Simulation of Supercritical CO2 Extraction for Peanut Oil Based on Artificial Neural Networks

Jin Shan Dong; Bo Qin Gu

doi:10.4028/www.scientific.net/AMM.37-38.1172

Paper Titles

Simulation and Analysis of Dynamic Evolution of Electricity Market Based on Bidding Decisions with Heterogeneous Expectations
p.1153

Simulation and Analysis on the Direct Shearing of Semi-Fixed Abrasive Tool
p.1157

Simulation Modeling of the Operating Room Based on SIMIO
p.1162

Simulation of Load-Displacement Relationship for Specially Shaped RC Columns
p.1167

Simulation of Supercritical CO₂ Extraction for Peanut Oil Based on Artificial Neural Networks
p.1172

Simulation of Temperature Field of Molten Steel in Mold for 700mm×700mm Billet Caster
p.1176

Simulation of Test Loads on Aqueduct with Multi-Longitudinal Reinforced Concrete Beams
p.1182

Simulation Research on Neural Network Sliding Mode Control of Energy-Regenerative Braking of Electric Vehicle
p.1187

Simulation Research on Special-Section Ring Radial Rolling Technology
p.1191

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 37-38Simulation of Supercritical CO2 Extraction for...

Simulation of Supercritical CO₂ Extraction for Peanut Oil Based on Artificial Neural Networks

Abstract:

The BP ANN was established based on MATLAB to simulate the supercritical CO₂ extraction process for extracting peanut oil. The supercritical CO₂ extraction experiment for peanut oil was carried out and the experimental results were used to train the BP ANN. The operating pressure, temperature and time were regarded as the inputs of the BP ANN and the percentage extraction as the output. By testing the BP ANN with other groups of experimental data, the precision of the BP ANN was verified. This BP ANN can predict the percentage extraction when the processing parameters of supercritical CO₂ extraction are given, and the optimization of the processing parameters can also be realized.