Abstract

Recently, research on data-driven bearing fault diagnosis methods has attracted increasing attention due to the availability of massive condition monitoring data. However, most existing methods still have difficulties in learning representative features from the raw data. In addition, they assume that the feature distribution of training data in source domain is the same as that of testing data in target domain, which is invalid in many real-world bearing fault diagnosis problems. Since deep learning has the automatic feature extraction ability and ensemble learning can improve the accuracy and generalization performance of classifiers, this paper proposes a novel bearing fault diagnosis method based on deep convolutional neural network (CNN) and random forest (RF) ensemble learning. Firstly, time domain vibration signals are converted into two dimensional (2D) gray-scale images containing abundant fault information by continuous wavelet transform (CWT). Secondly, a CNN model based on LeNet-5 is built to automatically extract multi-level features that are sensitive to the detection of faults from the images. Finally, the multi-level features containing both local and global information are utilized to diagnose bearing faults by the ensemble of multiple RF classifiers. In particular, low-level features containing local characteristics and accurate details in the hidden layers are combined to improve the diagnostic performance. The effectiveness of the proposed method is validated by two sets of bearing data collected from reliance electric motor and rolling mill, respectively. The experimental results indicate that the proposed method achieves high accuracy in bearing fault diagnosis under complex operational conditions and is superior to traditional methods and standard deep learning methods.

Highlights

  • Nowadays, with the rapid development of modern industry, fault diagnosis technology, as a core of Prognostics and Health Management (PHM) system, is playing an increasingly important role in intelligent equipment maintenance [1,2]

  • Traditional data-driven fault diagnosis methods based on machine learning techniques have achieved significant success, in which support vector machine (SVM), k-nearest neighbor (KNN) and artificial neural network (ANN) are the most widely applied

  • The general procedure of the proposed fault diagnosis method based on convolutional neural network (CNN) and random forest (RF) ensemble is given in Algorithm 1

Read more

Summary

Introduction

With the rapid development of modern industry, fault diagnosis technology, as a core of Prognostics and Health Management (PHM) system, is playing an increasingly important role in intelligent equipment maintenance [1,2]. Several studies have investigated the multi-level and multi-scale features aggregation of CNN models, which proves to be more effective in fault diagnosis and many other applications [24,25,27,28,29] These models summarize multi-level or multi-scale features altogether into a category-level feature, use it as the input of the full connection layer for more accurate classification. This paper takes the full advantage of the extracted multi-level features [30,31,32] This is achieved by the following steps: firstly, A CWT-based signal-to-image conversion method is presented.

Data-Driven Fault Diagnosis
Deep Learning and CNN
Ensemble Learning
Theoretical Background
Ensemble Learning and RF
Proposed Method
Signal-to-Image Conversion Based on CWT
Design of the Proposed CNN
Ensemble Classification
Experimental Results
Experimental Setup and Dataset
Results and Discussion
Visualization
As shown
Comparison with Other Methods
Discussion
Conclusions and Future Work
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call