Fault diagnosis for spent fuel shearing machines based on Bayesian optimization and CBAM-ResNet

Wang, Pingping; Chen, Jiahua; Wang, Zelin; Shao, Wenhan

doi:10.1088/1361-6501/ad03b3

Cited by 3 publications

(3 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the time-domain branch, the introduction of the channel attention module aims to enhance the model's adaptability to the importance of different channels senting key information in time-series data [24]. It is based on the assumption tha ent channels contribute differently to representing crucial information in the tim Through global average pooling and global max pooling, CAM extracts global s features from the multi-channel data, which are subsequently used to train a mu perceptron (MLP).…”

Section: Channel Attention Module (Cam)mentioning

confidence: 99%

“…In the time-domain branch, the introduction of the channel attention module (CAM) aims to enhance the model's adaptability to the importance of different channels in representing key information in time-series data [24]. It is based on the assumption that different channels contribute differently to representing crucial information in the time series.…”

Section: Channel Attention Module (Cam)mentioning

confidence: 99%

See 1 more Smart Citation

LMA-EEGNet: A Lightweight Multi-Attention Network for Neonatal Seizure Detection Using EEG signals

Zhou,

Zheng,

Feng

et al. 2024

Electronics

View full text Add to dashboard Cite

Neonatal epilepsy is an early postnatal brain disorder, and automatic seizure detection is crucial for timely diagnosis and treatment to reduce potential brain damage. This work proposes a novel Lightweight Multi-Attention Network, LMA-EEGNet, for diagnosing neonatal epileptic seizures from multi-channel EEG signals employing dilated depthwise separable convolution (DDS Conv) for feature extraction and using pointwise convolution followed by global average pooling for classification. The proposed approach substantially reduces the model size, number of parameters, and computational complexity, which are crucial for real-time detection and clinical diagnosis of neonatal epileptic seizures. LMA-EEGNet integrates temporal and spectral features through distinct temporal and spectral branches. The temporal branch uses DDS Conv to extract temporal features, enhanced by a channel attention mechanism. The spectral branch utilizes similar convolutions alongside a spatial attention mechanism to highlight key frequency components. Outputs from both branches are merged and processed through a pointwise convolution layer and a global average pooling layer for efficient neonatal seizure detection. Experimental results show that our model, with only 2471 parameters and a size of 23 KB, achieves an accuracy of 95.71% and an AUC of 0.9862, demonstrating its potential for practical deployment. This study provides an effective deep learning solution for the early detection of neonatal epileptic seizures, improving diagnostic accuracy and timeliness.

show abstract

Section: Channel Attention Module (Cam)mentioning

confidence: 99%

Section: Channel Attention Module (Cam)mentioning

confidence: 99%

LMA-EEGNet: A Lightweight Multi-Attention Network for Neonatal Seizure Detection Using EEG signals

Zhou,

Zheng,

Feng

et al. 2024

Electronics

View full text Add to dashboard Cite

show abstract

“…Hou et al [21] used a transformer and ResNet to faultdiagnose bearings. Wang et al [22] carried out a fault diagnosis study on waste fuel shears, building a network architecture with Bayesian optimization and CBAM-ResNet. Figure 1 shows the structure of the ResNet part.…”

Section: Residual Neural Networkmentioning

confidence: 99%

Fault diagnosis of control valves based on small-sample hybrid physics improved Resnet

Xiaolin,

Hongkun,

Zhihua

2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Pneumatic control valves, as vital components of industrial process automation, ensure the smooth operation of industrial production systems. However, they are susceptible to various malfunctions due to harsh working environments and complex transmission media, which can significantly impact production safety and efficiency. To address the challenge of obtaining fault data in actual operational settings, we constructed a fault test bench for pneumatic control valves and simulated a variety of fault conditions. We collected 421 fault data samples across 4 valve opening conditions, categorizing them into 27 distinct states with varying sample sizes, averaging 3-4 samples per state. To tackle the small-sample issue, we proposed a data augmentation method using periodic extension, validated through comparative analysis with other algorithms. Additionally, we innovatively analyze the data flow of pneumatic control valves and explore the relationships between different parameters. Based on these relationships, the input structure of the residual network is optimized. The above theoretical approach reduces the number of variables that need to be captured by the pneumatic control valve inspection system. Finally, through experiments under extreme conditions, our approach successfully diagnoses faults in 26 subclasses of pneumatic control valves, providing a reliable safeguard for industrial production safety and stability.

show abstract

Alarm data mining in complex industrial facilities using adaptive discretization based on time clustering and unified pattern fusion mining

Hu,

Liu,

Shao

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Alarm systems in complex industrial facilities are crucial for ensuring operational efficiency and safety. However, the intricate interconnections and collaborations among facility components often lead to fault propagation, resulting in alarm redundancy and thereby increasing the difficulty of addressing genuine faults. One effective way to address this issue is to mine meaningful alarm patterns, which can be used to optimize alarm management. Existing alarm data mining techniques lack effective discretization methods for unlabeled continuous time-series alarm data during the data preprocessing stage, compromising the accuracy of mining results. Moreover, these methods typically identify only single association rules or sequential patterns, making it challenging to comprehensively reveal the interactions and dependencies among complex events—a critical factor for effective alarm management. To address these challenges, this paper proposes an Adaptive Discretization based on Time Clustering (ADTC) method, which transforms historical alarm data into transaction sets while effectively preserving the key features of the original data. Building on this, a Unified Pattern Fusion Mining (UPFM) method is developed to mine co-occurrence relationships and sequential dependency rules of alarm events, utilizing directed graphs for visualization. This approach enhances the accuracy of analyzing interactions and dependencies among complex equipment. To validate the effectiveness of the proposed methods, experiments were conducted on both synthetic alarm datasets and historical alarm data from a port transshipment system in northern China. Compared to discretization methods with different time window sizes and the density clustering discretization method based on DBSCAN, the ADTC method outperformed other methods in both support and confidence metrics. Additionally, the UPFM method successfully mined sequential dependencies and co-occurrence relationship rules of alarm events, demonstrating its effectiveness and accuracy in data mining within complex industrial environments.

show abstract

Fault diagnosis for spent fuel shearing machines based on Bayesian optimization and CBAM-ResNet

Cited by 3 publications

References 58 publications

LMA-EEGNet: A Lightweight Multi-Attention Network for Neonatal Seizure Detection Using EEG signals

LMA-EEGNet: A Lightweight Multi-Attention Network for Neonatal Seizure Detection Using EEG signals

Fault diagnosis of control valves based on small-sample hybrid physics improved Resnet

Alarm data mining in complex industrial facilities using adaptive discretization based on time clustering and unified pattern fusion mining

Contact Info

Product

Resources

About