The International Light Rail Magazine
+44 1733 367610

Digital disruption: Safety and efficiency

Intelligent autonomus monitoring of platforms can swiftly identify both safety and security risks and allow more effective staff intervention.

As railway systems become more complex, the importance of digital disruption is clearly evident. It is therefore imperative that organisations have the capability to turn data into value in order to drive out waste and improve system resilience.

We are entering a data-driven era that uses intelligent assets and involves unprecedented levels of digital transformation. This radical shift includes everything from the Internet of Things through Big Data, to new analytical approaches for scrutinising both business and personal needs.

Digital transformation is fundamentally changing our industry, particularly with regards to risk assessment and safety.

With modern computing power, and harnessing the explosion in data availability and advanced analytics, there are new opportunities to use a Big Data approach to proactively identify high risk scenarios on rail systems. This gives us the scope to reduce cost and increase resilience throughout the system lifecycle, including deriving new requirements, system design, risk analysis, manufacture, testing and operation.

The following projects describe how we are developing new products and processes to take advantage of this new world to make tramways and light rail systems more resilient, safe and efficient.

Increasing safety and security

The Autonomous Vision Systems workstream is funded via the Rail Safety and Standards Board’s ‘Faster, Safer, Better Boarding and Alighting’ competition. Under this project our intelligent computer vision system is optimising safety and vehicle dwell times.

The project is based upon patented technology developed at Lancaster University as part of military-funded research for tracking troop movements from drones. Years of research have allowed the intelligent vision system to be computationally efficient to reduce data dimensionality in detecting both static and moving objects.

It autonomously performs platform train interface (PTI) monitoring after being taught what both a good platform and an errant platform situation looks like. With on-train monitoring, it can also reduce dwell times by indicating space in any given passenger carriage and where bikes, wheelchairs and prams can best be accommodated. This has further potential security applications by monitoring, for example, suspicious luggage or passengers behaving strangely who may be potential suicides or safety/security risks.

Shedding light on wheel slides

When train and tram wheels brake unevenly the result is often wheel flats. Resulting wheel slides cost the industry millions of pounds in engineering costs and delays each year.

UK Railway Group Standard GM/RT2466 requires that wheel flats larger than 60mm on vehicles operating at speeds up to and including 200km/h (125mph) have to be returned to depots immediately – at greatly reduced speeds. For 40-60mm flats, a vehicle has to be returned to the depot within 24 hours of discovery of the fault.

Wheel slides are directly impacted on by a multitude of events, including service performance, weather conditions, time of year, vehicle condition, track quality, track cleaning approaches, leaf-fall data, level crossing proximity, driving policies and more. The issue has also resulted in several serious rail safety incidents in recent years.

Although it is recognised that there are many potential causes for wheel slide, and data needs to be acquired from a wide range of sources, the current approach to analysis is to simply use each individual data source, essentially in isolation. However if all the sources were examined in unison, using the power of Big Data analytics, it is probable that the industry would not only identify
the major contributions more effectively and efficiently, but would also make important discoveries of problem areas that would otherwise remain hidden.

Through ‘Knowledge Discovery from Data’ (KDD), there is a potential saving of millions.

Over the last few years there has been significant anticipation associated with the use of Big Data techniques for the analysis of rail-related data; however the major expectations have yet to be fully realised and we are currently performing an analysis of real-time train data to prove the technique.

For this project we have used in-service data that includes GPS positioning, braking and power application, dwell times, information on wheel slide, sanding application, speed, acceleration and more.  Our development includes a system that will predict when a train or tram is most at risk from sliding, when the driver needs to be warned and when sand needs to be applied to stop wheel slides. By reducing the number of alerts and optimising the use of sand, the rail system will be subject to reduced delays and damage.

Working it out in logs

Railway safety management is a complex subject that involves a significant amount of manual intervention in the assessment, analysis and control of risk. Supporting documentation is usually worked on by multiple parties, with differences in system viewpoints and writing styles. Maintaining quality safety documentation is therefore an interesting challenge for the industry.

Hazard logs, for example, play a central role in both system engineering and risk assessment activity. The role of the log is to present a representation of the risks related to the system under consideration; its content relies upon input from a variety of sources and collaborative activities involving teams with varying expertise and knowledge.

From experience, we have found that the quality of this information can vary greatly both within and between projects. The volume and variety of the data and the need for collaboration creates the significant challenge of managing the content, keeping the textual readability, format and consistency.

We are currently working on a tool that assesses the ‘quality’ of a risk log in either ‘real time’ or at regular intervals to check the output from critical risk workshop sessions. It uses Natural Language Processing and machine learning to assess the quality of a hazard log based solely on its textual content. The method includes text classification and term frequency-inversion to identify keywords to represent quality indicators.

The intention is not to replace a human expert, but rather to support assessments by providing an early indication of the textual data in a given log. This involves checking for signs of imprecise and unclear writing and identifying issues that may make it hard for readers to fully interpret incident sequences. The tool has been built around CENELEC standards to aid compliance with both standards and risk management best practice.

The Intelligent Hazard Log Tool (IHLT) has been developed in collaboration with Lancaster University and several applications have been undertaken to prove the method. Results have demonstrated the power of textual analysis in this arena and have identified a number of quality indicators; demonstrator software has performed well against a manual evaluation of a sample data set.

The results of this product deployment will be presented at the Transport Research Arena conference in Vienna in April 2018.

Cyber Security Risk

ISO 27001 (formally ISO/IEC 27001:2005) is a specification for an Information Security Management System (ISMS); a framework of policies and procedures that includes all legal, physical and technical controls involved in an organisation’s information risk management processes.

Partnering with AIT in Vienna, we are producing a cyber security compliance tool based upon the IS027001 standard and a risk management framework based upon the same. Aligned with the latest engineering, technological changes and industry best practice in cyber security, these processes are backed up with current field experience that provides continuity of business outcomes.

To counter threats from a cyber attack or the impact of operating in a cyber-denied area; this approach is tailored to address the risk levels within an organisation, taking into account the economic costs of cyber security measures.

Our cyber security personnel have extensive experience in accrediting systems up to the highest levels of security classification, within Railway and Government institutions in Europe and beyond. These services span ICT, industrial control and SCADA systems.


Originally featured in December 2017 TAUT (960).