Predictive Maintenance · Real-time Analytics
SNCF Gares&Connexions needed to understand and optimize safety, passenger flow, energy use, and maintenance across large rail stations, but manual monitoring and disconnected building systems could not simulate or manage those environments in real time.
Reported impact
SNCF Gares&Connexions reported a 20% reduction in energy consumption, completed 100% of preventive maintenance on time, cut downtime by 50%, and reduced response times by 50% by managing stations through a digital twin instead of isolated manual processes.
SNCF Gares&Connexions uses Akila's digital twin platform built on NVIDIA Omniverse, NVIDIA Metropolis, and OpenUSD to operate train stations as live simulated environments instead of isolated facilities. Station sensor feeds, building analytics, and visual data are centralized into a digital twin that can model crowd movement, airflow, solar heating, emergency scenarios, and future refurbishments. Metropolis and partner video analytics help feed live awareness into the twin, while Omniverse and OpenUSD make 4K visualization and scenario playback responsive enough for planners and operators to use routinely. The same environment flags leaks or abnormal energy consumption, supports preventive maintenance, and gives rail staff a place to test changes before touching live stations. That architecture turns rail operations from a reactive workflow into one driven by simulation, real-time analytics, and predictive intervention.
Station sensor and visual data flow into Akila's digital twin, Omniverse and OpenUSD synchronize the 3D station models, Metropolis-backed analytics surface live events and trends, and operators use the resulting environment to test scenarios, optimize energy, and trigger maintenance actions.
100% of preventative maintenance completed on time.
20% reduction in energy consumption.
Leading French rail network operator SNCF Gares&Connexions uses Akila's digital twin solution for live scenario planning and efficiency optimization.
Using OpenUSD enables smooth, real-time, 4K visualization of railway buildings.
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
NVIDIA Sample Aug 25, 2026 Siemens Siemens needed to help industrial teams overcome fragmented engineering tools, labor shortages, and slow design and maintenance workflows so they could design, simulate, and operate complex products and factories faster… 10%–15% reductions in capital expenditure NVIDIA CUDA · NVIDIA DGX B200 · NVIDIA DGX H200 
BCG Sample Modified · Jul 29, 2026 Dallas Fort Worth International Airport Dallas Fort Worth International Airport needed to absorb a historic expansion and rising passenger volumes while delivering over 20% efficiency in operations and maintenance, improving customer experience, and shifting… DFW's 26 key roadways AWARE (Advanced Warning and Response Exchange) · Resource Scheduling Optimizer · asset-health foundation NVIDIA Sample Jul 21, 2026 Wistron Corporation Wistron needed to scale production of NVIDIA AI infrastructure while improving quality, energy efficiency, and worker training across global plants, but traditional CFD studies, sparse defect data, and reactive factory… 10% energy reduction Apple Vision Pro · Cadence Reality Digital Twin Platform · NVIDIA Cosmos 