Sharif Digital Repository

In this work, neural networks are used for estimation of flow stress of AA5083 with regard to dynamic strain ageing that occurs in certain deformation conditions and varies flow stress behavior of the metal being deformed. The input variables are selected to be strain rate, temperature and strain and the output value is the flow stress. In the first stage, the appearance and terminal of dynamic strain aging are determined with the aid of tensile testing at various temperatures and strain rates and subsequently for the serrated flow and the smooth yielding domains different neural networks are constructed based on the achieved results. While a feed-forward backpropagation algorithm is... 

The aim of this work is to introduce a new method based on time frequency distribution for classifying the EEG signals. Some parameters are extracted using time-frequency distribution as inputs to a feed-forward backpropagation neural networks (FBNN). The proposed method had better results with 98.25% accuracy compared to previously studied methods such as wavelet transform, entropy, logistic regression and Lyapunov exponent  

This paper concerns the design of a neural state observer for nonlinear dynamic systems with noisy measurement channels and in the presence of small model errors. The proposed observer consists of three feedforward neural parts, two of which are MLP universal approximators, which are being trained off-line and the last one being a Linearly Parameterized Neural Network (LPNN), which is being updated on-line. The off-line trained parts are able to generate state estimations instantly and almost accurately, if there are not catastrophic errors in the mathematical model used. The contribution of the on-line adapting part is to compensate the remainder estimation error due to uncertain parameters... 

The electroencephalogram (EEG) is a representative signal containing information about the condition of the brain. The shape of the wave may contain useful information about its state. However, the human observer cannot directly monitor these subtle details. Besides, since bio-signals are highly subjective, the symptoms may appear at random in the time scale. Therefore, the EEG signal parameters, extracted and analyzed using computers, are highly useful in diagnosis. The aim of this work is to compare the different classifiers when applied to EEG data from normal and epileptic subjects. For this purpose an adaptive neural fuzzy network (ANFN) to classify normal and epileptic EEG signals is... 

Shot peening (SP), as one of the severe plastic deformation (SPD) methods is employed for surface modification of the engineering components by improving the metallurgical and mechanical properties. Furthermore, artificial neural network (ANN) has been widely used in different science and engineering problems for predicting and optimizing in the last decade. In the present study, effects of conventional shot peening (CSP) and severe shot peening (SSP) on properties of AISI 1060 high carbon steel were modelled and compared via ANN. In order to networks training, the back propagation (BP) error algorithm is developed and data of experimental tests results are employed. 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... 

A nonlinear position controller based on backstepping control technique is proposed for a hybrid stepper motor in micro-step operation. Backstepping control approach is adapted to derive the control scheme, which is robust to parameter uncertainties and external load disturbance. Simulation results clearly show that the proposed controller can track the position reference signal successfully under parameter uncertainties and load torque disturbance rejection. Copyright © 2005 by ASME  

Flow stress behavior of AA5086 was determined using tensile testing at different temperatures from room temperature to 500 °C and strain rates varying between 0.002 and 1 s−1. The strain rate sensitivity parameter and occurrence of dynamic strain aging were then investigated in which an Arrhenius-type model was employed to study the serrated flow. Additionally, hot deformation behavior at temperatures higher than 320 °C was evaluated utilizing hyperbolic-sine constitutive equation. Finally, a feed forward artificial neural network model with back propagation learning algorithm was proposed to predict flow stress for all deformation conditions. The results demonstrated that the strain rate... 

In the present study, bainite fraction results of continuous cooling of high strength low alloy steels have been modeled by artificial neural networks. The artificial neural network models were constructed by 16 input parameters including chemical compositions (C, Mn, Nb, Mo, Ti, N, Cu, P, S, Si, Al, V), Nb in solution, austenitizing temperature, initial austenite grain size and cooling rate over the temperature range of the occurrence of phase transformations. The value for the output layer was the bainite fraction. According to the input parameters in feed-forward back-propagation algorithm, the constructed networks were trained, validated and tested. To make a decision on the completion... 

Crude oil density is an important thermodynamic property in simulation processes and design of equipment. Using laboratory methods to measure crude oil density is costly and time consuming; thus, predicting the density of crude oil using modeling is cost-effective. In this article, we develop a neural network-based model to predict the density of undersaturated crude oil. We compare our results with previous works and show that our method outperforms them  

In the last decades, much attention has been paid to the design of multi-speaker voice conversion. In this work, a new method for voice conversion (VC) using nonlinear principal component analysis (NLPCA) is presented. The principal components are extracted and transformed by a feed-forward neural network which is trained by combination of Genetic Algorithm (GA) and Back-Propagation (BP). Common pre- and post-processing approaches are applied to increase the quality of the synthesized speech. The results indicate that the proposed method can be considered as a step towards multi-speaker Voice conversion. © 2007 IEEE  

The mechanism of flow around a pier structure is so complicated that it is difficult to establish a general empirical model to provide accurate estimation for scour. Interestingly, each of the proposed empirical formula yields good results for a particular data set. Hence, in this study, alternative approaches, artificial neural networks (ANNs) and adaptive neuro-fuzzy inference system (ANFIS), are proposed to estimate the equilibrium and time-dependent scour depth with numerous reliable data base. Two ANN models, multi-layer perception using back-propagation algorithm (MLP/BP) and radial basis using orthogonal least-squares algorithm (RBF/OLS), were used. The equilibrium scour depth was... 

An artificial neural network model, using a back-propagation learning algorithm is utilized, to predict the yield stress, elongation, ultimate tension stress, over(R, -) and {divides}ΔR{divides} during hot rolling, cold rolling and annealing of AA3004 aluminum alloy. Input nodes were chosen as the ratio of initial to final thicknesses, reduction, preheating time and temperature, finish rolling temperature and the final annealing temperature. The maximum error for predicted values was 6.35%, the average of absolute relative error was 0.57% and the RMS was 0.00998. It was found that the mechanical properties and anisotropy of AA3004 alloy sheets can be predicted by this approach. © 2006... 

Blur identification is one important part of image restoration process. Linear motion blur is one of the most common degradation functions that corrupts images. Since 1976, many researchers tried to estimate motion blur parameters and this problem is solved in noise free images but in noisy images improvement can be done when image SNR is low. In this paper we have proposed a method to estimate motion blur parameters such as direction and length using Radon transform and Feed-Forward back propagation neural network for noisy images. To design the desired neural network, we used Weierstrass approximation theorem and Steifel reference Sets. The experimental results showed algorithm precision... 

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... 

In this study, the prediction of flow stress in 304 stainless steel using artificial neural networks (ANN) has been investigated. Experimental data earlier deduced-by [S. Venugopal et al., Optimization of cold and warm workability in 304 stainless steel using instability maps, Metall. Trans. A 27A (1996) 126-199]-were collected to obtain training and test data. Temperature, strain-rate and strain were used as input layer, while the output was flow stress. The back propagation learning algorithm with three different variants and logistic sigmoid transfer function were used in the network. The results of this investigation shows that the R2 values for the test and training data set are about... 

The vibration of a simply-supported beam with rotary springs at either ends is studied. The governing equations of motion are investigated considering the nonlinear effect of stretching. These equations are made non-dimensional and solved to the first-order approximation using the two known methods, namely, the multiple scales and the mode summation. The first five natural frequencies of the beam for different pairs of the boundary condition parameters are evaluated. A multilayer feed-forward back-propagation artificial neural network is trained using these natural frequencies. The artificial neural network used in this study shows high degree of accuracy for the natural frequency of the... 

In this paper, two different hybrid intelligent systems are applied to develop practical soft identifiers for modeling the tool-tissue force as well as the resulted maximum local stress in laparoscopic surgery. To conduct the system identification process, a 2D model of an in vivo porcine liver was built for different probing tasks. Based on the simulation, three different geometric features, i.e. maximum deformation angle, maximum deformation depth and width of displacement constraint of the reconstructed shape of the deformed body are extracted. Thereafter, two different fuzzy inference paradigms are proposed for the identification task. The first identifier is an adaptive co-evolutionary... 

Friction stir welding (FSW) is a relatively new solid-state joining technique that is widely adopted in manufacturing and industry fields to join different metallic alloys that are hard to weld by conventional fusion welding. Friction stir welding is a very complex process comprising several highly coupled physical phenomena. The complex geometry of some kinds of joints makes it difficult to develop an overall governing equations system for theoretical behavior analyse of the friction stir welded joints. Weld quality is predominantly affected by welding effective parameters, and the experiments are often time consuming and costly. On the other hand, employing artificial intelligence (AI)...