Semi-supervised meta-learning networks with squeeze-and-excitation attention for few-shot fault diagnosis

Feng, Yong; Chen, Jinglong; Zhang, Tianci; He, Shuilong; Xu, Enyong; Zhou, Zitong

doi:10.1016/j.isatra.2021.03.013

Cited by 128 publications

(35 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Meta-learning models learn the common internal structure of discrepancies but related tasks to accomplish the data-domain adaptation and generalization. The implementations of the Meta-learning are often not limited to a specific network or algorithm, and many scholars have proved that it can be realized in different forms, such as convolution-based network, recurrent-based network or reinforcement-based network [22][23]. The following section will give a brief introduction to the idea of similarity metric-based meter-learning.…”

Section: Similarity Metric-based Meta-learningmentioning

confidence: 99%

“…Combining with semi-supervised training strategy, the DASMN could successfully detected various bearing failures under small samples condition. Chen et al [23] proposed a kind of squeeze-and-excitation meta-learning network (SEMN) for bearing vibration data analysis. The SEMN could extract representative prototype features and then utilize unlabeled samples to refine prototype features, which successfully solved the problem of bearing fault diagnosis under insufficient fault samples condition.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Attention-Based Meta Learning Network via Prior Meta-training Strategy for Intelligent Fault Detection of Shipboard Antenna under Small Samples Prerequisite

Chang

Chen

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Fault detection of shipboard antenna is of great significance to ensure the safe operation and smooth completion of astronautic measurement ship. With the development of data-oriented technology, intelligent fault detection is desiderated to improve self-management of entire shipboard antenna system. However, insufficient fault data results in intelligent algorithms stagnation. In this paper, a meta-learning network is specially designed for fault identification of shipboard antenna under small samples prerequisite, which is named affiliation network (AN). The AN consists of a random sampler, a feature extractor, an auxiliary classifier and a discriminator. The former three are utilized to extract and concatenate the features from training and testing samples, while the latter trains an adaptive pseudo-distance to evaluate the affiliation degree between concatenation features for identifying unknown data. Besides, a prior sufficient meta-training strategy is specially designed to realize metric-based knowledge transfer for acquiring the more generic AN, thus avoiding reiterative training of the AN in different application scenarios. Effectiveness of proposed method are validated by three experimental cases. Results indicate that, comparing with conventional intelligent models, the prior trained AN only utilized few samples to effectively identify failure categories of shipboard antenna even with complex operating conditions.

show abstract

Section: Similarity Metric-based Meta-learningmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

An Attention-Based Meta Learning Network via Prior Meta-training Strategy for Intelligent Fault Detection of Shipboard Antenna under Small Samples Prerequisite

Chang

Chen

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Li et al [ 19 ] used sparse automatic encoders based on deep non-negative constraints to perform diagnosis under the condition of a small amount of fault data, and achieved certain results, but the classification accuracy is significantly reduced in the case of very few samples. Feng et al [ 20 ] proposed a semi-supervised attention-attracting meta-learning network, which uses unlabeled data to refine the model and accurately identify faults. Li et al [ 21 ] proposed a new model-agnostic meta-learning method for fault diagnosis under complex working conditions, and acquired knowledge through the diagnosis task of known working conditions to quickly diagnose bearing faults under unknown operating conditions.…”

Section: Introductionmentioning

confidence: 99%

A Novel Bearing Fault Diagnosis Method Based on Few-Shot Transfer Learning across Different Datasets

Zhang

et al. 2022

Entropy

View full text Add to dashboard Cite

At present, the success of most intelligent fault diagnosis methods is heavily dependent on large datasets of artificial simulation faults (ASF), which have not been widely used in practice because it is often costly to obtain a large number of samples in reality. Fortunately, various faults can be easily simulated in the laboratory, and these simulated faults contain a lot of fault diagnosis knowledge. In this study, based on a Siamese network framework, we propose a bearing fault diagnosis based on few-shot transfer learning across different datasets (cross-machine), using the knowledge of ASF to diagnose bearings with natural faults (NF). First of all, the model obtains a good feature encoder in the source domain, then defines a fault support set for comparison, and finally adjusts the support set with a very small number of target domain samples to improve the fault diagnosis performance of the model. We carried out experimental verification from many aspects on the ASF and NF datasets provided by Case Western Reserve University (CWRU) and Paderborn University (PU). The results show that the proposed method can fully learn diagnostic knowledge in different ASF datasets and sample numbers, and effectively use this knowledge to accurately identify the health state of the NF bearing, which has strong generalization and robustness. Our method does not need second training, which may be more convenient in some practical applications. Finally, we also discuss the possible limitations of this method.

show abstract

“…Since different segments of the dataset have different contributions to the task, the attention mechanism only focuses on the feature vectors in the timefrequency domain that are highly correlated with the target features. At present, the attention mechanism is widely used in the predicted task [10,11], image processing [12,13], target tracking [14], fault diagnosis [15][16][17] and other fields. Among all kinds of deep learning network models, Temporal Convolutional neural Network (TCN) [18] is a neural network model with causal Convolutional Network as the main body, interlayer connection supplemented by extended convolution [19] and residual connection [20].…”

Section: Introductionmentioning

confidence: 99%

Three-Phase Fault Arc Phase Selection Based on Global Attention Temporal Convolutional Neural Network

Zhao

Yang

2022

Applied Sciences

View full text Add to dashboard Cite

For low-voltage three-phase systems, the deep fault arc features are difficult to extract, and the phase information has strong timing. This phenomenon leads to the problem of low accuracy of fault phase selection. This paper proposes a three-phase fault arc phase selection method based on a global temporal convolutional network. First, this method builds a low-voltage three-phase arc fault data acquisition platform and establishes a dataset. Second, the experimental data were decomposed by variational mode decomposition and analyzed in the time-frequency domain. The decomposed data are reconstructed and used as input to the model. Finally, in order to reduce the fault features lost during the causal convolution operation, the global attention mechanism is used to extract deep fault characterization to identify faults and their differences. The experimental results show that the accuracy of the three-phase arc fault arc phase selection of the model can reach 98.62%, and the accuracy of single-phase fault detection can reach 99.39%. This model can effectively extract three-phase arc fault and phase characteristics. This paper provides a new idea for series fault arc detection and three-phase fault arc phase selection research.

show abstract

Semi-supervised meta-learning networks with squeeze-and-excitation attention for few-shot fault diagnosis

Cited by 128 publications

References 25 publications

An Attention-Based Meta Learning Network via Prior Meta-training Strategy for Intelligent Fault Detection of Shipboard Antenna under Small Samples Prerequisite

An Attention-Based Meta Learning Network via Prior Meta-training Strategy for Intelligent Fault Detection of Shipboard Antenna under Small Samples Prerequisite

A Novel Bearing Fault Diagnosis Method Based on Few-Shot Transfer Learning across Different Datasets

Three-Phase Fault Arc Phase Selection Based on Global Attention Temporal Convolutional Neural Network

Contact Info

Product

Resources

About