Estimating torque and rotor temperature for improved motor performance

From manufacturing plants to transportation systems, precise motor control is vital. Torque and rotor temperature are two main parameters for motors and monitoring them leads to more accurate, efficient control of the motor, reducing power losses and eventually heat build-up.
Artificial Intelligence (AI) helps improve efficiency in various domains but also to unleash new features such as extrapolation to estimate values in order to optimize performance without having to add hardware components. Being able to have strong estimators for the torque and rotor temperature helps manufacture motors with less material and enables more efficient control strategies to ensure the motor is working at its maximum capability.


  • This use case is based on the “Electric Motor Temperature” dataset from Kaggle.
  • The goal was to estimate the torque and rotor temperature using only available information (motor speed, coolant temperature, voltages, etc.).
  • We created two sub datasets, one for estimating the torque and the other for the rotor temperature.
  • Using NanoEdge AI Studio, we then created two Extrapolation projects capable of estimating the torque and rotor temperature based on these inputs.


Generic sensors.


Extrapolation targets: Torque and rotor temperature
Signal length: 10 (multi-sensors)
Data rate: 2 Hz


Torque extrapolation (left):
98.77% accuracy, 0.1 Kbytes of RAM, 0.3 Kbytes of Flash memory

Rotor temperature extrapolation (right):
98.81% accuracy, 0.1 Kbytes of RAM, 0.3 Kbytes of Flash memory