Reliable AI for the measuring wheel set

AI Innovation Measurement technology Public Safety

SBB uses so-called measuring wheel sets to measure the dynamic contact forces between rail and wheel. Sensors on the wheels measure the forces. It is easier to measure the accelerations on the bogie and calculate the forces using AI algorithms. However, the algorithms must deliver the correct values in a comprehensible and reliable manner at all times.

  • Initial situation

    An ICN measuring train regularly measures the wheel/rail forces on the curved sections of the SBB railway network - for example along the southern foot of the Jura. The sensors (measuring wheelsets) on the rotating wheel are maintenance-intensive.

  • SCS solution

    Together with the Bern University of Applied Sciences, SCS developed a trustworthy machine learning algorithm that calculates the forces using acceleration sensors on the bogie. The calculated values are traceable and reliable at all times for all track geometries in Switzerland.

  • Added value

    The maintenance-intensive sensors on the rotating wheels can be largely omitted. All that is needed are simple acceleration sensors on the bogie. Thanks to the comprehensible development of the machine learning algorithm, the calculated values are reliable and safe.

Sensors on the wheel

The ICN runs along the southern foot of the Jura – a beautiful, but also winding route. To ensure the safety of the track, the forces between wheel and rail are measured regularly. To do this, SBB uses an ICN equipped with sensors. The sensors are attached to one of the bogies. On this bogie, measuring wheelsets on the rotating wheels measure the forces on the wheel. Further sensors are fitted to the bogie itself.

The sensors on the wheels require a lot of maintenance. It would be nice if the forces could only be measured or calculated from the sensors on the bogie. However, the physical relationship between the forces on the wheels and the accelerations on the bogie is complex. This cannot be easily converted analytically.

Machine learning algorithm

One possibility would be to use a machine learning algorithm. AI can deal with complex systems. It is trained with the available data and the physical relationships do not need to be known. However, the algorithm is a black box. It is not known exactly how the results are calculated. However, it is important for SBB’s measurement journeys that the results are correct at all times. So how can an AI algorithm be used on a measuring wheelset?

The AI is like a pilot

The AI can be compared to a pilot flying an aeroplane: The pilot can also make mistakes. Nevertheless, flying is considered safe. This is because the pilot is well trained, conveys trust through communication and adheres to standards and processes. In addition, the risk is minimised as much as possible through both technology and procedures. All of this is regularly checked and documented in a traceable manner.

Trustworthy AI

Applied to a machine learning algorithm, this means that AI is trustworthy if the algorithm has been trained correctly, the results are explainable, standards and processes are adhered to and the risk is minimised. All of this must be traceable at all times.

With the measuring wheelset, the algorithm must therefore be trained specifically in those areas that occur in everyday life on the SBB track network. These are curves with radii of 250 m and larger, as well as lateral accelerations of up to 1.8 m/s2.

The calculated values must be considered plausible by SBB experts, i.e. they must be explainable. In addition, the data used to train the algorithm and which data model was trained with which codes is documented at all times.

Minimise risk

To minimise the risk, a risk analysis is carried out and, for example, the plausibility of the sensor data is checked. It could be that the sensor provides data, but the wrong values – the sensor drifts. As the train always travels the same route, this can be checked quite easily by comparing the values with previous journeys. If the values are consistently too low, as in the example below, the sensor probably needs to be calibrated or zeroed.

Trustworthy AI in the tilting train

The process described, which can be traced at any time, makes it possible to use AI algorithms to calculate the wheel-rail forces using acceleration sensors. The solution was developed for SBB together with the Bern University of Applied Sciences. The University of Applied Sciences developed the original algorithm, while the developers at SCS modularised the code, tidied it up and integrated it into the automated data processing platform RCM-PP. The AI algorithm is currently being tested for reliability in a test phase. The measuring wheelsets – the sensors on the rotating wheels – are still being used occasionally for validation.

Related projects

Visual inspection of railway wagons

Is the block brake worn? How thick is the pantograph contact strip? Is an incorrectly fitted screw coupling hanging down? In future, SBB's "Visual ... More

Visual innovation through AI in ophthalmology

Optical coherence tomography (OCT) is a gentle laser microscope and is used by ophthalmologists to examine the retina for abnormalities. Trained AI ... More

Smart Meter Toolkit

According to the Electricity Supply Ordinance, the grid operator must enable the end customer to receive real-time measurement data from the smart ... More

IOBnet – Exchange platform for ophthalmologists

The IOBnet platform offers ophthalmologists the opportunity to exchange anonymised cases with experts at any time. By creating the platform, SCS is ... More

Predictive Alarm Detection

SBB ZKE measures the bearing and wheel temperatures of passing trains on the open track. SCS has trained an AI model that can predict applied brakes ... More
Show all projects
Pascal Iselin Algorithms, Analytics & AI How can I help you?