The pantograph–catenary system is a critical component of railway vehicles, and its performance directly affects the quality of current collection. Accurately measuring the arcing rate is essential for monitoring the system’s condition and ensuring safe operation. However, traditional arc detection methods are prone to increased false detection rates and reduced measurement accuracy in complex railway environments due to the diversity of arc sizes and shapes, environmental interference, instability in current collection, and power fluctuations. While deep learning-based methods can effectively address environmental interference, obtaining sufficient labeled training data is challenging because arc events occur infrequently. Moreover, a large number of unlabeled images of pantograph–catenary contacts cannot be directly utilized due to the lack of annotations. To solve these issues, a novel arc detection method is proposed: a multimodal arc detection network based on denoising diffusion probabilistic models (DDPMs-MILNet). First, a DDPM is pretrained using a large set of unlabeled images to acquire advanced image features. This model serves as a feature extractor, and a hierarchical variation semantic decoder is fine-tuned, thereby improving performance under small-sample conditions and reducing dependence on extensive labeled datasets. Building on this, an audiovisual semantic decoder is designed to incorporate audio signals as semantic cues, providing additional modality information for visual features. This approach not only reduces the model’s reliance on visual information but also enables it to locate the visual target of the arc even when the object is not simultaneously seen and heard, further alleviating the challenges posed by limited sample sizes. Experimental results demonstrate that DDPM-MILNet achieves excellent detection performance with minimal data in complex railway environments, indicating significant application potential, particularly in the state monitoring and anomaly detection of railway systems.

Multi-view clustering research is a hot topic in the field of data mining, where complementary information between views can better describe data objects and improve the clustering performance. Non-negative matrix factorization (NMF) based multi-view clustering algorithm suffers from weak feature extraction, slow convergence speed and low accuracy. To solve these problems, this paper proposes a generalized deep learning multi-view clustering (GDLMC) algorithm based on NMF. Firstly, via decoupling the elements in the matrix, the matrix elements are non-negatively restricted using an activation function with a non-negative value domain, and the elements are updated employing stochastic gradient descent with learning rate guidance. Then, the corresponding gradients when the elements update are transformed into generalized weights and generalized biases, followed by combining the generalized weights and generalized biases with activation functions to construct generalized deep learning (GDL). Further, GDL is adopted to learn the corresponding low-dimensional matrix of each view and consensus matrix for obtaining the GDLMC algorithm. In addition, the detailed reasoning of the GDLMC algorithm are given. Finally, extensive experiments are conducted on four public datasets including regular and large-scale datasets, and the experimental results show that GDLMC has significant advantages.

The Pantograph-Catenary System (PCS) is a critical component of railway vehicles, and its performance directly affects current collection quality. The arc rate serves as an essential measurement indicator for monitoring PCS state. However, in complex railway environments—where arc sizes and shapes can vary significantly and are further influenced by factors such as reflected light, glare, and adverse weather—traditional arc detection methods are easily affected by unstable current collection and power fluctuations, resulting in increased false detection rates and reduced measurement accuracy. Deep learning methods, while promising, also face limitations when dealing with such diverse arc morphologies and strong external interference. To address these challenges, this paper proposes a Multi-Modal Imitation Learning-based Arc Detection Network (MILADNet). First, the measurement system fuses infrared and visible-light image features to enhance arc feature extraction in scenarios with strong glare or reflective interference, thereby mitigating false alarms caused by relying on a single sensor. Second, to overcome the lack of information on small arcs, an online imitation learning framework is introduced to improve the system’s detection sensitivity for small arcs. Finally, to address data bias arising from uneven arc distributions, an unsupervised transferable representation learning method is employed to reduce dependence on labeled data and enhance model generalization. Experimental results show that MILADNet exhibits outstanding detection performance for arcs of various sizes and in complex environments, demonstrating both high efficiency and accuracy during measurement and data processing. Beyond improving the precision and reliability of arc detection, this method offers a novel solution for the instrumentation and measurement field and shows significant potential for condition monitoring and anomaly detection in railway systems.

In recent years, intelligent fault diagnosis methods for bearings, dominated by deep learning, have been widely applied. However, most current methods are still limited to diagnosing different types of faults or degrees of faults as single diagnostic targets. There is less research on methods that diagnose multiple fault tasks simultaneously, and there are difficulties in fully extracting complementary fault features, adapting to complex diagnostic environments with strong noise interference, and handling imbalanced data distribution across various working conditions. To overcome these difficulties and challenges, this paper proposes an innovative multitask CNN-Transformer bearing fault diagnosis method (MT-ConvFormer). This method consists of a shared layer responsible for learning global shared information and several task-specific branch networks designed for different fault diagnosis tasks. Firstly, the shared layer uses CNN to extract local feature information and combines it with Transformer to infer cyclic global dependencies of vibration signals, effectively mining global shared information. Then, the task branch networks, by adopting an effective redundancy filtering mechanism, can more efficiently extract useful feature information from the shared layer and suppress the interference of irrelevant information. Experimental results show that this method exhibits significant diagnostic performance both under noisy conditions and under conditions of imbalanced data distribution across different working conditions. Moreover, comparative experiments with other existing methods further confirm the superiority of MT-ConvFormer under the same experimental setups.