阿爾斯通公司

This work considers the problem of developing a data-driven anomaly detection method in the common situation in which a large dataset is available only for few systems of a fleet and the data therein are unlabeled, i.e., the equipment health state (normal/anomalous) is unknown. An innovative two-stage unsupervised Transfer Learning (TL) framework is developed. In the first stage, a Long Short-Term Memory Encoder-Decoder (LSTM-ED) is pre-trained to reconstruct the values expected in normal condition of a specific ("source") system of the fleet using a dataset of signal measurements collected during a long period of time. Since industrial systems are typically in normal condition during most of their operational time, this pre-trained model is expected to reproduce their behavior in normal condition. In the second stage, the network architecture and parameters of the pre-trained model are used to initialize the dedicated LSTM-ED-based signal reconstruction model for another ("target'') system of the same fleet, for which only a limited amount of data collected during a short period of time is available. Data of the Aramis Data Challenge and of traction systems of a fleet of trains have been used to validate the proposed anomaly detection method in two different case studies. The obtained results show the superior performance of the proposed method in comparison to other state-of-the-art methods.

Automated inspection of the welding process is essential for ensuring consistent quality and high operational reliability. While the opportunities offered by the recent advances in artificial intelligence have allowed for good progress in automated process monitoring, most proposals rely on static image analysis and overlook the temporal dynamics inherent to welding operations. In this work, we introduce a sequential dataset that we designed to capture four distinct welding process states: no welding, welding stable, welding deviated, welding unstable. This dataset differs from the state-of-the-art datasets by its temporal structure and the active vision setup, which enables the study of the dynamic behavior of the process. The introduced temporal dimension is essential for capturing the complex patterns associated with welding defects, particularly in scenarios involving weaving motions. Additionally, we evaluate and compare different state-of-the-art sequential data analysis deep learning models. The study carried out aims to assess the capabilities of these models to detect process instabilities from video sequences in real time and to establish a baseline for future research in intelligent welding process monitoring. Upon this benchmark, we provide recommendations on the most suitable deep learning models for similar applications involving sequential image analysis of the welding process. The obtained results demonstrated that the proposed dataset provides informative clues about the spatial and temporal state of the process. Notably, the MC3 model was capable of achieving the best compromise between performance and computational efficiency, classifying the state of the process at an accuracy of 99.12

This paper describes the setup developed for an on-site measurement campaign in an electrical substation that feeds a tram line network in the city of Hannover. Calibrated wideband sensors and power analyzers were installed for measurement of the efficiency of the 2 MVA power transformer and the bi-directional AC/DC converter, and of the power quality at different positions in the substation. In addition, the charging cycle of battery storage for collecting the energy from braking trams was monitored. The aim of the campaign was to verify the efficiency of the substation components, check the power quality, and collect abnormal transient phenomena. The planning of the campaign started about one year before the 6-week measurement period in May-July 2025.

Artificial Intelligence (AI) is currently only applied to non-safety critical applications due to the strict standards and regulations for railway industries. We propose to review the three main fields necessary to increase trust in data science and AI algorithms and reach compliance: robustness, Operational Design Domain (ODD), and explainability. Robustness is the ability of an AI system to maintain its level of performance under any circumstances (ISO24029). ODDs allow the explicit definition of operating conditions under which a system is intended to operate, according to the recently published DIN DKE SPEC 99004. Explainability is the property of an AI system to express important factors influencing the AI system results in a way that humans can understand. Those 3 domains of research are already well investigated by nonrailway actors, with algorithms and methods ready to use for railway applications. A system view is necessary to ensure all trustworthy requirements interact continuously in a safe MLOps environment thereby fostering acceptance from regulators, operators and the public. Beyond safeguarding safety-critical applications, we aim to show that fostering deep trust in AI, as now required by regulatory frameworks worldwide, will unlock its full potential and transform the pace of adoption across mission-critical domains.

Hyperloop is an emerging next generation transportation technology that has the potential to revolutionize intercity transportation with its ultra-high speed capabilities, energy efficiency, and sustainable operations. With Saudi Arabia’s Vision 2030 initiatives progressing, there has been growing interest in innovative transportation solutions, especially in the context of smart city and infrastructure development projects. The aim of this review was to investigate the operational and safety readiness of Hyperloop adoption in Saudi Arabia by assessing the maturity of the technology, the infrastructure needed, safety concerns, regulatory aspects, and the national readiness. The methods used was a narrative review of peer reviewed journal articles, conference papers, government reports, industry papers, and international transportation reports from 2020 to 2026 which included 26 studies. Literature was retrieved using electronic search and themed according to the following categories: operational readiness, safety readiness, infrastructure needs, regulatory aspects, and the Saudi Arabian context. The results show that Hyperloop technology has come a long way in terms of automation, propulsion and digital infrastructure. But there are significant issues with infrastructure spending, safety certification, emergency preparedness, cybersecurity and regulatory standardization. Saudi Arabia has a number of strategic strengths such as Vision 2030 projects, smart city projects like NEOM, government support, and the growing digital infrastructure, all of which, when combined, make the Kingdom ready for future adoption. Saudi Arabia has the potential to implement Hyperloop successfully, but there are still challenges related to operational, safety, and environmental considerations that need to be overcome, which will require further technological advancements, pilot testing, and public-private partnerships, as well as international cooperation.