Estimating torque and rotor temperature for improved motor performance
Using AI to extrapolate torque and rotor temperature values to improve 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.
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.
Approach
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.
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.
Sensor
Generic sensors.
Data
Extrapolation targets Torque and rotor temperature
Signal length 10 (multi-sensors)
Data rate 2 Hz
Signal length 10 (multi-sensors)
Data rate 2 Hz
Results
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
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
Resources
Model created with NanoEdge AI Studio
A free AutoML software for adding AI to embedded projects, guiding users step by step to easily find the optimal AI model for their requirements.
Compatible with Any STM32 MCU
The STM32 family of 32-bit microcontrollers based on the Arm Cortex®-M processor is designed to offer new degrees of freedom to MCU users. It offers products combining very high performance, real-time capabilities, digital signal processing, low-power / low-voltage operation, and connectivity, while maintaining full integration and ease of development.
