A Unified Experimental Database, Data Harmonisation Workflow and Leakage-Safe Pilot Machine Learning for Flow Boiling in Rectangular Minichannels

A unified experimental database and a reproducible Python-based harmonisation workflow are presented for local heat transfer analysis in rectangular-minichannel flow boiling. The database integrates 449 experimental source files and 64,385,791 point-level records covering six working fluids, multiple surface conditions, channel configurations, and orientations. The workflow combines template-based files, central-line in-frared wall-temperature data, geometric and operating metadata, local pressure and saturation-temperature reconstruction, bulk-fluid temperature interpolation, heat-loss correction, local heat transfer coefficient and Nusselt number calculation, operational regime labelling, and auditable quality-control flags. The database is characterised at point and source-file levels to identify regime imbalance, unequal experiment sizes, and heterogeneous coverage. A leakage-safe pilot benchmark is then conducted on streaming-sampled subcooled and saturated subsets using Random-Forest regressors with source-file-level train/test separation. The strongest result is obtained for subcooled Nusselt number (R² = 0.88), followed by subcooled heat transfer coefficient (R² = 0.80); saturated targets are more difficult (R² = 0.46 for Nu and 0.41 for heat transfer coefficient). These results are treated as feasibility screening rather than final model ranking. The proposed database architecture and validation strategy establish a repro-ducible foundation for controlled physical interpretation and extended machine-learning assessment.