Reliable Fault Diagnosis of Rotary Machine Bearings Using a Stacked Sparse Autoencoder-Based Deep Neural Network

Due to enhanced safety, cost-effectiveness, and reliability requirements, fault diagnosis of bearings using vibration acceleration signals has been a key area of research over the past several decades. Many fault diagnosis algorithms have been developed that can efficiently classify faults under constant speed conditions. However, the performances of these traditional algorithms deteriorate with fluctuations of the shaft speed. In the past couple of years, deep learning algorithms have not only improved the classification performance in various disciplines (e.g., in image processing and natural language processing), but also reduced the complexity of feature extraction and selection processes. In this study, using complex envelope spectra and stacked sparse autoencoder- (SSAE-) based deep neural networks (DNNs), a fault diagnosis scheme is developed that can overcome fluctuations of the shaft speed. The complex envelope spectrum made the frequency components associated with each fault type vibrant, hence helping the autoencoders to learn the characteristic features from the given input signals more readily. Moreover, the implementation of SSAE-DNN for bearing fault diagnosis has avoided the need of handcrafted features that are used in traditional fault diagnosis schemes. The experimental results demonstrate that the proposed scheme outperforms conventional fault diagnosis algorithms in terms of fault classification accuracy when tested with variable shaft speed data.

Download Full-text

Stacked sparse autoencoder with PCA and SVM for data-based line trip fault diagnosis in power systems

Neural Computing and Applications ◽

10.1007/s00521-018-3490-5 ◽

2018 ◽

Vol 31 (10) ◽

pp. 6719-6731 ◽

Cited By ~ 15

Author(s):

Yixing Wang ◽

Meiqin Liu ◽

Zhejing Bao ◽

Senlin Zhang

Keyword(s):

Fault Diagnosis ◽

Power Systems ◽

Sparse Autoencoder ◽

Stacked Sparse Autoencoder

Download Full-text

Rolling Bearing Fault Diagnosis Based on STFT-Deep Learning and Sound Signals

Shock and Vibration ◽

10.1155/2016/6127479 ◽

2016 ◽

Vol 2016 ◽

pp. 1-12 ◽

Cited By ~ 48

Author(s):

Hongmei Liu ◽

Lianfeng Li ◽

Jian Ma

Keyword(s):

Fourier Transform ◽

Deep Learning ◽

Fault Diagnosis ◽

Rolling Bearing ◽

Short Time Fourier Transform ◽

Bearing Fault Diagnosis ◽

Fault Features ◽

Sparse Autoencoder ◽

Stacked Sparse Autoencoder ◽

Short Time

The main challenge of fault diagnosis lies in finding good fault features. A deep learning network has the ability to automatically learn good characteristics from input data in an unsupervised fashion, and its unique layer-wise pretraining and fine-tuning using the backpropagation strategy can solve the difficulties of training deep multilayer networks. Stacked sparse autoencoders or other deep architectures have shown excellent performance in speech recognition, face recognition, text classification, image recognition, and other application domains. Thus far, however, there have been very few research studies on deep learning in fault diagnosis. In this paper, a new rolling bearing fault diagnosis method that is based on short-time Fourier transform and stacked sparse autoencoder is first proposed; this method analyzes sound signals. After spectrograms are obtained by short-time Fourier transform, stacked sparse autoencoder is employed to automatically extract the fault features, and softmax regression is adopted as the method for classifying the fault modes. The proposed method, when applied to sound signals that are obtained from a rolling bearing test rig, is compared with empirical mode decomposition, Teager energy operator, and stacked sparse autoencoder when using vibration signals to verify the performance and effectiveness of the proposed method.

Download Full-text

Weighted time series fault diagnosis based on a stacked sparse autoencoder

Journal of Chemometrics ◽

10.1002/cem.2912 ◽

2017 ◽

Vol 31 (9) ◽

pp. e2912 ◽

Cited By ~ 24

Author(s):

Feiya Lv ◽

Chenglin Wen ◽

Meiqin Liu ◽

Zhejing Bao

Keyword(s):

Time Series ◽

Fault Diagnosis ◽

Sparse Autoencoder ◽

Stacked Sparse Autoencoder

Download Full-text

Machinery Fault Diagnosis Based on Supervised Locally Linear Embedding

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.536-537.49 ◽

2014 ◽

Vol 536-537 ◽

pp. 49-52

Author(s):

Xiang Wang ◽

Yuan Zheng

Keyword(s):

Fault Diagnosis ◽

Learning Algorithm ◽

Classification Performance ◽

Fault Classification ◽

Locally Linear Embedding ◽

Diagnosis Method ◽

Linear Embedding ◽

Low Dimensional ◽

Machinery Fault Diagnosis ◽

Locally Linear

Fault diagnosis is essentially a kind of pattern recognition. In this paper propose a novel machinery fault diagnosis method based on supervised locally linear embedding is proposed first. The approach first performs the recently proposed manifold learning algorithm locally linear embedding on the high-dimensional fault signal samples to learn the intrinsic embedded multiple manifold features corresponding to different fault modes. Supervised locally linear embedding not only can map them into a low-dimensional embedded space to achieve fault feature extraction, but also can deal with new fault samples. Finally fault classification is carried out in the embedded manifold space. The ball bearing fault signals are used to validate the proposed fault diagnosis method. The results indicate that the proposed approach obviously improves the fault classification performance and outperforms the other traditional approaches.

Download Full-text

An Automatic Feature Learning and Fault Diagnosis Method Based on Stacked Sparse Autoencoder

Lecture Notes in Electrical Engineering - Advanced Manufacturing and Automation VII ◽

10.1007/978-981-10-5768-7_39 ◽

2018 ◽

pp. 367-375

Author(s):

Yumei Qi ◽

Changqing Shen ◽

Jie Liu ◽

Xuwei Li ◽

Dading Li ◽

...

Keyword(s):

Fault Diagnosis ◽

Feature Learning ◽

Diagnosis Method ◽

Sparse Autoencoder ◽

Stacked Sparse Autoencoder

Download Full-text

Research on typical fault classification method of DC-DC converter

Xibei Gongye Daxue Xuebao/Journal of Northwestern Polytechnical University ◽

10.1051/jnwpu/20213910071 ◽

2021 ◽

Vol 39 (1) ◽

pp. 71-76

Author(s):

Zhao Xu ◽

Yitong Zhang ◽

Zhen Pan ◽

Chengzhi Chi ◽

Xiaobin Liu

Keyword(s):

Fault Diagnosis ◽

Failure Modes ◽

Original Data ◽

Fault Classification ◽

Maintenance Cost ◽

Core Component ◽

Feature Extraction And Selection ◽

Use Efficiency ◽

Integrated Modular Avionics

DC-DC converter is the core component of power conversion module of integrated modular avionics. Condition monitoring and fault diagnosis of DC-DC converter can effectively improve the reliability of avionics equipment, reduce the maintenance cost and greatly improve the use efficiency of aircraft. In this paper, firstly, a typical DC-DC converter model based on SEPIC topology is designed in PSPICE environment, and the failure modes of DC-DC converter are analyzed. Secondly, the typical fault types of DC-DC converter are simulated, and the corresponding original data are obtained through simulation. Finally, the processing framework including data preprocessing, feature extraction and selection, and multi model fusion is used to do fault classification of the DC-DC converter. The fault diagnosis of the converter is simulated. Simulation results show the effectiveness of the proposed method.

Download Full-text

An Analog Circuit Fault Diagnosis Method Based on Circle Model and Extreme Learning Machine

Applied Sciences ◽

10.3390/app10072386 ◽

2020 ◽

Vol 10 (7) ◽

pp. 2386

Author(s):

Sumin Guo ◽

Bo Wu ◽

Jingyu Zhou ◽

Hongyu Li ◽

Chunjian Su ◽

...

Keyword(s):

Fault Diagnosis ◽

Extreme Learning Machine ◽

Analog Circuits ◽

Analog Circuit ◽

Classification Performance ◽

Fault Classification ◽

Diagnosis Method ◽

Circuit Fault Diagnosis ◽

Learning Machine ◽

Circle Model

The fault diagnosis of analog circuits faces problems, such as inefficient feature extraction and fault identification. To solve the problems, this paper combines the circle model and the extreme learning machine (ELM) into a fault diagnosis method for the linear analog circuit. Firstly, a circle model for the voltage features of fault elements was established in the complex domain, according to the relationship between the circuit response, element position and circuit topology. To eliminate the impacts of tolerances and signal aliasing, the 3D feature was introduced to make the indistinguishable features in fuzzy groups distinguishable. Fault feature separability is very important to improve the fault diagnosis accuracy. In addition, an effective classier can improve the precision and the time taken. With less computational complexity and a simpler process, the ELM algorithm has a fast speed and a good classification performance. The effectiveness of the proposed method is verified by simulation. The simulation results show the ELM-based algorithm classifier with the circle model can enhance precision and reduce time taken by about 80% in comparison with other methods for analog circuit fault diagnosis. To sum up, this proposed method offers a fault diagnosis method that reduces the complexity in generating fault features, improves the isolation probability of faults, speeds up fault classification, and simplifies fault testing.

Download Full-text

Fault Diagnosis Based on Batch-normalized Stacked Sparse Autoencoder

2020 39th Chinese Control Conference (CCC) ◽

10.23919/ccc50068.2020.9188430 ◽

2020 ◽

Author(s):

Liu Xiaozhi ◽

Gao Yang ◽

Yang Yinghua

Keyword(s):

Fault Diagnosis ◽

Sparse Autoencoder ◽

Stacked Sparse Autoencoder

Download Full-text

MODWT, PCA and Decision Tree based Fault diagnosis of Gear

Journal of University of Shanghai for Science and Technology ◽

10.51201/jusst/21/07161 ◽

2021 ◽

Vol 23 (07) ◽

pp. 376-386

Author(s):

Mansi Mansi ◽

◽

Sukhdeep S. Dhami ◽

Vanraj Vanraj ◽

◽

...

Keyword(s):

Signal Processing ◽

Fault Diagnosis ◽

Decision Tree ◽

Processing Technique ◽

Classification Performance ◽

Performance Comparison ◽

Vibration Monitoring ◽

Fault Classification ◽

Discrete Wavelet ◽

Signal Processing Technique

A gearbox is an important power transmission equipment. Its maintenance is a top requirement because it is prone to a variety of failures. For gearbox fault diagnosis, techniques such as vibration monitoring have been widely used. Also, when it comes to machine Condition monitoring and fault diagnostics, feature extraction is the crucial step. For a classifier to perform accurately, it must have the appropriate discriminative information or features. Hence, this paper proposes a signal processing methodology based on Maximal overlap discrete wavelet transform (MODWT) and a dimensionality reduction technique i.eprincipal component analysis (PCA) to reduce the dimensionality of the feature space and obtain an ideal subspace for machine fault classification. Firstly, the raw vibration signature is denoised with the help of a state-of-the-art MODWT signal processing technique to identify the hidden fault signatures. Then various traditional statistical features are extracted from this denoised signal. These multi-dimensional features are then processed with PCA and further, the Decision Tree is used for fault classification. Performance comparison of the proposed method with traditional raw analysis and without application of PCA is presented and the proposed method outperforms at every level.

Download Full-text