Research on dynamic cost prediction method for power technology upgrading projects based on improved transformer neural network
Qi Shi, Yue Le, Chunjie Gu, Yaming Geng · 2026
Read Research on dynamic cost prediction method for power technology upgrading projects based on improved transformer neural network by Qi Shi, Yue Le, Chunjie Gu, Yaming Geng (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/PMC13578334.txt.
Description
Qi Shi, Yue Le, Chunjie Gu, and Yaming Geng forecast the cost of power grid upgrade projects with a tuned transformer model, in a 2026 study. Renovation bills shift as prices, labor, and scope change over long jobs, which makes early budgets hard to trust. Their model reads cost history at several time scales at once and shifts its focus as conditions change.
The test bed held more than thirteen hundred finished projects from one province in eastern China. Against nine rival methods, from classic tools to newer time series designs, the new model posted the lowest average error and the tightest fit to real costs. Extra checks traced which inputs drove each forecast. The authors warn the model was tuned on one province, so wider use needs fresh proof.
Catalog record
| CREATOR | Qi Shi, Yue Le, Chunjie Gu, Yaming Geng |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 94443 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |