Battery state-of-health as a functional safety variable: an ISO 26262-aligned AI framework for electric vehicle ADAS power integrity
5 affiliations
- 1Department of Legal Medicine, Shiga University of Medical Science
- 2Faculty of Artificial Intelligence and Engineering, Multimedia University
- 3Department of Computer Science, College of Computing and Information Technology, Shaqra University
- 4Department of Electrical, Electronic and Communication Engineering, Military Institute of Science and Technology (MIST)
- 5Department of Computer Science and Engineering, Military Institute of Science and Technology
Abstract
A critical design blind spot persists in contemporary electric vehicle (EV) safety engineering: ISO 26262 functional-safety frameworks generally treat battery State-of-Health (SoH) as a passive maintenance metric rather than a live, mode-governing safety variable. This paper proposes a five-layer theoretical co-design framework that integrates SoH estimation, power-margin monitoring, functional-safety decision logic, actuation, and lifecycle management. A qualitative Fault Tree Analysis and preliminary Hazard Analysis and Risk Assessment are used to examine the representative BMS–ADAS power-interface hazard. The electrical analysis introduces a bounded DC/DC converter model and distinguishes two explicit converter-control scenarios: regulated operation with no active hard limit and an adverse 5.15 A hard-input-current-limit boundary condition. For the stated 851 W transient load, both scenarios retain positive converter margin; failed shedding of a 551 W comfort load is therefore the dominant source of power-margin compression, while the isolated SoH contribution is 0 W under regulated operation and approximately 40 W under the adverse hard-limit condition. A separate illustrative LiDAR subsystem-allocation model yields a beta-derived additional stopping-distance estimate of approximately 0.84–1.40 m, while an independently defined 100 ms recovery-delay scenario yields 1.67 m. These estimates are analytical scenario results rather than device-validated predictions. Platform-specific converter, power-allocation, sensor, timing, and hardware-in-the-loop validation is identified as the essential next steps.
Related
- Development of mechanically optimized biomimetic hybrid scaffold–stem cell constructs for functional tendon regeneration and restoration of mechanical integrity
- Safe and efficient intracellular delivery of functional antibodies into cultured neural cells shows a role for Alzheimer’s-relevant tau phosphorylation in cell integrity
- Proximity to an SGC–DLPFC individualized functional target and electric-field modeling do not predict clinical outcomes of rTMS for treatment-resistant depression
- Impact of Functional Frailty Measured by Short Physical Performance Battery Test on the Effectiveness of SGLT2 Inhibitors in Elderly Patients with Acute Heart Failure:PROFUND-IC Registry
- A high-fidelity modeling and simulation framework for a hydrogen fuel cell electric vehicle
BibTeX
@article{barua2026battery,
title = {{Battery state-of-health as a functional safety variable: an ISO 26262-aligned AI framework for electric vehicle ADAS power integrity}},
author = {Nick Barua and Md Tanjil Sarker and Marran Al Qwaid and Md. Shabiul Islam and Shah Mohazzem Hossain and Kazy Noor-e-Alam Siddiquee},
journal = {Scientific Reports},
year = {2026},
month = aug,
doi = {10.1038/s41598-026-65007-4},
url = {https://doi.org/10.1038/s41598-026-65007-4},
note = {CC BY},
}
RIS
TY - JOUR
TI - Battery state-of-health as a functional safety variable: an ISO 26262-aligned AI framework for electric vehicle ADAS power integrity
AU - Nick Barua
AU - Md Tanjil Sarker
AU - Marran Al Qwaid
AU - Md. Shabiul Islam
AU - Shah Mohazzem Hossain
AU - Kazy Noor-e-Alam Siddiquee
PY - 2026
DA - 2026/08/01
JO - Scientific Reports
DO - 10.1038/s41598-026-65007-4
UR - https://doi.org/10.1038/s41598-026-65007-4
AB - A critical design blind spot persists in contemporary electric vehicle (EV) safety engineering: ISO 26262 functional-safety frameworks generally treat battery State-of-Health (SoH) as a passive maintenance metric rather than a live, mode-governing safety variable. This paper proposes a five-layer theoretical co-design framework that integrates SoH estimation, power-margin monitoring, functional-safety decision logic, actuation, and lifecycle management. A qualitative Fault Tree Analysis and preliminary Hazard Analysis and Risk Assessment are used to examine the representative BMS–ADAS power-interface hazard. The electrical analysis introduces a bounded DC/DC converter model and distinguishes two explicit converter-control scenarios: regulated operation with no active hard limit and an adverse 5.15 A hard-input-current-limit boundary condition. For the stated 851 W transient load, both scenarios retain positive converter margin; failed shedding of a 551 W comfort load is therefore the dominant source of power-margin compression, while the isolated SoH contribution is 0 W under regulated operation and approximately 40 W under the adverse hard-limit condition. A separate illustrative LiDAR subsystem-allocation model yields a beta-derived additional stopping-distance estimate of approximately 0.84–1.40 m, while an independently defined 100 ms recovery-delay scenario yields 1.67 m. These estimates are analytical scenario results rather than device-validated predictions. Platform-specific converter, power-allocation, sensor, timing, and hardware-in-the-loop validation is identified as the essential next steps.
SN - 2045-2322
ER -