AusRAIL: Enhancing train performance with Artificial Intelligence

4Tel CEO Joanne Wust tells Rail Express about how the company is employing AI to develop its advanced driver advisory system, to help train drivers be safer and more efficient.


Ensuring safety within the rail corridor is essential to the effective delivery of train services. Various hazards, such as animals and people wandering into the rail corridor, or vehicles standing stationary across level crossings, can cause serious injury and death and lead to serious service disruptions on a network.

Safe and efficient operations require a train’s primary and secondary drivers to be aware of the precise location of the locomotive and the presence of potentially hazardous situations and objects along the route. In a high-consequence environment, train operators must keep an eye out for potential safety risks at all times, all while watching for safety-critical signals, and operating the train in as efficient a manner as possible.

This is no easy feat, and while train drivers in Australia and New Zealand consistently demonstrate a high level of competency, they are not infallible to human error. Fatigue, distraction and loss of concentration can affect anyone during a long journey. Complacency is a human trait that can set in for drivers operating the same route on a repeated basis, and a newer driver may not be as familiar with the route and its complexities.

Newcastle-based digital rail specialist 4Tel is working towards a solution which helps drivers perform their jobs in a safer and more efficient way.

In late September this year, 4Tel carried out a test run of its latest solution, HORUS. HORUS is an Artificial Intelligence (AI) Machine Learning system for an Advanced Driver Advisory System (ADAS) – ultimately a machine-human interface that assists train drivers in the safe operation of locomotives.

The company has been working on the AI system since 2016. With progress speeding up, the project is now moving into the final stages of development of an initial version for operational use.

“HORUS is the next technological enhancement for improving the safety and efficiency of train operations,” 4Tel CEO Joanne Wust tells Rail Express. “With this system, the onboard computers are able to sense a train’s surroundings and detect abnormal objects within the corridor and even beyond the corridor.

“Digital technology can do things that humans cannot do. For instance, we can use cameras that have superb visibility at night or in fog – humans often struggle to see much in these conditions. Also, different kinds of advanced sensors can be used to feed information into the train’s computers. Just as we humans use our different senses to detect whether or not we are in danger, sensor technology enables the same thing for AI computers, but more effectively.”

The HORUS system integrates the sensor data gathered from cameras, sensors and GPS in real-time. Using neural network processing in an on-board computer, the system carries out an ongoing and continuous comparison with previous data records of a given section of track. Advanced algorithms within the software then carry out processes for detection, localisation, awareness, dynamics and route monitoring.

“HORUS can detect the approaching signal and classify the illuminated signal aspect. It can also incorporate signalling telemetry data from the control system, where available, utilise AI and GPS for locational assurance (currently set to 50cm accuracy), and identify temporary and permanent speed boards to ensure the train going at the right speed,” Wust explains.

“The system can also carry out real-time calculations of the braking profile of the train. So if the train is approaching a signal at stop, HORUS can warn the driver and provide a braking profile to assist the driver in stoppint the train before the signal.”

HORUS features a central data centre that collects as-run video that is used to update the system’s track reference record, or the route “master sequence”. This process involves machine learning techniques, which assesses changes to the route on the basis of data collection, assimilating alterations and updating the master sequence. HORUS can therefore use AI to detect both normal and abnormal train operations at a given location.

“A route master sequence is the sum knowledge of what the AI system has learnt based on all the trains that have operated on that route. The more trains that operate a route, the more things are seen and processed, the more weather conditions are experienced, and the more intelligent the AI system will become in assessing hazards from normal route operations, it has been, the more things it has seen, the more situations it has been in, the more intelligent the AI will become,” Wust explains.

The process of developing the algorithms enabling the machine learning techniques took 4Tel three years with the research assistance of the University of Newcastle Robotics Laboratory.

The technology is now at a stage where the data gathered from a sensor array on a moving train can be integrated and analysed onboard to provide real-time information to a driver. “It took us some time to develop the mathematics and optimise them because the AI industry has specific requirements,” Wust says.

“The AI has to be able to interpret the different datasets coming from the various sensors and provide an integrated analysis of this information in real time. It is not to be understated how complex it is to do something like this.”

HORUS is designed to support a variety of sensors, which would be selected in consultation with the train operator to achieve their stated operational outcomes. HORUS collects as-run data that is subsequently processed by the data centre to update the system’s track reference record, or the route ‘master sequence’.

This process involves machine learning techniques, which assess changes to the route on the basis of data collection, assimilating alterations and updating the master sequence. HORUS can therefore use AI to detect both normal and abnormal train operations at a given location.

The updated master sequence is then shared with all other HORUS equipped locomotives to enable continuous learning of all HORUS equipped locomotives. Following the recent successful test run on a route through the Hunter Valley, 4Tel is planning to carry out additional train tests in the coming months. “We’re really happy with the data output that has been achieved. It is now just a case of ensuring the algorithms are not presenting false positives, and that we are processing the information in an efficient way,” Wust says.

According to Wust, early adopters of AI technology will reap the most rewards: they will get to shape the outcome of the DAS system and use the safety and efficiency benefits of HORUS to grow their market share of rail haul contracts.

HORUS also offers the opportunity to improve the competitiveness of intermodal rail freight against road freight.

“Long distance trucks are continuing to increase their capacity and efficiency with B-Triple combinations now appearing on main interstate roads, and vehicle manufacturers are competing to develop the first autonomous and driverless trucks. A truck driver also has few limitations on where they can drive their truck in Australia.

“By comparison, a train has two drivers and they are limited to operating in the territory of their route qualification,” Wust says.

“We see this as an opportunity to assist train drivers with better informed technology, to allow the drivers to focus on the tasks a computer can’t perform.

“Our HORUS technology is designed to work seamlessly across the various rail networks and contain the route master sequence data for all networks in one onboard database, which is continuously improved each time a HORUS equipped train runs on the network,” Wust explains. “Australia has some unique challenges – we have vast distances and the overall complexity of operating trains is quite high. So we have many reasons to adopt innovative technology to improve the safety and efficiency of rail transport.

“We’re excited about the technology we’ve been developing. It offers a lot of potential to the industry.”


Visit 4Tel at AusRAIL PLUS at Stand 180.

Contractors listed for Bendigo upgrade

A shortlist of contractors has been named to deliver signalling upgrades at Bendigo in central Victoria aimed at improving passenger services in the region.

The state government says the signalling works, part of the Bendigo and Echuca Line Upgrade, will allow for faster and more frequent services to Echuca and more services between Epsom, Eaglehawk and Bendigo.

Two teams have made the shortlist to deliver the project. The first, VicConnect, is comprised of UGL Limited, Decmil and Arup. The second group is comprised of CPB Contractors, John Holland, WSP and SMEC.

The winning bidder will deliver a modernised signalling system between Epsom, Eaglehawk and Bendigo to deliver Bendigo Metro 2, which provides for more frequent services within Greater Bendigo.

Construction is expected to begin in late 2020, with a target completion in 2021, subject to planning and environmental approvals.

Another contractor will be appointed later this year to improve accessibility and comfort at Bendigo Station. Using designs put together by Bendigo company e+ Architecture, the upgrades include lowering ticket counters to improve access for people with disability, improving the waiting and customer service areas, upgrading the toilets, and installing a new Changing Places facility.

Works are also underway to upgrade the car park and forecourt at Eaglehawk Station, including 60 new car spaces and new accessible parking, as well as a new taxi rank, bus bays and a drop off zone.

The station improvements are part of a state government $15.8 million project, included under the $1.75 billion Regional Rail Revival program.

“We’re getting on and delivering the infrastructure needed to run more trains more often between Epson, Eaglehawk and Bendigo,” transport infrastructure minister – and member for Bendigo East – Jacinta Allan said.

“The upgrades to the waiting room and car parks will make it easier for all passengers to access services, particularly those with reduced mobility.”

Digitising our future: Improving passenger experience through innovation

Downer’s Tim Young takes Rail Express through the company’s latest innovations in rail, and how modern data collection and analysis can drive passenger growth.


With governments at local, state and federal levels gradually approaching a consensus on the importance of growing public transport, Australia is on the cusp of an urban rail construction, operations and maintenance boom.

While rail patronage will undoubtedly rise when new connections are opened to growing areas, the addition of new services to already busy networks can compound challenges already faced getting stubborn road users to shift to public transport. Unplanned rail delays and congestion at busy stations are common excuses for commuters to continue driving to and from work, even if it is the more expensive, more stressful and – on the average day – more time-consuming option.

For Tim Young, Executive General Manager Rollingstock Services at Downer, answering these challenges will require modern, digital solutions.

“80 per cent of the world’s data has been created in the last five years,” Young tells Rail Express. “If you look at where we’ll be in 10 to 20 years, there will be a huge focus on ecosystem integration – integration between assets and people, and a huge focus on customer experience.”

Young wouldn’t always have been so optimistic about that rate of change. Over more than 20 years in the rail, aviation, safety, mining and manufacturing sectors, Young has witnessed, and taken part in rail’s digital journey, and says the sector has gotten better in its approach to change.

“My experience in the rail game has gone from staff and ticket operations and block limit boards to fully automated signals and points that are being set by Advanced Train Control Management Systems,” he says.

“Over that history the rail industry has, at times, been very slow to move and evolve. Its culture has at times been slow to adapt to the introduction of new technologies and new processes.”

Young recognises that part of the sector’s trepidation over the years has been well-founded. Rail operators bear a high level of safety responsibility, and all change must be with safety kept paramount.

“We need to understand how we play in this sphere that we don’t actually have 100 per cent control of. Because we’re dealing with commuters and their lives, we don’t take these decisions lightly – so more often than not this is also a precursor to why technology deployment in our industry is so slow,” he says.

With safety in mind, Young says change has become more rapid in the rail sector. But there are still barriers that could be lifted.

“The pace of change has certainly picked up, particularly when you look at the introduction of new technology in the rail industry in Australia. In the last decade we’ve seen advancements in signalling technology, we’ve seen advancements in onboard train technology, train control management systems. I think the evolution of digitalisation in the last decade has certainly been enhanced – the degree of introduction has increased,” he says.

“However, there are a number of constraints, particularly around the sense of urgency for those changes. Regulations and policies are things that constrain technology elasticity, and digitalisation in the rail industry more broadly.”

Another key hurdle for innovators is simple: capital cost.

“There’s a degree of risk associated with unknown applications, unknown technologies, and whether they’re actually going to deliver a tangible return, so capital is always going to be a question mark,” Young explains.

To ameliorate some of these concerns, Downer been looking to partner with more of its suppliers, and to collaborate with other technology firms and research bodies, with the aim of increasing the rate of development, and the success of project delivery.

In one example, Downer is working with the CSIRO and the Rail Manufacturing CRC to improve control battery technology, addressing issues like thermal runaway, and the potential of better battery solutions for improved life expectancy on Downer’s trainsets.

Collaboration is also taking place internally within Downer. Video analytics developments being made by Downer’s Defence business could have an application in public transport.

“This is leading-edge technology at the moment,” Young explains. “Technology that is able to detect either an incident that has occurred, or is about to occur, based on certain algorithms that are put into a database … We’re looking at whether that technology has applications, particularly from a safety perspective, within our industry, because there’s plenty of opportunities there as well.

“Obviously with surveillance-based technology there are privacy concerns to address, but that is something we’re working through with our Defence colleagues; working with that type of legislation.”

Ultimately, Young says the end customer is likely to be the biggest beneficiary of rail’s digital growth.

“We’re trying to deal to hyper global issues, with hyper local content experience,” he says. “Everybody carries a mobile device, and through it they’re connected globally. Well, we’re trying to take a local experience, like an urban rail service, and provide consumers with a global solution. We’re trying to solve today’s problems with some of today’s technology, but also trying to develop tomorrow’s technology today.”

How Downer is taking rail digital

Talking again about how the industry is set to become even more focused on the customer, Young says one example for Downer has been reducing delays and improving uptime for passenger rollingstock, through a reliability-centred approach to maintenance.

At the forefront of this is TrainDNA, which puts large volumes of data through an array of algorithms to highlight issues for maintenance before they cause delays.

Built on Downer’s Neuroverse platform, and based on the Microsoft Azure software stack, TrainDNA was developed over 18 months using in-house expertise and a strategic partnership with Deakin University and the Rail Manufacturing CRC.

The platform is now deployed on Sydney’s fleet of Downer-built Waratah trains, and will be rolled out across the rest of the fleet maintained by Downer by April next year.

“This is a data analytics platform on steroids,” Young says. “Analysing such volumes of data will allow our team to establish trends in relative real time, enabling us to proactively predict failures and calculate the remaining life of an asset more effectively.

“The advantage to our customers is that all of this takes place whilst the train is in service without interrupting the operation. At the same time, it enhances worker safety through the potential of removing high-risk inspections.”

Young expects TrainDNA to boost Downer’s ability to predict failure rates, and reduce unscheduled train downtime.

“TrainDNA demonstrates our capability as a world-class maintainer and asset management partner of choice. While we are still in the early stages of the solution, TrainDNA is a step in the right direction in our journey towards predictive maintenance.”

Mirroring this is TrackDNA, the equivalent platform for monitoring track for predictive maintenance purposes. “It will hang off some of the Waratah trains so we can extract information from the track,” Young explains.

“We can then put that data through a raft of algorithms, with the intent to understand not only track conditions for preventative maintenance activities, but also for further insight into the wheel-rail interface, something that no operator has at this time.

“It’s bringing the data from the train and the data from the track together, so you can understand the broader ecosystem health as it relates to the vehicle.”

Customers the focus of Wynyard trial

Another digital innovation Young says can improve the appeal of public transport comes in the form of a trial underway at Wynyard station in the heart of Sydney’s CBD, where Downer has installed its Dwell Track system to analyse and help manage movement through the busy station.

Developed by Downer and the University of Technology Sydney (UTS), and supported by the Rail Manufacturing CRC, the trial involves the installation of 16 infra-red and digital devices which sense customer movement, without identifying individuals.

“It allows station staff to understand the movements of consumers on and off the train, so they can try to position those consumers well on the platform,” Young explains.

“The passenger information display systems on the platform can also show passengers where seats are available onboard the approaching train coming to Wynyard station, through the airbag sensors. That culminates in allowing Sydney Trains to better manage the ease and speed of their consumers, through Wynyard train station, which has a direct consequence in managing dwell time more effectively, allowing for a better customer experience, and an improved ability to maintain their timetable.”

Dwell Track is undergoing a planned eight-week trial. Based on its performance, Sydney Trains will decide whether it will deploy it elsewhere on the

Latest-generation CBTC driving urban rail modernisation

Rail Express speaks with Thales’ Arnaud Besse about the company’s seventh-generation SelTrac CBTC system.

Over three decades since commercialisation, Thales’ SelTrac Communications Based Train Control (CBTC) system has been installed on more than 100 metro lines, in over 40 major cities around the world, and moves more than three billion passengers every year.

Thales launched the future-focused seventh generation of the SelTrac train control system, SelTrac G7, at Innotrans 2018, and will demonstrate the system again at AusRAIL PLUS 2019 in Sydney later this year.

Arnaud Besse, Marketing and Communications Director for Urban Rail Signalling at Thales, tells Rail Express the new generation of SelTrac is aimed at helping passenger operators achieve 100 per cent availability of service.

“Every operator wants to reach 100 per cent availability of service, and so do we,” Besse says.

Changes in SelTrac G7

With the share of global population living in cities expected to rise from 50 to 70 per cent by 2050, governments around the world must not only build new rail lines, but must maximise the capacity of existing infrastructure.

Thales says it has developed its SelTrac system with this in mind: SelTrac G7 is designed to be as flexible as possible, to help different operators, on new and existing lines, using varied rollingstock.

“SelTrac is both valid for greenfield and brownfield projects,” Besse explains, “and we are rollingstock provider agnostic. We have installed our system in trains from 14 different rollingstock manufacturers, which is pretty much every major rollingstock manufacturer on Earth.”

Besse says after safety, the top priority in the development of SelTrac G7 has been working with customers to assess their needs.

The result is a forward compatible system designed to ensure long and extendable design life, without the need for disruptive, system-wide re-signalling every time a new line is added or a new fleet enters service.

Thales says SelTrac G7 features a set of advanced functions designed to better help public transport operators manage network growth, extensions and fleet expansions, and prepare for the future of control operations.

Thales has improved the user interface for the centralised command-and-control system, which uses web technologies to allow users to work on their own workstations. The equipment installed on trains is also 20 per cent more compact for SelTrac G7, than for previous generations.

The seventh-generation system is also designed to operate with any kind of telecommunication system, including new-generation LTE, which is notably favoured in China over WiFi for CBTC communications.

Besse says one key innovation in SelTrac G7 is a bidirectional line management capability. This means if there is an issue at any given time, anywhere on the network, the operator can reconfigure the entire network to reduce or eliminate downtime.

“When you have an incident on your line, SelTrac G7 can very quickly and safely put in place any provisional services that require trains to do something they’re not usually supposed to do,” Besse explains.

“This means when a potentially disruptive incident occurs, the overall impact on the passenger and the operator is minimised.”

This added flexibility ties in with SelTrac’s decision support system, or DSS. “When an alarm occurs on the line, the DSS will propose to the operator a few scenarios,” Bess explains. “If there is a train broken down at a station, for example, the system could propose one option to run a provisional service, another for trains to skip the station, or turn around, and present the information needed for the operator to decide.”

Another customer-driven improvement made to SelTrac G7 relates to the first ‘C’ in CBTC – communication. When a train loses communication, SelTrac G7 allows it to continue until it reaches the limit of its movement authority. This means temporary, brief communications outages don’t impact operations.

“Our customers told us that losing communication on one train should not necessarily mean they don’t have room to manoeuvre, i.e. that the train cannot at least proceed with a few monitors. After all, in CBTC you are providing a limit of movement authority – basically how far the train can go given its position.”

In the case where a train does not re-establish communication before reaching the edge of its movement boundary, it will stop. But, as in most cases, if it has re-established its connection to the system, it will be able to continue.

“It’s all about minimising the cost of operations,” Besse explains. “Any disruption on the network costs the operator money, and costs satisfaction for the passenger. Nobody likes to be stuck on the network for additional time.”

With major research and development always going on in sectors like mission critical defence, security, and avionics, Thales has also applied its developments in cybersecurity to the new generation of SelTrac.

“The technology behind encryption analytics and hardware that we are supplying to banks, for example, is the same that supports SelTrac G7,” Besse says. “We have the best cybersecurity experts looking at our system, trying to break into it, and advising how it can be made even more secure. This relationship also means we have kept cybersecurity as one of the design constraints throughout development – so SelTrac G7 is what we call ‘cybersecure by design’.”

Always moving block

Besse credits the level of innovation Thales is able to achieve with SelTrac to the history of the system itself.

First developed by Standard Elektrik Lorenz (hence SEL in the name) in the 1970s, the technology now known as SelTrac began as the first fully automatic moving-block signalling system. It has never been a fixed block system, and is not based on fixed block technology. Besse notes this means Thales is not attempting to move innovation over from a fixed block mindset, into moving block; instead that innovation is always being made with moving block as the status quo.

Part of this alternative approach means SelTrac has been designed to not require a secondary train detection system, which can cost millions of dollars to install and maintain. Typically, such systems are installed as fixed “backup” systems, using things like axle counters to detect when a train enters a section of the network.

“This would be a fixed block system, added to a moving block solution,” Besse reasons. “Because our competitors are coming from a fixed block background and moving to a moving block, this secondary train detection is embedded into their system. But we started from the other end, so we don’t need it.”

Besse notes SelTrac has been used in Vancouver for more than 30 years without secondary train detection.

“We can equip a secondary train detection system if our customer wants one, but SelTrac does not need one by definition. And from our perspective, this secondary train detection infrastructure becomes another thing that can eventually impact the availability of the network.”

Flushing line conversion

Thales recently helped MTA New York City Transit convert one of its busiest subway lines, the Flushing line, to full CBTC, and launched Automatic Train Operation (ATO) capabilities on the line in May.

The Flushing line, which serve 400,000 daily passengers, went into revenue service using SelTrac CBTC in December 2018. A Certificate of Substantial Completion was finalised for the project in March 2019. Two months later, in May 2019, Thales ATO capabilities were enabled.

Thales says the project was the first irreversible re-signalling cutover project in North America. Modernising 17 kilometres of track connecting 22 stations with a fleet of 46 trains, the result of the project is a more efficient operation.

On-time performance since revenue service began has increased by more than 16 percentage points to 91 per cent. For riders, the average amount of time they now spend onboard a train beyond their scheduled travel time has been slashed by over a minute, to just 39 seconds.

The ATO also means train operators can put more focus on platform procedures and emergency breaking, while the train runs automatically.

“We are committed to supporting the future of New York City with its Fast Forward plan and contribute to increased public transit capacity for New Yorkers,” Thales Urban Rail Signalling Managing Director Dominique Gaiardo said in July.

“By re-signalling one of the busiest lines in New York, Thales has once again proven its outstanding capabilities in urban rail modernisation.”

Thales to bring SelTrac G7 to Australian Market

Thales is actively engaging with local industry to bring it’s SelTrac G7 solution to the Australian Market – starting in Sydney and then expanding to other neighbouring geographic regions.

“Thales is excited to bring this world class CBTC solution to the Australian market in order to help our local customers achieve their project objectives – it is already in operation in a number of major cities around the world – reducing congestion in our customer’s cities and improving the safety of their networks, reducing travel times for their commuters and providing major economic and social benefits to their countries,” General Manager of the Ground Transportation Systems business for Thales Australia Elias Barakat said.


CPB Contractors, John Holland, AECOM awarded second stage of Sunbury Line works

The Victorian government has awarded a $534 million contract to the Rail Infrastructure Alliance (RIA) for the delivery of the next stage of upgrade works on the state’s Sunbury Line.

The works will provide upgrades to the rail network’s power system, including overhead electrification works between Sunbury and South Kensington and at South Yarra, and signalling power upgrades.

This is the second package of works for the Sunbury Line that has been awarded to the RIA, which includes CIMIC Group’s CPB Contractors, John Holland,AECOM, Metro Trains Melbourne, and project owner Rail Projects Victoria.

CIMIC Group CEO Michael Wright said the company was pleased to continue work on the Sunbury Line Upgrade.

“Our end-to-end capability and major project experience enables us to deliver high-quality rail assets and world class public transport, supporting Melbourne and Victoria’s growth,” said Wright.

Mark McManamny, AECOM regional managing director for Victoria South Australia and Tasmania, said that he was delighted the Victorian government had entrusted his team with the planning and design works for the project.

“We are privileged to be involved in iconic projects like the Melbourne Metro Tunnel, where we have the opportunity to create a positive legacy for the communities in which we all live,” McManamny said.

The first package of works, which was awarded in August, will extend platforms, boost accessibility and build new stabling at stations along the line.

Overall the upgrade program covers platform extensions at every station between Sunbury and Footscray, wheelchair boarding platforms at eight stations, traction power upgrades and improvements to train stabling at Sunbury, Calder Park and Watergardens.

The project is designed to facilitate the operation of a fleet of 65 new high-capacity metro trains (HCMTs) to run all the way to Sunbury once the Metro Tunnel is opened in 2025.

The RIA has begun preparatory works on the first stage of the Sunbury Line Upgrade. These works include geotechnical, service and site investigations along the Sunbury rail corridor.

Further work will commence this year, with the upgrade project scheduled to be completed in 2023.

Understanding the challenges of condition monitoring

Electronic equipment manufacturer MRD Rail Technologies says the primary goal of its predictive asset condition monitoring system, TrackSense, is to give meaning to data to allow the customer to make data driven maintenance decisions.


MRD Rail Technologies has 30 years’ experience designing and manufacturing electronic equipment for the rail industry. Three years ago, it looked to capitalise on this with a push into the growing space of predictive maintenance and condition monitoring.

TrackSense, the system designed by MRD to carry out this task, has grown to now collect data and measure various parameters of condition in thousands of railway assets across Australia and in international markets.

In just three years, several operators throughout Australia and New Zealand are already using TrackSense, and it’s not slowing down: after attracting international attention exhibiting at Innotrans in Berlin last year, the Queenslandand-based company will exhibit at Railway Interchange USA in September.

Product Manager Yvie Hough says through a continued focus on listening to and communicating with customers, the TrackSense team hopes to refine its state-of-the-art approach, and help new and existing customers best take advantage of what it has to offer.

“The MRD team has been working closely with our customers to refine and improve our solution to provide a robust, easy to install system that is user friendly and provides valuable information to users,” Hough says.

Cost of ownership

Despite operational savings being a core benefit of condition monitoring and predictive maintenance systems, one major obstacle MRD has seen operators struggle to overcome is simply the cost of installing and maintaining a condition monitoring system, and the inflexibility of many common solutions available in the market.

“Some vendors charge exorbitant amounts for hardware and lock customers into fixed contracts,” MRD Managing Director Rob Gersbach tells Rail Express.

“The obvious downside to this is that should you decide to break ties with the vendor or they go out of business, you’re basically left with an expensive paperweight.”

Taking a different approach, the MRD loggers used in the TrackSense solution are not bound to that system.

“Yes, we offer a local or cloud server option for accessing the data, but this is optional as our loggers are capable of stand-alone operation,” Gersbach explains. “Our loggers log, process and alarm directly from the device without the need for external servers or software.

“This gives the customer total ownership and control of their hardware and data.”

Tuning for perfection

One misconception MRD aims to address is that a condition monitoring solution will provide maximum results from day one.

“When implementing a condition monitoring solution it’s important to understand it’s not a set and forget solution. It requires operator training, tuning and data input from the user,” Gersbach says.

To address this, MRD has developed tried and tested workflows to help operators get started with condition monitoring. The TrackSense team will also work with the customer to refine that workflow to their individual needs.

“Our auto-tuning feature will get you up and running fast and our teach feature will keep the system performing optimally,” Gersbach adds.

“We use shape recognition to identify anomalies, and KPIs are extracted from logged parameters and used to gauge an assets health and identify trends. All positive alerts and alarms are sent to the system’s fault library and fed back into the system to improve the systems performance. This library is also available for reference and training purposes.”

Critical to this is the use of machine learning to refine how data is analysed.

“The primary output of any condition monitoring system is data. Performing complex analysis of data collected from hundreds or thousands of sensors is a tedious and time-consuming activity, beyond the capabilities of human operators.”

By putting machine learning to work, Gersbach says TrackSense can help operators maximise the value of predictive maintenance while keeping costs down.

Local presence

MRD designs and builds hardware, and develops its software and applications locally in Australia.
Along with TrackSense, the company also provides EarthSense, a solution for detecting earth leakage; and RelaySense, a solution to test the condition of relays.

Its range of smart sensors collect data from fixed rail infrastructure, including points machines, batteries, track circuits and relays, as well as environmental, mechanical and portable assets. Measurements taken by MRD’s sensors includes current, voltage, pressure, temperature, vibration, and so on.


Siemens Mobility ANZ names new CEO

Transport solutions provider Siemens Mobility has named Raphaelle Guerineau as its new chief executive officer in Australia and New Zealand.

Guerineau, previously head of products and operations for Siemens Mobility in ASEAN Pacific, has been tasked with driving strategic growth and managing roughly 650 employees in Australia and New Zealand.

She is the first CEO for Siemens Mobility in Australia, following its recent establishment as a separately managed company of Siemens AG.

Michel Obadia, Siemens Mobility’s Asia Pacific CEO, said Guerineau was bringing a wealth of experience to a growing business.

“There’s growing demand for the products manufactured at our facility in Port Melbourne and for the services provided by our rail specialists. In addition to this, the team at MRX in Perth, a company we recently welcomed to our family, are doing some great work here in Australia and on global projects such as Thameslink in London,” Obadia noted.

Guerineau has been with Siemens since 2011, working as head of projects in Singapore, and as head of tendering for ASEAN Pacific. Before joining Siemens she worked with Alstom in Singapore, including as project manager for the signalling portion of the Circle Line.

Siemens Mobility’s portfolio includes rollingstock, rail automation and electrification, turnkey systems, intelligent traffic systems and related services.

Guerineau said she was pleased to be appointed to the new role during an “exciting phase” for the business.

“From our role in significant projects such as the level crossings removal in Victoria, North West Rail Link in Sydney, Gold Coast Light Rail in Queensland, KiwiRail work in New Zealand and to a new world-class data centre in Perth, our people are doing some fantastic work across the region,” she said.

“It’s an honour and a privilege to lead this team of experts and I look forward to it.”

Businesses call for review of ‘archaic’ Sydney Trains systems

The Sydney Business chamber has called for an independent audit of the Sydney Trains network after the operator’s CEO blamed an “archaic” system for delays.

After a damaged train at Town Hall caused significant delays across the Sydney Trains network on August 23, CEO Howard Collins said delays could be avoided when such incidents occur if not for the network’s “archaic” systems.

“It is a failure of the way our system is built that one train can stop the entire network,” Collins was quoted as saying by News. “We took the right decision not to try to move this train forward but to isolate and get people up on ladders literally to try to remove the [damaged] hatch. That cause a two-and-a-half hour delay to a critical point in the network.”

He continued: “Being an ex-London Underground guy, we developed that system that could be remotely switched off for each train. Seven minutes, bang the power off. Back on, off we go. Here we have to send men and women down tunnels to pull big switches and open them and close them, which takes hours. They have to come with forms, they have to work through things. It is archaic.”

Responding to Collins’ comments the Sydney Business Chamber has now called on the government to review the network so such incidents can be eliminated in the future.

“Over recent years billions have been spent on new light rail with more to come, but our existing heavy rail network is struggling to support the increase in rail commuters,” the chamber’s executive director Katherine O’Regan said.

“We need to establish if the heavy rail network is being maintained and updated to keep pace with the 28 per cent increase in passenger numbers over the past five years.

“This rise in usage demands a commensurate increase in maintenance expenditure.”

Prevention to prediction: The future of maintenance

Alstom’s Services Director for Australia Nicolas Thiebot says the company is working with operators and asset owners to demonstrate that it is safe to move to predictive maintenance across their networks.

For generations, rail operators and owners have relied on fixed schedules to maintain their fixed and rolling assets. General maintenance and component replacement was scheduled based on the distance travelled by a piece of rollingstock, or the amount of use endured by a section of track.

While this “preventative maintenance” gets the job done, it is far from the most efficient method. What if a replaced component is still in good condition? What if a component is faulty and degrades faster than it should? What if you’re performing general maintenance too often? Not often enough?

The basic theory behind the development of condition monitoring systems was to address these concerns. Devices installed in trains and around railways record and report data, so assets can be maintained and replaced when needed; not before or after.

Despite the rapid development of proven technologies in this space, however, Alstom’s Nicolas Thiebot says many operators are still hesitant to complete the shift from the old preventative maintenance model, to the new predictive maintenance model.

“The industry has a range of tools and initiatives around condition monitoring, but it’s often bolted onto a systematic maintenance plan,” Thiebot, Alstom’s Services Director in Australia, tells Rail Express.

“People are still a bit reluctant to move away from this systematic, preventative maintenance approach, to a more predictive model. At the moment, it’s a bit of a belt and braces approach, and we really need to move to an optimised version.

“I think the future lives in an understanding that it’s safe and more cost effective, to move on from the preventative to the predictive model.”

Since 2014, Alstom has used its platform, HealthHub, to facilitate a more wholehearted shift towards predictive methods for rail passenger rail operators. HealthHub looks to include as much of the data being collected from around the network, and incorporate it into a central hub to drive maintenance. It takes prioritisation into consideration before making recommendations for work to take place.

“Some of HealthHub’s tools are very mature such as the train to ground remote condition monitoring systems and have been a part of the maintenance industry for a long time,” he says. “The value of HealthHub is to bring them together into a shared platform, and to take the data and convert it into recommended actions to help keep assets in the best possible condition.

“When all the different initiatives around maintenance and asset management are put into one package, you can optimise your operation through dynamic maintenance planning.

“Some of those initiatives are based around asset planning, workload optimisation and work execution, some are to do with remote condition monitoring; they are all important factors in a smart maintenance program.”


Thiebot says Alstom has developed – and continues to develop – HealthHub primarily to aid its own maintenance operations.

Alstom is delivering ongoing rail maintenance for the fi rst stage of Sydney Metro, which opened in May 2019. On that project it is using HealthHub to integrate tools like Catenary Tracer, Track Tracer, Train Tracer, broken rail detection and point machine detection.

Throughout the world, the platform is also available to customers who want to do their own maintenance, however.

“We are developing HealthHub primarily for ourselves, because we believe in the technology and the benefi ts it adds to us,” Thiebot says. “But on operations where we don’t do the maintenance, we can package HealthHub as a product that a customer can use themselves, or as a service that we can perform for them: we produce the reports, do the data mining and so on, to make recommendations to their maintenance operation.”

HealthHub has included onboard rollingstock monitoring and track and catenary monitoring for some time. Thiebot says points machine monitoring is a more recent addition, and the company is looking to add signalling monitoring to the suite as it develops, as well as tools to rationalise the high volumes of data generated by power monitoring and infrastructure monitoring SCADA systems around the rail network.

“The end goal for HealthHub is to help an operator have the smallest downtime possible due to maintenance,” he concludes.


Thales successfully delivers CCS for Sydney Metro

Technology firm Thales has announced the successful rollout of its Central Control and Communication System for the Sydney Metro North West rail system.

The company detailed its work on the project, which commenced operations in May, on August 21.

The Central Control System ensures seamless rail operations, including real-time control mechanisms and data for various diverse systems, while providing a ‘big picture’ holistic view of the entire network.

Meanwhile the Communications System links up the public address and passenger information systems, CCTV and digital information boards, into a centralised system allowing a fully integrated operation.

“We’re proud to have delivered technology that will contribute to fast, safe and reliable journeys for Sydney commuters,” Thales Ground Transportation Australia Vice President Peter Bull said.

“The Sydney Metro project will define our great city for many years to come, encouraging growth and building continued prosperity.”

Thales was selected by the Northwest Rapid Transit consortium to deliver the technology in 2015. NRT was the lead consortium selected by the state government to deliver work for the $7.3 billion Sydney Metro North West project.