An Intelligent Fault Diagnosis Method Using Unsupervised Feature Learning Towards Mechanical Big Data

By Yaguo Lei, Feng Jia, Jing Lin, Saibo Xing, Steven X. Ding. IEEE transactions on industrial electronics (1982. Print), 2016

1,047 citations recorded by the source corpus.

Subfields: Control and Systems Engineering, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/2d2fe4a73c98933ae9b8df73c8452b0d8be6475e

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

1. Shen Zhang
2. Bingnan Wang
3. Shibo Zhang
4. Thomas G. Habetler
5. Xiang Li
6. Qian Ding
7. Liang Gao
8. Xinyu Li

In Molecular Biology

1. Xiang Li
2. Qian Ding
3. Liang Gao
4. Xinyu Li
5. Long Wen

Citations in the corpus

• Multiscale Convolutional Neural Networks for Fault Diagnosis of Wind Turbine Gearbox (2019, methodology): “In the output layer, we use a softmax function [17] that outputs a conditional probability for each class.”
• Deep Transfer Network with Joint Distribution Adaptation: A New Intelligent Fault Diagnosis Framework for Industry Application (2018, background): “Besides, the designed features always aim at special application object, and thus have limited adaptability when facing new diagnosis issues or changing the physical characteristics of the original systems [9].”
• A New Deep Transfer Learning Based on Sparse Auto-Encoder for Fault Diagnosis (2019, methodology): “[22] studied an unsupervised two-layer neural network based on the sparse filtering method and applied it on the fault diagnosis.”
• Deep Learning Algorithms for Bearing Fault Diagnosticsx—A Comprehensive Review (2019, methodology): “Besides the commonly used ML methods listed above, many other algorithms have been applied to the identification of bearing faults, bringing in different characteristics and benefits, including neural fuzzy network [62]–[64], Bayesian networks [65]–[67], self-organizing maps [68], [69], extreme lear”
• Machine Learning and Deep Learning Algorithms for Bearing Fault Diagnostics - A Comprehensive Review (2019, methodology): “Besides the commonly used ML methods listed above, many other algorithms have been applied to the identification of bearing faults, bringing in different characteristics and benefits, including neural fuzzy network [61]–[63], Bayesian networks [64]–[66], self-organizing maps [67], [68], extreme lear”
• Intelligent Bearing Fault Diagnosis Method Combining Compressed Data Acquisition and Deep Learning (2018, background): “on the acquisition hardware, data storage, transmission bandwidth, and on the subsequent processing [20], but also drives the mechanical health monitoring toward the big data era [21].”
• Cross-Domain Fault Diagnosis of Rolling Element Bearings Using Deep Generative Neural Networks (2019, methodology): “The softmax classifier, which has been popularly used in most classification tasks, is adopted in this study [10].”
• A transfer convolutional neural network for fault diagnosis based on ResNet-50 (2019, background): “They are normalized SAE (NSAE-LCN) from Jia et al. [23], stacked sparse autoencoder (SSAE) from Qi et al. [24], sparse filter from Lei et al. [48], deep belief network (DBN) form Gan et al. [25], deep CNN from Wang et al. [30], adaptive deep convolution neural network (ADCNN) from Guo et al. [31],…”
• A New Deep Learning Model for Fault Diagnosis with Good Anti-Noise and Domain Adaptation Ability on Raw Vibration Signals (2017, background): “Therefore, some studies proposed that the classifier should have the ability to classify the data from the raw signal directly, without feature extraction or manual selection [24,27].”