Sharif Digital Repository

Position control of Shape Memory Alloy (SMA) actuators has been a challenging topic during the last years due to their nonlinearities in the governing physical equations as well as their hysteresis behaviors. Using the inverse of phenomenological hysteresis model in order to compensate the input-output hysteresis behavior of these actuators shows the effectiveness of this approach. In this paper, in order to control the tip deflection of a large deformation flexible beam actuated by an SMA actuator wire, a feedforward-feedback controller is proposed. The feedforward part of the proposed control system, maps the beam deflection into SMA temperature, is based on the inverse of the generalized... 

This paper presents a new robust control strategy for an islanded microgrid in the presence of load unmodeled dynamics. The microgrid consists of parallel connection of several electronically interfaced distributed generation units and a local load. The load is parametrically uncertain and topologically unknown and, thus, is the source of unmodeled dynamics. The objective is to design a robust controller to regulate the load voltage in the presence of unmodeled dynamics. To achieve the objective, the problem is first characterized by a two-degree-of-freedom (2DOF) feedback-feedforward controller. The 2DOF control design problem is then transformed to a nonconvex optimization problem.... 

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... 

Hysteresis and significant nonlinearities in the behavior of Shape Memory Alloy (SMA) actuators encumber effective utilization of these actuator. Due to these effects, the position control of SMA actuators has been a great challenge in recent years. Literature review of the research conducted in this area shows that using the inverse of the phenomenological hysteresis models can compensate the hysteresis of these actuators effectively. But, inverting some of these models, such as Preisach model, is numerically a complex task. However, the generalized Prandtl-Ishlinskii model is analytically invertible, and therefore can be implemented conveniently as a feedforward controller for compensating... 

Magnetorheological (MR) damper is a prominent semi-active control device to vibrate mitigation of structures. Due to the inherent non-linear nature of MR damper, an intelligent non-linear neuro-fuzzy control strategy is designed to control wave-induced vibration of an offshore steel jacket platform equipped with MR dampers. In the proposed control system, a dynamic-feedback neural network is adapted to model non-linear dynamic system, and the fuzzy logic controller is used to determine the control forces of MR dampers. By use of two feedforward neural networks required voltages and actual MR damper forces are obtained, in which the first neural network and the second one acts as the inverse... 

A method for noise reduction in active-$RC$ circuits is introduced. It is shown that the output noise in an active-$RC$ circuit can be considerably reduced, without disturbing the circuit transfer function by inserting appropriate passive or active components in the circuit. The inserted components introduce new signal paths in the circuit for noise reduction while the original circuit transfer function is kept unchanged. The procedure to define the proper paths in the circuit and their transfer functions is given. The effectiveness of the presented method is demonstrated using a second-order active-RC filter fabricated in a 0.18-$ {m}$ CMOS technology  

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  

The past few years have witnessed a growing rate of attraction in adoption of Artificial Intelligence (AI) techniques and combining them to improve forecasting accuracy in different fields. Besides, stock market forecasting has always been a subject of interest for most investors and professional analysts. Stock market forecasting is a tough problem because of the uncertainties involved in the movement of the market. This paper proposes a hybrid artificial intelligence model for stock exchange index forecasting, the model is a combination of genetic algorithms and feedforward neural networks. Actually it evolves neural network weights by using genetic algorithms. We also employ preprocessing... 

The process of local scour around bridge piers is fundamentally complex due to the three-dimensional flow patterns interacting with bed materials. For geotechnical and economical reasons, multiple pile bridge piers have become more and more popular in bridge design. Although many studies have been carried out to develop relationships for the maximum scour depth at pile groups under clear-water scour condition, existing methods do not always produce reasonable results for scour predictions. It is partly due to the complexity of the phenomenon involved and partly because of limitations of the traditional analytical tool of statistical regression. This paper addresses the latter part and... 

Artificial Neural Networks (ANNs) have recently been introduced as an efficient artificial intelligence modeling technique for applications involving a large, number of variables, especially with highly nonlinear and complex interactions among input/output variables in a system without any prior knowledge about the nature, of these, interactions. Various types of ANN models are developed and used for different problems. In this paper, an artificial neural network of the feed-forward back-propagation type has been applied for the prediction of density and compressive strength properties of the cement paste portion of concrete mixtures. The mechanical properties of concrete are highly... 

The performance of degree of polarization (DOP) is investigated as a control signal in polarization-mode dispersion (PMD) compensation systems aided by polarization scrambling. The relation between the input and output polarization states of a signal propagating through a polarization scrambler and a PMD-induced optical fiber is described by a 3 × 3 Stokes transfer matrix. The average DOP of the output signal over a period of polarization scrambling is derived as an alternative to the conventional DOP-based control signal, i.e., minimum DOP. In the presence of first- and all-order PMDs, the performance of the average and minimum DOPs in monitoring of differential group delay (DGD) for... 

Numerous methods have been proposed previously to describe the characterization of porous materials; however, no well-developed theory is still available. Three different modeling methods were employed in this study to explore the relationship between the characterization parameters of activated carbon (AC) and its methane uptake. The first and the second methods were based on the Radial Basis Function (R.B.F) neural networks. At the first R.B.F. modeling, the neural networks algorithm was designed using the Gaussian function. The collected data for modeling were divided into two parts; (i) the data used for training the network and (ii) the data used for testing the predicted network. At... 

In this paper, the truly Meshless Local Petrov-Galerkin (MLPG) method is extended for computation of steady incompressible flows, governed by the Navier-Stokes equations (NSE), in vorticity-stream function formulation. The present method is a truly meshless method based on only a number of randomly located nodes. The formulation is based on two equations including stream function Poisson equation and vorticity advection-dispersion-reaction equation (ADRE). The meshless method is based on a local weighted residual method with the Heaviside step function and quartic spline as the test functions respectively over a local subdomain. Radial basis functions (RBF) interpolation is employed in shape... 

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... 

Feed-forward is one of the best methods for linearizing microwave power amplifiers, but due to device tolerance in implementation of the system components, the practical Inter-Modulation Rejection (IMR) value may differ quite much from the theoretical IMR value. One of the methods to improve the practical performance of the system is using the multi-loop configuration. Here we have introduced the multi-loop feedforward systems and we have estimated the practical IMR values of the system using Monte-Carlo analysis. As the analysis shows, although the number of components in a multi-loop system is increased with respect to a simple feed-forward system, but the difference between the practical... 

The current statistical model and adaptive filtering (CSMAF) algorithm is one of the most effective methods for tracking the maneuvering targets. However, it is still worthy to investigate the characteristics of the CSMAF algorithm, which has a higher precision in tracking the maneuvering targets with larger accelerations while it has a lower precision in tracking the maneuvering targets with smaller acceleration. In this paper a novel adaptive tracking algorithm for maneuvering targets is proposed. To overcome the disadvantage of the CSMAF algorithm, a simple multi-layer feedforward neural network (NN) is used By introducing NN, two sources of information of the filter are fused while its... 

In this paper, a feedforward proportional-integral-derivative (PID) controller is developed to effectively control the clad height in laser solid freeform fabrication (LSFF). The scanning velocity is selected as the input control variable and the clad height is chosen as the output. A novel knowledge-based Hammerstein model, including a linear dynamic and a nonlinear memoryless block, is developed, and its parameters are identified offline using experimental data. The architecture of the controller consists of a PID and a feedforward module, which is the inverse of the identified model. The advantage of adding a feedforward path to the PID controller is evaluated experimentally, in which the... 

In this study, we have proposed a novel approach to investigate the features of four subbands of 2-D wavelet transform in magnetic resonance images (MRIs) for normal and abnormal brains which defected by Multiple Sclerosis (MS). Concurrently, another method extracts different kinds of features in spatial domain. Totally, 116 features have been extracted. Before applying the algorithm, we have to use a registration method because of variety in size of brain images. All extracted features have been passed over the Principal Component Analysis (PCA) and have been pushed to an Artificial Neural Network (ANN) that is a feed-forward type. According to changing in position of defected parts of... 

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  

In this paper, the application of neural networks for simulation and optimization of the cogeneration systems has been presented. CGAM problem, a benchmark in cogeneration systems, is chosen as a case study. Thermodynamic model includes precise modeling of the whole plant. For simulation of the steady sate behavior, the static neural network is applied. Then using dynamic neural network, plant is optimized thermodynamically. Multi layer feed forward neural networks is chosen as static net and recurrent neural networks as dynamic net. The steady state behavior of CGAM problem is simulated by MFNN. Subsequently, it is optimized by dynamic net. Results of static net have excellence agreement...