A holistic switch vision: Integrating track & signalling insights

Spring '24 Product Update


Maintaining the efficient and reliable operation of switches is critical for the safety and performance of rail networks. Traditionally, track and signalling systems have been treated as separate entities in railway maintenance. However, a holistic approach that combines insights from both track and signalling can significantly enhance the overall efficiency of switch maintenance, leading to improved reliability and safety in rail transportation. KONUX does exactly this by utilising IIoT devices and artificial intelligence to improve network capacity and extend asset lifetime while reducing costs.


Our approach to track insights

The condition and health of the trackbed is especially critical for the areas such as point machine and crossing (frog) as these components are exposed to high forces. Unhealthy trackbed conditions can drastically increase wear, failures and safety risks. Railway infrastructure managers identify unhealthy trackbed conditions as a root cause for 60-80% of the failures at signalling components of a switch – that is the point machine, locking, driving rods, end position controller. 

KONUX Switch allows for continuous monitoring and prediction of voiding of the sleepers, providing the necessary lead time to plan and execute maintenance. Specifically, we display continuous records of the current and the past trackbed displacement values under the influence of passing trains. Using this historical data our AI models are able to provide an estimate of how voiding will progress in the future. These prediction models, tested against the historical customer data, revealed an accuracy of over 90%. Additionally, our models take into account the context of elements like speed and temperature, which enables us to deliver alerts on events that are meaningful and relevant to the context of the assets as well as the users.

KONUX also measures the vertical and lateral impact force at the switch which can inform of hard spots and excessive vibrations that do not manifest as high displacement. This allows for a view of trackbed and asset health beyond simple voiding measurements. Furthermore, we are able to provide visibility into which maintenance actions performed best as our system validates maintenance activities that occur where the IIoT device is installed and assesses the effectiveness of maintenance actions to avoid repeating failures.


Our approach to signalling insights

Signalling systems also play a crucial role in ensuring the safe and efficient movement of trains. The integration of signalling insights into switch maintenance involves monitoring the performance of the point machine, locking, movement etc, associated with switches. KONUX Point Machine detects and diagnoses underlying faults of different subcomponents using electric current data.  It alerts users to potential failures while factoring in weather data and track condition. Additionally, our system assesses the effectiveness of maintenance actions to avoid repeating failures. This approach helps our users identify root causes of failures and optimise maintenance. KONUX Point Machine forms a key part of the KONUX vision for holistic switch monitoring, since point machine failures are responsible for nearly 60% of switch delays. 


Our holistic vision

KONUX aims to reduce delays, optimise inspection and maintenance planning, and ensure that faults are maintained effectively by identifying their root cause. In addition to IoT data from our devices, we aim to integrate multiple additional data sources such as track geometry and photos of the track to give our users a single holistic view of their switch.

Holistic Switch viewed in our UI

By integrating both track and signalling insights KONUX Switch leverages the power of understanding all the switch interactions which no other solution on the market offers. With this holistic approach KONUX is able to provide our users with decision support insights along with relevant context, predicting when it is most optimal to act, which action should be taken, and supporting maintenance teams by identifying the effectiveness of their interventions.

Share this post