Loram – a leading supplier of track maintenance, inspection services and infrastructure optimisation services and equipment – is expanding its track condition analytics capability for heavy haul railways.
Building on its established use of Loram’s Ground Penetrating Radar (GPR), LiDAR (Light Detection and Ranging) and track geometry data provided by the infrastructure owner, the company has developed TRACE (Track Root-cause Analytics and Condition Evaluation).
TRACE is an advanced methodology for track geometry-based condition diagnostics, root-cause analysis and predictive maintenance planning.
Australia’s heavy haul railways operate under extreme loading conditions, where small structural weaknesses can quickly develop into recurring track defects.
Where high axle loads and long freight trains operate across remote corridors, track geometry performance is closely linked to ballast and drainage condition.
Mika Silvast, Managing Director at Loram Finland, said: “Under repeated loading, even relatively small structural weaknesses can gradually develop into recurring vertical defects if moisture retention, fouling or drainage constraints are not properly addressed.
“Where transitions in vertical stiffness take place – such as at switches and crossings, culverts, bridges and rail joints – high dynamic loads can also frequently lead to geometry deterioration.”
Integrating geometry, GPR and LiDAR data
GPR provides continuous insight into ballast fouling, moisture distribution and layer thickness within the track structure.
In heavy haul corridors, longitudinal contamination patterns within the ballast can indicate fines migration (the movement of fine particles) and reduced drainage capacity.
When analysed alongside geometry trend data, or acceleration measurements from instrumented ore cars, these indicators help to explain why certain locations repeatedly deteriorate under traffic.
Loram’s measurement programs combine GPR and LiDAR surveys with track geometry records and historical maintenance data.
“LiDAR contributes corridor and embankment context, while spatial alignment of all datasets within Loram’s trademarked Rail Doctor platform provides a coherent view of both structural and functional track condition,” said Silvast.
Identifying root causes and evaluating maintenance
Building on this integrated data foundation, TRACE links track geometry condition, structural behaviour and maintenance response over time.
The methodology analyses track geometry condition at the level of individual defect parameters and investigates their root causes through multi-source data integration.
Rather than evaluating geometry channels in isolation, TRACE correlates defect behaviour with ballast condition, stiffness transitions, moisture distribution, drainage performance and previous maintenance actions to identify the structural drivers behind recurring issues.
TRACE also evaluates the durability and timing of maintenance interventions. By analysing how defect parameters respond before and after treatment, the methodology helps determine whether actions were carried out at the right location and time and whether they delivered lasting performance improvement.
Predictive analytics supporting targeted maintenance
Through geometry and acceleration time-series analysis combined with sub-surface condition indicators, TRACE supports forecasting of defect development and emerging risk. Silvast said this means asset managers can prioritise work based on deterioration trends and structural condition, instead of solely on threshold exceedances.
“This capability is particularly valuable in Australian heavy haul networks, where defects can develop rapidly and maintenance windows are limited,” he said.
“Experience from multi-year deployments in other high-demand rail networks shows that repeat monitoring combined with data-driven maintenance planning can reduce recurring defect areas by up to 70 to 80 per cent over several years.”
Silvast said Loram’s Rail Doctor software presents the integrated measurements and TRACE outputs in a practical visual format, enabling maintenance planners to identify priority sections and understand the underlying causes of deterioration.
“The results can be translated directly into prioritised work plans and longer-term maintenance programs.
“By connecting diagnostics, prioritisation and work planning, TRACE helps railways move from isolated condition reports toward a systematic, data-driven maintenance workflow that improves reliability and optimises maintenance investment in high-tonnage operations.”
From analytics to actionable maintenance planning
TRACE converts integrated measurement data into practical decision-support outputs for asset managers and maintenance planners.
At the location level, the methodology identifies defect locations, analyses their root causes and recommends the most appropriate maintenance response.
These insights are then aggregated to produce section-level and network-level indicators that provide an overview of track condition, deterioration trends and structural risk areas.
“The results can be presented as prioritised maps or target lists supported by concise analytical explanations, enabling maintenance planners to focus resources on the locations with the greatest long-term impact,” said Silvast.
“The outputs can be translated directly into structured work plans, while predictive analysis also highlights locations that are likely to require intervention in the future.
“This improves the predictability of maintenance needs and supports more efficient long-term planning of track works.”
Silvast said Loram continues to advance automation and analytics assisted by artificial intelligence to accelerate processing and expand predictive capability.
“The objective is to support railways in transitioning from periodic condition assessment toward a continuous, data-driven asset management approach that improves reliability, optimises maintenance investment and sustains long-term track performance in high-tonnage operations.”
.png){kind=small}
.png){kind=small}
.JPG)
