Attention-based Convolutional Neural Networks for Diesel Fuel System Fault Diagnosis

Xie, Yijing; Niu, Tianlin; Shao, Siyu; Zhao, Yuhong; Cheng, Yuemeng

doi:10.1109/icsmd50554.2020.9261700

Cited by 8 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Bi et al [8] used variational mode decomposition and expectation maximization method to analyze multi-channel vibration signals and extract knowledge features for internal combustion engine state recognition. Further, deep learning techniques, including convolutional neural networks [9]- [11], graph attention networks [12] and autoencoders [13] are employed to explore the deep features of internal combustion engine vibration signals.…”

Section: Introductionmentioning

confidence: 99%

“…For instance, Xiong et al [10] and Huang et al [11] constructed internal combustion engine vibration signal feature extraction models based on autoencoders and graph attention networks, respectively, using vibration signals directly as input. However, internal combustion engine faults often manifest as abnormal impacts in time domain signals, with a particularly severe feature aliasing problem [15].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Transfer Diagnosis Model of Internal Combustion Engine With Embedded Vibration Signal Impact Decomposition

Li,

Dong,

Peng

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Traditional transfer diagnosis models for internal combustion engines show a decrease in generalization ability due to the multisource features aliasing in vibration signals and the effect of variable operating conditions. To address this problem, this paper proposes a transfer diagnosis model based on the deep subdomain adaptive network framework. To address feature aliasing, based on minimizing amplitude moment and reconstruction loss, a new adaptive decomposition layer is designed and embedded into the framework to decompose complex signals into single-impact components in time domain. To alleviate the effect of operating conditions, a new constraint for minimizing signal feature variance loss is designed and introduced into the framework's loss function. This constraint calculates the variance of the sample features of the same fault label under variable operating conditions, aiming to excavate invariant features of operating conditions and complete feature mapping of domain adaptation. Validation with experimental data yields an accuracy of 94.81%.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Transfer Diagnosis Model of Internal Combustion Engine With Embedded Vibration Signal Impact Decomposition

Li,

Dong,

Peng

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Li et al [24] designed a fusion strategy based on a channel attention mechanism to obtain more fault-related information during the fusion of multisensor data features. Xie et al [25] constructed an improved convolutional neural network incorporating a channel attention mechanism for fault diagnosis of diesel engine systems. Huang et al [26] designed a hybrid attention method to adaptively select important features through tandem spatial and channel attention.…”

Section: Introductionmentioning

confidence: 99%

Multiscale Convolutional Neural Network Based on Channel Space Attention for Gearbox Compound Fault Diagnosis

Jiang

Zhang

et al. 2023

Sensors

View full text Add to dashboard Cite

Gearboxes are one of the most widely used speed and power transfer elements in rotating machinery. Highly accurate compound fault diagnosis of gearboxes is of great significance for the safe and reliable operation of rotating machinery systems. However, traditional compound fault diagnosis methods treat compound faults as an independent fault mode in the diagnosis process and cannot decouple them into multiple single faults. To address this problem, this paper proposes a gearbox compound fault diagnosis method. First, a multiscale convolutional neural network (MSCNN) is used as a feature learning model, which can effectively mine the compound fault information from vibration signals. Then, an improved hybrid attention module, named the channel–space attention module (CSAM), is proposed. It is embedded into the MSCNN to assign weights to multiscale features for enhancing the feature differentiation processing ability of the MSCNN. The new neural network is named CSAM-MSCNN. Finally, a multilabel classifier is used to output single or multiple labels for recognizing single or compound faults. The effectiveness of the method was verified with two gearbox datasets. The results show that the method possesses higher accuracy and stability than other models for gearbox compound fault diagnosis.

show abstract

“…Li et al [16] designed a fusion strategy based on the channel attention mechanism to obtain more fault-related information when fusing multi-sensor data features. Xie et al [17] constructed an improved CNN incorporating the channel attention mechanism for fault diagnosis of diesel engine systems. The model mentioned above, considering feature weights, achieves good results, but scalar neurons reduce specific parameters such as location and scale in the feature mapping of their subject network CNN.…”

Section: Introductionmentioning

confidence: 99%

Application of Deep Neural Network in Gearbox Compound Fault Diagnosis

Zhang¹,

Jiang²,

Xu³

et al. 2023

Preprint

View full text Add to dashboard Cite

To realize the diagnosis of compound faults in gearboxes at different speeds, an "end-to-end" intelligent diagnosis method based on a deep neural network is proposed, named efficiency channel attention-capsule network (ECA-CN). First, the process uses a deep convolutional neural network to extract fault features from the collected raw vibration signals, then embeds the efficient channel attention module to filter important fault features, then uses the capsule network to vectorize the feature space information, and finally calculates the correlation between different levels of capsules by the dynamic routing algorithm to achieve accurate gearbox compound fault diagnosis. The effectiveness of the proposed ECA-CN fault diagnosis method was verified by the composite fault dataset of the 2009 PHM Challenge gearbox, with an average accuracy of 99.63% and a standard deviation of 0.22%. In the comparison experiments with the traditional fault diagnosis method, the average accuracy of the ECA-CN method was improved by 4.62%, and the standard deviation was reduced by 0.58%. The experimental results show that ECA-CN has a more competitive diagnostic performance.

show abstract

Attention-based Convolutional Neural Networks for Diesel Fuel System Fault Diagnosis

Cited by 8 publications

References 15 publications

Transfer Diagnosis Model of Internal Combustion Engine With Embedded Vibration Signal Impact Decomposition

Transfer Diagnosis Model of Internal Combustion Engine With Embedded Vibration Signal Impact Decomposition

Multiscale Convolutional Neural Network Based on Channel Space Attention for Gearbox Compound Fault Diagnosis

Application of Deep Neural Network in Gearbox Compound Fault Diagnosis

Contact Info

Product

Resources

About