发表机构
Department of Mechatronics and Robotics Engineering; Egypt-Japan University of Science and Technology (E-JUST)（机电工程与机器人工程系; 埃及-日本科学技术大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对无刷直流电机精确动力学建模问题，提出基于ResNet主干的PINN，以仿真时间等为输入预测电机状态变量，满足相关常微分方程，用课程调度策略防过早收敛，训练快且推理延迟低，适用于实时应用。
AI 中文摘要
无刷直流（BLDC）电机的精确动力学建模是高性能机器人关节控制的基础。本文提出了一种具有深度残差（ResNet）主干的物理信息神经网络（PINN），用于学习完整六状态BLDC电机动力学的连续时间替代模型。以仿真时间、施加的三相电压和励磁参数作为输入，该网络直接预测所有电机状态变量，包括转子角度、角速度、三相电流和绕组温度，同时通过复合物理数据损失满足主导的机电和热常微分方程。一种课程调度策略逐渐激活物理惩罚以防止过早收敛。在标准CPU上训练运行在两分钟内完成。关键的是，一旦训练完成，PINN推理每次查询的延迟为0.1 - 22微秒，比传统常微分方程求解器快118倍，适用于实时观测器和控制应用。
英文摘要
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.
