The oldest railway network in the world, with more than 32,000 km. of track, invests in artificial intelligence and machine learning to streamline maintenance and tackle weather-related challenges.
Two months ago, during the AI and Big Data Expo, I had the opportunity to meet Nikolaos (Nick) Kotsis, Chief Data Scientist at Network Rail. At the conference, he was one of the speakers, talking about their digital transformation and how Network Rail was implementing new ways to inspect and manage network assets, shifting work from traditional schedules to planning and maintenance to a proactive “forecast and prevention” approach.
At the time, Kostis mentioned the real-time data collection, simultaneously from trains using the network, people inspecting tracks, drones, helicopters and more than 30,000 IoT sensors deployed across the country.
All of this data collection allows Network Rail to know what’s going on and take immediate action when something goes wrong or needs to be fixed. But the real magic, which helps predict and prevent incidents, and provides predictive maintenance, happens when AI and machine learning are applied to this massive amount of data.
To find out more about how Network Rail’s Data Science department works and its impact on the organization, we contacted Nick Kotsis again. He answered our questions by email.
PV: As discussed in our previous conversation, Network Rail is undergoing a substantial digital transformation in the field and in the data center. Can you tell us a bit about your data science department and its role within the organization?
Nick kotsis: Our initial plan for the data science function was primarily oriented towards guidance and counseling; However, once we started engaging with customers, we realized that taking responsibility for delivery would not only bring financial benefits to the taxpayer, but would also help our partner network operate more efficiently.
Inspiring trust and earning the trust of our customers and suppliers has been at the heart of my role for the first six months. Since then, we’ve evolved into a true delivery function for data analytics, advanced machine learning, and AI technology bundled into fully integrated digital products that customers can use with minimal training. The end result is a trusted service backed by a knowledgeable and confident team that is customer-centric and responds to Network Rail’s most complex problems.
When customers across the organization ask for help, it means we are doing something right.
PV: You said before that NR is a complex machine, managing the network and some of the biggest stations and maintaining freight trains. How does data analytics (and AI) affect different departments?
Nick kotsis: Our organization is responsible for maintaining a complex infrastructure that is vulnerable to environmental and weather conditions and the constant pressure of hundreds of daily train journeys.
Network Rail maintains 20,000 miles of track. Our job is to maximize the use of data to make infrastructure maintenance a safer and more efficient environment for our passengers and staff.
To give you an example, performing remote inspections on track assets using AI technology instead of touring the track is a real safety benefit for our maintenance teams. Of course, we don’t plan to suspend physical inspections, but if we could confidently limit them to those that are absolutely necessary, that would be a real benefit.
Enable remote inspection using AI technology
More sophisticated data analysis and machine learning techniques consistently demonstrate high quantitative and qualitative benefits. Examples of these advantages can be seen in: incident prediction; the automation of tasks that would be repetitive and mundane for a human; complex risk assessment on thousands of assets in a fraction of a second; and managing complexity using optimization algorithms that also speed up complex decision making.
In our case, we have successfully developed automated risk assessments using computer vision techniques that identify assets for immediate attention on the track and surrounding areas. We have also implemented a preventive maintenance process driven by predictive algorithms that calculate the likelihood of an asset going down days or weeks before it actually happens, allowing us to fix a problem before it happens. that it does not become a problem. Both systems offer significant improvements in safety as well as reduced delays and disruption to passengers.
The advanced big data engineering and algorithmic logic (AI) that we use behind the scenes should, and will continue to extend to all parts of our infrastructure. I am confident that over time we will achieve the desired levels of deployment necessary to scale up our operations to prevent incidents.
PV: The UK has the oldest rail service in the world. However, across Europe and in many other places there are also “old” rail services, each with complex and specific challenges. Based on your experience, what would you recommend for organizations starting or undergoing a digital transformation?
Nick kotsis: Finding the correct answer to this question is not easy as each organization will start at a different point and have a different maturity trajectory. In addition, financial investments for some organizations may be easier compared to others, and the digital journey will therefore be very different.
As with most complex initiatives, the success of digital, data, and AI depends on leadership and commitment to making the journey successful. In our case, we are fortunate to have strong technical leadership from our CIO and CTO. They saw our destination from the early stages of development and helped us make the data science vision a reality.
My advice to colleagues from other organizations? Be clear on the data vision and strategy, engage with customers who need your help, build the right team and prepare them for delivery, and focus on projects with clear benefits.