Battery intelligence, built on physics and Bayesian inference
We build MW Battery Analytics on the Modak–Walawalkar (MW) Battery Engine: a Bayesian, physics-constrained approach that reads ordinary BMS/CAN data and says not just a battery’s health, but how sure we are and what to do next.
Who is behind MW Battery Analytics
We are also working with battery startups founded by globally leading battery researchers.
Rahul Modak
Co-founder & CEO, Technical Lead
30+ years in applied Bayesian statistics. Co-developer of the MW Battery Engine.
LinkedIn(opens in a new tab)
Dr. Rahul Walawalkar
Co-founder & Executive Chairman
PhD, Carnegie Mellon University
Clean-energy entrepreneur and founder of Walawalkar Enterprise LLP. Angel investor, board advisor and keynote speaker on the energy transition.
LinkedIn(opens in a new tab)
The work behind the engine
Trained only on electrochemical priors, the engine independently reproduced a leading battery researcher’s published SEI-cracking findings on his own data, a result he has confirmed.
- View DOI(opens in a new tab)
MW Framework: Bayesian manifold learning for physical systems
Preprint · Zenodo - Read
Steganographic LLM-powered red teaming
Research - Subscribe(opens in a new tab)
AI Cyber Security @ OSI
Newsletter
Why we open-source the framework
Models that inform critical-infrastructure decisions should not be a black box. Our GitHub hosts an open demo of the MW Framework on non-battery verticals, so researchers can audit the priors and the maths. Battery Analytics is the commercial offering built on top.
See what your own battery data is telling you.
Share a BMS/CAN log. We run it through the MW Battery Engine and send back an MW Battery Assessment Report: findings, how sure we are, and what to do next. The first assessment is free.