Sharif Digital Repository

One of the requirements for the operation and planning activities of an electrical utility is the prediction of load for the next hour to several days out, known as short term load forecasting (STLF). This paper presents the STLF of the Iranian national power system (INPS) using artificial neural networks (ANN) and fuzzy expert systems (FES). The ANN is trained with the load patterns corresponding to the forecasting hours and the forecasted load is obtained. The FES modifies the initial forecasted load for the special holidays and also in the case sudden changes in temperature. A data analyser and a temperature forecaster are also included in the NRI STLF (NSTLF) package. The program has... 

In this work, an optimum multilayer perceptron neural network is developed to model the correlation between hot working parameters (temperature, strain rate and strain) and flow stress of IN625 alloy. Three variations of standard back propagation algorithm (Broyden, Fletcher, Goldfarb and Shanno quasi-Newton, Levenberg-Marquardt and Bayesian) are applied to train the model. The results show that, in this case, the best performance, minimum error and shortest converging time are achieved by the Levenberg-Marquardt training algorithm. Comparing the predicted values and the experimental values reveals that a well trained network is capable of accurately calculating the flow stress of the alloy... 

One of the most important requirements for the operation and planning activities of an electrical utility is the prediction of load for the next hour to several days out, known as short term load forecasting (STLF). This paper presents STLF of Iran national power system (INPS) using artificial neural network (ANN). The developed program is based on a four-layered perceptron ANN building block. The optimum inputs were selected for the ANN considering historical data of the INPS. Instead of conventional back propagation (BP) methods, Levenberg-Marquardt BP (LMBP) method has been used for the ANN training to increase the speed of convergence. A data analyzer and a temperature forecaster are... 

In the restructured power markets, price of electricity has been the key of all activities in the power market. Accurately and efficiently forecasting electricity price becomes more and more important. Therefore in this paper, an Artificial Neural Network (ANN) model is designed for short term price forecasting of electricity in the environment of restructured power market. The proposed ANN model is a four-layered perceptron neural network, which consists of, input layer, two hidden layers and output layer. Instead of conventional back propagation (BP) method, Levenberg- Marquardt BP (LMBP) method has been used for the ANN training to increase the speed of convergence. Matlab is used for... 

Biological cell studies have many applications in biology, cell manipulation, and diagnosis of diseases such as cancer and malaria. In this study, Inverse Finite Element Method (IFEM) combined with Levenberg-Marquardt optimization algorithm has been used to extract and characterize material properties of mouse oocyte and embryo cells at large deformations. Then, the simulation results have been validated using data from experimental works. In this study, it is assumed that cell material is hyperelastic, isotropic, homogenous, and axisymmetric. For inverse analysis, FEM model of cell injection experiment implemented in Abaqus software has been coupled with Levenberg-Marquardt optimization... 

One of the most important challenges in target parameters estimation via model-free methods is selection of the most effective input parameters namely features selection (FS). Indeed, irrelevant features can degrade the estimation performance. In the current study, the challenge of choosing among the several plant parameters is tackled by means of the innovative FS algorithm named ranking of features with minimum deviation from the target parameter (RFMD). The selected features accompanied with the stable and the fast learning algorithm of multilayer perceptron (MLP) neural network (i.e. Levenberg-Marquardt algorithm) which is a combination of gradient descent and Gauss-newton learning... 

In this study, accurate estimation of nuclear power plant (NPP) parameters is done using the new and simple technique. The proposed technique using the genetic algorithm (GA) in combination with the Bayesian regularization (BR) and Levenberg- Marquardt (LM) learning algorithms identifies the appropriate architecture for estimation of the target parameters. In the first step, the input patterns features are selected using the features selection (FS) technique. In the second step, the appropriate number of hidden neurons and hidden layers are investigated to provide a more efficient initial population of the architectures. In the third step, the estimation of the target parameter is done using... 

In this study, the artificial neural network (ANN) was used for the prediction of WDT. The inputs to network are molar mass and pressure, and the output is WDT at each input. A two-layer network with different hidden neurons and different learning algorithms such as LM, SCG, GDA and BR were examined. The network with 16 hidden neurons and Levenberg-Marquardt (LM) train function showed the best results in comparison with the other networks. Also, the predicted results of this network were compared with the thermodynamic models and better accordance with experimental data for ANN was concluded  

In this study, artificial neural network (ANN) was used to model the hot deformation behavior of 7075 aluminum alloy during compression test, in the strain rate range of 0.0003-1 s-1 and temperature range of 200-450 C. The inputs of the model were temperature, strain rate, and strain, while the output of the model was the flow stress. The feed-forward back-propagation network with two hidden layers was built and successfully trained at different deformation domains by Levenberg-Marquardt training algorithm. Comparative analysis of the results obtained from the hyperbolic sine, the power law constitutive equations, and the ANN shows that the newly developed ANN model has a better performance... 

In this study, a two-layer feed-forward neural network was constructed and applied to determine a mapping associating mix design and testing factors of cement-nano silica (NS)-rice husk ash ternary blended concrete samples with their performance in conductance to the water absorption properties. To generate data for the neural network model (NNM), a total of 174 field cores from 58 different mixes at three ages were tested in the laboratory for each of percentage, velocity and coefficient of water absorption and mix volumetric properties. The significant factors (six items) that affect the permeability properties of ternary blended concrete were identified by experimental studies which were:... 

Analysis and investigation of the relation between different parts of biological cells such as biomembrane, cytoplasm and nucleus can help to better understand their behaviors and material properties. In this paper, first, the whole elastic properties of mouse oocyte and embryo cells have been computed by inverse finite element and Levenberg-Marquardt optimization algorithm and second, using the derived mechanical properties and the mechanical properties of its bio membrane from the literature, the mechanical properties of its cytoplasm has been characterized. It has been assumed that the cell behavior is as continues, isotropic, nonlinear and homogenous material for modeling. Matching the... 

Global motion estimation (GME) is an important technique in image and video processing. Whereas the direct global motion estimation techniques boast reasonable precision they tend to suffer from high computational complexity. As with indirect methods, though presenting lower computational complexity they mostly exhibit lower accuracy than their direct counterparts. In this paper, the authors introduce a robust algorithm for GME with near identical accuracy and almost 50-times faster than MPEG-4 verification model (VM). This approach entails two stages in which, first, motion vector of sampled block is employed to obtain initial GME then Levenberg-Marquardt algorithm is applied to the... 

In this article, a feed-forward neural network is explored to reconstruct the performance map of an axial compressor through the utilization of a limited number of experimental data. The Levenberg-Marquardt algorithm with Bayesian regularization method is used to adjust the weights and biases of the network. The proposed technique is utilized to estimate the mass flowrate, the pressure ratio, the shaft speed, and the efficiency in regions where no experimental data are available. The surge line is predicted and the line of maximum efficiencies is determined. The results are compared with experimental data  

In the present investigation, design of integrated numerical computing through Levenberg-Marquardt backpropagation neural network (LMBNN) is presented to examine the fluid mechanics problems governing the dynamics of expanding and contracting cylinder for Cross magneto-nanofluid flow (ECCCMNF) model in the presence of time dependent non-uniform magnetic force and permeability of the cylinder. The original system model ECCCMNF in terms of PDEs is converted to nonlinear ODEs by introducing the similarity transformations. Reference dataset of the designed LMBNN methodology is formulated with Adam numerical technique for scenarios of ECCCMNF by variation of thermophoresis temperature ratio... 

Sensors are one of the most vital instruments in Nuclear Power Plants (NPPs), and operators and safety systems monitor and analyze various parameters reported by them. Failure to detect sensors malfunctions or anomalies would lead to the considerable consequences. In this research, a new method based on thermal–hydraulic simulation by RELAP5 code and Feed-Forward Neural Networks (FFNN) is introduced to detect faulty sensors and estimate their correct value. For design an efficient neural net, seven feature selectors (i.e., Information gain, ReliefF, F-regression, mRMR, Plus-L Minus-R, GA, and PSO), three sigmoid activation functions (i.e., Logistic, Tanh and Elliot), and three training... 

In this experimental study, a kinetic model has been developed for Fischer-Tropsch synthesis reactions by using sol-gel technique and Fe/Ni/Al 2O 3 as the catalyst (40% Fe/60% Ni/40 wt.%Al 2O 3) in a differential fixed-bed micro reactor assuming no internal or external diffusion. Operating conditions of the reactor were as follows: total pressure 1-12 atm; Temperature 220-260 °C; H 2/CO feed ratio 1.5-2; gas hourly space velocity 2100-7000 cm 3(STP)/h/ g cat and conversions of 6-37% of hydrogen and 7-21% of carbon monoxide. Mass transfer limitations were investigated by changing synthesis gas velocity in reactors which differ in size. Based on the hypothesis that water inhibits the intrinsic... 

Global Motion Estimation (GME) has many important roles in numerous applications, such as video compression, image stabilization, video-object segmentation, and etc. One well-known GME method is the gradient-based technique. This method uses optimization techniques, like the Levenberg-Marquardt algorithm, to minimize estimation error. Such algorithms require an initial value for the initializing step. In this paper, we propose a simple and reliable GME structure with a new predictor. This structure uses a three-step search and a predictor for the initializing step. It is also incorporated with a fast GME method that uses pixel subsampling. This incorporation reduces the computational... 

A chemical kinetic model for i-butane and n-butane catalytic cracking over synthesized HZSM-5 zeolite, with SiO 2/Al 2O 3 = 484, and in a plug flow reactor under various operating conditions, has been developed. To estimate the kinetic parameters of catalytic cracking reactions of i-butane and n-butane, a lump kinetic model consisting of six reaction steps and five lumped components is proposed. This kinetic model is based on mechanistic aspects of catalytic cracking of paraffins into olefins. Furthermore, our model takes into account the effects of both protolytic and bimolecular mechanisms. The Levenberg-Marquardt algorithm was used to estimate kinetic parameters. Results from statistical... 

In this paper we present a method of localizing multiple wideband acoustic sources based on both signal attenuation pattern and delays in the reception of the signal. Moreover, an additional order of flexibility is added to the problem by considering the attenuation model as an unknown function with reasonable prior assumptions about its functional space. Such approach is capable of enhancing the localization performance compared to when only the signal attenuation data or the time delays are used. A cost function is then formed in terms of the sources locations and the attenuation model parameters. Having different types of unknowns in the cost function, convergence concerns, and the... 

A Magneto rheological (MR) rotary brake as a prosthesis knee is addressed here. To the gait of the amputee, the brake, automatically adapts knee damping coefficient using only local sensing of the knee torque and position. It is difficult to design a model-based controller, since the MR knee system has nonlinear and very complicated governing mathematical equations. Hence, a Hybrid self-organizing fuzzy controller and multidimensional wavelet neural network (HSFCMWNN) is proposed here to control the knee damping coefficient using of the inverse dynamics of the MR rotary damper. A Self-organizing fuzzy controller (SOFC) is also proposed and during the control process, the SOFC continually...