Study on optimization of lipase-catalyzed synthesis of 2-ethylhexyl salicylate by response surface methodology and artificial neural network
| Autor: | Tzu-Hsiang Hung, 洪子翔 |
|---|---|
| Rok vydání: | 2015 |
| Druh dokumentu: | 學位論文 ; thesis |
| Popis: | 104 2-ethylhexyl salicylate is a common chemical found in sunscreen and certain types of makeup with sun-blocking properties. It protects against harmful ultraviolet radiation from the sun''s rays, 2-ethylhexyl salicylate absorbs UVB rays but not UVA, which can avoid skin cancer. In the first part, 2-ethylhexyl salicylate (2-EHS) was synthesized from methyl salicylate (MS) with 2-Ethyl hexanol (2-EH) in a solvent free system using evaporation. Experiment conditions under reaction time (2 – 24 h), reaction temperature (50 – 70 ℃ ) and enzyme amount (500 – 1,000 PLU). The 3-level-3-factor Box-Behnken design was applied to optimize the response. In second part, compared with response surface methodology (RSM) and artificial neural network (ANN). First step is establish a model of ANN, used BBD data for further analysis, the learning cycle number is ranging from 1,000-100,000 times, and transfer function including 3-6 nodes. To find minimum root mean square error (RMSE) and absolute average deviation (AAD) and maximum R2. As result the model with the condition of 10,000 learning cycle number, Hypertangent transfer function, Quick propagation algorithm and 6 nodes in hidden layer. Comparing with RSM, the R2 of ANN is 0.998, better than the R2 of RSM is 0.992. The RMSE and AAD in ANN model is 1.115 and 0.621 respectively, and RMSE and AAD in RSM model is 1.875 and 2.273 respectively. The lower RMSE and AAD values represents the more precise prediction of molar conversion. Therefore the ANN model is more suitable than the RSM model to explain the data of this study. |
| Databáze: | Networked Digital Library of Theses & Dissertations |
| Externí odkaz: |
|