Residual life predictions from vibration-based degradation signals: a neural network approach

By N. Gebraeel, Mark A. Lawley, Richard Liu, Vijay Parmeshwaran. IEEE transactions on industrial electronics (1982. Print), 2004

547 citations recorded by the source corpus.

Subfields: Control and Systems Engineering, Mechanical Engineering, Mechanics of Materials

View Paper: https://www.semanticscholar.org/paper/8d9596c94c71f36d33abc4b5ae2a409ddd7d1145

How researchers see this paper

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

In Control and Systems Engineering

In Mechanical Engineering

In Mechanics of Materials

Citations in the corpus

Residual life predictions for ball bearings based on self-organizing map and back propagation neural network methods (2007, methodology): “Representation of the WAFT approach [5].”
Stochastic modelling and analysis of degradation for highly reliable products (2015, methodology): “Machine learning methods include artificial neural networks [89], support vector machines [90] and Bayesian networks [91].”
An artificial neural network method for remaining useful life prediction of equipment subject to condition monitoring (2009, methodology): “Gebraeel et al. developed ball bearing remaining life prediction methods based on feedfor-ward neural networks (Gebraeel et al. 2004; Gebraeel and Lawley 2008).”
Enabling Health Monitoring Approach Based on Vibration Data for Accurate Prognostics (2015, background): “More precisely, predicting the behavior of critical machinery, such as bearings [3] and cutting tools [4], is a challenging task while handling raw vibration data due to its inherent nonlinearity.”
Direct Remaining Useful Life Estimation Based on Support Vector Regression (2017, background): “There exist several data-driven approaches such as artificial neural networks [4]–[8], autoregressive models [9], hidden Markov models [10], Bayesian networks [11], and stochastic processes [12]–[14].”
Machine Remaining Useful Life Prediction via an Attention-Based Deep Learning Approach (2021, unknown): “Afterextracting someinformativefeatures,theconventionalmachinelearning algorithms,suchasartiﬁcialneuralnetwork[12],[13],ex-tremelearningmachine(ELM)[14],SVM[15],[16],neural networks[17],andrandomforest(RF)[18],canbeemployed topredicttheRUL.”
Remaining useful life estimation based on nonlinear feature reduction and support vector regression (2013, methodology): “[6] used the Feedforward Neural Networks (FFNNs) to project the degradation by computing exponential parameters that give the best exponential fit.”
A Bidirectional LSTM Prognostics Method Under Multiple Operational Conditions (2019, background): “Overall, general AI techniques include the support vector machine [12], artificial neural networks (ANNs) [16]–[18], etc.”
Cloud-enabled prognosis for manufacturing (2015, methodology): “Other prognosis techniques for manufacturing processes include decision trees [99], genetic algorithms [100], and c-means clustering [101].”
Estimation of Bearing Remaining Useful Life Based on Multiscale Convolutional Neural Network (2019, methodology): “[13] built the data-driven model and estimated bearing RUL.”
Remaining Useful Life Prediction Based on a Double-Convolutional Neural Network Architecture (2019, methodology): “Support vector regression (SVR) [12] and artiﬁ-cial neural network (ANN) [13] are two widely used regression methods.”
An Improved Exponential Model for Predicting Remaining Useful Life of Rolling Element Bearings (2015, methodology): “developed an artificial neural network-based method to predict the RUL of bearings [7].”
Machinery health prognostics: A systematic review from data acquisition to RUL prediction (2018, methodology): “The AI techniques were often combined with random coefficient models in hybrid approaches [23,117,360,361].”