Machine Learning Approach for the Prediction of Biomass Waste Pyrolysis Kinetics from Preliminary Analysis
Kai Xiao, Xianghui Zhu · 2024
Read Machine Learning Approach for the Prediction of Biomass Waste Pyrolysis Kinetics from Preliminary Analysis by Kai Xiao, Xianghui Zhu (2024) 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-11635464.txt.
Description
Heating plant waste without oxygen, a process called pyrolysis, turns biomass into fuel and chemicals. Predicting how fast that breakdown runs at each stage usually takes slow lab work. Kai Xiao and Xianghui Zhu instead train neural networks to predict the energy barrier of the reaction from simple lab measures of the raw material.
They built three models using different input sets: full chemical analysis, quick burn-and-ash measures, and the shares of three plant fibers. The data covered 32 kinds of biomass and 270 kinetic data sets. The fiber-based model matched lab results best, with the largest error near 13 percent. Adding a swarm search method to tune the network cut that error to about 7 percent. The authors present the models as a faster way to screen waste feedstocks for fuel production.
Catalog record
| CREATOR | Kai Xiao, Xianghui Zhu |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 43 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |