United KingdomLogistics and transport2024 – ongoingNetwork Rail
insight data and machine learning tool for track maintenance
Network Rail's insight tool lets engineers read track data 50% faster and flag faults up to a year ahead
Problem
Track, weather and inspection data sat in separate systems. Combining sources such as track geometry and ultrasonic rail tests could take months, and maintenance was often reactive.
Approach
The Intelligent Infrastructure program built insight with Microsoft engineers on Azure Data Factory, Databricks, Machine Learning and Power BI. It puts data streams in one view and uses machine learning to forecast track deterioration and plan maintenance.
Results
Takeaway
Joining separate asset datasets let engineers move from fixing faults to planning work. Emergency speed restrictions on busy sections can cost about 250,000 pounds, which is the cost such planning aims to avoid.
Categories
- Size
- Large enterprise
- Industry
- Logistics and transport
- Business function
- Production and quality
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and ML
- Adoption
- Co-developed with a partner
- Evidence
- Vendor's case study
Sources
Source summaries
Microsoft explains how Network Rail combined its asset data into one Azure-based tool. It reports faster data analysis and earlier fault detection.
Full details are in the original sources.
