A Novel Intelligent Fault Diagnosis Method for Rolling Bearing Based on Integrated Weight Strategy Features Learning

He, Jun; Ouyang, Mingxing; Chen, Yong; Chen, Danfeng; Guo, Jing; Zhou, Yan

doi:10.3390/s20061774

Cited by 17 publications

(16 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Shi et al proposed an intelligent fault diagnosis method based on deep learning and particle swarm optimization support vectors machine [10]. He et al reported an intelligent bearing fault diagnosis method based on sparse autoencoder [11]. In [12], authors proposed a CNN model based on dislocation time series for fault diagnosis.…”

Section: Introductionmentioning

confidence: 99%

Deep Transfer Learning Method Based on 1D‐CNN for Bearing Fault Diagnosis

Chen

et al. 2021

Shock and Vibration

Self Cite

View full text Add to dashboard Cite

In mechanical fault diagnosis, it is impossible to collect massive labeled samples with the same distribution in real industry. Transfer learning, a promising method, is usually used to address the critical problem. However, as the number of samples increases, the interdomain distribution discrepancy measurement of the existing method has a higher computational complexity, which may make the generalization ability of the method worse. To solve the problem, we propose a deep transfer learning method based on 1D-CNN for rolling bearing fault diagnosis. First, 1-dimension convolutional neural network (1D-CNN), as the basic framework, is used to extract features from vibration signal. The CORrelation ALignment (CORAL) is employed to minimize marginal distribution discrepancy between the source domain and target domain. Then, the cross-entropy loss function and Adam optimizer are used to minimize the classification errors and the second-order statistics of feature distance between the source domain and target domain, respectively. Finally, based on the bearing datasets of Case Western Reserve University and Jiangnan University, seven transfer fault diagnosis comparison experiments are carried out. The results show that our method has better performance.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep Transfer Learning Method Based on 1D‐CNN for Bearing Fault Diagnosis

Chen

et al. 2021

Shock and Vibration

Self Cite

View full text Add to dashboard Cite

show abstract

“…Although model-based methods do work and achieve an extraction of an accurate HI, they still have two deficiencies: (1) Feature selection is heavily dependent on prior knowledge and diagnostic expertise. Moreover, it often focuses on a specific fault type, and thus it may be unsuitable for other faults [27,28]. (2) In real industries, acquired signals are usually exposed to environmental noises, and are transient and non-stationary.…”

Section: Introductionmentioning

confidence: 99%

“…(2) In real industries, acquired signals are usually exposed to environmental noises, and are transient and non-stationary. Therefore, signal processing technologies need to be employed to filter the collected signals, which can result in a loss of information [27,29].…”

Section: Introductionmentioning

confidence: 99%

“…In recent years, deep learning has emerged as a powerful tool to extract the representative feature from the collected signals [30,31]. Different deep learning architecture, including convolutional neural network (CNN) [29,32], recurrent neural network (RNN) [33], autoencoder [27], and generative adversarial network (GAN) [34], are successfully used to extract features automatically. The greatest advantage of deep learning is that it needs no prior expert knowledge and represents more accurate features [35].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Constructing a Reliable Health Indicator for Bearings Using Convolutional Autoencoder and Continuous Wavelet Transform

2020

View full text Add to dashboard Cite

Estimating the remaining useful life (RUL) of components is a crucial task to enhance reliability, safety, productivity, and to reduce maintenance cost. In general, predicting the RUL of a component includes constructing a health indicator (HI) to infer the current condition of the component, and modelling the degradation process in order to estimate the future behavior. Although many signal processing and data-driven methods have been proposed to construct the HI, most of the existing methods are based on manual feature extraction techniques and require the prior knowledge of experts, or rely on a large amount of failure data. Therefore, in this study, a new data-driven method based on the convolutional autoencoder (CAE) is presented to construct the HI. For this purpose, the continuous wavelet transform (CWT) technique was used to convert the raw acquired vibrational signals into a two-dimensional image; then, the CAE model was trained by the healthy operation dataset. Finally, the Mahalanobis distance (MD) between the healthy and failure stages was measured as the HI. The proposed method was tested on a benchmark bearing dataset and compared with several other traditional HI construction models. Experimental results indicate that the constructed HI exhibited a monotonically increasing degradation trend and had good performance in terms of detecting incipient faults.

show abstract

“…Additionally, [ 3 ] incorporates a shallow artificial neural network to scan-chains (using failure feature vectors). The mentioned papers utilize shallow networks, whereas in [ 4 ], the authors implement a deep network in form of a stacked autoencoder for the fault diagnosis of roll bearings. Similarly, in [ 5 ], the authors present convolutional a deep neural network to classify the potential faults.…”

mentioning

confidence: 99%