CSIR and Transnet engineers are developing the first 13 units of a system that monitors the condition of Transnet’s locomotives, following the earlier successful deployment of two prototypes. The system will enable Transnet to implement predictive maintenance and detect rail infrastructure defects.

Transnet Freight Rail requires the ability to track and trace its fleet of locomotives and determine its condition. Currently, the staff offload data from some of the systems on board the locomotives manually.

The newly developed locomotive condition monitoring system provides an alternative, automated solution, which gathers sensor and fault data through a real-time mechanism, which is then sent to the Transnet servers automatically for evaluation. The system has been designed and tested on all applicable rail standards. It has a unique communications module that integrates GPRS/3G, WiFi, satellite and ultra-high frequency radio into a single module, allowing communication even in adverse conditions. An integrated battery back-up system allows the device to function for at least one hour in the event of a power failure.

The platform has been designed to allow easy expansion of both hardware and software capabilities and there are plans to implement on-board real-time data analysis. Through machine learning and computer vision algorithms, the system is used to implement predictive maintenance, as well as detect rail infrastructure defects.

Transnet aims to deploy the locomotive condition monitoring systems on all locomotives in its fleet.