Hierarchical adaptive deep convolution neural network and its application to bearing fault diagnosis

By Xiaojie Guo, Liang Chen, Changqing Shen. 2016

733 citations recorded by the source corpus.

Abstract Traditional artificial methods and intelligence-based methods of classifying and diagnosing various mechanical faults with high accuracy by extracting effective features from vibration data, such as support vector machines and back propagation neural networks, have been widely investigated. However, the problems of extracting features automatically without significantly increasing the demand for machinery expertise and maximizing accuracy without overcomplicating machine structure have to date remained unsolved. Therefore, a novel hierarchical learning rate adaptive deep convolution neural network based on an improved algorithm was proposed in this study, and its use to diagnose bearing faults and determine their severity was investigated. To test the effectiveness of the proposed method, an experiment was conducted with bearing-fault data samples obtained from a test rig. The method achieved a satisfactory performance in terms of both fault-pattern recognition and fault-size evaluation. In addition, comparison revealed that the improved algorithm is well suited to the fault-diagnosis model, and that the proposed method is superior to other existing methods.

Subfields: Control and Systems Engineering, Mechanics of Materials

View Paper: https://www.semanticscholar.org/paper/728285c1b96768c117e9c60ed4652d3de4689403

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 Mechanics of Materials

Citations in the corpus

Transfer Learning With Neural Networks for Bearing Fault Diagnosis in Changing Working Conditions (2017, methodology): “[11] proposed a model based on adaptive convolutional neural network on the bearing diagnosis.”
Estimation of Bearing Remaining Useful Life Based on Multiscale Convolutional Neural Network (2019, background): “[23] presented a new adaptive CNN, in which an adaptive learning rate was introduced to take both convergence time and loss error into consideration instead of a global constant learning rate.”
Deep Learning Enabled Fault Diagnosis Using Time-Frequency Image Analysis of Rolling Element Bearings (2017, methodology): “…by means of a short-time Fourier transform was completed and either images or a vector of these outputs, independent of time, was used as the input layer to the CNN. Guo et al. [17] used Case Western’s bearing data set [4] and an adaptive deep CNN to accomplish fault diagnosis and severity.”
Bearing Fault Detection and Diagnosis Using Case Western Reserve University Dataset With Deep Learning Approaches: A Review (2020, methodology): “Ahierarchical adaptive deep convolutional neural network (ADCNN) is applied on the CWRU dataset in [88], which has two hierarchically organized components: a fault determination layer and a fault size evaluation layer.”
Machine Learning and Deep Learning Algorithms for Bearing Fault Diagnostics - A Comprehensive Review (2019, methodology): “To obtain a better trade-off between the training speed and accuracy, an adaptive CNN (ADCNN) is applied on the CWRU dataset to dynamically change the learning rate in [104].”
Remaining useful life estimation in prognostics using deep convolution neural networks (2018, background): “It should be noted that the selection of batch size aﬀects the network training performance [45].”
A transfer convolutional neural network for fault diagnosis based on ResNet-50 (2019, background): “Guo et al. [31] investigated a hierarchical adaptive CNN by adding an adaptive learning rate and a momentum component to the weight updating process.”
A New Convolutional Neural Network-Based Data-Driven Fault Diagnosis Method (2018, methodology): “Guo et al [30] investigated the LeNet-5-based adaptive deep CNN on the bearing fault diagnosis.”