Train physics Engine. Full Network and Fleet.
Built for the operational complexities of freight, passenger, and connected logistics
GNOS removes guesswork from mine planning by delivering a precise, data-driven simulation platform. It integrates haulage, energy, and cost modelling in a single environment to replicate real operational conditions. The platform translates every operational change into specific, quantitative metrics, giving clear evidence of cost, efficiency, and environmental impact differences.
Our platform models vehicle and route dynamics far beyond fixed-time or simple event approximations to reveal actual haul cycle variability under varying payloads, gradients, and network congestion. Teams evaluate fleet adjustments, route layouts, and technology transitions using measurable operational data.
GNOS simulates longitudinal traction forces for haul trucks, shovels, and conveyors. It captures regenerative braking to enable energy recovery on downgrades. Our terrain-responsive model adjusts vehicle speed and fuel or battery consumption based on grade steepness, surface roughness, and weather-affected adhesion changes, including seasonal variations such as rain, dust, and snow.
Built as an integrated environment, GNOS extends beyond rail to model transport logistics including yard flows, berth scheduling, container handoffs, and road haulage coordination to optimise resource use, throughput, and resilience across the entire transport network.
Traditional simulation tools often run from $50,000 to $150,000+ per licence with ongoing maintenance fees. GNOS delivers broader capability at a flat annual subscription with no hardware cost, multi-year contract, or onboarding complexity.
Request a platform walkthrough with our team
Rail physics and transport network simulation
Longitudinal train dynamics
Configure locomotive and wagon specifications, track geometry, speed restrictions, and consist makeup to match actual operations. Test braking curves on descending grades, measure coupler forces (through consist makeup changes), and quantify regenerative energy yield under different operating strategies.
Every simulation provides traction force, speed, position, and energy use at each timestep—data engineers need to validate rolling stock performance, analyse headways, measure timetable adherence, and assess network capacity.
Alongside rail operations, GNOS captures transport handoffs, yard movements, and road-rail interactions. Operators configure terminal rules, crane allocations, and vehicle dispatch logic to model the full transport lifecycle, underpinned by validated asset behaviours and operational constraints.
Timetable validation and capacity analysis
Unlike static timetabling tools, GNOS runs live capacity simulations using real train dynamics and control rules. Measure train movements per hour, meet-pass rules, and corridor occupancy to identify capacity constraints before they impact service. Model signalling headways, platform dwell times, crossing conflicts, and recovery margins to test how timetable changes propagate through the network.
Run multi-corridor simulations that capture interactions between freight, passenger, and maintenance services competing for track access. Model junction conflicts, single-line working, and bidirectional movements to find where capacity hits its limit.
Compare infrastructure scenarios like passing loops, grade separations, signalling upgrades, to determine which investments deliver the greatest throughput improvement. Quantify the cost of delays by tracking how disruptions ripple through the network, affecting fuel use, asset deployment, and service targets.
Configure assets and constraints
Import network geometry, elevation profiles, curvature data, and infrastructure specifications from standard rail engineering formats. The platform accepts existing models from OpenTrack, RailSys, and other tools, preserving operational logic while enabling validation against recorded train runs.
The GNOS Sim platform supports detailed configuration of transport assets including cranes, trucks, and loaders, alongside rolling stock. Scheduling logic covers berth occupancy, yard capacity, loading windows, and multimodal handoffs, letting teams identify bottlenecks and optimise resource allocation across the transport chain.
Energy and decarbonisation
GNOS models every source of traction energy used across rail and transport fleets — from diesel and electric to battery and hydrogen. The platform tests power profiles, duty cycles, and fuel strategies to show how fleet configuration, infrastructure, and scheduling affect total energy demand and cost.
It measures regenerative braking recovery, fuel burn, charging or refuelling requirements, and load-cycle efficiency for each operating scenario. Users can compare rollingstock or vehicle options side by side and evaluate how energy mix, route profile, and utilisation influence emissions, throughput, and operating cost.
Model energy consumption and emissions not just for rail fleets but across connected logistics operations. Analyse fuel use, regenerative braking return, charging infrastructure, and alternative energy options holistically across transport modes to build effective decarbonisation pathways.
Cloud execution and AI setup deliver unmatched speed to validated scenarios.
GNOS runs through a web browser, supported by distributed cloud infrastructure that executes large-scale rail simulations in parallel. Launch hundreds of timetable variants simultaneously, compare results in real time, and export scenario outcomes without waiting for sequential desktop processing.
AI-guided configuration accelerates model setup by suggesting relevant parameters, pre-populating common signalling and dispatch logic, and identifying missing constraints before simulation runs. Engineers spend less time on platform mechanics and more time validating operational assumptions.
Results are presented in units engineers already measure. Transit times, energy per gross tonne-kilometre, headway compliance, so teams can validate the digital twin against actual performance before testing operational changes.
Case Study: Rolling Stock Fleet Expansion
A rail operator used GNOS to test rolling stock expansion scenarios before committing capital to fleet procurement. The simulation modelled timetable capacity, headway constraints, and service frequency across multiple corridors to determine minimum fleet size required to meet demand growth targets.
Engineers tested different consist configurations, maintenance window allocations, and depot turnaround times to identify where additional rolling stock would remove operational constraints. The validated model provided the data needed to justify fleet procurement timing, specifications, and staging strategy.
Technical differentiators
Feature
- Multi-domain Simulation Engines
- Advanced Rail Physics
- Sophisticated Energy Modelling
- AI-assisted onboarding
- Cloud-based elastic compute
GNOS
- Integrates rail and road physics with agent-based simulation
- Models train dynamics, coupler forces, signalling
- Fuel consumption, battery cycling, emissions fully modelled
- Automated setup, error-checking, run guidance
- Rapid, scaled parallel and rewindable scenarios
Legacy / Competitor Tools
- Separate, domain-limited tools
- Simplified rail modules
- Limited or separate energy modules
- Manual onboarding, higher learning curve
- Slower, on-premise, limited scalability
Benefit
- One platform covers multiple domains, reducing tool sprawl
- More accurate rail behaviour and risk modelling
- Direct insight into operational and sustainability metrics
- Faster user productivity and fewer errors
- Faster analytics enabling more scenario testing