eng
Pouyan Press
Journal of Soft Computing in Civil Engineering
2588-2872
2017-07-01
1
1
1
11
10.22115/scce.2017.46317
46317
Advanced ANN Prediction of Moisture Damage in CNT Modified Asphalt Binder
Md Arifuzzaman
arafiquzzaman@uob.edu.bh
1
Assistant Professor, Department of Civil Engineering, University of Bahrain, Bahrain
Moisture penetration causes many direct and indirect distresses in flexible asphalt pavement. Due to damage in asphalt concrete and binder by moisture are the prime concern of failure for flexible pavement worldwide. The causes and prediction are investigated in this study. The asphalt binder was modified with carbon nanotubes (CNT) with very small percentages. The modified binder was simulated with moisture damage with AASHTO T-283 methods. In this study, polymer and carbon nanotubes (CNT) have been added to liquid asphalt binder to examine whether the resulting modified binder has improved moisture damage resistance. Using laboratory tested data, an artificial intelligence modeling technique has been utilized to determine the moisture damage behavior of the modified binder. Multi-Layer Perceptron (MLP) provides the best prediction for wet and dry samples AFM readings with R2 values respectively 0.6407 and 0.8371.
https://www.jsoftcivil.com/article_46317_d2d39703c7530cbfaa91c357d3803ecc.pdf
Fuzzy System
Artificial Neural Network
Atomic force microscopy
Adhesion forces
Functionalized tips
Moisture
Damage model
eng
Pouyan Press
Journal of Soft Computing in Civil Engineering
2588-2872
2017-07-01
1
1
12
28
10.22115/scce.2017.46318
46318
Comparison Study of Soft Computing Approaches for Estimation of the Non-Ductile RC Joint Shear Strength
Masoomeh Mirrashid
m.mirrashid@semnan.ac.ir
1
Faculty of Civil Engineering, Semnan University, Semnan, Iran
Today, retrofitting of the old structures is important. For this purpose, determination of capacities for these buildings, which mostly are non-ductile, is a very useful tool. In this context, non-ductile RC joint in concrete structures, as one of the most important elements in these buildings are considered, and the shear capacity, especially for retrofitting goals can be very beneficial. In this paper, three famous soft computing methods including artificial neural networks (ANN), adaptive neuro-fuzzy inference system (ANFIS) and also group method of data handling (GMDH) were used to estimating the shear capacity for this type of RC joints. A set of experimental data which were a failure in joint are collected, and first, the effective parameters were identified. Based on these parameters, predictive models are presented in detail and compare with each other. The results showed that the considered soft computing techniques are very good capabilities to determine the shear capacity.
https://www.jsoftcivil.com/article_46318_06bfd51bf218fa8c5f876009f5a5428e.pdf
ANFIS
RC joint
Shear strength
Soft Computing
Neural Networks
Non-Ductile
eng
Pouyan Press
Journal of Soft Computing in Civil Engineering
2588-2872
2017-07-01
1
1
29
53
10.22115/scce.2017.46845
46845
No-Deposition Sediment Transport in Sewers Using Gene Expression Programming
Isa Ebtehaj
isa.ebtehaj@gmail.com
1
Hossein Bonakdari
bonakdari@yahoo.com
2
Ph.D. Candidate, Department of Civil Engineering, Razi University, Kermanshah, Iran
Professor, Department of Civil Engineering, Razi University, Kermanshah, Iran
The deposition of the flow of suspended particles has always been a problematic case in the process of flow transmission through sewers. Deposition of suspended materials decreases transmitting capacity. Therefore, it is necessary to have a method capable of precisely evaluating the flow velocity in order to prevent deposition. In this paper, using Gene-Expression Programming, a model is presented which properly predicts sediment transport in the sewer. In order to present Gene-Expression Programming model, firstly parameters which are effective on velocity are surveyed and considering every of them, six different models are presented. Among the presented models the best is being selected. The results show that using verification criteria, the presented model presents the results as Root Mean Squared Error, RMSE=0.12 and Mean Average Percentage Error, MAPE=2.56 for train and RMSE=0.14 and MAPE=2.82 for verification. Also, the model presented in this study was compared with the other existing sediment transport equations which were obtained using nonlinear regression analysis.
https://www.jsoftcivil.com/article_46845_edbf71f986f538a32046c72950b67c92.pdf
Bed load
Sediment transport
Sewer
No-deposition
Gene-Expression Programming
eng
Pouyan Press
Journal of Soft Computing in Civil Engineering
2588-2872
2017-07-01
1
1
54
64
10.22115/scce.2017.48040
48040
Using of Backpropagation Neural Network in Estimation of Compressive Strength of Waste Concrete
Ali Heidari
heidari@eng.sku.ac.ir
1
Masoumeh Hashempour
ms.hashempour@gmail.com
2
Davoud Tavakoli
tavakoli.d@gmail.com
3
Associate Professor, Department of Civil Engineering, Shahrekord University, Shahrekord, Iran
M.Sc. Student, Department of Civil Engineering, Shahrekord University, Shahrekord, Iran
Ph.D., Department of Civil Engineering, Shahid Rajaee Teacher Training University, Tehran, Iran
Waste concrete is one of the most usable and economic kind of concrete which is used in many civil projects all around the world, and its importance is undeniable. Also, the explanation of constructional process and destruction of them cause the extensive growth of irreversible waste to the industry cycle, which can be as one of the main damaging factors to the economy. In this investigation, with using of constructional waste included concrete waste, brick, ceramic and tile and stone new aggregate was made. Also it was used with different weight ratios of cement in the mix design. The results of laboratory studies showed that the using of the ratio of sand to cement 1 and waste aggregate with 20% weight ratio (W20), replacing of normal aggregate, increased the 28 days compressive strength to the maximum stage 45.23 MPa. In the next stage, in order to develop the experimental results backpropagation neural network was used. This network with about 91% regression, 0.24 error, and 1.41 seconds, is a proper method for estimating results.
https://www.jsoftcivil.com/article_48040_c7aa81ed8b39a6f8771b0e198dd81dfa.pdf
Waste materials
Concrete
Compressive strength
Backpropagation neural network
eng
Pouyan Press
Journal of Soft Computing in Civil Engineering
2588-2872
2017-07-01
1
1
65
85
10.22115/scce.2017.48336
48336
A Method for Constructing Non-Isosceles Triangular Fuzzy Numbers Using Frequency Histogram and Statistical Parameters
Amin Amini
amin.amini@postgrad.curtin.edu.au
1
Navid Nikraz
navid.nikraz@curtin.edu.au
2
Ph.D. Student, Faculty of Science and Engineering, Curtin University, Kent St, Bentley WA 6102, Australia
Senior lecturer, Faculty of Science and Engineering, Curtin University, Kent St, Bentley WA 6102, Australia
The philosophy of fuzzy logic was formed by introducing the membership degree of a linguistic value or variable instead of divalent membership of 0 or 1. Membership degree is obtained by mapping the variable on the graphical shape of fuzzy numbers. Because of simplicity and convenience, triangular membership numbers (TFN) are widely used in different kinds of fuzzy analysis problems. This paper suggests a simple method using statistical data and frequency chart for constructing non-isosceles TFN when we are using direct rating for evaluating a variable in a predefined scale. In this method, the relevancy between assessment uncertainties and statistical parameters such as mean value and the standard deviation is established in a way that presents an exclusive form of triangle number for each set of data. The proposed method with regard to the graphical shape of the frequency chart distributes the standard deviation around the mean value and forms the TFN with the membership degree of 1 for mean value. In the last section of the paper modification of the proposed method is presented through a practical case study.
https://www.jsoftcivil.com/article_48336_23d451bdbc0de701221e4497911f1d64.pdf
Triangular fuzzy number
Non-isosceles
Membership function construction
Direct rating
statistical
eng
Pouyan Press
Journal of Soft Computing in Civil Engineering
2588-2872
2017-07-01
1
1
86
92
10.22115/scce.2017.48352
48352
GMDH-Network to Estimate the Punching Capacity of FRP-RC Slabs
Alla Azimi
alla.azimi@gmail.com
1
Department of Civil Engineering, University of Birmingham, United Kingdom
Determination of the punching shear capacity of FRP-reinforced concrete slabs was studied in this paper. A database including 81 pairs of data was collected and used. The method was considered in the paper, was group method of data handling (GMDH) which is one of the most structures which is used by researchers. The section area of the column, effective flexural depth of slab, the compressive strength of concrete, Young’s modulus of the FRP slab and reinforcement ratio were used as input variables. The target of the model was also the determination of the ultimate punching capacity of the FRP-reinforced concrete flat slab (Target). Based on this dataset, ten polynomials specified and its coefficients were presented. All of these ten polynomials used for the considered prediction. The proposed GMDH structure also validate by several experimental data. The results indicated that group method of data handling (GMDH) is beneficial for the prediction of the punching shear capacity of slabs.
https://www.jsoftcivil.com/article_48352_1785a265139d37edf9ea5bf7c899e7b2.pdf
GMDH
FRP
shear capacity
RC-Slabs
eng
Pouyan Press
Journal of Soft Computing in Civil Engineering
2588-2872
2017-07-01
1
1
93
98
10.22115/scce.2017.48392
48392
Capacity Prediction of RC Beams Strengthened with FRP by Artificial Neural Networks Based on Genetic Algorithm
Ghazal Hosseini
ghazal.1792@yahoo.com.au
1
Department of Civil Engineering, University of New South Wales, Sydney, Australia
In this paper, the ability of the artificial neural network which was trained based on a Genetic algorithm used to predict the shear capacity of the reinforced concrete beams strengthened with the side-bonded fiber reinforced polymer (FRP). A database of experimental data including 95 data which were published in literature was collected and used to the network. Seven inputs including the width of the beam, effective depth, FRP thickness, Young modulus, the tensile strength of FRP and also FRP ratio were used to predict the shear capacity of the reinforced concrete beams strengthened with the side-bonded fiber reinforced polymer. The best values of the weights and the biases were obtained by the Genetic algorithm. For increasing the ability of the model to predict the considered target, it was suggested that the predicted values considered smaller. The results indicated that the proposed neural network based on genetic algorithm was able to predict the shear capacity of the considered elements.
https://www.jsoftcivil.com/article_48392_2755eca3acc5d9ec0c0433fde00755db.pdf
Artificial Neural Networks
FRP
Shear strength
Genetic Algorithm