Future-oriented application of tools: AI-based systems as support in engineering processes at Siemens Mobility

We have been active in rail transportation for around ten years, particularly in the area of predictive maintenance using Railigent X. Here we try to use intelligent models and data analysis to predict when maintenance work is required on points or train doors. We are convinced that the use of artificial intelligence can help to predict and thus prevent errors.

Another example is the pilot test with Ostdeutsche Eisenbahn GmbH (ODEG), which is responsible for operating regional trains in Brandenburg. At ODEG, we are using intelligent video surveillance (CCTV) in the vehicles. Train drivers and the control center have access to the video material. At present, people have to view this material, but with the help of AI it could be automatically evaluated and appropriate messages generated. For example, the system recognizes the occupancy in the vehicles or whether the wheelchair space is occupied. We then make this information available to passengers via corresponding apps.

A third topic that is currently occupying us is autonomous driving, which is also having a major impact on the automotive sector. We are working on the development of AI-supported assistance systems and autonomous technology. I will go into this in more detail later.

VDE: Which aspect of AI offers the greatest advantage: maintenance and reliability or cost reduction through increased efficiency?  

Edel: Artificial intelligence opens up completely new possibilities for automation. Things that were previously said to be impossible with traditional computer technology, such as autonomous driving or maintenance predictions, are being implemented. Automation also always means an improvement in quality compared to manual production. It makes processes more efficient and of higher quality. We have a team that focuses exclusively on improving internal processes. This applies not only to rail technology, but to Siemens as a whole. With regard to the railroads, however, it remains a question of combination. Processes will change, but they will also become more efficient and of higher quality.

VDE: And that is legitimate. Companies are focused on profits and have to sell their products at a price that customers are willing to pay. In this context, it is understandable that companies strive to optimize costs.

Edel: Both our costs and those of our customers are relevant. What we suggest to our customers today: "Invest in our latest signaling technology to run more trains on the same infrastructure without having to expand it", and: "Also consider using AI-based solutions to maintain your trains smarter and further reduce breakdowns." I am aware that this is currently a challenge as there are unreliability issues in rail transportation. The problem was aptly described by the CEO of Deutsche Bahn. He emphasized that there is simply too much traffic on the infrastructure. It is not individual trains that are unreliable or more unreliable than in other countries. On the contrary - reducing the volume of traffic by around ten percent would greatly improve reliability or the infrastructure would be digitized as described above so that it can cope with this volume of traffic. 

"We need artificial intelligence that can be licensed"

VDE: You mentioned in the run-up to  an aspect that I would like to expand on. You said that you could learn something from the automotive industry. Can the automotive industry also learn something from the rail industry? 

Edel: I had an interesting conversation with a tier-one supplier from the automotive industry about supplying sensors for our assistance systems. We wanted the sensors to be even smarter and better adapted to our needs. My conversation partner then asked me: "How many streetcars are sold worldwide each year?" I replied that there are around 600. He then said: "Even with 600,000 units sold, we can't find any companies in the automotive sector to support us in further development." We have also had similar discussions in connection with fuel cells. In the automotive sector, it only becomes interesting when sales reach millions. We would therefore have to transfer more developments from the automotive sector that are relevant to us to our area.

In the case of automated, assisted driving, however, the sensor technology in the automotive sector is not suitable for the specific requirements of rail transportation. The braking distances differ considerably due to the different tires (rubber on the road, steel on the rails). Although such sensors are available in military technology or aerospace, for example, they are too expensive for a high-speed train. We are currently pursuing a hybrid approach that combines intelligence in both the vehicle and the infrastructure. Can such a solution also be used in the automotive sector? We regularly have this discussion with representatives of the automotive industry, that it's not just about making vehicles more intelligent, but also the infrastructure. The railroads already have an intelligent infrastructure. We can therefore learn from each other.
 

VDE: You have convinced me with your arguments on the subject of artificial intelligence. But how do your customers react to the topic of AI? 

Edel: Customers in our B2B business are, for example, operators of rail vehicles and infrastructure. They are very open to testing new technologies together with manufacturers and as part of collaboration platforms such as Europe's Rail. European projects like this allow us to build and test prototypes. There is little skepticism on the customer side and a lot of courage to innovate. One example of an innovative technology is the European Train Control System, which has developed a common safety system for European rail transport. The idea has been well received and the infrastructure is gradually being upgraded to enable a system solution.

There are similar challenges with AI. If we want to drive autonomously, we need route data in the vehicle. Nowadays, a vehicle doesn't need to know anything about the route, but receives information via the signaling. But for autonomous driving, we need a route atlas that does not yet exist. Information about roadworks, the condition of the route, etc. must be available at all times. This is a challenge that requires digital solutions, such as cloud-based applications. 

The question arises as to who is responsible for this, who may have a business model and who bears the costs. Discussing this will probably be more difficult than finding customers for prototype testing.
 

VDE: This brings us to the question of the challenges involved in integrating artificial intelligence: what areas of tension do you see? 

Edel: Siemens Mobility and the entire industry are ambitiously pursuing the development of a licensable artificial intelligence, known as Safe Artificial Intelligence (Safe AI). In order to obtain approval, rail vehicles currently still require a driver, similar to autonomous shuttle buses on the road. This driver can intervene in an emergency and stop the vehicle. However, the question is whether approval is possible without a human backup.

To this end, we have launched the Safe-TrAIn project, which brings together relevant stakeholders such as customers, manufacturers, the German Federal Railway Authority and other approval bodies. Our aim is to develop an AI-based solution that can be approved for rail transport. This is our biggest challenge, not the system's capabilities, as these are already very advanced.

"We are creating the 'industrial metaverse' of the railroad"

VDE: It is very good that the VDE is involved in Safe TrAIn as a project partner. What is your vision for artificial intelligence at Siemens Mobility? What are the next steps?

Edel: In Engineering, we focus on topics such as Digital Twin and related technologies. In my first position at Siemens, I developed a digital twin: simulation software for railroad power supply networks that can predict how they will function under different conditions. I had the vision of engineers being able to plan their systems virtually with the help of a digital twin. AI-based systems should support engineers, but not completely replace them. A hybrid approach, in which humans remain in control and are supported by artificial intelligence at the same time, can enable faster and higher-quality results.

Thinking this through to the end, we are connecting the physical and virtual worlds and creating the "industrial metaverse" of the railroad. This would be a further step towards optimizing processes at the customer and manufacturer.

VDE: For new solutions and applications in the field of AI, we also need young people and their ideas. What advice would you give young people for the future and their career planning?

Edel: If someone wants to make a career and achieve something, it is initially important to dedicate oneself to the current task with a great deal of ambition and, if necessary, to seize the opportunity. It is crucial to have confidence in yourself. Of course, luck and timing also play a role in creating opportunities and your own performance is also important. 
It is advisable to ask yourself what career direction you would like to take, be it in management, project management or in a specific specialist function. The decision for career development is exciting and individual. It is possible to make this decision, but it seems counterproductive to set specific long-term goals at this stage. You should have fun, keep an open mind and focus on your own interests and developments. Siemens means opportunities and there are many ways to develop. The rail industry also needs young, committed minds and we welcome new applicants.

VDE: Mr. Edel, thank you very much for the interview.