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.

Characterization and application of nanostructured films containing Au and TiO2 nanoparticles supported in bacterial cellulose

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Comparative study between powers of sigmoid functions, MLP-backpropagation and polynomials in function approximation problems

Function approximation is a very important task in environments where the computation has to be based on extracting information from data samples in real world processes. So, the development of new mathematical model is a very important activity to guarantee the evolution of the function approximation area. In this sense, we will present the Polynomials Powers of Sigmoid (PPS) as a linear neural network. In this paper, we will introduce one series of practical results for the Polynomials Powers of Sigmoid, where we will show some advantages of the use of the powers of sigmiod functions in relationship the traditional MLP-Backpropagation and Polynomials in functions approximation problems.

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

Pós-graduação em Ciência Florestal - FCA

Obtenção e caracterização óptica e elétrica de 'La''Ta'O IND.4' e LiTaO Ind.3 puros e dopados com Eu POT.3+

Eletronicalceramics are used in many applications such as: multilayer capacitor, transducer, pyroelectric sensors and electrooptic devices. In recent years there has been a growing demand for eletronicalceramics with better performance and functionality. This demand has accelerated the development of synthesis techniques to produce powders with well-defined particle size, shape and crystallinity. The eletronicalceramics in the form of bulk are determined by their performance characteristics of the powders used and the preparation process. So, physical and chemical properties of powders, such as chemical control of stoichiometry, purity, homogeneity, particle size and shape should be observed when choosing the methods of synthesis. Among the techniques used so far, the polymeric precursor method, also known as Pechini, has been considered ideal for the preparation of nanosized powders. Thus, this research project aims to use the polymeric precursor method to prepare powders of lithium tantalate and lanthanum tantalate, with good chemical stability. In this aspect is proposed to investigate the effects of variation of the concentration of europium about the properties of tantalate because doping with Eu3 + indicates that they may occupy different sites in the crystal structure, as in the case of LiTaO3. Effects of things like occupation sites, stability of phases and formation temperature have been previously investigated by the group, which motivated the formulation of this project. Our proposal aims to introduce the Eu3 + LaTaO4 and LiTaO3 and study the structural and optical properties of the powders obtained by Pechini method, as well as correlate these studies with the electrical properties of the material, mainly the Ironelectricty Hysteresis.

Neural models for predicting hole diameters in drilling processes

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Renewable nanocomposite layer-by-layer assembled catalytic interfaces for biosensing applications

A novel, easily renewable nanocomposite interface based on layer-by-layer (LbL) assembled cationic/anionic layers of carbon nanotubes customized with biopolymers is reported. A simple approach is proposed to fabricate a nanoscale structure composed of alternating layers of oxidized multiwalled carbon nanotubes upon which is immobilized either the cationic enzyme organophosphorus hydrolase (OPH; MWNT−OPH) or the anionic DNA (MWNT−DNA). The presence of carbon nanotubes with large surface area, high aspect ratio and excellent conductivity provides reliable immobilization of enzyme at the interface and promotes better electron transfer rates. The oxidized MWNTs were characterized by thermogravimetric analysis and Raman spectroscopy. Fourier transform infrared spectroscopy showed the surface functionalization of the MWNTs and successful immobilization of OPH on the MWNTs. Scanning electron microscopy images revealed that MWNTs were shortened during sonication and that LbL of the MWNT/biopolymer conjugates resulted in a continuous surface with a layered structure. The catalytic activity of the biopolymer layers was characterized using absorption spectroscopy and electrochemical analysis. Experimental results show that this approach yields an easily fabricated catalytic multilayer with well-defined structures and properties for biosensing applications whose interface can be reactivated via a simple procedure. In addition, this approach results in a biosensor with excellent sensitivity, a reliable calibration profile, and stable electrochemical response.

Preliminary diagnosis of ophtalmological diseases through machine learning techniques

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Neural models for predicting hole diameters in drilling processes

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Filmes de Langmuir-Blodgett de nanopartículas de prata

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Comportamento biomecânico de estruturas multicamadas em restaurações protéticas

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

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

Pós-graduação em Engenharia Elétrica - FEIS

Robust isothermal electric control of exchange bias at room temperature

Voltage-controlled spin electronics is crucial for continued progress in information technology. It aims at reduced power consumption, increased integration density and enhanced functionality where non-volatile memory is combined with highspeed logical processing. Promising spintronic device concepts use the electric control of interface and surface magnetization. From the combination of magnetometry, spin-polarized photoemission spectroscopy, symmetry arguments and first-principles calculations, we show that the (0001) surface of magnetoelectric Cr2O3 has a roughness-insensitive, electrically switchable magnetization. Using a ferromagnetic Pd/Co multilayer deposited on the (0001) surface of a Cr2O3 single crystal, we achieve reversible, room-temperature isothermal switching of the exchange-bias field between positive and negative values by reversing the electric field while maintaining a permanent magnetic field. This effect reflects the switching of the bulk antiferromagnetic domain state and the interface magnetization coupled to it. The switchable exchange bias sets in exactly at the bulk Néel temperature.

Immobilization of cholesterol oxidase in LbL films and detection of cholesterol using ac measurements

The preserved activity of immobilized biomolecules in layer-by-layer (LbL) films can be exploited in various applications. including biosensing. In this study, cholesterol oxidase (COX) layers were alternated with layers of poly(allylamine hydrochloride) (PAH) in LbL films whose morphology was investigated with atomic force microscopy (AFM). The adsorption kinetics of COX layers comprised two regimes, a fast, first-order kinetics process followed by a slow process fitted with a Johnson-Mehl-Avrami (JMA) function. with exponent similar to 2 characteristic of aggregates growing as disks. The concept based on the use of sensor arrays to increase sensitivity, widely employed in electronic tongues, was extended to biosensing with impedance spectroscopy measurements. Using three sensing units, made of LbL films of PAH/COX and PAHIPVS (polyvinyl sulfonic acid) and a bare gold interdigitated electrode, we were able to detect cholesterol in aqueous solutions down to the 10(-6) M level. This high sensitivity is attributed to the molecular-recognition interaction between COX and cholesterol, and opens the way for clinical tests to be made with low cost. fast experimental procedures. (C) 2008 Published by Elsevier B.V.