As the rail industry grows and passenger numbers boom, the rail industry appears to be in pretty robust health. It may hold true to a certain extent. The important questions to ask right now — how do you increase capacity? How do you ensure the railway industry keeps pace with a fast-moving, technology-savvy world?
Artificial intelligence (AI) can often conjure up images of powerful computers capable of performing multiple tasks better than humans. However, currently, the term AI is commonly used to refer to a range of technologies such as software, algorithms, processes, and robots that are able to acquire analytical capabilities and perform tasks, This is shifting technology’s role from enabler to advisor.
That said, there is no way around AI and machine learning (ML) anymore, in railways. AI offers the greatest leverage to meet these challenges. This isn’t just about automating processes. AI helps improve the efficiency, flexibility, and safety of railroad operations to an unprecedented level.
The rail industry’s focus on AI has increased at a rapid pace in the last few years. Managing all aspects such as growing passenger numbers, complex route networks, tightly scheduled timetables, the coexistence of passenger and freight traffic side by side are some of the growing challenges. This is difficult to achieve due to challenges with integration of various systems such as signaling, telecom, operation, rolling stock, electrical, information technology, traffic, infrastructure, etc. And, of course, the involvement of human factors.
Let us consider various areas of interest separately for the railways industry:
AI requires a large amount of linkable data. In railways, a vast amount of operational data is available for modeling and training purposes.
Digitized versions of railway infrastructure should also be readily available. The same applies for rake information and crew rosters.
Signal and telecom
Historical information can be obtained from the data loggers of the interlocking system. This can help to schedule the arrival and departure of trains and also to manage machine-driven operations.
“If we are able to properly introduce AI we could think that in a few years time the next groundbreaking designs will not be done entirely by humans, but with AI support.”
—Giorgio Travaini, Shift2Rail Head of Research & Innovation
There is a whole range of applications and use cases for AI in the railways. Here is a quick look at some of them.
Train schedules can be accomplished using algorithms, simulation models, graphs, heuristics and control systems.
Controlling the speed profiles of trains
An AI-based conﬂict resolution scheme helps achieve hard signaling (signal aspects). It also helps with train speed management. Using Reinforcement Learning (RL) or dynamic programming, this can be computed.
Predicting and reducing delays
Delays are caused due to priorities, downstream conﬂicts with other trains, freight loads, and irregular stopping times. AI can help in the prediction of train delays.
The flawless working of the signaling system is important for safe train operations. Railways completely depend on the health of its signaling assets along with real-time information. By embedding smart sensors on critical rail components and taking necessary preventive actions on a real-time basis.
This enables the operators to quickly react to the existing issues and detect any potential failures before they happen. This way, the need for lengthy root cause identification is eliminated. This results in reduced maintenance costs, less machine failure rate, faster repairs and improved customer satisfaction.
The rail industry uses many procedures. Such procedures will generate a vast amount of data which will only grow in the future and can prove to be difficult to handle. Cloud-based AI technology can be used to collect data digitally. This in turn saves costs and provides consistent accessibility.
Biometric ticketing includes retina scans, voice verification, vein scans, facial recognition and fingerprint scans. This would greatly improve overcrowding issues at many train stations, ending ticket barriers and rush-hour queues.
Systems based on unsupervised learning are implemented in network security: an automatic learning system detects abnormal behavior.
Another important application of AI is driverless automated driving. Automated trams, metros and automated trains provide greater capacity on the rail network. It also enables adapting the transport system to the needs of users by optimizing public transport schedules and transport capacity.