Few-Shot Rolling Bearing Fault Diagnosis with Metric-Based Meta Learning

Self Cite

Considering various fault states under severe working conditions, the comprehensive feature extraction from the raw vibration signal is still a challenge for the diagnosis task of rolling bearing. To deal with strong coupling and high nonlinearity of the vibration signal, this article proposes a novel multilocation and multikernel scale learning network based on deep convolution encoder (DCE) and bidirectional short-term memory network (BiLSTM). The former multifeature learning network of this article proposed combines the skip connection and the DCE network. The network can automatically extract and fuse global and local features from different network depth and time scales of the raw vibration signal. Then, the former network as the input of the latter network is fed into the feature protection layer for further mining sensitive and complementary features. Consequently, the proposed network scheme can perform well in generalization capability. The performance of the proposed method is verified on the two kinds of bearing datasets. The diagnostic results demonstrate that the proposed method can diagnose multiple fault types more accurately. Also, the method performs better in load and speed adaptation compared with other intelligent fault classification methods.

Section: Methodsmentioning

confidence: 99%

Multilocation and Multiscale Learning Framework with Skip Connection for Fault Diagnosis of Bearing under Complex Working Conditions

Ban

Wang

et al. 2021

Self Cite

“…Current state-of-the-art literature has produced FSL for various applications mostly featuring computer vision tasks and only a few implementations can be found for time-series classification. The authors in [19][20][21][22] proposed a metalearning model for few-shot fault diagnosis applications. The prototypical network is also a popular FSL technique for timeseries classification.…”

Section: Introductionmentioning

confidence: 99%

Efficient Feature Learning Approach for Raw Industrial Vibration Data Using Two-Stage Learning Framework

Tnani

Subarnaduti

Diepold

2022

In the last decades, data-driven methods have gained great popularity in the industry, supported by state-of-the-art advancements in machine learning. These methods require a large quantity of labeled data, which is difficult to obtain and mostly costly and challenging. To address these challenges, researchers have turned their attention to unsupervised and few-shot learning methods, which produced encouraging results, particularly in the areas of computer vision and natural language processing. With the lack of pretrained models, time series feature learning is still considered as an open area of research. This paper presents an efficient two-stage feature learning approach for anomaly detection in machine processes, based on a prototype few-shot learning technique that requires a limited number of labeled samples. The work is evaluated on a real-world scenario using the publicly available CNC Machining dataset. The proposed method outperforms the conventional prototypical network and the feature analysis shows a high generalization ability achieving an F1-score of 90.3%. The comparison with handcrafted features proves the robustness of the deep features and their invariance to data shifts across machines and time periods, which makes it a reliable method for sensory industrial applications.

“…However, the CE function only measures the difference between the predicted probability distribution and the target distribution [ 23 ], which means that CE-based models cannot analyze the distribution of samples and classes. Compared with regular CNN models, some models for few-shot recognition tasks adopt different losses where the deep metric learning (DML) technique is involved [ 24 ]. The DML losses take advantage of data distribution for discovering the differences among classes and finding the major common patterns for each category.…”

Section: Introductionmentioning

confidence: 99%

Batch Similarity Based Triplet Loss Assembled into Light-Weighted Convolutional Neural Networks for Medical Image Classification

Huang

Zhou

Zhu

et al. 2021

In many medical image classification tasks, there is insufficient image data for deep convolutional neural networks (CNNs) to overcome the over-fitting problem. The light-weighted CNNs are easy to train but they usually have relatively poor classification performance. To improve the classification ability of light-weighted CNN models, we have proposed a novel batch similarity-based triplet loss to guide the CNNs to learn the weights. The proposed loss utilizes the similarity among multiple samples in the input batches to evaluate the distribution of training data. Reducing the proposed loss can increase the similarity among images of the same category and reduce the similarity among images of different categories. Besides this, it can be easily assembled into regular CNNs. To appreciate the performance of the proposed loss, some experiments have been done on chest X-ray images and skin rash images to compare it with several losses based on such popular light-weighted CNN models as EfficientNet, MobileNet, ShuffleNet and PeleeNet. The results demonstrate the applicability and effectiveness of our method in terms of classification accuracy, sensitivity and specificity.