Use of neural networks to correlate enzymatic hydrolysis with biomass properties /
A neural network was used to correlate enzymatic digestibility with the following biomass properties: lignin content, acetyl content, and crystallinity index (CrI). The neural network model was not able to improve a previously developed empirical curve-fitting regression model used to predict glucan...
| Main Author: | |
|---|---|
| Format: | Thesis eBook |
| Language: | English |
| Published: |
[Place of publication not identified] :
[publisher not identified] ;
2001.
|
| Subjects: | |
| Online Access: | Link to OAKTrust copy |
| Summary: | A neural network was used to correlate enzymatic digestibility with the following biomass properties: lignin content, acetyl content, and crystallinity index (CrI). The neural network model was not able to improve a previously developed empirical curve-fitting regression model used to predict glucan, xylan, and total sugar conversions. The neural network model identified that glucan conversion affected xylan conversion, which was not evident from the empirical model. The digestibility of lime-treated biomass samples agreed with the neural network model. Lignin content and CrI had the greatest impact on biomass digestibility, whereas acetyl content had a minor impact. |
|---|---|
| Item Description: | "Major subject: Civil Engineering". Vita. |
| Physical Description: | xiii, 128 leaves : illustrations ; 28 cm. Also available online. Issued also on microfiche from Lange Micrographics. |
| Bibliography: | Includes bibliographical references (leaves 75-76). |