Optimization of additive contents in cottonseed meals during the solid-state fermentation using response surface methodology and artificial neural network-based genetic algorithm
The response surface methodology (RSM) and an artificial neural network-based genetic algorithm (ANN-GA) were carried out to investigate the effects of urea content, Na<sub>2</sub>CO<sub>3</sub> content and rapeseed meal content on free gossypol detoxification from cottonseed...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Zhejiang University Press
2011-01-01
|
| Series: | 浙江大学学报. 农业与生命科学版 |
| Subjects: | |
| Online Access: | https://www.academax.com/doi/10.3785/j.issn.1008-9209.2011.01.014 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The response surface methodology (RSM) and an artificial neural network-based genetic algorithm (ANN-GA) were carried out to investigate the effects of urea content, Na<sub>2</sub>CO<sub>3</sub> content and rapeseed meal content on free gossypol detoxification from cottonseed meals by solid-state fermentation. The modeling and optimizing abilities of the two methods were compared. The results showed that according to RSM, the optimal additive contents for free gossypol detoxification were 0.97% urea, 2.47% Na<sub>2</sub>CO<sub>3</sub> and 24.32% rapeseed meal, and the predicted detoxification and experimentally measured detoxification ratios were 77.71% and 79.10%, respectively. Among the three factors, Na<sub>2</sub>CO<sub>3</sub> content had the biggest effect on free gossypol detoxification. According to the ANN-GA method, the maximum detoxification ratio of 81.36% was predicted when the urea content, Na<sub>2</sub>CO<sub>3</sub> content and rapeseed meal content were 0.98%, 2.45% and 23.66%, respectively. While the experimentally measured detoxification ratio was 80.09%. The correlation efficiency of 0.9191 identified by response surface methodology was a little lower than that of 0.9991 identified by genetic algorithm based on an artificial neural network model, which also was with a lower RMSE value by 0.13, indicating that the artificial neural network-based genetic algorithm had a much higher optimizing ability and modeling ability during the optimization of the solid-state fermentation process. |
|---|---|
| ISSN: | 1008-9209 2097-5155 |