Recurrent neural networks for remaining useful life estimation

By F. Heimes. International Conference on Prognostics and Health Management, 2008

563 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Control and Systems Engineering

View Paper: https://www.semanticscholar.org/paper/2a0954cc53e3220bae63fe9b67dc15c528d9c164

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Control and Systems Engineering

Citations in the corpus

Temporal Convolutional Memory Networks for Remaining Useful Life Estimation of Industrial Machinery (2018, background): “The literature on RUL estimation includes sliding window approaches [2], hidden Markov model (HMM) based approaches [3] and recurrent neural network (RNN) based approaches [4].”
Remaining useful life predictions for turbofan engine degradation using semi-supervised deep architecture (2019, methodology): “information regarding RUL predictions [19,33].”
Remaining useful life estimation in prognostics using deep convolution neural networks (2018, methodology): “On the other hand, the constant UL value for the early period is widely used in the corresponding reearches [2,5,42] .”
Ensemble of data-driven prognostic algorithms for robust prediction of remaining useful life (2011, methodology): “In each case study, the ensemble approach combines RUL predictions from five popular data-driven prognostic algorithms, namely, a similaritybased interpolation (SBI) approach with RVM as the regression technique (RVM–SBI) [15,49], SBI with SVM (SVM–SBI) [47,15], SBI with the least-square exponential”
Deep Convolutional Neural Network Based Regression Approach for Estimation of Remaining Useful Life (2016, methodology): “Operating Conditions: Several literature [9,16,23], have shown that by plotting the 3 operating setting values, the data points are clustered into six different distinct clusters.”
Long Short-Term Memory Network for Remaining Useful Life estimation (2017, methodology): “To better model the Remaining Useful Life changes along with time, in [8] [13], a piece-wise linear RUL target function was proposed, as in Figure 5, which limits the maximum RUL to a constant value and then start linear degradation after a certain degree of usage.”
Machine Learning for Reliability Engineering and Safety Applications: Review of Current Status and Future Opportunities (2020, unknown): “RUL estimation [75]”
Machinery health prognostics: A systematic review from data acquisition to RUL prediction (2018, methodology): “[17] proposed a prognostic approach based on an RNN which was trained using time gradient calculations and extended KF.”
Remaining Useful Lifetime Prediction via Deep Domain Adaptation (2019, background): “As Heimes [53] has shown it is reasonable to estimate the RUL as a constant value when the engines operate in normal conditions.”
Multiobjective Deep Belief Networks Ensemble for Remaining Useful Life Estimation in Prognostics (2017, methodology): “13 compares the RMSE and scores over ten runs obtained by MODBNE, DBN without TW processing, and DBN with TW processing to the publicly available results achieved by DSR, SVM, RNN, comentropy-based fusion, particle filter, and SKF.”
A Bidirectional LSTM Prognostics Method Under Multiple Operational Conditions (2019, methodology): “In addition, a piecewise linear degradation model [38] is used to obtain the target output (i.”
Using Deep Learning-Based Approach to Predict Remaining Useful Life of Rotating Components (2018, background): “For example, recurrent neural networks [4], [5], Kalman filter [6]–[8], dynamic Bayesian networks [9], k-reliable decentralized prognosis [10], particle filter [11]–[15], and combined particle filter and neural networks [16].”