{"id":8414,"date":"2026-09-10T06:38:01","date_gmt":"2026-09-10T04:38:01","guid":{"rendered":"https:\/\/www.scs.ch\/uncategorized-en-us\/predictive-alarm-detection\/"},"modified":"2026-09-20T07:38:41","modified_gmt":"2026-09-20T05:38:41","slug":"predictive-alarm-detection","status":"publish","type":"post","link":"https:\/\/www.scs.ch\/en\/case-studies\/predictive-alarm-detection\/","title":{"rendered":"Predictive Alarm Detection"},"content":{"rendered":"

Initial Situation<\/h2><\/div>

SBB uses HFO systems (hot box and stuck brake detection) to measure the bearing and wheel temperatures of passing trains on open tracks. Stuck brakes or overheated wheel bearings damage rolling stock and can lead to axle or wheel failure, resulting in derailment. If temperatures exceed defined limits, an alarm is triggered. On track sections where a train cannot be stopped at short notice, such as in the Gotthard Base Tunnel, this alarm may arrive too late for optimal operational intervention. Earlier detection makes it possible to remove at-risk trains from service before they reach critical sections, thereby avoiding track blockages.<\/p>\n<\/div>

\"In<\/span><\/div><\/div><\/div>

Project Overview<\/h3><\/div>

Client<\/strong>
SBB<\/p>\n<\/div>

<\/div><\/div>

Area<\/strong>
Data & High Performance<\/p>\n<\/div>

<\/div><\/div>

Solution<\/strong>
Early detection of stuck brakes from measurement data.<\/p>\n<\/div>

<\/div><\/div>

System Environment <\/strong>
\nTrain Control Center (TCC), HFO systems (hot box and stuck brake detection), SBB historical measurement database<\/p>\n<\/div>

<\/div><\/div>

Type<\/strong>
\nStudy<\/p>\n<\/div><\/div><\/div><\/div><\/div>

The SCS Contribution<\/h2><\/div>

To achieve this, SCS combined historical HFO measurement data from several checkpoints and developed a model that evaluates temperature development on an axle-by-axle basis to derive the risk of an impending stuck brake alarm.<\/p>\n<\/div><\/div><\/div>

<\/i><\/div>

Early Detection Before the Alarm<\/h4><\/div>
<\/div>
\n

Critical temperature developments are identified in the measurement series before the defined alarm limits are exceeded.<\/p>\n<\/div><\/div><\/div>

<\/i><\/div>

Trained with Real Operational Data<\/h4><\/div>
<\/div>
\n

The HFO measurements and evaluations stored by SBB over many years form the data basis for training and validating the model.<\/p>\n<\/div><\/div><\/div>

<\/i><\/div>

Designed for Minimal False Alarms<\/h4><\/div>
<\/div>
\n

Since each axle is evaluated individually, the model had to achieve an exceptionally low false alarm rate without overlooking actual alarm cases.<\/p>\n<\/div><\/div><\/div>

<\/i><\/div>

Developed Together with SBB Experts<\/h4><\/div>
<\/div>
\n

SBB’s domain knowledge was specifically incorporated into the feature selection, parameters, and evaluation of the model.<\/p>\n<\/div><\/div><\/div>

<\/div><\/div><\/div><\/div><\/div><\/div>
<\/div>

Result<\/h2><\/div>

The study demonstrated that imminent stuck brakes can be detected based on consecutive HFO measurements even before a limit is exceeded. This allows affected trains to be removed from service before critical track sections, preventing disruption to subsequent operations.<\/p>\n<\/div><\/div><\/div>

1:1,000,000<\/h3><\/div>

Targeted maximum false alarm rate per analyzed axle.<\/p>\n<\/div><\/div><\/div>

1 Checkpoint Ahead<\/h3><\/div>

Prediction of a possible alarm at the next HFO checkpoint.<\/p>\n<\/div><\/div><\/div><\/div><\/div>

Services Provided<\/h2><\/div><\/div><\/div>

Algorithms, ML & AI<\/h3><\/div><\/div><\/div><\/div><\/div><\/div>

Data & High Performance<\/h3><\/div><\/div><\/div><\/div><\/div><\/div><\/div><\/div>
\"The<\/div><\/div>

Your Contact Person<\/h2><\/div>
Pascal Iselin<\/div><\/div>

Algorithms, Analytics & AI
\n+41 43 456 16 00<\/a><\/p>\n<\/div>

Speak with the responsible specialist<\/span>Speak with the responsible specialist<\/span><\/div><\/a><\/div>

For questions regarding machine learning, data analysis, and the early detection of critical system states.<\/p>\n<\/div><\/div><\/div><\/div><\/div><\/div><\/div><\/div><\/div>

Further Case Studies<\/h2><\/div>