用残差物理神经网络实现高精度无刷电机实时建模
Residual Physics-Informed Neural Networks for High-Fidelity BLDC Motor Modeling
- 基于残差结构的物理信息神经网络，联合学习电机六状态动态
- 推理延迟仅0.1–22微秒，比传统求解器快118倍
- 适合机器人关节实时控制与观测器设计
无刷直流电机的精确动力学建模对高性能机器人关节控制至关重要。本文提出一种采用深度残差（ResNet）主干的物理信息神经网络（PINN），学习全六状态无刷电机连续时间的代理模型。输入为仿真时间、三相电压及激励参数，网络直接预测转子角度、角速度、三相电流和绕组温度等全部状态变量，同时通过复合物理-数据损失项满足电磁与热力学常微分方程。采用课程调度策略逐步激活物理惩罚项，防止过早收敛。训练在标准CPU上不到两分钟完成。关键的是，模型推理延迟仅为0.1–22微秒/查询，最高比传统常微分方程求解器快118倍，适用于实时观测器与控制应用。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。