End User
UTBM
Description
The AI-Driven Energy Management service optimises power allocation between fuel cells and batteries in Fuel Cell Hybrid Electric Vehicles (FCHEVs) using a reinforcement learning framework. The service minimises hydrogen consumption, maintains battery SoC, and extends powertrain component lifetime through adaptive power-split decisions evaluated over complete driving cycles.
Core Capabilities
Predictive & Prescriptive Analytics
Optimization & Decision Support
Business Need
In FCHEVs, the power split between the fuel cell and battery determines hydrogen consumption, system efficiency, and component longevity. Fixed rule-based strategies cannot adapt to the sequential and dynamic nature of driving conditions. Reinforcement learning enables intelligent strategies that learn optimal behaviour from historical driving data, improving hydrogen range and system sustainability.
Key Performance Indicators
Total hydrogen consumption per driving cycle vs. baseline strategies
Battery SoC balance and powertrain operational constraint compliance
Estimated driving range improvement
Robustness across varying driving profiles and load conditions
Data Provided
Power-split decisions between fuel cell and battery per time step
Fuel cell and battery utilisation profiles, SoC evolution, hydrogen consumption
Aggregated efficiency indicators over complete driving cycles
Inputs: vehicle speed, acceleration, power demand, fuel-cell V&I, hydrogen flow/pressure, battery SoC, thermal conditions
TEF
TEF H2