Compound fault diagnosis for industrial robots based on dual-transformer networks

Chen, Chong; Liu, Chao; Wang, Tao; Zhang, Ao; Wu, Wenhao; Cheng, Lianglun

doi:10.1016/j.jmsy.2022.12.006

Cited by 39 publications

(9 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared with the shallow learning-based method, the major difference is that the deep learning-based method aims to bridge the relationship between the health condition and the monitoring data in an end-to-end manner by utilizing hierarchical architectures to learn discriminative and fault-related representations from raw vibration signals. Various deep learning algorithms and its variant were developed by scholars for intelligent compound fault diagnosis, such as Deep Belief Networks (DBNs) [108][109][110][111][112], Sparse Auto-encoder (SAE) [113][114][115][116][117], Convolutional Neural Networks (CNNs) [118][119][120][121][122][123][124][125][126][127], Long Short-Term Memory (LSTM) Neural Networks [128], Capsule Networks (CapsNet) [129], and others [130]. Examples include but are not limited as follows: Shao et al proposed various intelligent fault diagnosis methods for rolling bearings with compound faults, in which the DBNs algorithms are combined with other techniques like dual-tree complex wavelet packet and compressed sensing to enhance the performance of the proposed diagnosis model [108,109]; Xiang et al proposed a multiple fault detection method based on DBNs and applied it for axial piston pumps [110]; Wang et al proposed a compound fault diagnosis method for analog circuit system, in which multiple ELM with AE is used to automatically extract the faultrelated representations from raw signals [117]; Combining with other algorithms, such as fast spectral kurtosis (FSK), SVMs, and data fusion techniques, CNNs have also been developed by many scholars and applied to compound fault diagnosis of rotating machinery [118][119][120][121][122]…”

Section: ) Supervised Learning-based Methodsmentioning

confidence: 99%

Compound Fault Diagnosis for Rotating Machinery: State-of-the-Art, Challenges, and Opportunities

Huang

Xia

Zhang

et al. 2023

JDMD

View full text Add to dashboard Cite

Compound fault, as a primary failure leading to unexpected downtime of rotating machinery, dramatically increases the difficulty in fault diagnosis. To deal with the difficulty encountered in implementing compound fault diagnosis (CFD), researchers and engineers from industry and academia have made numerous significant breakthroughs in recent years. Admittedly, many systematic surveys focused on fault diagnosis have been conducted by reputable researchers. Nevertheless, previous review articles paid more attention to fault diagnosis with several single or independent faults, resulting in that there is still lacking a comprehensive survey on CFD. Therefore, to fulfill the above requirements, it is necessary to provide an in-depth overview of fault diagnosis methods or algorithms for compound faults of rotating machinery and uncover potential challenges or opportunities that would guide and inspire readers to devote their efforts to promoting fault diagnosis technology more effective and practical. Specifically, the backgrounds including the related definitions and a new taxonomy of CFD methods are detailed according to the way of implementing compound fault recognition. Then, the state-of-the-art applications of CFD are overviewed based on relevant publications in the past decades. Finally, the challenges and opportunities associated with implementing CFD are concluded and followed by a conclusion for ending this survey. We believe that this review article can provide a systematic guideline of CFD from different aspects for potential readers and seasoned researchers.

show abstract

Section: ) Supervised Learning-based Methodsmentioning

confidence: 99%

Compound Fault Diagnosis for Rotating Machinery: State-of-the-Art, Challenges, and Opportunities

Huang

Xia

Zhang

et al. 2023

JDMD

View full text Add to dashboard Cite

show abstract

“…On another front, numerous experts have conducted research to address the issue of noise removal from input signals. Chen et al [18] introduced a denoising network based on dual transformers, which processes noise-corrupted time-frequency spectrum images using a U-Net-like approach for fault diagnosis. Additionally, Liu et al [19] investigated noise influence at different scales and developed a variablescale evolutionary adaptive mode denoising method, using adaptively designed Wiener filters.…”

Section: Introductionmentioning

confidence: 99%

Adversarial training of multi-scale channel attention network for enhanced robustness in bearing fault diagnosis

Peng,

Du,

Gao

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

For bearing fault diagnosis problems in extremely noisy environments, this paper proposes an innovative universal adversarial training method. This method dynamically introduces noise into the training data, adaptively optimizing the model's robustness. It applies to any neural network without incurring additional computational overhead in the reasoning process. Additionally, we introduce the Multi-Scale Channel Attention Network (MSCAN). This network employs stacked convolutional kernels of varying sizes to extract features at different scales from the input signal. The incorporation of the channel attention mechanism allocates distinct weights to features of different scales, further enhancing the network's representational capacity. Moreover, an AutoML-based automated tuning approach is employed to optimize the model training process, aiding in improving inference accuracy. Compared to existing designs, MSCAN exhibits exceptional accuracy. Through adversarial training, it maintains a 99.44% accuracy rate on the CWRU dataset under strong -3dB noise conditions. On the PU dataset at 0dB, this adversarial training significantly improves the testing accuracy of various models by an average of 36.42%.

show abstract

“…Zhong et al [16] introduced a deep progressive shrinkage learning method to classify and diagnose the compound faults of gearboxes as a new kind of fault. Chen et al [17] provided a compound fault identification method consisting of two compact Transformer networks for robots in different environments. The Transformer model was applied to a real industrial robot dataset, and it was demonstrated the model has a better diagnosis result of compound faults in noisy situations.…”

Section: Introductionmentioning

confidence: 99%

A novel decoupling method of compound faults with incomplete dataset of rotating machinery

Hu,

Yang,

Xing

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

The occurrence of fault in rotating machinery is random and complex, and the diagnosis of the compound faults has been a challenge in industrial production. Accurate diagnosis of the compound faults can be of significant help to practical maintenance and management. However, most existing intelligent diagnostic methods typically require abundant data for training, which is often difficult to collect for compound faults. In this paper, a novel method called impact feature-based decoupling capsule network (IFDCN) is proposed for diagnosing compound faults with incomplete datasets. In this model, an improved Laplace wavelet kernel capsule neural network is proposed to extract and enhance the impact features of vibration signal. A decoupling classifier is designed to decouple the compound faults in the diagnostic process so as to identify the sub-faults contained in the compound faults. In using this proposed model for incomplete datasets, the compound fault data is not trained and is not labeled. Through training on single-fault data, the proposed model is capable of classifying and decoupling the fault types. The feature extraction capability of the network is visualized by heat maps, and the physical significance of feature extraction is explained by deep learning network. The effectiveness of IFDCN is verified through different experimental of gear and bearing and the experiment results indicate that the proposed model has higher identifying precision and can accurately decouple the compound faults without compound fault samples.

show abstract

Compound fault diagnosis for industrial robots based on dual-transformer networks

Cited by 39 publications

References 50 publications

Compound Fault Diagnosis for Rotating Machinery: State-of-the-Art, Challenges, and Opportunities

Compound Fault Diagnosis for Rotating Machinery: State-of-the-Art, Challenges, and Opportunities

Adversarial training of multi-scale channel attention network for enhanced robustness in bearing fault diagnosis

A novel decoupling method of compound faults with incomplete dataset of rotating machinery

Contact Info

Product

Resources

About