PERMODELAN DAN OPTIMASI HIDROLISA PATI MENJADI GLUKOSA DENGAN METODE ARTIFICIAL NEURAL NETWORK - GENETIC ALGORITHM

*Istadi Istadi  -  , Indonesia
Dian Rahmayanti  -  , Indonesia
Published: .
Open Access
Citation Format:
Abstract
Modeling and optimization methods are commonly used, still not able to model and optimize the complexchemical processes non-linear. Hybrid method of Artificial Neural Network-Genetic Algorithm (ANN-GA) isconsidered as an effective method for resolving these problems and obtain optimum conditions globally. Theaim of this study is to develop a modeling and optimization with hybrid ANN-GA methods, which applied inprocess of making glucose from starch hydrolysis. The ANN-GA stategy consists of two steps. In the first step,an ANN-based prosess model is developed. Therefore, the input at ANN model will be optimized using GAtechnique. The optimal values of starch concentration, enzyme concentration, temperature and time with ANNGAmethod were 7,13 % (w/v), 1,47 %(w/v), 40,53ºC, and 166,04 min respectively with predicted glucose yieldof 6,08 mg/mL. These result differed from the secondary data (Baskar et al., 2008) which were used RSM. Itwas because R2 values of ANN-GA method was 0,9755. While RSM method was only able to achieved value ofR2 for 0,842. Modeling and optimization with the GA-ANN can be developed and used to obtain the model instarch hydrolysis into glucose and the optimal operating conditions simultaneouosly.
Keywords: ANN-GA; hydrolysis; modeling and optimization; glucose yield

Article Metrics:

Last update: 2021-02-25 01:49:50

No citation recorded.

Last update: 2021-02-25 01:49:51

No citation recorded.