Electric Locomotive Bearing Fault Diagnosis Using a Novel Convolutional Deep Belief Network

By Haidong Shao, Hongkai Jiang, Haizhou Zhang, Tianchen Liang. IEEE transactions on industrial electronics (1982. Print), 2018

434 citations recorded by the source corpus.

Subfields: Control and Systems Engineering, Mechanical Engineering

View Paper: https://www.semanticscholar.org/paper/b31241b7a939fc9f8bd9fe40d430e8f4f2444bb7

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

Intelligent fault diagnosis of machinery using digital twin-assisted deep transfer learning (2021, background): “…raw data and accurately establishing nonlinear mapping of different health conditions, popular DL techniques including deep belief network (DBN) [8], stacked auto-encoder (SAE) [9], and convolutional neural network (CNN) [10] have attracted increasing attention and become the very popular tools…”
Deep-Convolution-Based LSTM Network for Remaining Useful Life Prediction (2021, background): “Learning representations of vibration time–frequency features with convolutional operation have shown clear advantages over “hand-crafted” features in bearing’s diagnosis and prognosis [28], [29].”
Machine Learning and Deep Learning Algorithms for Bearing Fault Diagnostics - A Comprehensive Review (2019, methodology): “In [140], a convolutional DBN constructed with convolutional RBMs is applied on the locomotive bearing vibration, where n auto-encoder is firstly used to compress the data and re uce its dimension.”
Understanding and Learning Discriminant Features based on Multiattention 1DCNN for Wheelset Bearing Fault Diagnosis (2020, background): “Therefore, denoising autoencoder [9], deep belief network [10], and convolutional neural network (CNN) [10] have been studied for rolling bearing fault diagnosis.”
Deep Transfer Learning for Bearing Fault Diagnosis: A Systematic Review Since 2016 (2023, background): “The typical deep learning models include but are not limited to the convolutional neural network (CNN) [14], [36], [37], recurrent neural network [38], restricted Boltzmann machine [39], autoencoder [40], [41], deep belief network [42], and their variants.”
Deep Learning Algorithms for Bearing Fault Diagnosticsx—A Comprehensive Review (2019, methodology): “In [141], a convolutional DBN constructed with convolutional RBMs is applied on the locomotive be ring vibration, where an auto-encoder is firstly used to compress the data and reduce its dimension.”
Online Fault Diagnosis Method Based on Transfer Convolutional Neural Networks (2020, neutral): “[21]”
An Improved Quantum-Inspired Differential Evolution Algorithm for Deep Belief Network (2020, methodology): “Shao et al. [17] presented an electric locomotive bearing fault diagnosis method using DBN. Zhao et al. [18] presented a fault diagnosis method using principal component analysis (PCA) and a broad learning system.”
Intelligent Fault Diagnosis of Rotor-Bearing System Under Varying Working Conditions With Modified Transfer Convolutional Neural Network and Thermal Images (2020, methodology): “ROTATING machinery plays an increasing role in electric power, manufacturing, transportation, and other industries [1], [2].”
Deep Transfer Network with Joint Distribution Adaptation: A New Intelligent Fault Diagnosis Framework for Industry Application (2018, background): “To tackle these issues, an adaptive feature learning based diagnostic framework with deep learning technology is emerging in the second stage [11]-[14].”
WaveletKernelNet: An Interpretable Deep Neural Network for Industrial Intelligent Diagnosis (2019, background): “There are many kinds of neural network structures in deep learning, such as deep belief network (DBN) [9], [10], auto-encoder (AE) [11], [12] and convolutional neural network (CNN) [13], [14].”
A Motor Current Signal-Based Bearing Fault Diagnosis Using Deep Learning and Information Fusion (2020, background): “With the ability of automatically learning multiple levels of data abstraction, when applied to extract features from the raw signals in the fault diagnosis application, DL achieves high accuracy and outperforms other traditional signal processing and feature extraction techniques [15]–[17].”
Deep Residual Shrinkage Networks for Fault Diagnosis (2020, background): “Shao et al. [9] applied a convolutional deep belief network for fault diagnosis of electric locomotive bearings.”