Deep Subdomain Transfer Learning with Spatial Attention ConvLSTM Network for Fault Diagnosis of Wheelset Bearing in High-Speed Trains

Wang, Jiujian; Yang, Shaopu; Liu, Yongqiang; Wen, Guilin

doi:10.3390/machines11020304

Cited by 5 publications

(3 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In real industrial scenarios, the training and test datasets are not independent and identically distributed, which often results in deep learning models losing diagnostic performance [42][43][44][45]. To address the aforementioned limitations, transfer diagnosis has gained prominence [46][47][48][49][50].…”

Section: Case Two: Application In Transfer Diagnosismentioning

confidence: 99%

Rolling element bearing fault diagnosis based on multi-objective optimized deep auto-encoder

Chang,

Yang,

et al. 2024

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

Bearing fault diagnosis holds significant importance, with widespread attention focused on enhancing its accuracy and efficiency. Existing diagnostic methods based on deep learning and transfer learning typically tackle this issue by introducing new function modules and diagnostic strategies, such as attention mechanism, adversarial domain adaptation, etc. However, most studies do not consider the structure and hyperparameters optimization of the network to improve the diagnostic performance of the network itself. To address this limitation, a novel multi-objective optimized deep auto-encoder (MODAE) is proposed in this paper. The optimal network structure and hyperparameters is determined by a multi-objective particle swarm optimization algorithm. Crucially, the method is based on a data-driven approaches to automatically search for network structures with stronger generalization and feature extraction capabilities to address engineering problems in different scenarios. Finally, this method is examined in both multi-fault classification diagnosis and transfer diagnosis scenarios, demonstrating strong self-adaptability through experimental results. In comparison with typical deep learning fault diagnosis methods, the proposed method demonstrates higher diagnostic accuracy and superior generalization ability.

show abstract

Section: Case Two: Application In Transfer Diagnosismentioning

confidence: 99%

Rolling element bearing fault diagnosis based on multi-objective optimized deep auto-encoder

Chang,

Yang,

et al. 2024

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Transfer learning can also be useful [40,41] as well as pretraining [42]. In addition, there are more focused techniques on limited data applications, like active learning [43] (a technique partly applied also in tool wear detection [44]), while physics-informed techniques [45,46] could be beneficial here, and more elaborated cases would require advanced techniques, such as neural operators [47].…”

Section: Introductionmentioning

confidence: 99%

Learning More with Less Data in Manufacturing: The Case of Turning Tool Wear Assessment through Active and Transfer Learning

Papacharalampopoulos,

Alexopoulos,

Catti

et al. 2024

Processes

View full text Add to dashboard Cite

Monitoring tool wear is key for the optimization of manufacturing processes. To achieve this, machine learning (ML) has provided mechanisms that work adequately on setups that measure the cutting force of a tool through the use of force sensors. However, given the increased focus on sustainability, i.e., in the context of reducing complexity, time and energy consumption required to train ML algorithms on large datasets dictate the use of smaller samples for training. Herein, the concepts of active learning (AL) and transfer learning (TL) are simultaneously studied concerning their ability to meet the aforementioned objective. A method is presented which utilizes AL for training ML models with less data and then it utilizes TL to further reduce the need for training data when ML models are transferred from one industrial case to another. The method is tested and verified upon an industrially relevant scenario to estimate the tool wear during the turning process of two manufacturing companies. The results indicated that through the application of the AL and TL methodologies, in both companies, it was possible to achieve high accuracy during the training of the final model (1 and 0.93 for manufacturing companies B and A, respectively). Additionally, reproducibility of the results has been tested to strengthen the outcomes of this study, resulting in a small standard deviation of 0.031 in the performance metrics used to evaluate the models. Thus, the novelty presented in this paper is the presentation of a straightforward approach to apply AL and TL in the context of tool wear classification to reduce the dependency on large amounts of high-quality data. The results show that the synergetic combination of AL with TL can reduce the need for data required for training ML models for tool wear prediction.

show abstract

“…Secondly, more and more research has been conducted on fault identification and the diagnosis of mechanical equipment by acoustic signal features, from the traditional spectral amplitude feature clustering comparison diagnosis method [27,28] and further acoustic field diagnosis techniques [29,30] to the popular machine learning [31,32] and deep learning techniques [33][34][35] today. These methods include Acoustic Imaging technology [36,37], Recursive Denoising diagnosis [38], Sparse Representation [39] and One-shot Learning [40].…”

Section: Introductionmentioning

confidence: 99%

Fault Diagnosis of Train Wheelset Bearing Roadside Acoustics Considering Sparse Operation with GA-RBF

et al. 2023

View full text Add to dashboard Cite

Trackside acoustic signals are useful for non-contact measurements as well as early warnings in the diagnosis of train wheelset bearing faults. However, there are two important problems when using roadside acoustic signals to diagnose wheel-to-wheel bearing faults; one is the presence of strong interference from strong noise and high harmonics in the signal, and the other is the low efficiency of bearing fault identification caused by it. Therefore, from the viewpoint of solving the two problems, a sparse operation method is proposed for denoising and detuning the modulation of the roadside acoustic signal, and a machine learning classifier with a Genetic Algorithm (GA)-optimized Radial Basis Neural Network (RBFNN) is proposed to improve the rate at which the features of roadside acoustic signal faults are recognized. Firstly, the background noise is filtered out from the Doppler-corrected acoustic signal using the Sparse Representation method, and the inverse wavelet transform is reconstructed into a noiseless signal. Secondly, the interference high-harmonic signal in the signal is filtered out using the Resonant Sparse Signal Decomposition (RSSD) method. Then, the GA is selected to optimize the parameters of the RBF neural network and build a fault diagnosis model. Finally, the extracted acoustic signal feature set is trained on the network model, and the trained model is used for testing. In summary, the sparse operation on the roadside acoustic signal processing and the GA-RBFNN diagnosis model were verified as being very effective in the diagnosis of roadside acoustic train wheel pair faults through the simulation experiment.

show abstract

Deep Subdomain Transfer Learning with Spatial Attention ConvLSTM Network for Fault Diagnosis of Wheelset Bearing in High-Speed Trains

Cited by 5 publications

References 36 publications

Rolling element bearing fault diagnosis based on multi-objective optimized deep auto-encoder

Rolling element bearing fault diagnosis based on multi-objective optimized deep auto-encoder

Learning More with Less Data in Manufacturing: The Case of Turning Tool Wear Assessment through Active and Transfer Learning

Fault Diagnosis of Train Wheelset Bearing Roadside Acoustics Considering Sparse Operation with GA-RBF

Contact Info

Product

Resources

About