AI- and Digital Twin-Driven Intelligent Diagnostics and Predictive Maintenance for Transportation Systems

Dear Colleagues,

Modern transportation systems—spanning complex vehicles and critical infrastructures—underpin safety, mobility, and the global economy. As these cyber–physical assets grow in scale and complexity, maintenance must evolve from reactive policies to data-driven Prognostics and Health Management (PHM). The convergence of Artificial Intelligence (AI) and Digital Twins (DTs) offers a powerful pathway: AI leverages multi-modal sensing and operations data for accurate diagnostics and Remaining Useful Life (RUL) prediction, while DTs provide high-fidelity virtual counterparts for real-time monitoring, “what-if” maintenance simulation, and risk-aware decision-making.

This Special Issue aims to advance the science and practice of AI–DT-enabled PHM for transportation systems by foregrounding the following key research challenges: seamless AI–DT integration and real-time synchronization; explainable and trustworthy decision support; uncertainty quantification and propagation across the sensing–modeling–decision chain; benchmarking and reproducibility; and scalable deployment across heterogeneous fleets and infrastructures. We particularly welcome methodologies that address multi-modal data fusion, edge and federated learning under privacy/latency constraints, digital-twin fidelity assessment and verification/validation, lifecycle management, and sustainability evaluation of maintenance policies.

We invite contributions that develop foundational theory, algorithmic innovation, and rigorous applications across vehicles (railway, automotive, aviation, maritime) and infrastructures (tracks, bridges, tunnels, roadways, depots, communications). Contributions should include novel hybrid AI–DT architectures; real-time prognostics and risk-informed scheduling; cost–benefit and lifecycle analyses; or interoperable frameworks that align with standards. We also welcome case studies demonstrating measurable safety, reliability, and availability gains.

Topics of interest, include but are not limited to, the following:

• Hybrid AI–DT architectures for diagnostics, prognostics, and predictive maintenance.
• Real-time synchronization between physical assets and DTs; streaming analytics and online learning.
• Multi-modal data fusion (vibration, acoustic, image/video, operational logs, environmental and network data).
• Edge and federated learning for privacy-preserving, low-latency deployment at scale.
• RUL prediction, health indicators, and risk-aware/uncertainty-aware decision-making (UQ).
• Trustworthy/Explainable AI (XAI), robustness to domain shift, and safety assurance.
• Digital Twin modeling, calibration, fidelity assessment, V&V, and co-simulation.
• Condition-based maintenance (CBM), maintenance optimization, and scheduling under constraints.
• Benchmarking datasets, evaluation protocols, and reproducible baselines.
• Lifecycle management and sustainability assessment of maintenance strategies.

Dr. Xiaoxi Hu
Dr. Junyu Qi
Dr. Dandan Peng
Dr. Jiusi Zhang
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• transportation systems
• artificial intelligence (AI)
• digital twins (DT)
• prognostics and health management (PHM)
• condition-based maintenance (CBM)
• predictive maintenance
• remaining useful life (RUL)
• explainable AI (XAI)
• data fusion
• edge and federated learning