Aurel Vlaicu University of Arad

About: Aurel Vlaicu University of Arad is a education organization based out in Arad, Romania. It is known for research contribution in the topics: Fuzzy logic & Fuzzy control system. The organization has 312 authors who have published 904 publications receiving 6727 citations. The organization is also known as: UAV & Universitatea „Aurel Vlaicu” din Arad.

Particle swarm optimization trained neural network for structural failure prediction of multistoried RC buildings

Abstract: Faulty structural design may cause multistory reinforced concrete (RC) buildings to collapse suddenly. All attempts are directed to avoid structural failure as it leads to human life danger as well as wasting time and property. Using traditional methods for predicting structural failure of the RC buildings will be time-consuming and complex. Recent research proved the artificial neural network (ANN) potentiality in solving various real-life problems. The traditional learning algorithms suffer from being trapped into local optima with a premature convergence. Thus, it is a challenging task to achieve expected accuracy while using traditional learning algorithms to train ANN. To solve this problem, the present work proposed a particle swarm optimization-based approach to train the NN (NN-PSO). The PSO is employed to find a weight vector with minimum root-mean-square error (RMSE) for the NN. The proposed (NN-PSO) classifier is capable to tackle the problem of predicting structural failure of multistoried reinforced concrete buildings via detecting the failure possibility of the multistoried RC building structure in the future. A database of 150 multistoried buildings’ RC structures was employed in the experimental results. The PSO algorithm was involved to select the optimal weights for the NN classifier. Fifteen features have been extracted from the structural design, while nine features have been opted to perform the classification process. Moreover, the NN-PSO model was compared with NN and MLP-FFN (multilayer perceptron feed-forward network) classifier to find its ingenuity. The experimental results established the superiority of the proposed NN-PSO compared to the NN and MLP-FFN classifiers. The NN-PSO achieved 90 % accuracy with 90 % precision, 94.74 % recall and 92.31 % F-Measure.

Multilayer perceptron and neural networks

Abstract: The attempts for solving linear inseparable problems have led to different variations on the number of layers of neurons and activation functions used. The backpropagation algorithm is the most known and used supervised learning algorithm. Also called the generalized delta algorithm because it expands the training way of the adaline network, it is based on minimizing the difference between the desired output and the actual output, through the downward gradient method (the gradient tells us how a function varies in different directions). Training a multilayer perceptron is often quite slow, requiring thousands or tens of thousands of epochs for complex problems. The best known methods to accelerate learning are: the momentum method and applying a variable learning rate. The paper presents the possibility to control the induction driving using neural systems.

Design of a proportional-integral-derivative controller for an automatic generation control of multi-area power thermal systems using firefly algorithm

Abstract: Essentially, it is significant to supply the consumer with reliable and sufficient power. Since, power quality is measured by the consistency in frequency and power flow between control areas. Thus, in a power system operation and control, automatic generation control ( AGC ) plays a crucial role. In this paper, multi-area ( Five areas: area 1, area 2, area 3, area 4 and area 5 ) reheat thermal power systems are considered with proportional-integral-derivative ( PID ) controller as a supplementary controller. Each area in the investigated power system is equipped with appropriate governor unit, turbine with reheater unit, generator and speed regulator unit. The PID controller parameters are optimized by considering nature bio-inspired firefly algorithm ( FFA ). The experimental results demonstrated the comparison of the proposed system performance ( FFA-PID ) with optimized PID controller based genetic algorithm ( GA-PID ) and particle swarm optimization ( PSO ) technique ( PSO-PID ) for the same investigated power system. The results proved the efficiency of employing the integral time absolute error ( ITAE ) cost function with one percent step load perturbation ( 1 % SLP ) in area 1. The proposed system based FFA achieved the least settling time compared to using the GA or the PSO algorithms, while, it attained good results with respect to the peak overshoot / undershoot. In addition, the FFA performance is improved with the increased number of iterations which outperformed the other optimization algorithms based controller.

Stable fuzzy logic control of a general class of chaotic systems

Abstract: This paper proposes a new approach to the stable design of fuzzy logic control systems that deal with a general class of chaotic processes. The stable design is carried out on the basis of a stability analysis theorem, which employs Lyapunov's direct method and the separate stability analysis of each rule in the fuzzy logic controller (FLC). The stability analysis theorem offers sufficient conditions for the stability of a general class of chaotic processes controlled by Takagi---Sugeno---Kang FLCs. The approach suggested in this paper is advantageous because inserting a new rule requires the fulfillment of only one of the conditions of the stability analysis theorem. Two case studies concerning the fuzzy logic control of representative chaotic systems that belong to the general class of chaotic systems are included in order to illustrate our stable design approach. A set of simulation results is given to validate the theoretical results.