Residual life predictions for ball bearings based on self-organizing map and back propagation neural network methods

By R. Huang, L. Xi, Xinglin Li, C. Liu, Hai Qiu, Jay H. Lee. 2007

526 citations recorded by the source corpus.

Subfields: Control and Systems Engineering, Mechanical Engineering

View Paper: https://www.semanticscholar.org/paper/4fbb52dcf88c5986f661ad50f05c469334bde9bd

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

Citations in the corpus

Estimation of Bearing Remaining Useful Life Based on Multiscale Convolutional Neural Network (2019, unknown): “[14] proposed a SOM, which treated”
Remaining useful life estimation in prognostics using deep convolution neural networks (2018, methodology): “[16] utilized the traditional multi-layer perceptron (MLP) approach for modeling the remaining useful life of the laboratory-tested bearings, and reported the prediction results were superior to the reliability-based approaches.”
Prognostics and Health Management: A Review of Vibration Based Bearing and Gear Health Indicators (2018, methodology): “[92] used a self-organising map to derive the minimum quantisation error as a bearing health indicator.”
Bearing performance degradation assessment using locality preserving projections (2011, methodology): “Thus, a new feature named ‘‘power ratio of maximal defective frequency to mean’’ (PMM) (Huang et al., 2007) is used as follows:”
Multipoint Optimal Minimum Entropy Deconvolution and Convolution Fix: Application to vibration fault detection (2017, background): “Often these me thods are combined together [19, 8], and are often used in conjunction with machine learning as features to identify faults [3, 21, 22, 23].”
A comprehensive review of digital twin — part 1: modeling and twinning enabling technologies (2022, methodology): “Direct mapping approaches bypass health forecasting and directly map features (ML model input) to RUL (ML model output) using ML models such as standard feedforward neural networks (Huang et al. 2007; Tian 2012), deep CNN (Li et al.”
Deep Learning Based Approach for Bearing Fault Diagnosis (2017, methodology): “As one of the typical classical neural networks, the BP neural networks have been widely used in machinery fault diagnosis [22], [23].”
Accurate bearing remaining useful life prediction based on Weibull distribution and artificial neural network (2015, unknown): “[19] Data interpolation using SelfOrganizing – Longer prediction horizon – Requires training one BPNN for each historical dataset”
An artificial neural network method for remaining useful life prediction of equipment subject to condition monitoring (2009, background): “Artiﬁcial neural networks (ANNs) have been considered to be very promising tools for equipment health condition and RUL prediction due to their adaptability, nonlinearity, and arbitrary function approximation ability (Tian and Zuo 2009; Rojas 1996; Huang et al. 2007; Tse and Atherton 1999).”