Ensuring road safety is heavily reliant on the effective maintenance of vehicles. Accurate predictions of maintenance requirements can substantially reduce ownership costs for vehicle owners. Consequently, this field has attracted increasing attention from researchers in recent years. However, existing studies primarily focus on predicting a limited number of maintenance needs, predominantly based solely on vehicle mileage and driving time. This approach often falls short, as it does not comprehensively monitor the overall health condition of vehicles, thus posing potential safety risks. To address this issue, we propose a deep fusion network model that utilizes multi-source data, including vehicle maintenance record data and vehicle base information data, to provide comprehensive predictions for vehicle maintenance projects. To capture the relationships among various maintenance projects, we create a correlation representation using the maintenance project co-occurrence matrix. Furthermore, building on the correlation representation, we propose a deep fusion network that employs the attention mechanism to efficiently merge vehicle mileage and vehicle base information. Experiments conducted on real data demonstrate the superior performance of our proposed model relative to competitive baseline models in predicting vehicle maintenance projects.

It is of paramount importance to accurately predict the maintenance demands of vehicles in order to guarantee their sustainable use. Nevertheless, the current methodologies merely predict a partial aspect of a vehicle’s maintenance demands, rather than the comprehensive maintenance demands. Moreover, the process of predicting vehicle maintenance demands must give due consideration to the influence of mileage on such demands. In light of the aforementioned considerations, we put forth a vehicle overall maintenance demand prediction method that incorporates vehicle mileage awareness. In order to address the discrepancy between the vector space of mileage and that of the project, we put forth a mileage representation method for the maintenance demand prediction task. To capture the significant impact of key mileage and projects on future demand, we propose a learning module for key temporal information using a fusion of Long Short-Term Memory (LSTM) networks and attention mechanism. Moreover, to integrate maintenance mileage and projects, we propose a fusion method based on a gated unit. The experimental results obtained from real datasets demonstrate that the proposed model exhibits a superior performance compared to existing methods.

The balise transmission system (BTS) is essential for train position sensing and safe operation. Transmission loss is a key parameter particularly required for the evaluation of systems. The eddy current loss (ECL), caused by the conductivity of debris, affects the transmission performance of the BTS when the balise is immersed in water. This study proposes an effective modeling for the BTS using S-parameters. Utilizing the electromagnetic coupling analysis in the near-field region, we derived an equivalent circuit with the frequency and conductivity of water taken into consideration. The S21 can be predicted accurately by using the proposed equivalent circuit. For validation, a BTS system was implemented and measured to compare with theoretically calculated results and electromagnetic simulation results in the main lobe zone. The measurement results, simulation, and calculation were in good agreement. Moreover, the modeling was used to predict the I/O characteristics of the balise. The power of the balise uplink FSK signal was measured in the water debris and found to be approximately 0.62 dB less than in air. These findings aligned well with theoretical predictions.

Accurate prediction of vehicle maintenance demands is crucial for enhancing service longevity and minimizing costs. However, current methods are limited to predicting maintenance demands for individual vehicle components. They fail to offer a comprehensive prediction that encompasses diverse maintenance demands. Additionally, vehicle maintenance demand prediction must consider the interrelationships among various maintenance projects and maintenance project records. To address these issues, we propose a vehicle maintenance demand prediction method that employs a collaborative approach. This method utilizes both static and dynamic correlation-aware learning techniques. We design a static correlation-aware method for maintenance project representation learning by leveraging prior statistical data from various maintenance projects. To effectively capture the temporal correlations inherent in different maintenance project records, we propose an attention-based dynamic correlation-aware technique. Experiments conducted on real-world datasets demonstrate that the proposed model outperforms existing methods.

Balise is a critical trackside component in railway systems, operating in harsh environments where silicone gel potting enhances reliability. However, the potting process is irreversible; defects lead to costly scrap and operational delays. For this reason, this study introduces an anomaly detection method for the transponder potting process for the first time. We propose an attention-enhanced autoencoder (AEA) for anomaly detection. Our approach integrates three core innovations: max-min normalisation to handle scaling discrepancies between input attributes, an attention mechanism that dynamically highlights key features, and empirically derived adaptive reconstruction error thresholds to discriminate anomalies. Experiments on real production data show that the AEA model achieves Precision of 97.10%, Recall of 100.00%, weighted F1-Score of 98.53%, Accuracy of 99.90%, ROC-AUC of 99.96%, and G-means of 98.54%, outperforming all baselines. Compared to the best baseline AE model, the AEA model improves Precision by 1.45%, Recall by 1.49%, weighted F1-Score by 1.47%, Accuracy by 0.09%, ROC-AUC by 0.03%, and G-means by 1.47%. These results demonstrated that our model significantly outperforms existing well-regarded models in anomaly detection performance.