Scalable Physics-Informed Neural Differential Equations and Data-Driven Algorithms for HVAC Systems
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911616182779904 |
|---|---|
| author | Zhai, Hanfeng Qiao, Hongtao Mansour, Hassan Laughman, Christopher |
| author_facet | Zhai, Hanfeng Qiao, Hongtao Mansour, Hassan Laughman, Christopher |
| contents | We present a scalable, data-driven simulation framework for large-scale heating, ventilation, and air conditioning (HVAC) systems that couples physics-informed neural ordinary differential equations (PINODEs) with differential-algebraic equation (DAE) solvers. At the component level, we learn heat-exchanger dynamics using an implicit PINODE formulation that predicts conserved quantities (refrigerant mass $M_r$ and internal energy $E_\text{hx}$) as outputs, enabling physics-informed training via automatic differentiation of mass/energy balances. Stable long-horizon prediction is achieved through gradient-stabilized latent evolution with gated architectures and layer normalization. At the system level, we integrate learned components with DAE solvers (IDA and DASSL) that explicitly enforce junction constraints (pressure equilibrium and mass-flow consistency), and we use Bayesian optimization to tune solver parameters for accuracy--efficiency trade-offs. To reduce residual system-level bias, we introduce a lightweight corrector network trained on short trajectory segments. Across dual-compressor and scaled network studies, the proposed approach attains multi-fold speedups over high-fidelity simulation while keeping errors low (MAPE below a few percent) and scales to systems with up to 16 compressor-condenser pairs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_18438 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Scalable Physics-Informed Neural Differential Equations and Data-Driven Algorithms for HVAC Systems Zhai, Hanfeng Qiao, Hongtao Mansour, Hassan Laughman, Christopher Machine Learning Systems and Control Adaptation and Self-Organizing Systems We present a scalable, data-driven simulation framework for large-scale heating, ventilation, and air conditioning (HVAC) systems that couples physics-informed neural ordinary differential equations (PINODEs) with differential-algebraic equation (DAE) solvers. At the component level, we learn heat-exchanger dynamics using an implicit PINODE formulation that predicts conserved quantities (refrigerant mass $M_r$ and internal energy $E_\text{hx}$) as outputs, enabling physics-informed training via automatic differentiation of mass/energy balances. Stable long-horizon prediction is achieved through gradient-stabilized latent evolution with gated architectures and layer normalization. At the system level, we integrate learned components with DAE solvers (IDA and DASSL) that explicitly enforce junction constraints (pressure equilibrium and mass-flow consistency), and we use Bayesian optimization to tune solver parameters for accuracy--efficiency trade-offs. To reduce residual system-level bias, we introduce a lightweight corrector network trained on short trajectory segments. Across dual-compressor and scaled network studies, the proposed approach attains multi-fold speedups over high-fidelity simulation while keeping errors low (MAPE below a few percent) and scales to systems with up to 16 compressor-condenser pairs. |
| title | Scalable Physics-Informed Neural Differential Equations and Data-Driven Algorithms for HVAC Systems |
| topic | Machine Learning Systems and Control Adaptation and Self-Organizing Systems |
| url | https://arxiv.org/abs/2604.18438 |