Residual Physics-Informed Neural Networks for High-Fidelity BLDC Motor Modeling
2026-07-10 • Robotics
Robotics
AI summaryⓘ
The authors developed a special neural network that learns how a Brushless DC motor behaves over time, including its angle, speed, currents, and temperature. Their method uses physics rules combined with data to make predictions very quickly and accurately. They also designed a training trick to make learning stable and fast, finishing in just a few minutes on a regular computer. After training, their model can predict motor states much faster than traditional methods, which is helpful for controlling robots in real time.
Brushless DC motorsPhysics-Informed Neural NetworksResNetOrdinary Differential EquationsElectromechanical systemsThermal dynamicsSurrogate modelingCurriculum learningReal-time controlNeural network inference
Authors
Haitham El-Hussieny
Abstract
Accurate dynamics modeling of Brushless DC (BLDC) motors is fundamental to high-performance robotic joint control. This paper presents a Physics-Informed Neural Network (PINN) with a deep residual (ResNet) backbone that learns a continuous-time surrogate of the full six-state BLDC motor dynamics. Given simulation time, applied three-phase voltages, and excitation parameters as inputs, the network directly predicts all motor state variables -- rotor angle, angular velocity, three-phase currents, and winding temperature -- while simultaneously satisfying the governing electromechanical and thermal ODEs through a composite physics-data loss. A curriculum scheduling strategy gradually activates the physics penalty to prevent premature convergence. Training runs are completed in under two minutes on a standard CPU. Crucially, once trained, PINN inference achieves latencies of 0.1--22, mu s per query, up to 118x faster than conventional ODE solvers, making it suitable for real-time observer and control applications.