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

scholarly journals Learned Prediction of Compressive Strength of GGBFS Concrete Using Hybrid Artificial Neural Network Models

Materials ◽  
2019 ◽  
Vol 12 (22) ◽  
pp. 3708 ◽  
Author(s):  
In-Ji Han ◽  
Tian-Feng Yuan ◽  
Jin-Young Lee ◽  
Young-Soo Yoon ◽  
Joong-Hoon Kim
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Compressive Strength ◽  
Experimental Studies ◽  
Back Propagation ◽  
Network Models ◽  
Neural Network Models ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Artificial Neural Network Models

A new hybrid intelligent model was developed for estimating the compressive strength (CS) of ground granulated blast furnace slag (GGBFS) concrete, and the synergistic benefits of the hybrid algorithm as compared with a single algorithm were verified. While using the collected 269 data from previous experimental studies, artificial neural network (ANN) models with three different learning algorithms namely back-propagation (BP), particle swarm optimization (PSO), and new hybrid PSO-BP algorithms, were constructed and the performance of the models was evaluated with regard to the prediction accuracy, efficiency, and stability through a threefold procedure. It was found that the PSO-BP neural network model was superior to the simple ANNs that were trained by a single algorithm and it is suitable for predicting the CS of GGBFS concrete.

scholarly journals Analyzing the Compressive Strength of Ceramic Waste-Based Concrete Using Experiment and Artificial Neural Network (ANN) Approach

Materials ◽  
2021 ◽  
Vol 14 (16) ◽  
pp. 4518
Author(s):  
Hongwei Song ◽  
Ayaz Ahmad ◽  
Krzysztof Adam Ostrowski ◽  
Marta Dudek
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Compressive Strength ◽  
Solid Waste ◽  
Mean Square Error ◽  
Partial Replacement ◽  
Mean Square ◽  
Ceramic Waste ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

In a fast-growing population of the world and regarding meeting consumer’s requirements, solid waste landfills will continue receiving a substantial amount of waste. The utilization of solid waste materials in concrete has gained the attention of the researchers. Ceramic waste powder (CWP) is considered to be one of the most harmful wastes for the environment, which may cause water, soil, and air pollution. The aim of this study was comprised of two phases. Phase one was based on the characterization of CWP with respect to its composition, material testing (coarse aggregate, fine aggregate, cement,) and evaluation of concrete properties both in fresh and hardened states (slump, 28 days compressive strength, and dry density). Concrete mixes were prepared in order to evaluate the compressive strength (CS) of the control mix, with partial replacement of the cement with CWP of 10 and 20% by mass of cement and 60 prepared mixes. However, phase two was based on the application of the artificial neural network (ANN) and decision tree (DT) approaches, which were used to predict the CS of concrete. The linear coefficient correlation (R2) value from the ANN model indicates better performance of the model. Moreover, the statistical check and k-fold cross validation methods were also applied for the performance confirmation of the model. The mean absolute error (MAE), mean square error (MSE), and root mean square error (RMSE) were evaluated to confirm the model’s precision.

Sign in / Sign up

Export Citation Format

Share Document