Search published articles


Showing 40 results for Ann

P. Muthupriya, K. Subramanian, B.g. Vishnuram,
Volume 1, Issue 1 (3-2011)
Abstract

Neural networks have recently been widely used to model some of the human activities in many areas of civil engineering applications. In the present paper, artificial neural networks (ANN) for predicting compressive strength of cubes and durability of concrete containing metakaolin with fly ash and silica fume with fly ash are developed at the age of 3, 7, 28, 56 and 90 days. For building these models, training and testing using the available experimental results for 140 specimens produced with 7 different mixture proportions are used. The data used in the multi-layer feed forward neural networks models are designed in a format of eight input parameters covering the age of specimen, cement, metakaolin (MK), fly ash (FA), water, sand, aggregate and superplasticizer and in another set of specimen which contain SF instead of MK. According to these input parameters, in the multi-layer feed forward neural networks models are used to predict the compressive strength and durability values of concrete. It shown that neural networks have high potential for predicting the compressive strength and durability values of the concretes containing metakaolin, silica fume and fly ash.
A. Hadidi, A. Kaveh, B. Farahmand Azar, S. Talatahari, C. Farahmandpour,
Volume 1, Issue 3 (9-2011)
Abstract

In this paper, an efficient optimization algorithm is proposed based on Particle Swarm Optimization (PSO) and Simulated Annealing (SA) to optimize truss structures. The proposed algorithm utilizes the PSO for finding high fitness regions in the search space and the SA is used to perform further investigation in these regions. This strategy helps to use of information obtained by swarm in an optimal manner and to direct the agents toward the best regions, resulting in possible reduction of the number of particles. To show the computational advantages of the new PSO-SA method, some benchmark numerical examples are studied. The PSO-SA algorithm converges to better or at least the same solutions, while the number of structural analyses is significantly reduced
A. Tahershamsi , R. Sheikholeslami,
Volume 1, Issue 3 (9-2011)
Abstract

In engineering, flood routing is an important technique necessary for the solution of a floodcontrol problem and for the satisfactory operation of a flood-prediction service. A simple conceptual model like the Muskingum model is very effective for the flood routing process. One challenge in application of the Muskingum model is that its parameters cannot be measured physically. In this article we proposed imperialist competitive algorithm (ICA) for optimal parameter estimation of the linear Muskingum model. This algorithm uses imperialism and imperialistic competition process as a source of inspiration. Optimization to identify Muskingum model parameters can be considered as a suitable field to investigate the efficiency of this algorithm.
S. Adarsh,
Volume 2, Issue 1 (3-2012)
Abstract

To ensure efficient performance of irrigation canals, the losses from the canals need to be minimized. In this paper a modified formulation is presented to solve the optimization model for the design of different canal geometries for minimum seepage loss, in meta-heuristic environment. The complex non-linear and non-convex optimization model for canal design is solved using a probabilistic search algorithm namely Probabilistic Global Search Lausanne (PGSL). The solutions are found to be competitive to those reported in literature while applied for different example problems. To suit for real field applications, three site specific constraints are considered and the sensitivity of solutions for the most popular trapezoidal canals is investigated. The study shows the potential of the proposed approach to perform optimal design of irrigation canals for minimum seepage loss.
S.h. Mirmohammadi, Sh. Shadrokh, K. Eshghi,
Volume 2, Issue 2 (6-2012)
Abstract

The purpose of this paper is to present a polynomial time algorithm which determines the lot sizes for purchase component in Material Requirement Planning (MRP) environments with deterministic time-phased demand with zero lead time. In this model, backlog is not permitted, the unit purchasing price is based on the all-units discount system and resale of the excess units is possible at the ordering time. The properties of an optimal order policy are argued and on the basis of them, a branch and bound algorithm is presented to construct an optimal sequence of order policies. In the proposed B&B algorithm, some useful fathoming rules have been proven to make the algorithm very efficient. By defining a rooted tree graph, it has been shown that the worst-case time complexity function of the presented algorithm is polynomial. Finally, some test problems which are randomly generated in various environments are solved to show the efficiency of the algorithm.
M.r. Ghasemi, E. Barghi,
Volume 2, Issue 3 (7-2012)
Abstract

In this paper the performance of Artificial Neural Networks (ANNs) and Adaptive Neuro- Fuzzy Inference Systems (ANFIS) in simulating the inverse dynamic behavior of Magneto- Rheological (MR) dampers is investigated. MR dampers are one of the most applicable methods in semi active control of seismic response of structures. Various mathematical models are introduced to simulate the dynamic behavior of MR dampers. The Modified Bouc-Wen model is an appropriate model that has an acceptable accuracy in calculating the generated force of dampers compared to others. In this model displacement and voltage of a MR damper are known while the force generated by MR damper is considered as the unknown. Because of highly nonlinear characteristics of modified bouc-wen model determination of inverse dynamic behavior of MR dampers are generally done using ANNs and ANFIS. Since the ANNs and ANFIS have different mechanisms for emulating desired functions, their responses may be different. In this research the performance of a Back Propagation Neural Network (BPNN), Radial Basis Functions Neural Network (RBFNN) and ANFIS in estimating the inverse dynamic behavior of MR dampers are compared. The results emphasize on the advancement of ANFIS to the other methods studied in estimation of inverse dynamic behavior of MR dampers.
A. Baghlani,
Volume 2, Issue 3 (7-2012)
Abstract

Optimum control of upstream pumping station in open channels with given constraint in downstream end is presented in this paper. The upstream control is capable of minimizing water level fluctuations in the channel in which the downstream pumping station causes an undesirable wave. The proposed method combines an unsteady non-uniform flow solver with shock-capturing capability, Fourier series and metaheuristic firefly algorithm. Fourier series is used to estimate the optimum inflow control and firefly algorithm is utilized to determine the unknown coefficients in the series. With a suitable objective function, the procedure generates the optimum inflow hydrograph that can effectively cancel destructive downstream waves. The results have been compared with the results obtained by a variational approach and show satisfactory improvement both in simplicity and the value of objective function.
S.s. Naseralavi, E. Salajegheh, J. Salajegheh, M. Ziaee,
Volume 2, Issue 4 (10-2012)
Abstract

A novel two-stage algorithm for detection of damages in large-scale structures under static loads is presented. The technique utilizes the vector of response change (VRC) and sensitivities of responses with respect to the elemental damage parameters (RSEs). It is shown that VRC approximately lies in the subspace spanned by RSEs corresponding to the damaged elements. The property is leveraged in the first stage of the proposed method by seeking RSEs whose spanned subspace best contains the VRC. Consequently, the corresponding elements are regarded as damage candidates. To alleviate the exploration among RSEs, they are first partitioned into several clusters. Subsequently, discrete ant colony optimization (ACO) is utilized to find the clusters containing the RSEs of damaged elements. In the second stage of the algorithm, damage amounts for the restricted elements are determined using a continuous version of ACO. Two numerical examples are studied. The results illustrate that the method is both robust and efficient for detection of damages in large-scale structures.
G. Ghodrati Amiri, P. Namiranian,
Volume 3, Issue 1 (3-2013)
Abstract

The main objective of this paper is to use ant optimized neural networks to generate artificial earthquake records. In this regard, training accelerograms selected according to the site geology of recorder station and Wavelet Packet Transform (WPT) used to decompose these records. Then Artificial Neural Networks (ANN) optimized with Ant Colony Optimization and resilient Backpropagation algorithm and learn to relate the dimension reduced response spectrum of records to their wavelet packet coefficients. Trained ANNs are capable to produce wavelet packet coefficients for a specified spectrum, so by using inverse WPT artificial accelerograms obtained. By using these tools, the learning time of ANNs reduced salient and generated accelerograms had more spectrum-compatibility and save their essence as earthquake accelerograms.
H. Fattahi, S. Shojaee, M A. Ebrahimi Farsangi, H. Mansouri,
Volume 3, Issue 3 (9-2013)
Abstract

The excavation damaged zone (EDZ) can be defined as a rock zone where the rock properties and conditions have been changed due to the processes related to an excavation. This zone affects the behavior of rock mass surrounding the construction that reduces the stability and safety factor and increase probability of failure of the structure. In this paper, a methodology was examined for computing the creation probability of damaged zone by Latin hypercube sampling based on a feed-forward artificial neural network (ANN) optimized by hybrid particle swarm optimization and genetic algorithm (HPSOGA). The HPSOGA was carried out to decide the initial weights of the neural network. A case study in a test gallery of the Gotvand dam, Iran was carried out and creation probabilities of 0.191 for highly damaged zone (HDZ) and 0.502 for EDZ were obtained.
S. Afandizadeh , M. A Arman , N. Kalantari,
Volume 3, Issue 4 (10-2013)
Abstract

Network design problem is one of the most complicated and yet challenging problems in transportation planning. The Bi-level, non-convex and integer nature of network design problem has made it into one of the most complicated optimization problems. Inclusion of time dimension to the classical network design problem could add to this complexity. In this paper an Ant Colony System (ACS) has been proposed to solve the Time Dependent Network Design Problem (T-NDP). The proposed algorithm has been used to solve different networks: A small size, a medium size and a large scale network. The results show that the proposed model has superior performance compared to the previous method proposed for solving the T-NDP.
A. Gholizad , S. D. Ojaghzadeh Mohammadi,
Volume 4, Issue 1 (3-2014)
Abstract

Structural vibration control is one of the most important features in structural engineering. Real-time information about seismic resultant forces is required for deciding module of intelligent control systems. Evaluation of lateral forces during an earthquake is a complicated problem considering uncertainties of gravity loads amount and distribution and earthquake characteristics. An artificial neural network (ANN) has been trained in this article to estimate these forces. This ANN was trained on the results of time history analysis of a three-story building under 702 different loadings. Results of numerical examples verify that the trained ANN can predict the expected forces with negligible deviations.
H. Rahami, A. Kaveh,
Volume 4, Issue 1 (3-2014)
Abstract

In this paper simple formulae are derived for calculating the number of spanning trees of different product graphs. The products considered in here consists of Cartesian, strong Cartesian, direct, Lexicographic and double graph. For this purpose, the Laplacian matrices of these product graphs are used. Form some of these products simple formulae are derived and whenever direct formulation was not possible, first their Laplacian matrices are transformed into single block diagonal forms and then using the concept of determinant, the calculations are performed.
A. Afshar , H.r. Zolfaghar Dolabi,
Volume 4, Issue 4 (11-2014)
Abstract

Safety risk management has a considerable effect on disproportionate injury rate of construction industry, project cost and both labor and public morale. On the other hand time-cost optimization (TCO) may earn a big profit for project stakeholders. This paper has addressed these issues to present a multi-objective optimization model to simultaneously optimize total time, total cost and overall safety risk (OSR). The present GA-based optimization model possesses significant features of Pareto ranking as selection criterion, elite archiving and adaptive mutation rate. In order to facilitate safety risk assessment in the planning phase, a qualitative activity-based safety risk (QASR) method is also developed. An automated system is codded as an Excel add-in program to facilitate the use of the model for practitioners and researchers. The model has been implemented and verified on a case study successfully. Results indicate that integration of safety risk assessment methods into multi-objective TCO problem improves OSR of nondominated solutions. The robustness of the present optimization model has also been proved by its great ability to prevent genetic drift as well as the improvement in the bicriteria among generations.
H. Fathnejat, P. Torkzadeh, E. Salajegheh, R. Ghiasi,
Volume 4, Issue 4 (11-2014)
Abstract

Vibration based techniques of structural damage detection using model updating method, are computationally expensive for large-scale structures. In this study, after locating precisely the eventual damage of a structure using modal strain energy based index (MSEBI), To efficiently reduce the computational cost of model updating during the optimization process of damage severity detection, the MSEBI of structural elements is evaluated using properly trained cascade feed-forward neural network (CFNN). In order to achieve an appropriate artificial neural network (ANN) model for MSEBI evaluation, a set of feed-forward artificial neural networks which are more suitable for non-linear approximation, are trained. All of these neural networks are tested and the results demonstrate that the CFNN model with log-sigmoid hidden layer transfer function is the most suitable ANN model among these selected ANNs. Moreover, to increase damage severity detection accuracy, the optimization process of damage severity detection is carried out by particle swarm optimization (PSO) whose cost function is constructed based on MSEBI. To validate the proposed solution method, two structural examples with different number of members are presented. The results indicate that after determining the damage location, the proposed solution method for damage severity detection leads to significant reduction of computational time compared to finite element method. Furthermore, engaging PSO algorithm by efficient approximation mechanism of finite element (FE) model, maintains the acceptable accuracy of damage severity detection.
D. Meskó,
Volume 4, Issue 4 (11-2014)
Abstract

During the planning phase of modern, complex, block-structured, large-area located, but still landscape-harmonized health-care buildings, the key is the optimal positioning of the blocks and functions, simultaneously ensuring the most-effective backup-paths for any transportation route failure in the buildings in order to speed up system operation, reduce maintenance costs and especially to improve patient safety and satisfaction. The importance of improving reliability and boundary conditions of the modelling in modern complex health-care building-systems are emphasized. A cost efficient pre-phase solution of mathematical, graph modelling is presented, with introducing link doubling to linearize a two segment, non-linear capacity-cost function. The developed and detailed mathematical graph model can be used as part of the architectural planning workflow. This model allows distinguishing the sharable part from the free part of capacity on a link in case of simultaneously routing multiple protection paths. Link doubling allows finding optimal routing of shared protection paths for failure cases. Two algorithms are proposed for routing of the guaranteed bandwidth pipes with shared protection which provides reliable building structures through thrifty additional resources. It is assumed that a single working path can be protected by one or multiple protection paths, which are partially or fully disjoint from the working one. This approach allows better capacity sharing among protection paths. The main aim of the recommendations is to achieve a reliable, fully operational building even if a failure, a reconditioning or emergency situation happens.
A. Samadi , H. Arvanaghi,
Volume 4, Issue 4 (11-2014)
Abstract

Measurement of discharge in open channels is one of the main concerns in hydraulic engineering. The structures used for this aim should be accurate, economical and easy to use. Weirs are among the oldest and most convenient hydraulic structures that have been used in both laboratory and field for flow measurement in open channels. Due to limitations of simple sharp crested weirs, recently compound sharp crested weirs have attracted great attention of civil engineers. In general, use of compound sharp crested weirs can be an appropriate solution when the discharge should be measure accurately with a reasonable sensitivity over a wide range of flows. The aim of this research is three-dimensional simulation of flow on contracted compound arched rectangular sharp crested weirs by using FLUENT software. For multiphase flow simulation, VOF method is used and for simulation of turbulent flow, RNG k-ɛ turbulence model is used and the result of numerical model is compared with experimental data. The results of this study indicate that FLUENT simulate flow on contracted compound arched rectangular sharp crested weirs with high accuracy and we can use this software for determine the discharge coefficient on contracted compound weirs.
Z. Hajishafee , S.h. Mirmohammadi , S.r. Hejazi,
Volume 5, Issue 1 (1-2015)
Abstract

The overall cost of companies dealing with the distribution tasks is considerably affected by the way that distributing vehicles are procured. In this paper, a more practical version of capacitated vehicle routing problem (CVRP) in which the decision of purchase or hire of vehicles is simultaneously considered is investigated. In CVRP model capacitated vehicles start from a single depot simultaneously and deliver the demanded items of several costumers with known demands where each costumer must be met once. Since the optimal vehicle procurement cost is a function of total distance it traverses during the planning horizon, the model is modified in a way that the decision of purchasing or hiring of each vehicle is made simultaneously. The problem is formulated as a mixed integer programming (MIP) model in which the sum of net present value (NPV) of procurement and traveling costs is minimized. To solve the problem, a hybrid electromagnetism and parallel simulated annealing (PSA-EM) algorithm and a Shuffled Frog Leaping Algorithm (SFLA) are presented. Finally, the presented methods are compared experimentally. Although in some cases the SFLA algorithm yields better solutions, experimental results show the competitiveness of PSA-EM algorithm from the computational time and performance points of view.
I. Ahmadianfar, A. Adib , M. Taghian,
Volume 5, Issue 2 (3-2015)
Abstract

This paper presents a Multi-Objective Evolutionary Algorithm based on Decomposition (MOEA/D) for the optimal operation of a complex multipurpose and multi-reservoir system. Firstly, MOEA/D decomposes a multi-objective optimization problem into a number of scalar optimization sub-problems and optimizes them simultaneously. It uses information of its several neighboring sub-problems for optimizing each sub-problem. This simple procedure makes MOEA/D have lower computational complexity compared with non-dominated sorting genetic algorithm II (NSGA-II). The algorithm (MOEA/D) is compared with the Genetic Algorithm (NSGA-II) using a set of common test problems and the real-world Zohre reservoir system in southern Iran. The objectives of the case study include water supply of minimum flow and agriculture demands over a long-term simulation period. Experimental results have demonstrated that MOEA/D can improve system performance to reduce the effect of drought compared with NSGA-II superiority. Therefore, MOEA/D is highly competitive and recommended to solve multi-objective optimization problems for water resources planning and management.
I. Ahmadianfar, A. Adib , M. Taghian,
Volume 6, Issue 1 (1-2016)
Abstract

To deal with severe drought when water supply is insufficient hedging rule, based on hedging rule curve, is proposed. In general, in discrete hedging rules, the rationing factors have changed from a zone to another zone at once. Accordingly, this paper is an attempt to improve the conventional hedging rule to control the changes of rationing factors. In this regard, the simulation model has employed a fuzzy approach, and this causes rationing factor changing during a long term simulation gradually. To optimize different parameters of the purposed hedging a Multi-objective Particle Swarm Optimization (MOPSO) algorithm has been considered. The minimum of two objectives Modified Shortage Index (MSI) involving water supply of minimum flow and agriculture demands can be taken as the optimization objectives. The results of the proposed hedging rule indicate long term and annual MSI values have considerably improved compared to the conventional hedging rule. This determines that the proposed method is promising and efficient to mitigate the water shortage problem.

Page 1 from 2    
First
Previous
1
 

© 2019 All Rights Reserved | Iran University of Science & Technology

Designed & Developed by : Yektaweb