Synergistic effect on co-pyrolysis of rice husk and sewage sludge by thermal behavior, kinetics, thermodynamic parameters and artificial neural network

2019 ◽  
Vol 85 ◽  
pp. 131-140 ◽  
Author(s):  
Salman Raza Naqvi ◽  
Zeeshan Hameed ◽  
Rumaisa Tariq ◽  
Syed A. Taqvi ◽  
Imtiaz Ali ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Sewage Sludge ◽  
Synergistic Effect ◽  
Thermal Behavior ◽  
Thermodynamic Parameters ◽  
Rice Husk ◽  
Artificial Neural

Thermal Behavior Prediction of MDPE Nanocomposite/Cloisite Na+ Using Artificial Neural Network and Neuro-Fuzzy Tools

2010 ◽  
Vol 1 (4) ◽  
Author(s):  
J. Sargolzaei ◽  
B. Ahangari
Keyword(s):  
Neural Network ◽  
Thermal Stability ◽  
Artificial Neural Network ◽  
Thermal Behavior ◽  
Fuzzy Inference ◽  
Air Atmosphere ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Inference Systems ◽  
Thermal Stability Of

Recently, we successfully prepared medium density polyethylene (MDPE) nanocomposite with 3 wt %, 6 wt %, and 9 wt % cloisite Na+ and the thermal stability of nanocomposite was investigated using the thermogravimetric analysis (TGA). The TGA in air atmosphere showed significantly improved thermal stability of 3 wt %, 6 wt %, and 9 wt % cloisite Na+ nanocomposite in comparison to pure MDPE. In this paper, the results of TGA of MDPE/cloisite Na+ nanocomposites were predicted by the artificial neural network (ANN). The ANN and adaptive neural fuzzy inference systems (ANFIS) models were developed to predict the degradation of MDPE/cloisite Na+ nanocomposite with temperature. The results revealed that there was a good agreement between predicted thermal behavior and actual values. The findings of this study also showed that the artificial neural networks and ANFIS techniques can be applied as a powerful tool.

Thermal behavior of ferulic acid employing isoconversional models and artificial neural network

2019 ◽  
Vol 138 (5) ◽  
pp. 3715-3726 ◽  
Author(s):  
Luana Guedes Brito ◽  
Geovana Quixabeira Leite ◽  
Fernanda Ílary Costa Duarte ◽  
Elissa Arantes Ostrosky ◽  
Marcio Ferrari ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Thermal Behavior ◽  
Ferulic Acid ◽  
Artificial Neural ◽  
Isoconversional Models

scholarly journals PREDIKSI KUAT TEKAN PERVIOUS PAVING DENGAN CAMPURAN ABU SEKAM DENGAN MENGGUNAKAN PEMODELAN ARTIFICIAL NEURAL NETWORK (ANN)

2019 ◽  
Vol 1 (1) ◽  
pp. 46-52
Author(s):  
Erna Suryani ◽  
Wahyu Naris Wari
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Compressive Strength ◽  
Rice Husk ◽  
Empirical Equation ◽  
Rice Husk Ash ◽  
Asphalt Pavement ◽  
Construction Material ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Pervious Paving (Paving Berpori) adalah material konstruksi yang terbuat dari semen, air, agregat dan bahan campuran lainnya. Paving berpori dapat diapilkasikan pada trotoar, area bermain dan jalan perumahan. Dengan menggunakan paving berpori air akan langsung meresap, sehingga akan mencegah adanya genangan air pada lapis permukaan paving. Metode penelitian yang digunakan adalah menggunakan AAPA (Australian Asphalt Pavement Association) dimana dilakukan sistem Trial Eror. Campuran yang digunakan adalah 1:4, dengan menggunakan gradasi terbuka. Kuat tekan yang di rencanakan yaitu 18,00 MPa, masuk dalam kategori mutu B untuk tempat parkir mobil, pejalan kaki dan taman kota. Campuran paving menggunakan abu sekam padi sebagai reduksi semen dengan persentase 0%, 10%, 20% dan 30%. Pelaksanaan pekerjaan dimulai dari pengambilan bahan baku, pengujian material, perencanaan komposisi dan pembuatan benda uji dengan ukuran P = 21 cm, L = 11,5 cm dan T = 6 cm. Uji kuat tekan dilakukan untuk mengetahui pengaruh abu sekam sebagai bahan reduksi semen pada Paving Berpori. Nilai kuat tekan yang didapatkan akan menjadi input pada program Matlab untuk mendapatkan pemodelan Persamaan Empiris dengan ARTIFICIAL NEURAL NETWORK (ANN) sehingga didapatkan nilai kuat tekan dari berbagai komposisi penambahan bahan abu sekam. Dari hasil penelitian didapatkan persentase tertinggi dicapai pada tambahan abu sekam 30%.Kata kunci : Abu sekam, Artificial Neural Network (ANN), Pervious Paving, Kuat tekan, Persamaan EmpirisPervious Paving is a construction material made from cement, water, aggregate and other materials. Pervious paving can be applied to right on sidewalks, play ground and residential roads. By using Pervious Paving, the water will absorb quickly, so it will prevent the puddles on the surface layer. AAPA (Australian Asphalt Pavement Association) is the reserach methode which we used with Trial and Eror. The mixture of ingredients is 1: 4 with the open gradation. The compressive strength designed is 18 MPa, which is in category B for parking car, pedestrian and city park. Paving mixture consisted of rice husk ash as cement reduction with a percentage of 0%, 10%, 20% and 30%. The work starting from the taking of raw materials, material testing, composition planning and the making of specimens with sizes P = 21 cm, L = 11.5 cm and T = 6 cm. The compressive strength test was conducted to determine the effect of husk ash addition. The compressive strength will be input to the Matlab program to obtain the Empirical Equation modelling with ARTIFICIAL NEURAL NETWORK (ANN). Based on the results of the study, the highest percentage was achieved in the mixture with an addition of 30% rice husk ash.Keywords: Rice husk ash, Artificial Neural Network (ANN), Pervious Paving, Compressive strength, Empirical Equation

Sign in / Sign up

Export Citation Format

Share Document