A data-driven framework for structural health monitoring using reinforcement learning and deep autoencoders
Amin Hadizadeh, Amir Tarighat, Abbass Malian · 2026
Read A data-driven framework for structural health monitoring using reinforcement learning and deep autoencoders by Amin Hadizadeh, Amir Tarighat, Abbass Malian (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-13396415.txt.
Description
Amin Hadizadeh, Amir Tarighat, and Abbass Malian propose a bridge-checking framework in 2026 that learns damage signs on its own. Many bridges have passed their design life, and checking them by hand is slow and costly. Their method reads motion sensor data and flags odd patterns without anyone setting touchy thresholds by hand.
The team tested the method on a well-studied bridge with a rich sensor record. It blends learning from rewards with a deep network that compresses normal patterns and spots breaks from them. Against four standard methods, the new framework scored higher on accuracy and on a balanced quality score. The authors say it needs no sensitive hand tuning, which suits real bridge fleets.
Catalog record
| CREATOR | Amin Hadizadeh, Amir Tarighat, Abbass Malian |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 62 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |