Data-Driven Pressure Sensor Subset Selection for Long-Distance Water Transfer Pipelines: Q-DEIM Benchmarking with Spatial-Diversity Refinement
Chengkun Liu, Linjie Guan, Siqi Wei · 2026
Read Data-Driven Pressure Sensor Subset Selection for Long-Distance Water Transfer Pipelines: Q-DEIM Benchmarking with Spatial-Diversity Refinement by Chengkun Liu, Linjie Guan, Siqi Wei (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-13259217.txt.
Description
Chengkun Liu and co-authors ask how many pressure sensors a giant water pipeline really needs. A trunk line in northeast China runs one hundred twenty-two kilometers with sensors placed by habit, many redundant. Using thousands of hourly snapshots, their 2026 study benchmarks four selection strategies against random picking.
Fifteen well-chosen sensors rebuilt nearly the whole pressure field, cutting the cleaned network by three-quarters. A hybrid method that also spreads sensors out guarded worst-case gaps far better for almost no accuracy cost. Reaching the strictest accuracy bar took more sensors under every strategy. The catch, they note, is covering all operating regimes during training.
Catalog record
| CREATOR | Chengkun Liu, Linjie Guan, Siqi Wei |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 47 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |