Xiaohan Chen

Health monitoring and fault diagnosis of high-speed train traction systems are essential for maintaining reliable operation. To effectively process multisensor signals and avoid overfitting, ensemble learning methods are employed, leveraging multiple base models to integrate data from various sensors and enhance fault diagnosis performance. However, conventional ensemble frameworks are often burdened by excessive model parameters, limiting their applicability on edge computing processors. To address these challenges, this study proposes a novel dual attention-guided ensemble framework. This framework incorporates multiple multiscale feature attention (MFA) modules and a decision fusion attention (DFA) module, designed to capture critical features from multisensor signals, optimize the capacity of prominent feature extraction, and simultaneously reducing trainable parameters. The proposed ensemble framework is validated on the hardware-in-the-loop (HIL) simulation platform for high-speed train traction control systems, with experimental results demonstrating its superior effectiveness over several recently published ensemble learning methods.

The accurate determination of a material’s true stress-strain relationship is crucial for predicting its performance in engineering applications. However, traditional methods for determining material behavior often depend on extensive experiments. Although these methods are essential, they are inherently complex, time-consuming, and often suffer from limited accuracy and reliability when small sample sizes are involved. To address these challenges, this paper introduces a multi-fidelity deep neural network architecture that utilizes both low-fidelity and high-fidelity datasets to predict true stress-strain curves from small punch test data. The low-fidelity data are calculated using an empirical function based on the Swift model, providing an initial understanding of material behavior. In contrast, the finite element method provides high-fidelity data, enhancing the model’s ability to capture complex material characteristics. This framework merges low-fidelity and high-fidelity networks to estimate mechanical properties with low-fidelity and high-fidelity data. The effectiveness of the proposed approach has been demonstrated through experimental validation, highlighting its exceptional ability to generalize across material thicknesses and properties beyond the training set. The proposed approach outperformed traditional empirical methods and maintained strong performance even when applied to real-world materials.

Deep learning-based techniques have emerged as powerful tools for fault diagnosis. However, conventional deep learning methods require designing and training fault diagnosis models from scratch for each machine, necessitating a large-scale and high-quality labeled dataset. This limitation hinders the application of deep learning in practical settings, where labeled data is scarce and data distribution varies across different machines. To address these challenges, a novel self-supervised learning framework specifically designed for time-series data is proposed, aimed at enhancing cross-machine downstream fault diagnosis tasks with limited data. The proposed framework exploits inherent consistency between waveform and spectrogram representations, learning robust and transferable features from unlabeled data. Experimental results across three cross-machine fault diagnosis scenarios demonstrate that the proposed method outperforms existing state-of-the-art self-supervised methods, significantly reducing the reliance on labeled data and improving diagnostic performance.

Intelligent fault diagnosis of traction systems is vital for the reliability and safety of high-speed trains. Conventional methods extract features solely from fault signals to determine fault categories, neglecting the impact of operating conditions on traction systems. To address this limitation, multitask learning methods have been explored to simultaneously distinguish fault categories and operating conditions. However, due to the high cost of collecting high-speed train fault data, the available data are often extremely limited. Considering the parameter-intensive nature of multitask learning models and the scarcity of fault data, these models are prone to potential overfitting risks during the training process. In this work, we propose a novel joint attention-guided multitask feature sharing network (JA-MFSN) tailored for high-speed train traction system fault diagnosis. Our JA-MFSN integrates a novel joint attention module (JAM) that captures both task-shared and task-specific features with reduced parameter overhead, effectively mitigating overfitting risks. The network architecture balances model complexity and performance, enabling robust multitask learning under data-scarce conditions. Experimental results conducted on the hardware-in-the-loop (HIL) high-speed train traction control system simulation platform clearly demonstrate the superiority of the JA-MFSN approach over several existing methods.

Pedestrian trajectory prediction is an important research area with significant applications in autonomous driving and intelligent surveillance. However, existing studies on pedestrian trajectory prediction often suffer from a noticeable discrepancy between predicted and actual trajectories, due to incomplete extraction of pedestrian trajectory features and the randomness of the pedestrian walking process. The key objective of this article is to address this issue by proposing a method that can reasonably simulate the randomness of pedestrian walking and comprehensively extract pedestrian trajectory features. To achieve this, a novel social informer model built upon the informer model is proposed in this article. The social informer utilizes a transformer encoder-based interaction module to comprehensively extract pedestrian trajectory features, which are input into the informer model for further processing. Additionally, an adaptive variance mechanism is proposed to determine the optimal variance and accurately simulate the random nature of pedestrian walking. Finally, the proposed model is evaluated in a comparative experiment on ETH and UCY datasets, with results demonstrating that the proposed model outperforms other models, exhibiting improved accuracy and performance.

With the rapid development of high-speed train, health monitoring of high-speed train traction power system has gradually become a popular research topic. The traction asynchronous motor, as a key component in the traction power systems, greatly affects the reliability, stability, and safety of high-speed train operation. Normally, when faults occur, the train needs to immediately slow down or even stop to avoid unimaginable losses, resulting in limited fault data. Traditional data-driven fault diagnosis methods may face the local optimum problem during the optimization process when training samples are insufficient. In this study, a novel gossip strategy-based fault diagnosis method is proposed to prevent the local optimum problem, thus improving fault diagnosis performance. The proposed gossip strategy-based fault diagnosis method is validated on the hardware-in-the-loop high-speed train traction control system simulation platform, and the experimental results unequivocally show that the proposed method outperforms other well-known methods.

Deep transfer learning has become increasingly prevalent in various fields such as industry and medical science in recent years. To ensure the successful implementation of target tasks and improve the transfer performance, it is meaningful to prevent negative transfer. However, the dissimilarity between the data from source domain and target domain can pose challenges to transfer learning. Additionally, different transfer models exhibit significant variations in performance for target tasks, potentially leading to a negative transfer phenomenon. To mitigate the adverse effects of the above factors, transferability estimation methods are employed in this field to evaluate the transferability of the data and the models of various deep transfer learning methods. These methods ascertain transferability by incorporating mutual information between the data or models of the source domain and the target domain. This paper furnishes a comprehensive overview of four categories of transferability estimation methods in recent years. It employs qualitative analysis to evaluate various transferability estimation approaches, assisting researchers in selecting appropriate methods. Furthermore, this paper evaluates the open problems associated with transferability estimation methods, proposing potential emerging areas for further research. Lastly, the open-source datasets commonly used in transferability estimation studies are summarized in this study.

In bearing fault diagnosis, the faulty data are generally limited due to the high cost of fault signal collection. Considering the excessive parameters in the traditional convolutional neural network (CNN), such a limited data issue can cause overfitting problem during the model training, eventually resulting in poor fault diagnosis performance. To resolve the overfitting issue and elevate the diagnostic accuracy of the conventional methods, a novel fault diagnosis method based on local binary temporal convolutional neural network (LBTCNN) is proposed in this paper. In the proposed LBTCNN, a novel temporal module with dilated causal convolution for deep feature extraction is proposed to increase model depth under limited model parameters, and a local binary convolution (LBC) layer is adopted to reduce the computational parameters. To evaluate the effectiveness of the proposed method, several experiments under different scenarios such as limited samples and different noise levels are conducted on two datasets, including the rolling bearing accelerated life test dataset of Xi’an Jiaotong University and Changxing Sumyoung Technology, and the motor bearing dataset of Case Western Reserve University. The comparison results demonstrate that the LBTCNN method is superior over six other prominent fault diagnosis approaches under different bearing operation stages, different training samples and different signal-to-noise ratios.