A novel approach based on recurrent neural networks applied to nonlinear systems optimization

This paper presents an efficient approach based on recurrent neural network for solving nonlinear optimization. More specifically, a modified Hopfield network is developed and its internal parameters are computed using the valid subspace technique. These parameters guarantee the convergence of the network to the equilibrium points that represent an optimal feasible solution. The main advantage of the developed network is that it treats optimization and constraint terms in different stages with no interference with each other. Moreover, the proposed approach does not require specification of penalty and weighting parameters for its initialization. A study of the modified Hopfield model is also developed to analyze its stability and convergence. Simulation results are provided to demonstrate the performance of the proposed neural network. (c) 2005 Elsevier B.V. All rights reserved.

Stability and convergence analysis of a neural model applied in nonlinear systems optimization

A neural model for solving nonlinear optimization problems is presented in this paper. More specifically, a modified Hopfield network is developed and its internal parameters are computed using the valid-subspace technique. These parameters guarantee the convergence of the network to the equilibrium points that represent an optimal feasible solution. The network is shown to be completely stable and globally convergent to the solutions of nonlinear optimization problems. A study of the modified Hopfield model is also developed to analyze its stability and convergence. Simulation results are presented to validate the developed methodology.

Artificial neural networks applied in study of atmospheric parameters to high voltage substations concerning lightning

This gaper demonstrates that artificial neural networks can be used effectively for estimation of parameters related to study of atmospheric conditions to high voltage substations design. Specifically, the neural networks are used to compute the variation of electrical field intensity and critical disruptive voltage in substations taking into account several atmospheric factors, such as pressure, temperature, humidity, so on. Examples of simulation of tests are presented to validate the proposed approach. The results that were obtained by experimental evidences and numerical simulations allowed the verification of the influence of the atmospheric conditions on design of substations concerning lightning.

A fuzzy logic system applied in lightning models

This paper describes a novel approach for mapping lightning processes using fuzzy logic. The estimation process is carried out using a fuzzy system based on Sugeno's architecture. Simulation results confirm that proposed approach can be efficiently used in these types of problem.

Thermoeconomic analysis applied to an alternative wastewater treatment

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Thermoeconomic analysis applied in cold water production system using biogas combustion

In this paper is proposed the use of biogas generated in the Wastewater Treatment Plant of a Dairy industry. The objective is to apply a thermoeconomic analysis to the supplementary cold water production of an absorption refrigeration system (NH3 + H2O) by the burning of such gas. The exergoeconomic analysis is carried out to allow a comparison between an absorption refrigeration system and of an equivalent compression refrigeration system that uses NH3 as work fluid. The proposed exergoeconomic model uses functional diagrams and allows one to obtain the exergetic incremental functions for each component individually and for the system as a whole. The model minimizes the exergetic manufacturing cost (EMC) which represents the cost of supplementary cold water production at 1degreesC (exergetic base) needed for this dairy's cold storage. As a conclusion, the absorption refrigeration system is better than compression refrigeration system, when the biogas cost is not considered. 2004 Elsevier Ltd. All rights reserved.

Stratified Sampling Applied to Estimation of the Volumetric Fraction of Alumina in Cast Metal Matrix Composites

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Dynamic mechanical properties for polyurethane elastomers applied in elastomeric mortar

Dynamic mechanical properties of a polyurethane (PU) elastomer and a mortar processed with the same elastomer (modified polytetramethylene ether glycol (PTMEG)) were studied. The results obtained showed that the liquid aromatic amine ETHACURE (R) 300, used as cure agent, can be used to substitute the aromatic amine MOCA (R), which is usually used as cure agent in high performance elastomers. The resulting mortar produced with ETHACURE (R) 300 presents similar dynamic-mechanical thermal properties when compared with MOCA (R). However, dynamic-mechanical thermal analysis studies showed that the mortar developed with ETHACURE (R) 300 presents some advantages such as the low values of tan d, indicating a good capacity of recovery of the strain after retreating an applied force. (c) 2012 Wiley Periodicals, Inc. J Appl Polym Sci, 2012

Unscented Kalman Filter Applied to the Spacecraft Attitude Estimation with Euler Angles

The aim of this work is to test an algorithm to estimate, in real time, the attitude of an artificial satellite using real data supplied by attitude sensors that are on board of the CBERS-2 satellite (China Brazil Earth Resources Satellite). The real-time estimator used in this work for attitude determination is the Unscented Kalman Filter. This filter is a new alternative to the extended Kalman filter usually applied to the estimation and control problems of attitude and orbit. This algorithm is capable of carrying out estimation of the states of nonlinear systems, without the necessity of linearization of the nonlinear functions present in the model. This estimation is possible due to a transformation that generates a set of vectors that, suffering a nonlinear transformation, preserves the same mean and covariance of the random variables before the transformation. The performance will be evaluated and analyzed through the comparison between the Unscented Kalman filter and the extended Kalman filter results, by using real onboard data.

Carbon fiber non-crimp multi-axial reinforcement and epoxy mono-component system composite: fatigue behavior

Fiber reinforced polymer composites have been widely applied in the aeronautical field. However, composite processing, which uses unlocked molds, should be avoided in view of the tight requirements and also due to possible environmental contamination. To produce high performance structural frames meeting aeronautical reproducibility and low cost criteria, the Brazilian industry has shown interest to investigate the resin transfer molding process (RTM) considering being a closed-mold pressure injection system which allows faster gel and cure times. Due to the fibrous composite anisotropic and non homogeneity characteristics, the fatigue behavior is a complex phenomenon quite different from to metals materials crucial to be investigated considering the aeronautical application. Fatigue sub-scale specimens of intermediate modulus carbon fiber non-crimp multi-axial reinforcement and epoxy mono-component system composite were produced according to the ASTM 3039 D. Axial fatigue tests were carried out according to ASTM D 3479. A sinusoidal load of 10 Hz frequency and load ratio R = 0.1. It was observed a high fatigue interval obtained for NCF/RTM6 composites. Weibull statistical analysis was applied to describe the failure probability of materials under cyclic loads and fractures pattern was observed by scanning electron microscopy. (C) 2010 Published by Elsevier Ltd.

Fatigue Strength of X45CrSi93 stainless steel applied as internal combustion engine valves

Stainless steels are used to intake and exhaust valves production applied as internal combustion engines. In general valves are requested to support cyclic stresses applied due to opening and closing processes during the operation. The objective of this research is to study the influence on the axial fatigue strength of the resulting microstructure after heat treatment at the martensitic X45CrSi93 steel, combined with different surface treatments as hard chrome-plating, nitride and grinding. It was verified a significant increase on the fatigue strength of the martensitic steel after nitriding, compared with results from the chrome-plating specimens. A slight increase in the tensile strength was also noticed on nitrided parts as a consequence of a resistance increase due to nitrogen and carbon solid solution. (C) 2011 Published by Elsevier Ltd. Selection and peer-review under responsibility of ICM11

A DOE based approach for the design of RBF artificial neural networks applied to prediction of surface roughness in AISI 52100 hardened Steel turning

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Ergonomics work analysis applied to dentistry - a Brazilian case study

This paper presents the Ergonomic Work Analysis method in a Brazilian Dentist's office. Through the study, the constraints and the strategies in avoiding them were identified. It was found that dentists hardly use the position most indicated by the International Organization for Standardization (ISO) and the Federation Dentaire Internacionale (FDI) for both the patient and the dentist, which is respectively supine and 9 o'clock, due to the limited space and layout. Five types of treatments performed by the professional have been studied. The frequency and duration of actions in these treatments were accounted for and the standard positions adopted were identified. The AET was found to be a very suitable method to grasp the dentist's activity and build a point of view of the profession, which is characterized as: stressful, perfectionist and restrictive. Time management is presented as an important strategy to control the tension arising from performing the treatments.

Artificial neural networks and clustering techniques applied in the reconfiguration of distribution systems

One objective of the feeder reconfiguration problem in distribution systems is to minimize the power losses for a specific load. For this problem, mathematical modeling is a nonlinear mixed integer problem that is generally hard to solve. This paper proposes an algorithm based on artificial neural network theory. In this context, clustering techniques to determine the best training set for a single neural network with generalization ability are also presented. The proposed methodology was employed for solving two electrical systems and presented good results. Moreover, the methodology can be employed for large-scale systems in real-time environment.