Using 'Big Data' for Predictive Rail Maintenance

Trains and public transport in general are for many people, an important part of their daily lives. Large cities are particularly dependent on efficient public transport systems, and if disruption occurs, it affects many passengers while spreading across the transport network. But our requirements and expectations as passengers are growing and maturing. Safety is paramount, but we also care about timeliness, comfort, internet access, and other amenities. With strong competition for regional and long-distance trains, providing an attractive service has become critical for many rail operators today.

The railway industry is an old industry. For the last 150 years, this industry was built around mechanical systems maintained throughout a lifetime of 30 years, mostly through reactive or preventive maintenance. But this is not good enough anymore to deliver the type of service we all want and expect to experience for what we pay for.

If the temperature goes up, the rail expands, and all of a sudden, they’re dealing with kinks in the rail. If the temperature goes down, the rail contracts, and as a result, rail companies faces broken rails.

Passengers feel frustrated every now and then sometimes all too often due to rail delays, excessive rail demands, rail works and disturbances as a result of inclement weather especially when it is not expected, or accidents on the rail, UK rail operators continually face scrutiny over the quality of their service they are providing commuters versus the costs of the rail tickets which increase in price yearly. With services frequently disrupted by signalling problems, leaves on the tracks, broken-down trains and congestion, the industry, the Government and consumers all recognise that something needs to change and change must come as soon as soon as possible. This becomes more apparent when ticket prices are increased every year versus income level rises versus what is perceived to be the same or worse train service.

Predictive maintenance is a technique that predicts an incidence(s) when an in-service machine will fail so that maintenance can be planned in advance. It encompasses failure prediction, failure diagnosis, failure type classification, and recommendation of maintenance actions after failure.

Deriving insight from trains data

Over the last few years, the rail industry has been transforming itself, embracing IT, digitalization, Big data, and the related changes in business models. This change is driven both by the railway operating companies demanding higher vehicle and infrastructure availability, and, increasingly, wanting to transition their operational risk to suppliers. In parallel, the thought leaders among maintenance providers have embraced the technology opportunities to radically improve their offerings and help their customers deliver better value.

At the core of all these changes is the ability to derive insights and value from the data of trains, rail infrastructure, and operations. In essence, this means automatically gathering and transmitting data from rail vehicles and rail infrastructure, providing the rail operator with an up-to-date view of the fleet, and using data to improve maintenance processes and predict upcoming failures. When data is used to its full extent, the availability of rail assets can be substantially improved, while the costs of maintenance are reduced significantly. This can allow rail operators to create new offerings for customers.

Predictive Maintenance portrays its importance because businesses evolve in one of two ways; improving their product(s) or reducing their price. Predictive Maintenance allows them to do both. By being able to predict when components will fail, organisations can optimize their repair plans to minimise downtime and make unplanned stoppages or failures a thing of the past. That is the one-two one-two punch of predictive maintenance that’s going to knock out the competition. However, it goes beyond that. Predictive Maintenance models failure patterns, which gives you the ability to build fault trees, perform Root Cause Analysis (RCA) and essentially improve product engineering to reduce the number of faults in the future. It’s a circular continuous improvement cycle.

Predictive maintenance as a concept, is not new. The ‘predict and prevent’ maintenance methodology has existed since the moment the first linesman walked the track, tapping the rail. What’s changed, however, is the cost of collecting and storing the information. Where once actively monitoring the state of an asset required frequent, physical inspection and acres of physical storage space, now the same information can be gathered, transmitted and stored remotely.

Railway systems have complex technologies, with a wide range of human actors, organisations and technical solutions. To control such complexity, a viable solution is to apply intelligent computerised systems to make use of the big data that is collected on an everyday basis during operation of the rail system.

Whereas maintenance traditionally consisted of checking rail vehicles/rail cars at operating centres on a regular basis, resolving obvious problems, and maintaining machines, digital technology has opened the door to a new level of service. Remotely or locally collected sensor data, error messages, and log files provide Rail employees with an unprecedented level of detail regarding rail vehicles and their infrastructure.

Such data can be in the form of error messages, log files, sensor data snapshots, or true time series sensor data.

One technology that is starting to be used to address this challenge is Big Data through Predictive Maintenance (PM). This is a technology solution that has come to the forefront thanks to the recent advancements in sensors and communication technologies in trains. These sensors, embedded into various systems and sub-systems in trains, generate huge volumes of data, which can be collected and analysed 24 hours a day, seven days a week, 365 days a year. This helps operators identify looming faults, forecasting the optimal time for maintenance and ultimately enabling them to predict conditions that could cause problems in the future and tackling them early, before any service is affected. The success that this technology has already had, has led it to fast becoming one of the most sought after Maintenance, Repair and Overhaul (MRO) strategies in the industry.

Big data establishes the health of the infrastructure and - beyond that - contributing to strategic decisions about the railways.

Rail cars, Locomotives, wayside, signal equipment and track testing processes generate massive amounts of machine data that contain a mine of information. Using this data to identify future failures and degradations can allow railroad operators to improve performance. This allows maintenance teams to perform effective repairs and allow fleet managers to assign the healthiest assets to the most critical routes. Real time analysis of driver & vehicle data collected by onboard sensors is harnessed using modern data architecture and visualization software.

Big Data is mostly being used for maintenance rather than operational decisions. Data is used to predict failure.

As is shown in Figure 1 below, Big Data analytics helps to predict the optimal timing for maintenance. In most instances, the process becomes very costly, but if it is reactionary, the implications could be far worse. If looming faults are identified proactively, not reactively, then necessary maintenance work can be started just before a faults occur thus maximising the efficiency of the whole process.

The optimal maintenance timing: higher availability and lower maintenance costs - Figure 1

Today’s technology makes it possible to collect huge amounts of data from hundreds of systems in a single train, analyse that data in real-time and detect problems before they actually happen. This detailed overview provides much greater visibility, both on the train as a whole, and at a more granular component level. It’s this insight that allows maintenance activities to be planned with the maximum interval between repairs, while minimising the number and cost of unscheduled outages created by system failures.

It can do more than that, but to make strategic decisions you need more data.

THE BENEFITS OF USING DATA IN RAIL

Predictive Maintenance (PM) enhances the overall effectiveness of transportation systems, ultimately leading to improved safety and higher customer satisfaction overall, something that is very important for the continued credibility of the network operators. This later enables the justification of ticket prices versus the service provided.

Affordable solutions can generate Return On Investment(ROI) quickly while completely transforming the maintenance landscape. Computing systems are evolving rapidly to on-board intelligent systems without taking data to any remote cloud. However, these technologies are new and therefore immature within this service sector.

Looking at examples from other industries such as aerospace, train operators and Original Equipment Manufacturers(OEMs) should follow these five steps in order to deploy Data Analytics and Predictive Maintenance successfully. Each stage is crucial in ensuring that prediction is possible and that it can be implemented into the maintenance scenarios previously discussed:

1) Choose the right system or subsystem for prediction

Selection of the system is the most critical step in building a Predictive Maintenance (PM) solution. It is crucial to define a narrow scope and not try to predict everything. Doors would be a typical example of such systems.

It is therefore important to identify what is possible to predict. You can do this by mapping the available systems into a “prediction possibility zone” and a “prediction effectiveness zone” (as shown in Figures 2 and 3 further down below).

The latter of these is particularly dangerous, as organisations could potentially make the mistake of dismissing a vital solution that they have a clear need for, simply because they did not appropriately select the original parameters it was required to cover.

THE PREDICTION POSSIBILITY ZONE

The objective here is to predict the failure of the most critical systems. However, such systems run the risk of leaving very little data to build any consistent model. However, there is limited value in predicting the failure of less “vital” systems, even if they produce a plethora of data.

It is important to select the critical events that leave enough of a digital footprint that is required to build a consistent and reliable predictive model. In essence, a system has to fail enough to reveal the pattern, but it must equally be important enough to be worth predicting and investing time analysing in the first place. So the prediction possibility and viability zone is somewhere in between those limits of frequency of occurrence and event criticality. As shown in Figure 2, an ideal system or subsystem has to be chosen for building the PM solution based on the prediction possibility zone.

Prediction possibility zone - Figure 2

PREDICTION EFFECTIVENESS ZONE

Another way to look at system selection is to find where prediction is more effective from a maintenance point of view. The failure rate of mechanical and electrical systems typically follows a bathtub type of curve (as shown in Figure 3 below).

Figure 3: Bathtub type curve: Hypothetical failure rate Versus Time

In order to realise a quick Return on Investment(ROI), either early life or end-of-life systems are more suitable for deploying Predictive Maintenance solutions, as you will derive the greatest benefit from predicting their failure. Thus delivering a better service.

2) Identify the required data sets as early as possible

It is generally assumed that the sheer volume of data generated from systems is sufficient to build Predictive Maintenance solutions from it. However, it is important to remember the objectives behind collecting each data set. They may have been deployed by the manufacturer without any Predictive Maintenance solution in mind.

So preparing the data required for building Predictive Maintenance solutions is one of the key activities in the process of solution development. It is not always what operators already have, but it is about what the solution needs. A fair understanding of the objectives is necessary to come up with the required data sets.

Taking a top-down approach often leads to a successful outcome here. This is where the business objectives are clearly defined first, before the required data sets are identified, and then the data is prepared in order to develop an algorithm.

3) Identify the value-addition of Predictive Maintenance (PM) for maintenance strategies

The scope of a Predictive Maintenance solution can go beyond just predicting a failure, since in most situations; prediction is not the only objective. It’s also about identifying various business initiatives and building appropriate prescriptive actions.

Therefore, an effective Predictive Maintenance solution should also support the maintenance teams in planning the inventory for replacement of parts and suggesting which systems need an upgrade in their design due to their continued poor performance and or failure. This is possible by understanding the reasons behind various failure patterns and categorising them into various action points.

Predictive Maintenance solutions should address both short-term and long-term objectives.

4) Compliment your Data Science team with a Rail expertise team

It is important to support your Data scientists’ understanding with knowledge of the rail sector. It is generally assumed that a data scientist is all that is needed to build a cutting-edge algorithm for a Predictive Maintenance solution. A data scientist can develop any algorithm, but it takes a lot more to deliver the right algorithm for a specific business need with a view to getting a solution. Experience shows that it is the domain expert(rail in this case), as opposed to the data scientist, that is the real hero in achieving a successful solution, as they can guide the data scientist to build the right algorithm. Interpretation of patterns – vibration and noise for example – is a key area where the rail expert can guide the data analyst as to not over-interpret coincidence findings.

5) Look for the right skills when hiring Data Scientists

Lastly, as Big Data analytics is an industry that is still in its infancy, more specifically in the rail industry sector, it is incredibly important that individuals with the right skills and experience are brought on board. When hiring junior level developers, look for those with a general understanding of analytics and basic knowledge of java programming at least. This makes it easier to train them in Hadoop-based programming. For senior level roles, look for a strong technical background in analytics with matching exposure to the transportation domain to some extent.

PREDICTIVE MAINTENANCE IN RAIL

As Big data analytics is bound to establish its position in the rail industry, operators should look to successes that have already been gained in other industry sectors to deploy effective solutions. It is already a mature and proven concept elsewhere and there is no reason why the rail industry cannot reap the same derived benefits. The success of Predictive Maintenance in the rail industry lies in the selection of the right systems, creating and preparing the necessary data, and getting the right combination of rail experts and data scientists on board. Combine those factors and you have a winning formula in achieving your objectives.

In addition, Original Equipment Manufacturers(OEMs) should look to Predictive Maintenance (PM) to deliver beyond mere prediction of failures but also to identify those systems that need design upgrades for example.

Big data analytics in railway Operations and Maintenance(O&M) will use advanced technologies to perform predictive analytics and make decisions based on the analysis of huge amounts of data.

The benefits of using data for predictive maintenance include:

• Minimised maintenance costs. Don’t waste money through over-cautious, time-bound maintenance. Repair equipment only when repairs are actually needed.
• Reduced unplanned downtime. Implement predictive maintenance to predict future equipment malfunctions and failures, and minimize the risk for unplanned disasters that could put your business at risk.
• Root-cause analysis. Find causes for equipment malfunctions and work with suppliers to switch off reasons for high failure rates. Increase return on your assets.
• Efficient labour planning. Stop wasting time and parts replacing and fixing equipment that doesn’t need it.
• Avoidance of warranty cost to recover failure. Minimize recalls and assembly-line production loss.

Preventive maintenance strategies make sure that failures are avoided as much as possible, and safety for the passengers is ensured

Too many sudden machine failures can result in contract penalties which can lead to lost revenue, and can even ruin the reputation of affected business which can lead to the loss of contracts. Big Data/Data science can help avoid problems in real time and before they happen.

Therefore, besides increased availability and cost efficiency, train commuters will have fewer delays and increased safety which will result in higher customer satisfaction. The industry continues to embrace technology as an enabler of safe and profitable performance.

Widespread adoption of predictive maintenance tools signals a meaningful advancement in the use of technology, and it has reduced the probability of unplanned downtime due to asset failures. Predictive analytic technologies have been applied in other industries to successfully solve complex asset reliability challenges.

The use of new and emerging technologies is leading to improved quality of services, new savings, enhanced resource utilisation and efficiency. It has also enabled the development of new services and business models based on the capability of the industrial internet and the analytics capabilities of big data. Big data has the potential to transform the current state-of-art railway technology platforms into a network of collaborative communities seamlessly moving freight and passengers and delivering services in a planned way with less disruption. 

The advantages for the rail system operators and maintenance teams are obvious because the system results in greater availability, a longer service life, and substantially increased efficiency when it comes to maintenance and the operation of all of the trains and infrastructure components.

Optimising maintenance for rail assets is vital for delivering a safe, reliable, and profitable rail network. Acquiring precise information about rail assets is a crucial part of predictive maintenance decision support environment.

A data-driven approach is revolutionizing many ecosystems. We are all benefitting from the ease with which enormous data sets can be processed.  Big data enables us to understand and optimise the consumption patterns of equipment which leads to cost reduction and enables green operations of equipment, systems, facilities and businesses.

There is no doubt that some parts of the rail sector have already embraced the digital revolution. Making use of big data to improve passenger information, streamline ticketing and payment methods, and even optimising scheduling, a digital revolution is already underway. However, the same cannot always be said of the grimier face of the rail industry – the operational maintenance side. The revolution that predictive maintenance will bring about for the whole rail sector is now invaluable.

#predictivemaintenance #BigDataOnRails #Bigdata #Transportation #Rail #RailMaintenance #viable data-enabled business #data-driven services

Credit: Bhoopathi Rapolu, Dr. Diego Galar, P.M.