Case Study: Network Rail achieves more reliable, cost-efficient maintenance with KONUX AI predictive maintenance

Use of ai to achieve a reliability-centered maintenance regime

Network Rail faced the challenge of an inefficient, interval-based maintenance regime for rail switches. This approach provided biased condition snapshots, often leading to unnecessary maintenance on healthy assets, accelerated degradation, and a lack of insight into which maintenance activities were actually effective. To address this, they embarked on trials with KONUX to explore a more data-driven solution using its Predictive Maintenance System for Rail Switches.

KONUX implemented its IIoT system to provide constant monitoring of switch conditions. The solution delivered insights into trackbed health, true asset usage, and the effectiveness of maintenance actions like tamping. For Network Rail, the results included avoiding unnecessary tamping, preventing track closures, and identifying ineffective maintenance practices early. The KONUX system demonstrated a potential for a 20% reduction in delay minutes, leading to significant cost savings and improved operational efficiency.

Network Rail