AI 中文总结
该研究提出基于JAX的端到端可微有限体积蒸汽压缩框架，统一设备选型、动态仿真与最优控制，经实验验证精度良好，为相关自动化与协同设计提供开源基础。
AI 中文摘要
热能电气化进程的加速要求蒸汽压缩热泵能够实现动态的、响应电网的运行。然而，设备工程目前仍在静态额定点选型、刚性多相瞬态仿真以及基于梯度的最优控制这几个环节相互割裂。为此，我们提出一种端到端可微的有限体积蒸汽压缩框架，该框架基于JAX原生实现，可根据给定的热负荷直接完成设备选型自动化，并在单一编译残差形式$\bar{y}={f}(t,{y},{u})$下将动态仿真与预测控制统一起来。\n热力学计算通过由亥姆霍兹状态方程预闪蒸得到的双线性$(p,h)$流形绕过了运行时的求根步骤，从而支持解析的前向模式自动微分。通过将$(\partialρ/\partial p)_h$和$(\partialρ/\partial h)_p$这两个偏导数纳入动态压力微分方程，多相盘管的质量守恒得到了严格保证。选型器利用相同的多变压缩机特性曲线，通过四点循环综合和ε-NTU匹配，直接反算出压缩机排量、电子膨胀阀面积和换热器管数。\n关键的是，编译后的物理内核在L稳定的TR-BDF2刚性积分器和隐式欧拉模型预测控制（MPC）之间对称共享，从根本上消除了被控对象与控制器之间的代理模型失配问题。该框架在无需参数拟合的情况下，经开放获取的实验基准验证：在16次小型分体式空调运行工况中，制冷量预测的平均绝对百分比误差（MAPE）为7.37%；在公用事业级硬件在环（Hardware-in-the-Loop）测试序列中，运行时段制冷误差被控制在1.19%–1.62%范围内。本工作为自动化设备综合、动态电网调度以及基于梯度的硬件-控制协同设计提供了一个开源的可微分基础。
英文摘要
Accelerating the electrification of thermal energy requires vapor-compression heat pumps capable of dynamic, grid-responsive operation. However, equipment engineering remains fragmented across static rating-point selection, stiff multi-phase transient simulation, and gradient-based optimal control. Here, we present an end-to-end differentiable, finite-volume vapor-compression framework implemented natively in JAX that automates machine sizing directly from stated thermal duties and unifies dynamic simulation with predictive control under a single compiled residual $\dot{y}={f}(t,{y},{u})$. Thermodynamic evaluations bypass runtime root-finding via bilinear $(p,h)$ manifolds pre-flashed from Helmholtz equations of state, enabling analytical forward-mode automatic differentiation. Mass conservation across multi-phase coils is strictly preserved by incorporating both $(\partialρ/\partial p)_h$ and $(\partialρ/\partial h)_p$ partial derivatives into the dynamic pressure differential equation. The sizer directly inverts compressor displacement, electronic expansion valve area, and heat-exchanger tube counts via four-point cycle synthesis and $\varepsilon$-NTU matching using the identical polytropic compressor map. Crucially, the compiled physics kernel is shared symmetrically between $L$-stable TR-BDF2 stiff integration and implicit-Euler Model Predictive Control (MPC), eliminating plant-controller surrogate mismatch. Validated against open-access experimental benchmarks without parameter fitting, the framework predicts cooling capacity with $7.37\%$ MAPE across 16 mini-split operational runs and bounds on-period cooling error within $1.19\%$--$1.62\%$ on utility-scale Hardware-in-the-Loop traces. This work provides an open-source, differentiable foundation for automated machine synthesis, dynamic grid orchestration, and gradient-based hardware-control co-design.
Commentsthe paper is not novel enough; need further investigation
