance cost of an industrial equipment. Traditional machine learning method is not fit for dealing with time series signals and has low generalization and stability in prognostic. In this article, a novel ensemble long short-term memory neural network (ELSTMNN) model for RUL prediction is proposed to enhance the RUL prognosis accuracy and improve the adaptive and generalization abilities under different prognostic scenarios. The ELSTMNN contains a series of long short-term memory neural networks (LSTMNNs), each of which is trained on a unique set of historical data. A novel ensemble method is first proposed using Bayesian inference algorithm to integrate multiple predictions of the LSTMNNs for the optimal RUL estimation. The effectiveness of the ELSTMNN-based RUL prognosis method is validated using two characteristically different turbofan engine data sets. The experimental results show a competitive performance of the ELSTMNN in comparison with other prognostic methods.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据