EV Battery-Pack Thermal Monitoring Module
US-based EV / battery technology companyA distributed monitoring module captures thermal conditions across an EV battery pack and identifies abnormal temperature behavior for battery-management and diagnostic systems.
Where AI accelerated vs. where our engineers led.
Every project follows the same Rivix Split — AI drafts the mechanical work, a named engineer reviews and owns every decision that touches safety, cost, or a regulatory limit.
Where AI accelerated
- Device drivers & firmware implementation
- Diagnostics logic
- Data-processing code
- Test generation, documentation & code review
Where our engineers led
- Thermal architecture
- Safety behavior & fault handling
- Real-time constraints
- Hardware design & validation
- Automotive compliance considerations
Technical deep-dive
Additional detail on architecture, stack and implementation specifics for this engagement.
Architecture & stack
The module distributes thermal sensing across the battery pack, feeding readings into firmware running on an automotive-grade MCU that performs real-time diagnostics and communicates pack health over the vehicle's in-vehicle bus to the broader battery-management system.
- Distributed thermal sensing across the pack feeding an automotive-grade MCU
- Real-time diagnostics logic running locally, reporting over the in-vehicle bus
- No external network dependency — this is an in-vehicle real-time system
Connectivity & data pipeline
Thermal data is sampled at a rate fast enough to catch abnormal temperature gradients between cells, processed locally against fault-detection logic, and reported over the vehicle bus rather than an external network — this is an in-vehicle real-time system, not a cloud-connected consumer device.
- Sampling rate tuned to catch abnormal inter-cell temperature gradients, not just averages
- Fault-detection logic evaluated locally before anything reaches the BMS
- Diagnostics reported over the vehicle bus using existing in-vehicle communication conventions
Key engineering challenges
Detecting early signs of thermal abnormality at the cell level, ahead of pack-level BMS thresholds, required tuning fault-detection logic against real thermal behavior while avoiding false triggers that would degrade trust in the system. Meeting automotive real-time and reliability expectations — deterministic timing, fault tolerance, and compliance with automotive engineering practices — shaped both the hardware and firmware design throughout.
- Detecting early thermal-fault signatures at cell level, ahead of pack-level BMS thresholds
- Avoiding false triggers that would erode trust in the diagnostic system
- Meeting automotive deterministic-timing and fault-tolerance expectations throughout
Why this approach
Cell-level rather than pack-level monitoring was the point of the engagement: pack-level BMS thresholds catch problems later than a distributed sensing approach can, so the module's value depends on genuinely earlier, localized fault detection.
- Cell-level (not pack-level) monitoring was the explicit point of the engagement
- Local, bus-reported diagnostics chosen over any cloud dependency for a safety-relevant real-time system
- Fault-detection thresholds tuned conservatively to avoid alert fatigue in the field