Laser Rail Inspection System (LRAIL™)
Pavemetrics® Laser Rail Inspection System (LRAIL™) delivers an entirely new and more cost effective means to inspect railway assets.
Most rail inspection sensors in the marketplace today are limited to a single function; they measure a specific parameter such as gauge, or perform a single task, such as imaging or tie grading.
The LRAIL delivers greater ROI by delivering a multi-functional inspection that delivers 2D imaging and 3D scanning in a single pass with fully automated analysis using Artificial Intelligence.
The LRAIL captures an impressive 1 mm X and Y, and 0.1 mm Z, resolution scan of the rails, ties and ballast area at speeds up 120 km/h.
The LRAIL’s Artificial Intelligence algorithms automatically measure and detect changes related to gauge, cross level, alignment, spikes, clips, tie plates, joint gap, joint bar bolting, rail surface wear and tie grade.
Artificial Intelligence-based Inspection and Change Detection
The LRAIL’s advanced Deep Neural Network automatically detects railway components, assesses their condition and detects changes between repeat runs.
Sensor Technology That is Proven in More than 45 Countries
The LRAIL leverages Pavemetrics prolific LCMS® technology; with more than 200 units in use in more than 45 countries, the LCMS is hands-down the most widely adopted and trusted sensor of its kind.
FRA Field-proven Results
The inspection process is fully computer-driven and objective, with results being just as accurate, and much more repeatable, than manual inspections. The LRAIL’s performance has also been field-tested and verified by the United States Federal Railroad Administration (FRA).
Simultaneous Geometry Measurement, 2D Imaging and 3D Scanning
By capturing both 2D images and 3D profiles all in the same pass, and including Artificial Intelligence-based data processing, the LRAIL can easily replace multiple legacy measurement systems. Saving you cost, weight and power.
See it in Action
Click on the movie below to see high resolution 3D scans from the LRAIL.
Key Features
- Inspection at speeds up to 120 km/h
- Supports narrow, standard and wide gauge measurements
- Simultaneous 3D point cloud and and 2D high-resolution Imaging
- Daytime and night-time operation, immunity to shadows
- Fully automated Artificial Intelligence-based railway inspection:
- Change detection
- Wooden tie grading (location, skew angle, crack length, crack depth, crack width, tie grade)
- Concrete tie grading (location, skew angle, crack length, crack depth, crack width, tie grade)
- Clip inspection (location, type, loose, missing, damaged, covered)
- Crossing inspection (location, crossing point detection, wear profiles)
- Switch inspection (location, toe detection, toe damage, foot detection)
- Rail open surface damage (chips, cracks)
- Joint detection and gap measurement
- Joint bar bolt counting
- Gauge width, cross-level between rails, alignment
- Railhead top and side wear (also grooved rail wear)
- Data are automatically location-referenced using mile-point and inertially corrected GPS (x, y and z)
- Compact; sensors weigh only 13 kg each and can be mounted on a high-rail vehicle or a dedicated inspection car
- Rugged components mounted in environmentally-sealed enclosures
- Low-power consumption
- Data compression algorithms to minimize storage requirements
Specifications
- 16,666 Hz scanning frequency
- Speed up to 120 km/h
- 1 mm transverse resolution
- 0.1 mm vertical resolution
- 0.25 mm vertical accuracy
Deep Learning for Railroad Inspection – Phase 2
Authors: Richard Fox Ivey, Mario Talbot, John Laurent (Pavemetrics)
Abstract: This paper builds on prior work (Deep Learning for Railroad Inspection – Phase 1) to develop a Deep Neural Network that can automatically identify key railway components as a step in the process of automating rail inspection in an effort to overcome the limitations of traditional methods. This new study adds the identification of new railway components (Tie Plates) as well as the automated assessment of their condition.
Deep Learning for Railroad Inspection – Phase 1
Authors: Richard Fox Ivey, Mario Talbot, John Laurent (Pavemetrics)
Abstract: Railway networks around the world are an important part of the transportation network and represent billions of dollars of investment. Poorly maintained networks negatively impact asset longevity, schedule performance and pose a serious threat to safety. In order to safeguard against these risks, Railroads typically inspect 100% of their mainline network at least annually and key locations even more frequently. Railroad inspection has traditionally been a manual process with inspectors walking the track or driving slowly in a high-rail vehicle to visually spot problems. This practice is very costly, time consuming, impacts schedule performance (due to the need for track possession), and puts staff at risk. While there have been some recent attempts to modernize the inspection process through the adoption of machine-vision technologies, these technologies are often still reliant on human inspectors manually reviewing images in order to spot defects. Manual review of images suffers from many of the same problems as manual inspections do: it is time consuming, subjective as opposed to being objective, and requires significant amounts of labor. This paper will explore a new approach which makes use of Deep Learning algorithms, specifically a Deep Neural Network, to automatically inspect images and has the potential to overcome these limitations.
Laser Triangulation for Track Change and Defect Detection
Authors: Federal Railroad Administration
Abstract:This report documents the successful demonstration of automated change detection on railroad track. Pavemetrics Systems Inc. performed this research under contract with the Federal Railroad Administration between March and December 2017. The project successfully demonstrated the ability of its Laser Rail Inspection System (LRAIL) to detect changes in fasteners, anchors,spikes, ties, joints, and ballast—as well as record rail stamping information on Amtrak’s Harrisburg line.
Extended Field Trials of LRAIL for Automated Track Change Detection
Authors: Federal Railroad Administration
Abstract:This report details the deployment of Pavemetrics’ Laser Rail Inspection System, “LRAIL,” for the purposes of automated change detection. The project was conducted between September 2018 and December 2019 at filed locations on Amtrak property and at Pavemetrics’ offices in Quebec, Canada.The project involved a combination of field sensor data acquisition, deliberate manual changes in the field, office algorithm development, algorithm testing and validation, and system performance reporting. The extended field trial proved successful. Repeatability, mean, and standard deviation of change measurements were determined and noise floors for each measured parameter were established.
