Battery value is unmanaged
Charging decisions affect ageing, residual value, usable capacity and operational readiness.
Turning EV fleets from passive energy consumers into intelligent energy assets
BlueMaat turns fleet batteries into managed economic assets across charging, site energy, operations and flexibility markets.
Battery Intelligence Engine
01
Operational data
Charging, vehicle, site and market signals
02
Battery intelligence
State, health, ageing and usable capacity
03
Economic decisions
Cost, peak, battery value and flexibility
Battery-level intelligence for fleet energy decisions
Real-time optimization across energy cost, peak demand, battery ageing, solar self-consumption and flexibility value.
The hidden economic problem
Batteries are the most valuable assets of EV fleets, yet they are still managed as simple electrical loads.
Energy systems optimize in silos
Charging, site energy, fleets and markets are usually optimized separately, with limited battery visibility.
Flexibility value is emerging
Demand response, smart charging and future bidirectional services require trusted battery-aware decisions.
Who we are
A team combining market execution, battery expertise and industrial credibility.
BlueMaat is currently founder-led, with senior battery expertise supporting the scientific and industrial roadmap through the Advisory Board.
Founder & CEO
Shabnam Gholamifard, PhD
17+ years across energy, industrial systems and the battery ecosystem, combining market insight, commercial execution and ecosystem access to turn BlueMaat from technical vision into deployable product.
- Former Business Development & Commercial Director at Veolia
- Battery ecosystem, circular economy and industrial partnerships
- Product vision, business model and go-to-market execution
Advisory Board Member
Claude Chanson, PhD
25+ years across Li-ion technology, industrial strategy and the European battery ecosystem. Claude officially supports BlueMaat through the Advisory Board, with guidance on battery technology, model validation and industrial positioning.
- Former Li-ion Technology Director at Saft
- Former General Manager of RECHARGE Batteries
- Guidance on battery modelling, R&D roadmap and industry positioning
Product
BlueMaat Battery Intelligence Platform
The next value creation layer for EV fleet energy management: connecting operational data, battery models and real-time economic decisions.
The EV industry optimizes charging infrastructure.
BlueMaat manages also the battery itself as an economic asset.
Technology
Battery Intelligence Engine
From operational data to battery-aware economic decisions in real time.
Multi-source operational data
Charging sessions, vehicle usage, environmental conditions, tariffs, prices, grid constraints and available BMS signals when accessible.
Battery behaviour reconstruction
Hybrid battery models estimate battery condition across different levels of data access, with or without direct BMS data.
Real-time decision engine
Decides when to charge, how much to charge, which vehicle first, when to preserve battery value and when to activate flexibility.
Economic value
From optimization to measurable financial impact
BlueMaat turns technical decisions into value creation for depot-based EV fleets.
Proof of value
POC 1: three EV fleet charging strategies compared under identical operating conditions.
Industrial-scale fleet environment modelled with real-world operational constraints.
Scenario
- Fleet100 EVs, corporate vans
- Daily usage60 km / vehicle, 12 kWh / vehicle
- Charging infrastructure20 AC chargers, 7 kW each, 140 kW total
- Energy demand1,200 kWh / night
- OperationsMain charging window 6 PM - 7 AM
- Readiness constraint100% vehicles ready by morning, 7 AM - 9 AM departure window
Uncontrolled, full-power charging with no optimization.
Rule-based scheduling with peak limitation and cost optimization.
Real-time multi-objective optimization across cost, grid and battery constraints.
BlueMaat impact
vs. immediate charging baseline
Peak demand-25%
Charging cost index-11%
Battery stress index-59%
Vehicle readinessMaintained
Data sources and references: public EV battery evidence from He et al., EVBattery: A Large-Scale Electric Vehicle Dataset for Battery Health and Capacity Estimation, arXiv:2201.12358, and the associated Figshare dataset, DOI 10.6084/m9.figshare.23301881. The 100 EV depot scenario and optimization comparison are BlueMaat POC calculations built on these public-data insights and transparent operating assumptions; results are indicative and not yet a confirmed customer pilot.
Battery model evidence
POC 2: cell ageing and public OEM EV thermal behaviour in one modelling workflow.
A technical demonstrator combining a degradation model inspired by NASA battery ageing data with thermal reconstruction on publicly available real-driving EV data.
1. Model cell ageing
Transparent empirical capacity-fade model fitted to NASA cell ageing data.
Median R²: 0.887
Median SoH MAE: 0.017
2. Reconstruct OEM EV thermal behaviour
Thermal model calibrated on public real-driving EV measurements.
Test RMSE: 2.81°C
MAE: 1.31°C
What this demonstrates
BlueMaat can combine cell ageing evidence and vehicle thermal behaviour in one modelling workflow, then translate battery-aware decisions into measurable stress reduction and asset-value preservation.
BlueMaat stress index18.1
Avoided stress exposure81.9 pts
Illustrative battery valueEUR 17k
Data sources and references: B. Saha and K. Goebel, NASA Prognostics Center of Excellence Battery Data Set, NASA Ames, 2007; M. Steinsträter, J. Buberger and D. Trifonov, Battery and Heating Data in Real Driving Cycles, IEEE DataPort, 2020, DOI 10.21227/6JR9-5235; BlueMaat model development and performance metrics. Public datasets are used for technical validation only; no vehicle manufacturer affiliation, collaboration or endorsement is implied.
