Neural network firmware for sensorless motor rotor positioning
This technology uses a neural network to figure out exactly where a motor's spinning part (rotor) is positioned relative to its stationary part (stator) at any given moment, without needing a physical position sensor. It does this by feeding the motor's current and magnetic flux-linkage data into a neural network that learns the relationship between how energy is applied to the motor and how the motor responds. That learned model lets a controller make smarter, more precise decisions about when and how to energize the motor's windings. The result is more efficient, accurate motor control that can adapt to different operating conditions.
What you could build
A sensorless motor control chipset or embedded firmware module for switched reluctance or brushless DC motors, sold to industrial equipment OEMs, appliance manufacturers, or electric vehicle drivetrain suppliers who want to cut sensor costs without sacrificing control precision.
Who in Virginia should care
Defense and aerospace contractors in Northern Virginia and Newport News (e.g., shipbuilders, propulsion system suppliers) working on electric drive systems could find sensorless motor control directly relevant.
Readiness: Lab validated
Concept — described but not yet demonstrated. Lab validated — supported by experimental results in the patent. Prototype likely — the text describes a built, working embodiment.
Readiness is inferred from the patent text, not from a lab visit.
The record
- Inventors
- Christopher Allen Hudson, Nimal Lobo, Krishnan Ramu
- Granted
- December 20, 2011
- Status
- Granted patent
- Patent number
- 8080964
Ready to talk?
Virginia Tech Intellectual Properties handles licensing for this technology.
Prosim summaries are generated from public patent text and are not legal advice.