首页|Data on Nanoflakes Detailed by Researchers at Sohar University (Specific Heat Ca pacity Extraction of Soybean Oil/MXene Nanofluids Using Optimized Long Short-Ter m Memory)
Data on Nanoflakes Detailed by Researchers at Sohar University (Specific Heat Ca pacity Extraction of Soybean Oil/MXene Nanofluids Using Optimized Long Short-Ter m Memory)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News – A new study on nanoflakes is now available. Accor ding to news originating from Sohar University by NewsRx correspondents, researc h stated, “Researchers are turning to nanofluids in PV/T hybrid systems for enha nced efficiency due to nanoparticle dispersion, improving thermal and optical pr operties over conventional fluids. Three different concentrations of formulated soybean oil based MXene nanofluids are considered 0.025, 0.075 and 0.125 wt.% .” The news editors obtained a quote from the research from Sohar University: “Maxi mum specific heat capacity nanofluids ( $c_{ pNF}$ ) augmentation is 24.49% at 0.125 wt.% loading of Ti3C2 in the base oil. The calculation of the $ c_{pNF}$ based on the tempe rature and nanoflakes concentration is very expensive and time-consuming as it s hould be calculated via the practical test investigation. This study employs a l ong short-term memory (LSTM) as an efficient machine learning method to extract the surrogate model for calculating the $c_{ pNF}$ based on the temperature and nanoflakes concent ration. In addition, a couple of other machines learning methods, including supp ort vector regression (SVR), group method of data handling (GMDH), and multi-lay er perceptron (MLP), are developed to prove the higher efficiency of the recentl y proposed LSTM model in the calculation of the $c_{ pNF}$. In addition, the Bayesian optimization techniqu e is employed to calculate the optimal hyperparameters of the developed SVR, GMD H, MLP and LSTM to reach the highest efficiency of the system in predicting the $c_{pNF} $ base d on temperature and nanoflakes concentration. Notably, 95% of the recorded data via differential scanning calorimetry (DSC) is used for training machine learning techniques. In comparison, 5% is used for testing and validation purposes of the developed algorithm. The newly proposed optimize d SVR, GMDH, MLP, and LSTM are modelled in MATLAB software.”
NETL
NSTL
