France’s BPL-HSL: AI-Powered Predictive Maintenance for Rail Safety

Introduction

Eiffage Énergie Systèmes is trialling an artificial intelligence (AI) system on the 182km Brittany–Pays de la Loire high-speed line (BPL-HSL) in France to support predictive maintenance. The project aims to identify potential faults before they cause service disruptions.

Predictive Maintenance System

The predictive maintenance system integrates data from multiple sources. It analyzes sensor readings from SNCF Réseau’s IRIS trains, maintenance records from Ferlioz’s computerised maintenance management system (CMMS), and geometric track design and traffic data, including train counts, speeds, and tonnages. Eiffage’s AI Expertise Centre uses a hybrid approach combining machine learning and deep learning to detect anomalies that could indicate forthcoming failures and inform maintenance scheduling.

Data Collection and Analysis

Engineers are measuring the mechanical behavior of track structures using more than 100 sensors across four representative sections of the line. The instrumentation records temperature, humidity, deformation, and acceleration to supply contextual inputs for the AI models.

Project Goals and Benefits

According to the company, the initiative aims to maintain passenger comfort, ensure train safety, and extend track service life by using data to prioritize interventions. Project teams stated that combining algorithmic analysis with field expertise enables earlier detection of issues, improved allocation of maintenance activity, and continued adherence to safety requirements. The method could be applied to other rail corridors and to different categories of infrastructure as demand for sustainable mobility grows.

Industry Context

The BPL-HSL, which opened in 2017, links Paris and Rennes in 85 minutes. Ferlioz manages infrastructure that carries about 30,000 trains a year and reports a punctuality rate of 99.2%. Eiffage digital expertise activities manager Jean-Louis Haller said that predictive maintenance offers an innovative approach using AI to anticipate failures and optimize operations, addressing the challenges of availability, cost and safety.

Conclusion

The trial on the 182km BPL-HSL aims to maintain passenger comfort, ensure train safety, and extend track service life by using data to prioritise interventions. The predictive maintenance system integrates data from multiple sources. Engineers are measuring the mechanical behavior of track structures using more than 100 sensors. Combining algorithmic analysis with field expertise enables earlier detection of issues. In 2022, a 50:50 Colas Rail–Eiffage Énergie Systèmes joint venture won a €26m Société du Grand Paris contract.

Eiffage Énergie Systèmes

Eiffage Énergie Systèmes is involved in a trial of an artificial intelligence (AI) system to support predictive maintenance on the French Brittany–Pays de la Loire high-speed line (BPL-HSL).

Ferlioz

Ferlioz manages infrastructure that carries about 30,000 trains a year and reports a punctuality rate of 99.2%.

SNCF Réseau

SNCF Réseau’s IRIS trains are used to collect data for the predictive maintenance system.

Colas Rail

In 2022, a 50:50 Colas Rail–Eiffage Énergie Systèmes joint venture won a €26m Société du Grand Paris contract to supply traction equipment for Express Line 18.