Dual-Aspect Self-Attention Based on Transformer for Remaining Useful Life Prediction

Zhang, Zhizheng; Song, Wen; Li, Qiqiang

doi:10.1109/tim.2022.3160561

Cited by 68 publications

(34 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For RUL prediction, Ref. [ 129 ] propose a transformer-based encoder–decoder structure with a dual-aspect encoders design to extract features from the sensor and time step simultaneously, while adaptively learning to focus on more important part of input and processing long data sequences.…”

Section: Part Ii: Supervised DL Methods For Intelligent Industrial Fdpmentioning

confidence: 99%

Deep Learning Techniques in Intelligent Fault Diagnosis and Prognosis for Industrial Systems: A Review

Qiu

Cui

Ping

et al. 2023

Sensors

View full text Add to dashboard Cite

Fault diagnosis and prognosis (FDP) tries to recognize and locate the faults from the captured sensory data, and also predict their failures in advance, which can greatly help to take appropriate actions for maintenance and avoid serious consequences in industrial systems. In recent years, deep learning methods are being widely introduced into FDP due to the powerful feature representation ability, and its rapid development is bringing new opportunities to the promotion of FDP. In order to facilitate the related research, we give a summary of recent advances in deep learning techniques for industrial FDP in this paper. Related concepts and formulations of FDP are firstly given. Seven commonly used deep learning architectures, especially the emerging generative adversarial network, transformer, and graph neural network, are reviewed. Finally, we give insights into the challenges in current applications of deep learning-based methods from four different aspects of imbalanced data, compound fault types, multimodal data fusion, and edge device implementation, and provide possible solutions, respectively. This paper tries to give a comprehensive guideline for further research into the problem of intelligent industrial FDP for the community.

show abstract

Section: Part Ii: Supervised DL Methods For Intelligent Industrial Fdpmentioning

confidence: 99%

Deep Learning Techniques in Intelligent Fault Diagnosis and Prognosis for Industrial Systems: A Review

Qiu

Cui

Ping

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…The Transformer architecture has recently become a new option for predictive maintenance [93,148,180]. For example, the Dual Aspect Self-attention based on Transformer (DAST) uses the Transformer architecture as a self-attention model without using any of the common model choices (e.g., CNN or RNN) for prediction, showing a wide range of options for customization [54,158]. Ma et al [53] created a variation of the G-Transformer model architecture that uses the encoder from traditional Transformer models as it is applied to natural language processing for sampling and extracting features for PM.…”

Section: ) Transformermentioning

confidence: 99%

Scalability, Explainability and Performance of Data-Driven Algorithms in Predicting the Remaining Useful Life: A Comprehensive Review

Ramezani¹,

Cummins²,

Killen³

et al. 2023

Preprint

View full text Add to dashboard Cite

<ul> <li>This work summarizes the state-of-the-art data-driven methods for prediction of the Remaining Useful Life<br> (RUL)<br> </li> <li>It discusses challenges and open problems faced in PdM<br> </li> <li>This study presents a discussion on the new problems that need to be considered towards the Industry 4.0 goals<br> </li> <li>We propose the future direction for each challenge discussed in this article</li> </ul>

show abstract

“…In 2017, Google Brain proposed a new sequence modeling architecture called a Transformer to process variable-length inputs as an alternative to CNNs or RNNs [53]. Transformers utilize a multi-head self-attention process to extract long-term dependencies in a sequence with no regard for distance [54]. This approach allows the model to be more resilient against sequence-length increases and avoid using recurrence or convolution methods [54,55].…”

Section: ) Deep Neural Networkmentioning

confidence: 99%

Scalability, Explainability and Performance of Data-Driven Algorithms in Predicting the Remaining Useful Life: A Comprehensive Review

et al. 2023

View full text Add to dashboard Cite

Early detection of faulty patterns and timely scheduling of maintenance events can minimize risk to the underlying processes and increase a system's lifespan, reliability, and availability. Two main data-driven approaches are used in the literature to determine the Remaining Useful Life (RUL): direct calculation from raw data and indirect analysis by revealing the transitions from one latent state to another and highlighting degradation in a system's Health Indices. The present study discusses the state-of-theart data-driven methods introduced for RUL prediction in predictive maintenance, by looking at their capabilities, scalability, performance, and weaknesses. We will also discuss the challenges faced with the current approaches and the future directions to tackle the current limitations.

show abstract

Dual-Aspect Self-Attention Based on Transformer for Remaining Useful Life Prediction

Cited by 68 publications

References 32 publications

Deep Learning Techniques in Intelligent Fault Diagnosis and Prognosis for Industrial Systems: A Review

Deep Learning Techniques in Intelligent Fault Diagnosis and Prognosis for Industrial Systems: A Review

Scalability, Explainability and Performance of Data-Driven Algorithms in Predicting the Remaining Useful Life: A Comprehensive Review

Scalability, Explainability and Performance of Data-Driven Algorithms in Predicting the Remaining Useful Life: A Comprehensive Review

Contact Info

Product

Resources

About