Multimodal modeling framework and characteristic analysis of a new air-source heat pump heating system
Mingzhi Jiang, Guohui Feng, Zhiwei Wang, Mingchao Jiang, Yongliang Fu, Run Bai · 2026
Read Multimodal modeling framework and characteristic analysis of a new air-source heat pump heating system by Mingzhi Jiang, Guohui Feng, Zhiwei Wang, Mingchao Jiang, Yongliang Fu, Run Bai (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13473553.txt.
Description
Mingzhi Jiang and five colleagues modelled in 2026 a heating system that pairs an air-source heat pump with a tank storing heat in phase-change material. Such systems can use cheap off-peak electricity and store energy efficiently, but in real industrial buildings many interacting factors shape heat demand, and single-factor models miss dynamics. The team collected operating data from a working system, then built a stacking ensemble called XMS, combining XGBoost and a multi-layer perceptron under a meta-learner.
Compared with a traditional perceptron model alone, the ensemble cut root mean square error by 22.5 percent and raised the coefficient of determination by 10.1 percent, capturing the system's nonlinear, coupled behaviour far better. The authors present the model as a reliable tool for forecasting heating load and tuning controls in heat-pump storage systems. Wider testing across climates and building types remains the next step.
Catalog record
| CREATOR | Mingzhi Jiang, Guohui Feng, Zhiwei Wang, Mingchao Jiang, Yongliang Fu, Run Bai |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 33 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |