Automated generation of experimentally validated digital twins for desiccant-based low-dew-point air-conditioning systems from declarative topology specifications
2026-08-10 • Computational Engineering, Finance, and Science
Computational Engineering, Finance, and Science
AI summaryⓘ
The authors developed a way to quickly create and calibrate a digital twin—a computer model—of an air-conditioning system used in dry rooms for battery making. Their method uses a simple description of the system to automatically build a physics-based model that matches real data well, predicting important details like temperature and power use accurately. They tested this on a complex 10-part system and found it works much faster and with fewer manual steps than expert efforts. This approach helps improve energy use by making it easier to simulate and optimize the system's operation.
digital twinHVAC systemlow-dew-point air conditioningdesiccant wheelheat and mass transfersorption isothermmodel calibrationparameter identificationenergy optimizationbattery manufacturing
Authors
Younghwan Joo, Jeonghoon Han, Sang Hyun Oh, Soosik Bang, Sung-il Kim
Abstract
In battery manufacturing, the low-dew-point air conditioning of dry rooms is among the largest energy consumers, and a physics-based digital twin offers insight for operating-point optimization beyond the installed monitoring points. Building one and calibrating it to field data each demand distinct expertise, which limits industrial uptake. We present a framework that generates a dynamic digital twin of an HVAC system from a declarative topology specification, concise enough to draft from a natural-language plant description, compiled against a purpose-built physical component library with wiring, solver, and telemetry synthesized automatically. The models carry equipment-level physics: the desiccant wheel couples heat and mass transfer through an interchangeable sorption-isotherm component, so an undisclosed commercial sorbent is calibrated as an effective isotherm rather than asserted as a material. For experimental validation we built an industrial-grade, ten-component low-dew-point system whose commercial desiccant-wheel unit holds a chamber near -40 °C frost point, and operated it in both dehumidification and bypass regimes. Generation reached a runnable model fifteen times faster than expert manual construction, and a single parameter set, fitted only to three closed-loop humidity nodes, predicts the bypass regime within 0.1 °C, the reactivation-heater power within 5%, and measured input-step responses. Identifiability analysis shows why this is prediction, not fitting: ordinary operating points constrain only one parameter combination, and the deep-dry equilibrium level of the recirculating loop supplies the missing signal. The framework shortens the path from plant description to measurement-validated twin; its criteria-based calibration is a step toward twins calibrated, not only constructed, automatically.