Solubility prediction of mangosteen peel oil in Supercritical Carbon Dioxide using Neural Network

Hamid, Izni Atikah Abd; Mustapa, Ana Najwa; Ismail, Norhuda; Abdullah, Zulhamri

doi:10.1109/beiac.2013.6560269

Cited by 2 publications

(1 citation statement)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ANN is inspired by the human brain, and its structure mimics the way biological neurons transmit signals to each other. 16 The references [17][18][19][20][21][22][23] show that a neural network can highly efficiently fit and predict the solubility of material.…”

Section: Introductionmentioning

confidence: 99%

Solubility prediction of CI Disperse Red 4 and CI Disperse Red 15 in supercritical carbon dioxide based on the back propagation neural network

Yan

et al. 2023

Coloration Technology

View full text Add to dashboard Cite

The solubility of 1‐amino‐2‐hydroxy‐4‐methoxy‐anthraquinone (CI Disperse Red 4) and 1‐amino‐2‐hydroxy‐anthraquinone (CI Disperse Red 15) in supercritical carbon dioxide was measured using a dynamic method over a temperature range from 343.15 to 373.15 K and a pressure range from 14 to 22 MPa. The experimental data are analysed by using the back propagation neural network constructed by MATLAB. In the back propagation neural network, the input layer consisted of two inputs, which are temperature and pressure, the output layer consisted of the solubility of dyes, and the hidden layer function was composed of a non‐linear function. The results of the analysis showed that a good fitting level of 0.99 was obtained, which means that the back propagation neural network can accurately estimate the solubility data in supercritical carbon dioxide.

show abstract