Segurança em redes sem fio: estudo sobre o desenvolvimento de conjuntos de dados para comparação de IDS

Pós-graduação em Engenharia Elétrica - FEIS

Neural tool condition estimation in the grinding of advanced ceramics

Ceramic parts are increasingly replacing metal parts due to their excellent physical, chemical and mechanical properties, however they also make them difficult to manufacture by traditional machining methods. The developments carried out in this work are used to estimate tool wear during the grinding of advanced ceramics. The learning process was fed with data collected from a surface grinding machine with tangential diamond wheel and alumina ceramic test specimens, in three cutting configurations: with depths of cut of 120 mu m, 70 mu m and 20 mu m. The grinding wheel speed was 35m/s and the table speed 2.3m/s. Four neural models were evaluated, namely: Multilayer Perceptron, Radial Basis Function, Generalized Regression Neural Networks and the Adaptive Neuro-Fuzzy Inference System. The models'performance evaluation routines were executed automatically, testing all the possible combinations of inputs, number of neurons, number of layers, and spreading. The computational results reveal that the neural models were highly successful in estimating tool wear, since the errors were lower than 4%.

Tool condition monitoring of aluminum oxide grinding wheel in dressing operation using acoustic emission and neural networks

The grinding operation gives workpieces their final finish, minimizing surface roughness through the interaction between the abrasive grains of a tool (grinding wheel) and the workpiece. However, excessive grinding wheel wear due to friction renders the tool unsuitable for further use, thus requiring the dressing operation to remove and/or sharpen the cutting edges of the worn grains to render them reusable. The purpose of this study was to monitor the dressing operation using the acoustic emission (AE) signal and statistics derived from this signal, classifying the grinding wheel as sharp or dull by means of artificial neural networks. An aluminum oxide wheel installed on a surface grinding machine, a signal acquisition system, and a single-point dresser were used in the experiments. Tests were performed varying overlap ratios and dressing depths. The root mean square values and two additional statistics were calculated based on the raw AE data. A multilayer perceptron neural network was used with the Levenberg-Marquardt learning algorithm, whose inputs were the aforementioned statistics. The results indicate that this method was successful in classifying the conditions of the grinding wheel in the dressing process, identifying the tool as "sharp''(with cutting capacity) or "dull''(with loss of cutting capacity), thus reducing the time and cost of the operation and minimizing excessive removal of abrasive material from the grinding wheel.

Utilização de redes neurais artificiais aplicadas na discriminação de padrões de doenças florestais

Pós-graduação em Ciência Florestal - FCA

Neural models for predicting hole diameters in drilling processes

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Neural models for predicting hole diameters in drilling processes

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Mapeamento da cinemática inversa de um manipulador robótico utilizando redes neurais artificiais configuradas em paralelo

Pós-graduação em Engenharia Elétrica - FEIS

Effects of gamma-irradiation on caprolactam level from multilayer PA-6 films for food packaging: Development and validation of a gas chromatographic method

A gas chromatographic method to determine caprolactam in multilayer PA-6 films used for meat foodstuffs and cheese was developed and validated. A wide linear range (0.8-400 mu g/ml), RSD <= 4.1% and recovery higher than 90.0% were obtained for the chromatographic system, while precision and accuracy of the method showed RSD <= 3.8%, recovery from 95.5-100.0% and LOQ of 32 mu g/g. Irradiated (3, 7 and 12 kGy) and non-irradiated commercial films were analyzed. Most of them increased caprolactam levels with the increase of irradiation doses. (C) 2008 Elsevier Ltd. All rights reserved.

EFFECT of GAMMA IRRADIATION on CAPROLACTAM MIGRATION FROM MULTILAYER POLYAMIDE 6 FILMS INTO WATER FOOD SIMULANT and VALIDATION of THE METHOD

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Identification and migration of degradation compounds from irradiation of multilayer polyamide 6 films for meat foodstuffs and cheese

The aim of this work was to identify the degradation compounds produced during irradiation of multilayer polyamide 6 (PA-6) films and to study their migration into water and 95% ethanol food simulant. After irradiation of multilayer PA-6 films at 3, 7 and 12 kGy, degradation compounds were extracted using solid-phase microextraction, for which the time and temperature of extraction and stirring were optimized, and identified by gas chromatography-mass spectrometry. Caprolactam, 2-cyclopentylcyclopentanone and aldehydes, among other compounds, were identified in the headspace of the films. Polydimethylsiloxane was considered the best fiber for extraction. The optimum conditions of time, temperature and stirring to extract the compounds were 20 min, 80 degrees C and 225 rpm. For validation purposes, the compounds were quantified in water and 95% ethanol and the results showed high sensitivity, good precision and accuracy. Migration of compounds from irradiated and non-irradiated multilayer PA-6 films into water and 95% ethanol food simulants was carried out at 40 degrees C for 10 days. The method was efficient for the quantification of decaldehyde, 2-cyclopentylcyclopentanone and caprolactam that migrated from multilayer PA-6 films into food simulants.

Modeling of organic light-emitting diodes with graded concentration in the emissive multilayer

We model the electrical behavior of organic light-emitting diodes whose emissive multilayer is formed by blends of an electron transporting material, tris-(8-hydroxyquinoline) aluminum (Alq(3)) and a hole transporting material, N,N-'-diphenyl-N,N-'-bis(1,1(')-biphenyl)-4,4-diamine. The multilayer is composed of layers of different concentration. The Alq(3) concentration gradually decreases from the cathode to the anode. We demonstrate that these graded devices have higher efficiency and operate at lower applied voltages than devices whose emissive layer is made of nominally homogeneous blends. Our results show an important advantage of graded devices, namely, the low values of the recombination rate distribution near the cathode and the anode, so that electrode quenching is expected to be significantly suppressed in these devices. (C) 2004 American Institute of Physics.

Photoluminescence of barium titanate and barium zirconate in multilayer disordered thin films at room temperature

The emission of wide band photoluminescence showed a synergic effect on barium zirconate and barium titanate thin films in alternate multilayer system at room temperature by 488 nm exiting wavelength. The thin films obtained by spin-coating were annealed at 350, 450, and 550 degrees C for 2 h. The X-ray patterns revealed the complete separation among the BaTiO3 and BaZrO3 phases in the adjacent films. Visible and intense photoluminescence was governed by BaZrO3 thin films in the multilayer system. Quantum mechanics calculations were used in order to simulate ordered and disordered thin films structures. The disordered models, which were built by using the displacement of formers and modifier networks, showed a different symmetry in each system, which is in accordance with experimental photoluminescence emission, thus allowing to establish a correlation among the structural and optical properties of these multilayered systems.

Photoluminescent behavior of SrZrO3/SrTiO3 multilayer thin films

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Dielectric properties and microstructure of SrTiO3/BaTiO3 multilayer thin films prepared by a chemical route

Multilayer thin films with perovskite structures were produced by the polymeric precursor method. SrTiO3/BaTiO3 (STO/BTO) multilayers were deposited on Pt(111)/Ti/SiO2/Si(100) substrates by the spin-coating technique and heated in air at 700 degreesC. The microstructure and crystalline phase of the multilayered thin films were examined by field-emission scanning electron microscopy (FE-SEM), transmission electron microscopy (TEM), resolution-high transmission electron microscopy (HRTEM), atomic force microscopy (AFM) and X-ray diffraction. The SrTiO3/BaTiO3 multilayer thin films consisted of grainy structures with an approximate grain size of 60 nm. The multilayered thin films showed a very clear interface between the components. The SrTiO3/BaTiO3 multilayer thin films revealed dielectric constants of approximately 527 and loss tangents of 0.03 at 100 kHz. The dielectric constant calculated for this multilayer film system is the value of the sum of each individual component of the film, i.e. The total value of the sum of each SrTiO3 (STO) and BaTiO3 (BTO) layer. The multilayer SrTiO3/BaTiO3 obtained by the polymeric precursor method, also showed a ferroelectric behavior with a remanent polarization of 2.5 muC/cm(2) and a coercive field of 30 kV/cm. The multilayer films displayed good fatigue characteristics under bipolar stressing after application of 10(10) switching cycles. (C) 2001 Published by Elsevier B.V. B.V. All rights reserved.

Variational studies and replica symmetry breaking in the generalization problem of the binary perceptron

We analyze the average performance of a general class of learning algorithms for the nondeterministic polynomial time complete problem of rule extraction by a binary perceptron. The examples are generated by a rule implemented by a teacher network of similar architecture. A variational approach is used in trying to identify the potential energy that leads to the largest generalization in the thermodynamic limit. We restrict our search to algorithms that always satisfy the binary constraints. A replica symmetric ansatz leads to a learning algorithm which presents a phase transition in violation of an information theoretical bound. Stability analysis shows that this is due to a failure of the replica symmetric ansatz and the first step of replica symmetry breaking (RSB) is studied. The variational method does not determine a unique potential but it allows construction of a class with a unique minimum within each first order valley. Members of this class improve on the performance of Gibbs algorithm but fail to reach the Bayesian limit in the low generalization phase. They even fail to reach the performance of the best binary, an optimal clipping of the barycenter of version space. We find a trade-off between a good low performance and early onset of perfect generalization. Although the RSB may be locally stable we discuss the possibility that it fails to be the correct saddle point globally. ©2000 The American Physical Society.