Distillation-enhanced fast neural architecture search method for edge-side fault diagnosis of wind turbine gearboxes

Wu, Yanling; Tang, Baoping; Deng, Lei; Li, Qikang

doi:10.1016/j.eswa.2022.118049

Cited by 24 publications

(5 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This superiority was validated across three mechanical system fault test benches. (1). In comparison to ot her methods mentioned in this paper, the two modules propos ed in our paper exhibit significant advantages in both comple xity and diagnostic accuracy.…”

Section: ) Bearing Fault Diagnosis Results Analysismentioning

confidence: 89%

See 1 more Smart Citation

A New Lightweight Fault Diagnosis Framework Towards Variable Speed Rolling Bearings

Liu,

Zhang,

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Under the variable speed condition, the rolling bearing vibration signal shows non-smooth characteristics such as frequency modulation and amplitude modulation, which makes it difficult to effectively extract the fault characteristics by relying on the analysis method of traditional signals based on the smooth assumption, as well as the excessive speed change and the excitation response caused by the failure of the equipment components will lead to the change of the detected vibration signal. In this paper, a lightweight fault diagnosis framework called variable speed fault diagnosis framework (VSFD-Net) is proposed to address the above challenges. Firstly, a separable multi-scale convolutional block is proposed to achieve the extraction of multi-local sensory field features, thus reducing the learning parameters and computational effort during the training process. Secondly, the development of a broadcast self-concern block is introduced to achieve capturing the critical fine-grained global extent of the signal while avoiding complex operations such as matrix multiplication and multi-dimensional exponentials. Through experiments on three mechanical systems, it is demonstrated that the framework has significant advantages over existing neural network models, possessing lightweight and robustness.

show abstract

Section: ) Bearing Fault Diagnosis Results Analysismentioning

confidence: 89%

“…Mechanical systems play a crucial role in various industria l sectors, and maintaining their optimal performance is ess ential for ensuring stable and efficient equipment operatio n [1,2]. Nevertheless, prolonged exposure to high-intensit y working conditions makes mechanical systems susceptib le to a range of failure modes.…”

Section: A Background Researchmentioning

confidence: 99%

A New Lightweight Fault Diagnosis Framework Towards Variable Speed Rolling Bearings

Liu,

Zhang,

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In the field of computer vision, the lightweight design of deep learning models has been a hot research spot for edge implementation, and typical methods are network pruning [ 173 ] and knowledge distillation [ 174 ]. Currently, some pioneer work [ 175 , 176 ] has been conducted and shown promising results for intelligent FDP on edge ends.…”

Section: Challenges and Possible Solutionsmentioning

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

“…The datadriven fault-detection method does not consider the gearbox fault mechanism, but directly extracts the implicit information that can reflect the gearbox operating status from the monitoring data (e.g. vibration acceleration, temperature, and active power) [13][14][15]. Thereafter, it realizes an early warning against the faults in the wind turbine gearboxes.…”

Section: Introductionmentioning

confidence: 99%

A multi-head self-attention autoencoder network for fault detection of wind turbine gearboxes under random loads*

Yu,

Zhang,

Tang

et al. 2024

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

Wind turbine gearboxes work under random load for extended periods of time, and the fault detection indicator constructed by the existing deep learning models fluctuate constantly due to the load, which is easy to cause frequent false alarms. Therefore, a multihead self-attention autoencoder network is proposed and combined with a dynamic alarm threshold to detect faults in a wind turbine gearbox subjected to random loads. The multiheaded attention mechanism layer enhances the feature-extraction capability of the proposed network by extracting global and local features from input data. Furthermore, to suppress the influence of the random load, a dynamic warning threshold was designed based on the reconstruction error between the inputs and outputs of the proposed network. Finally, the effectiveness of the proposed method was verified using the vibration data of wind turbine gearboxes from an actual wind farm.

show abstract

Distillation-enhanced fast neural architecture search method for edge-side fault diagnosis of wind turbine gearboxes

Cited by 24 publications

References 22 publications

A New Lightweight Fault Diagnosis Framework Towards Variable Speed Rolling Bearings

A New Lightweight Fault Diagnosis Framework Towards Variable Speed Rolling Bearings

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

A multi-head self-attention autoencoder network for fault detection of wind turbine gearboxes under random loads*

Contact Info

Product

Resources

About