A Fault Diagnosis Method for Rolling Bearing Based on 1D-ViT Model
TL;DR: Wang et al. as mentioned in this paper proposed a fault diagnosis method for rolling bearings based on 1D-vision transformer encoder structure, which applies vision transformer (ViT) model to the fault diagnosis area.
read more
Abstract: Rolling bearings are the key component of large rotating machinery. When such components fail completely, the equipment will be out of service, causing significant economic loss, and even leading to safety accidents, threatening the lives of workers. However, it is difficult to detect the early failure symptom of rolling bearings during the routine maintenance. Advanced fault diagnosis tools are limited in cost and technology. Therefore, researchers focus on how to implement accuracy and convenience of fault diagnosis method. This paper proposes a fault diagnosis method for rolling bearings based on 1D-vision transformer (1D-ViT) encoder structure, which applies vision transformer (ViT) model to the fault diagnosis area. The end-to-end fault diagnosis can be realized by directly inputting the original one-dimensional acquired data without additional time-frequency domain conversion. After the encoder ablation experiment, the model structure was optimized. With the rolling bearing data set of Southeast University and Case Western Reserve University (CWRU), the number of floating point operations (FLOPs) is as low as 0.169G, the parameter number is as low as 4.13M, and average accuracy is 99.9%, which also has better noise-resistance performance. Compared with common classification models, the 1D-ViT model has achieved great comprehensive advantages in fault diagnosis accuracy, time complexity, space complexity and noise-resistance performance, which verifies the effectiveness and convenience of the proposed fault diagnosis method.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
A hybrid approach for gearbox fault diagnosis based on deep learning techniques
Mokrane Bessaoudi,Houssem Habbouche,Tarak Benkedjouh,Ammar Mesloub +3 more
- 26 Feb 2024
TL;DR: A hybrid approach for gearbox fault diagnosis based on deep learning techniques achieves superior performance in fault identification compared to existing methods.
A lightweight multi-feature fusion vision transformer bearing fault diagnosis method with strong local sensing ability in complex environments
Sen Li,Xiaomei Zhao +1 more
TL;DR: A lightweight multi-feature fusion vision transformer bearing fault diagnosis method with strong local sensing ability in complex environments can effectively diagnose faults in rolling bearings under complex environmental conditions.
Dynamic MAML with Efficient Multi-Scale Attention for Cross-Load Few-Shot Bearing Fault Diagnosis
Abstract: Accurate bearing fault diagnosis under various operational conditions presents significant challenges, mainly due to the limited availability of labeled data and the domain mismatches across different operating environments. In this study, an adaptive meta-learning framework (AdaMETA) is proposed, which combines dynamic task-aware model-independent meta-learning (DT-MAML) with efficient multi-scale attention (EMA) modules to enhance the model’s ability to generalize and improve diagnostic performance in small-sample bearing fault diagnosis across different load scenarios. Specifically, a hierarchical encoder equipped with C-EMA is introduced to effectively capture multi-scale fault features from vibration signals, greatly improving feature extraction under constrained data conditions. Furthermore, DT-MAML dynamically adjusts the inner-loop learning rate based on task complexity, promoting efficient adaptation to diverse tasks and mitigating domain bias. Comprehensive experimental evaluations on the CWRU bearing dataset, conducted under carefully designed cross-domain scenarios, demonstrate that AdaMETA achieves superior accuracy (up to 99.26%) and robustness compared to traditional meta-learning and classical diagnostic methods. Additional ablation studies and noise interference experiments further validate the substantial contribution of the EMA module and the dynamic learning rate components.
An Interpretable Hybrid Framework Combining Convolution Latent Vectors with Transformers Based Attention Mechanism for Rolling Element Fault Detection and Classification
Ali Saeed Khan,Muhammad Usman Akram,Muazzam A. Khan,Belal Khan +3 more
- 01 Jan 2024
References
•Posted Content
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
TL;DR: A new language representation model, BERT, designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers, which can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks.
81.7K
Attention Is All You Need
Ashish Vaswani,Noam Shazeer,Niki Parmar,Jakob Uszkoreit,Llion Jones,Aidan N. Gomez,Łukasz Kaiser,Illia Polosukhin +7 more
- 01 Jan 2017
Abstract: The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 28.4 BLEU on the WMT 2014 English-to-German translation task, improving over the existing best results, including ensembles by over 2 BLEU. On the WMT 2014 English-to-French translation task, our model establishes a new single-model state-of-the-art BLEU score of 41.8 after training for 3.5 days on eight GPUs, a small fraction of the training costs of the best models from the literature. We show that the Transformer generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.
51.8K
•Proceedings Article
Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
Haoyi Zhou,Shanghang Zhang,Jieqi Peng,Shuai Zhang,Jianxin Li,Hui Xiong,Wancai Zhang +6 more
- 14 Dec 2020
TL;DR: Informer as discussed by the authors proposes a probSparse self-attention mechanism, which achieves O(L log L) in time complexity and memory usage, and has comparable performance on sequences' dependency alignment.
Applications of machine learning to machine fault diagnosis: A review and roadmap
TL;DR: A review and roadmap to systematically cover the development of IFD following the progress of machine learning theories and offer a future perspective is presented.
2K
Highly Accurate Machine Fault Diagnosis Using Deep Transfer Learning
TL;DR: A novel deep learning framework to achieve highly accurate machine fault diagnosis using transfer learning to enable and accelerate the training of deep neural network is developed.
1.2K