A Data-Driven Method for Determining the Loading Spectrum in Fatigue Tests for Working Device of Engineering Machinery
Yuqi Li, Wudi Yue, Xiaoming Wang, Yaozhi Xiong, Bing Li · 2026
Read A Data-Driven Method for Determining the Loading Spectrum in Fatigue Tests for Working Device of Engineering Machinery by Yuqi Li, Wudi Yue, Xiaoming Wang, Yaozhi Xiong, Bing Li (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/PMC13468749.txt.
Description
Yuqi Li and co-authors solve in 2026 a practical fatigue problem for wheel loaders. The load spectrum at the bucket edge decides how the working arm fatigues. It cannot be measured directly, because sensors cannot be mounted there. Their data-driven method learns the machine nonlinear input-output behavior with a NARX model, a neural-style predictor that uses past inputs and outputs. A genetic algorithm then runs the model backwards, searching for the input spectrum that reproduces the structural responses engineers can measure.
That inverted spectrum becomes the load program for bench fatigue tests, standing in for expensive field campaigns. The authors frame the payoff plainly: fatigue-resistant design of loader working devices without direct testing at the unmeasurable point, and a much shorter development loop. Construction machinery lives under random punishing loads, so a cheap, credible load history is valuable intellectual infrastructure for every redesign.
Catalog record
| CREATOR | Yuqi Li, Wudi Yue, Xiaoming Wang, Yaozhi Xiong, Bing Li |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 54 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |