The control signal of railway pointing systems provides critical information about the health of the system and reveals faults and ageing phenomena.
The electrical current of the railway pointing system activator was captured. A dataset was available describing healthy and faulty behaviour. The need is to build a model that automatically detects faulty behaviour to alert maintenance operators.
DiagFit was used to build a predictive model to alert on faulty behaviour. Both supervised and unsupervised learning (without erroneous data) was possible.