| 杨海燕，王丁禾，段之阳，杨晶，吴卓夫.响应面法联合人工神经网络优化
亚麻荠油体提取工艺[J].中国油脂,2026,51(6):.[YANG Haiyan, WANG Dinghe, DUAN Zhiyang, YANG Jing, WU Zhuofu.Extraction process optimization of camelina oil body by response surface methodology and artificial neural network[J].China Oils and Fats,2026,51(6):.] |
| Extraction process optimization of camelina oil body by response surface methodology and artificial neural network |
|
投稿时间：2025-01-23 修订日期：2026-02-23 录用日期：2025-07-01
Published：2026-06-20
|
| DOI：10.19902/j.cnki.zgyz.1003-7969.250050 |
| KeyWord:camelina oil body extraction particle size response surface methodology artificial neural network genetic algorithm |
| FundProject:吉林省科学技术厅重点研发项目(20220202081NC) |
|
| 摘要点击次数: 674 |
| 全文下载次数: 17 |
| Abstract: |
| Aiming to obtain a high extraction yield of oil body while ensuring their basic physical stability, the extraction process of camelina oil body was optimized using response surface methodology (RSM) combined with artificial neural network (ANN). The Effect of process conditions on camelina oil body extraction was investigated by single-factor experiments, and response surface model was established with the yield of oil body, particle size, and Zeta potential as the evaluation indicators. On this basis, ANN and genetic algorithm (GA) were used to search for the optimal extraction process. The results showed that the optimal process conditions were as follows: solid-liquid ratio 1∶ 20.45, pH 12.28, NaCl concentration 0.53 mol/L, sucrose concentration 0.8 mol/L, and grinding time 60 s. Under these conditions, the yield of camelina oil body was 41.7%, with a particle size of 438 nm and a Zeta potential of -19.1 mV. In conclusion, the RSM-ANN-GA-based process optimization can effectively predict and improve the extraction efficiency of camelina oil body. |
| View full text 查看/发表评论 下载PDF阅读器 |
| 关闭 |
|
|
|
