Data analytics for smart railways

SUNIL JOSE

Big Data, or the ‘Internet of Trains’, can help the national carrier transform its services to world class standards

The task of the Indian Railways is best captured in the words of the railway minister during the presentation of the 2016-17 Railway Budget: “Railway facilities have not improved very substantially over the past few decades. A fundamental reason for this is the chronic underinvestment in Railways, which has led to congestion and over-utilisation. As a consequence, capacity augmentation suffers, safety is challenged and the quality of service delivery declines, leading to poor morale, reduced efficiency, sub-optimal freight and passenger traffic, and fewer financial resources. This again feeds the vicious cycle of under-investment. This cycle must be put to an end. …”

The mission, the minister said, is to “reorganise, restructure, rejuvenate Indian Railways”.No easy task

Given the size of the mammoth organisation this is not going to be easy, and nearly impossible without resorting to information technology (IT).

The numbers show why human intervention alone is not enough — the Railways carries more than 23 million passengers over a route of 66,000 km, passing through more than 7,100 railways stations and employing over 1.3 million people.

These overwhelming statistics disclose the millions of contact points with passengers and the information (data) that this throws up can lead to actionable insights.

The need is to apply analytics to the Big Data churned out encompassing all aspects — millions travelling long distance at any given time, ticket reservations, passengers commuting over shorter distances in the millions (the Mumbai rail network, for example), sales points of various items in stations; locomotives, passenger and freight cars, maintenance and service, weighing, loading, dispatching and unloading freight, vendor management, hundreds of thousands of staff at work across the country!

If this is not a scenario that cries out for using analytics, it is hard to imagine any other, anywhere in the world that does.

There are global examples of the likes of Siemens and Burlington Northern Santa Fe Corporation, among others, that use analytics to meet acute service and availability targets, using data for everything from being on time to predicting failures.

In the case of Siemens, it uses and re-uses existing data, creating what it calls an ‘Internet of Trains’.

Towards this end, Siemens analyses sensor data in near real time, which means they can react very quickly, ensuring uninterrupted customer transport service.

In the case of Spanish train operator RENFE, which uses Siemens’ high-speed train, a train developing abnormal patterns is sent for inspection to prevent failure on the track, helping keep RENFE services unbelievably reliable. Only one of 2,300 journeys has been noticeably delayed (by 5 minutes. Passengers are reimbursed fully, if a delay is over 15 minutes.

And it allows the train to compete with flights on routes between Madrid, Barcelona and others.Power of data

This is an existing scenario made possible by analytics and there is no reason why we cannot have the same in India! A pilot project done in the UK by Siemens analysed a data set of one million sensor-log readings, taken in five-minute intervals over one year.

Analysts measured variables such as component temperature and pressure from 300 different sensors and this data was overlaid with many thousands of corresponding reports of failures and fixes. Then the team combined data sources, defined the most relevant engine problems, and divided the data into sections.

They used analytic tools to evaluate the combined data from different perspectives, highlighting variables that helped predict engine problems and identify failed elements that triggered the malfunction of other components.

Siemens then categorised using tools, the different sensors attributing normal, high and low values and, then, tracked changes that showed which sensor pattern was likely to result in engine failure. For example, many a time Siemens found that when the engine temperature dropped from mid to low then rose to mid value again, an engine failed three days later!

Such are the uses of technology that are available for the Railways too! There are various aspects that the Railways has expressed interest in growing, such as e-catering (by the IRCTC). Food safety, availability and choice are at the centre of this and sheer passenger numbers and the ubiquity of social media will mean near-instant customer feedback.Game changer

E-catering can be a game changer for the travelling public and while its operations will constitute that of a medium-sized company, the huge numbers open it up for applying analytics for improvement.

But e-catering is just one aspect of the railways; another is partnering with the Khadi and Village Industries Commission to support creation of employment in rural India resulting in the generation of 17 lakh man days; there are dozens of other programmes all statistically heavy — so the possibilities of using analytics in these aspects can stretch the imagination!

The decision announced in the budget, that the Railways is working on an IT vision is gratifying; while the total investments planned by it over the next five years is a cumulative ₹8.5 lakh crore, a minute percentage of it will have to be in analytics tools, a fraction of a fraction of this figure — but, with the ability to tangibly beneficially impact the entire railway organisation and its patrons for the better.

The writer is the managing director of Teradata India