How the Railroad Industry is Leveraging IoT Edge Computing

Barbara IoT
railroad iot
Illustration: © IoT For All

The railroad industry is one of the most complex industries in terms of digitization. From a technical perspective, it has many barriers that make it rather difficult to integrate existing systems into modern digital architectures. This can explain its low level of digitization. IoT Edge Computing can be the answer to many of the challenges for railroads.

In a study in the Harvard Business Review, the transport industry is identified at the tail of digital maturity, and the rail sector, in particular, contributes significantly to this low level of digitization. This is not only because it undergoes very strict regulation, but also because technically speaking, it exhibits many challenges that make it difficult to integrate legacy systems infrastructure into modern digital architectures. 

The 5 Vs of Big Data in Railroad IoT

In an article written by a group of experts of the IEEE (Institute of Electrical and Electronics Engineers) in 2020, they identified the main technical challenges of integrating big data in the railway sector. They did so by clustering them into what they called “the 5 Vs”: 

  • Variety: The railway sector is a highly fragmented vendor and technology environment. There are hundreds of different systems on a train, many of which are obsolete due to their long lifetime and low technology turnover.
  • Volume: There is a sheer volume of data reaching up to Terabytes per day which cannot be processed by traditional hardware and software.
  • Velocity: Not only is there a large volume of data that needs to be processed, but it also needs to be fast in order to be considered real-time or near real-time processes.
  • Veracity: Due to the critical nature of railway operations, it is essential to ensure the veracity and reliability of any advanced data processing.
  • Value: Most of the systems are considered of high value, as well as geographically dispersed.

What Is Edge Computing?

IoT Edge Computing is a combination of IoT and edge computing technologies, often used in industrial environments. If we analyze the strengths of Industrial IoT (IIoT) and edge computing as digitization technologies, we realize that it is precisely the answer to most of the challenges aforementioned. 

IIoT allows data to be captured from a number of sources, and edge computing enables the analysis of large volumes of distributed data in real-time, and in a cyber-secure and scalable way, allowing the integration of field equipment from a multitude of suppliers, technologies, and protocols. 

Railroads & Beyond: Benefits of IoT Edge Computing

Let’s take a look at five use cases that describe the potential benefits of IoT Edge Computing in for both railroads and other critical industries.

1. Digital Twin and Predictive Maintenance

The digital twin, or digital twin instances, allow for digital representations of each working part in a physical system. They are one of the pioneering innovations of Industry 4.0, but also one of the most profitable from the business point of view. These digital instances are needed to optimize the product value chain spanning from manufacturing to maintenance and after-sales service. They can be used for remote diagnostics and monitoring, leading to important cost savings in personnel and travelling. 

They can also automatically anticipate the possibility of incidents, combine historical data, human experience, machine learning and simulations, all of which improves the forecasting results. McKinsey has calculated that 51 percent of companies using artificial intelligence have witnessed their operating costs reduce by more than 20 percent. Decisions based on where to locate supply bases, how and when to plan overhauls, and what materials to use have a direct impact on the operating costs. Likewise, for real-time digital twins to operate, it is necessary to process large amounts of data while ensuring low-latency.

For example, a vibration IoT sensor for motor fault detection requires an algorithm that processes data at a minimum rate of 1kHz (1000 data per second). This, coupled with the common coverage issues of any transport, makes Edge Computing the most suitable technology for these use cases.

2. Obstacle Detection

Safety in rail transport is traditionally another major challenge for operators. In the event of poor visibility due to bad weather or human error, computer vision emerges as one of the most interesting solutions towards a smarter and more automated transport. An automatic obstacle detection system helps improve the emergency handling capacity, and the safety of travelers or pedestrians.

The Shift2Rail organization, whose mission is to define and deliver digital capabilities that make European rail transport a more customer-centric and sustainable mode of transport, is dedicating a working group and an entire project to this subject. Obstacle detection is a critical mission that demands high computation processing, one that only Edge Computing architectures can execute.

3. Software and Firmware Upgrades

On-board systems are getting smarter and more software oriented. The requirements of these systems change over time, and it’s very common for many iterations to be able to optimize the use of these systems. Moreover, the IT systems can become obsolete due to security vulnerabilities. This is why the ability to run updates in software configurations and firmware is becoming increasingly important.

An unified system, as well as a homogeneous remote process for equipment updates can save costs. In fact, manufacturers such as Alstom are already deploying containerized application architectures on the Edge, which helps them reduce manual processes by automating the lifecycle of edge devices and deploying new versions on-demand.

4. Improving the Safety of Moving Trains

To ensure the safety and stability of a moving train, real-time monitoring of parameters such as speed and load are of great importance. The combination of IoT sensors with high computing power is an optimal solution in this sense.

With small sensors, high-frequency rail vibration information caused by the wheels can be collected. Through edge computing, the speed and the status of the parameters associated with the current rolling risk can be calculated. Scientists at the University of Hong Kong have demonstrated that continuous 24-hour monitoring is feasible with edge computing architecture. It has impressive results such as speed errors of less than 0.2 km/h, and with the advantage of taking up very little space on tracks and trains, all at a much more controlled cost compared to the traditional systems.

5. Improvements in Health and Compliance

There is no doubt that the COVID-19 pandemic has abruptly forced many industries to change their priorities and address issues related to health and social distancing more efficiently.

Through IoT edge computing, it is possible to monitor in real-time elements such as the quality of the air, and the compliance of using face masks or social distances in stations and trains for instance. With more advanced algorithms, it will be possible to identify areas that require a more thorough cleaning or even guide automated cleaning systems to disinfect areas.

The Impressive Influence of IoT for Railroads

There is no doubt that the railway sector is one of the most complex industrial environments in terms of digitization. edge computing can work to improve safety for travelers, detect potential obstacles, and enhance predictive maintenance. The 5 Vs make the integration of big data into the railway sector more difficult, but edge computing can be the solution to overcoming these technical challenges, allowing the analysis of large volumes of data in a real-time, cyber-secure, and scalable way.

Barbara IoT
Barbara IoT
Barbara is the Cybersecure Industrial Edge Platform to govern the distributed intelligence.
Barbara is the Cybersecure Industrial Edge Platform to govern the distributed intelligence.