• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 570
  • 336
  • 39
  • 21
  • 15
  • 12
  • 11
  • 8
  • 8
  • 8
  • 8
  • 4
  • 4
  • 3
  • 3
  • Tagged with
  • 1191
  • 1191
  • 1191
  • 571
  • 556
  • 423
  • 157
  • 134
  • 129
  • 128
  • 120
  • 110
  • 94
  • 93
  • 92
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
131

Detecção de adulteração de combustíveis com sensores poliméricos eletrodepositados e redes neurais artificiais. / Fuel adulteration detection using electrodepositated polymer sensors and artificial neural networks.

Ozaki, Sérgio Tonzar Ristori 11 June 2010 (has links)
A adulteração de combustíveis é uma grande preocupação no Brasil. A agência reguladora nacional (ANP) detecta anualmente de 1 a 3% de adulterações nas amostras coletadas, o que é um índice alto considerando o tamanho do mercado brasileiro. As alternativas de adulteração são vastas e muito dinâmicas, por isso os arranjos de sensores baseados no conceito de seletividade global parecem os mais adequados para detectar falsificação de combustíveis. O conceito de seletividade global leva em conta a sensibilidade cruzada de sensores químicos não específicos e o uso de métodos de análise multivariada de dados para encontrar padrões para amostras de diferentes composições químicas. Os sensores químicos podem ser obtidos de uma variedade de materiais sensoativos, cujas respostas elétricas variam de acordo com as propriedades físico-químicas do meio em que se encontra. Os polímeros condutores são excelentes materiais sensoativos, pois sua condutividade elétrica é grandemente influenciada pelas condições ambientais e podem ser processados na forma de filmes finos através várias técnicas. No presente trabalho, filmes de poli(3-metiltiofeno) (PMTh) e poli(3-hexiltiofeno) são depositados por cronopotenciometria e cronoamperometria sobre microeletrodos interdigitados e são caracterizados por espectroscopia de impedância. Os dados são analisados por redes neurais artificiais do tipo multilayer perceptron e bons resultados são obtidos na detecção de adulteração de gasolina. O mesmo estudo também pode ser aplicado na detecção de adulteração de álcool etílico combustível com um desempenho um pouco pior. / Fuel adulteration is a major concern in Brazil. The local governmental agency detects from 1 to 3% of problematic samples yearly, which is a lot considering Brazils market size. The myriad of adulteration possibilities is vast and it is very dynamic, thus array of sensors based on global selectivity concept seems to be more suitable methodology to detect problems in fuel. The global selectivity concept encompasses the cross-sensitivity of non-specific chemical sensors and the use of multivariated data analysis methods as a way to provide fingerprints for samples of different chemical composition. The chemical sensors can employ different types of sensoactive materials, whose electrical responses are dependent on the physicochemical characteristics of the media they get in contact with. Conducting polymers (CP) are per excellence suitable sensoactive materials, since their electrical conductivity is highly influenced by the environmental conditions and they can be easily processed in the thin film form by different techniques. In the present work films of poly(3-methylthiophene) (PMTh) and poly(3-hexylthiophene) (PHTh) are deposited by chronopotenciometry and chronoamperometry onto interdigitated microelectrodes and characterized through Impedance Spectroscopy. This data was analyzed with Multilayer perceptron neural networks and a very good performance is found in gasoline adulteration detection. A less great performance was also achieved in the investigation vehicular ethanol adulteration.
132

Procedimentos para tornar mais efetivo o uso das redes neurais artificiais em planejamento de transportes. / Alternative procedures to make more effective the application artificial neural network in transportation planning.

Bocanegra, Charlie Williams Rengifo 05 February 2002 (has links)
O objetivo deste trabalho é explorar procedimentos alternativos capazes de tornar mais efetiva a aplicação, em planejamento de transportes, de modelos desenvolvidos através de redes neurais artificiais (RNA). Pensar, do ponto de vista prático, que um programa de computador seja imprescindível para a fase de treinamento da rede é aceitável, mas depender deste programa também para estimativas e simulações a partir da rede treinada é muito restritivo. Desta forma, o ideal seria obter instrumentos capazes de reproduzir, fora do software de RNA, o comportamento de redes treinadas, integrando a capacidade de predição das RNAs a outros ambientes e ferramentas. Isto ampliaria os recursos de diferentes ferramentas de planejamento, permitindo, por exemplo, análises de sensibilidade mais simples e diretas. Este trabalho será baseado em um modelo já desenvolvido em outra pesquisa, na qual se treinou uma rede neural artificial para estimar um índice de potencial de viagens para planejamento estratégico de transportes. Trata-se de um caso típico em que, embora a rede treinada conduza a estimativas razoáveis de número de viagens por domicílio a partir de variáveis que caracterizam a mobilidade e a acessibilidade, não se pode realizar outras análises a partir dos resultados sem fazer uso do software em que a rede neural artificial foi treinada e obviamente do arquivo com a rede já treinada. Daí a importância de desenvolver alternativas capazes de tornar mais efetivo o uso desse tipo de modelo. Dentre as alternativas aqui exploradas está a reprodução do modelo de RNA em uma planilha eletrônica, o desenvolvimento de um programa em visual basic, a construção de ábacos e a integração, de forma direta, do modelo de RNA a um sistema de informações geográficas (SIG). Para esse último caso, o modelo em ambiente SIG foi utilizado em uma aplicação na cidade de Bauru, a partir de dados agregados em zonas, onde se simulou alterações nos valores das variáveis de entrada, de forma a avaliar o seu impacto sobre as viagens estimadas em diferentes regiões da cidade. Todas as alternativas exploradas ilustram bem a ampliação das possibilidades de realização de análises de sensibilidade com os modelos de RNA, sobretudo quando combinados com os SIG, particularmente quando a localização dos valores estimados como saída é importante no contexto de análise e tomada de decisão. É importante destacar ainda que, além de permitir a condução de análises de sensibilidade, as alternativas apresentadas neste estudo podem, de certa forma, ajudar aos planejadores e tomadores de decisão a entender a lógica do modelo. / The objective of this work is to explore alternative procedures to make more effective the application of ANN (artificial neural network) models in transportation planning. While the use of a specific computer program for training the networks is acceptable, the requirement of the same dedicated software also for predictions and simulations using the trained network is very restrictive from a practical point of view. An alternative to tackle this problem would be to reproduce the behavior of the trained ANN models out the training package through the integration of their estimation capabilities to other tools and environments. This could extend the resources of different planning tools, allowing, for instance, simpler and direct sensitivity analyses. The present study is based on a model developed in previous research work, in which a particular ANN model has been developed to estimate a Trip Potential Index for transportation planning at a strategic level. This is a typical example of a model able to produce acceptable trip number estimations based on input variables associated to mobility and accessibility. Any further analyses, however, are usually dependent on the use of the same package used for training the network and the file with the trained network. This stresses the importance of developing alternatives to make more effective the use of this sort of model. Among the alternatives explored in this work are: the use of electronic spreadsheets, a computer program written in visual basic, graphs, and the direct integration of the ANN model into a geographic information system (GIS) commercial package. In the last case, the model in a GIS-environment has been used to run an application in the city of Bauru. Using data aggregated at the zonal level, changes in the input variables have been simulated in order to evaluate their impact on the trips estimated for different city regions. All alternatives explored here demonstrate the possibilities offered by the ANN models for sensitivity analyses. This is even more evident in the case of ANN models combined with GIS, particularly when the location of the predicted values is a relevant element in the analysis or decision making context. In addition, the procedures presented here may somehow help planners and decisionmakers in understanding the logic behind the models.
133

Metodologia para elaboração de modelos de fragilidade ambiental utilizando redes neurais / Methodology for the elaboration of environmental fragility models using artificial neural networks

Sporl, Christiane 29 August 2007 (has links)
Este trabalho aborda o desafio da modelagem da fragilidade ambiental, que implica em, além de compreender a intrínseca e dinâmica relação existente entre as componentes físicas, bióticas e sócio-econômicas dos sistemas ambientais, em traduzir esse conhecimento num modelo matemático. Para elucidar essa dificuldade foram apresentados e comparados os resultados gerados por dois modelos empíricos de fragilidade ambiental amplamente utilizados no planejamento físico-territorial brasileiro (CREPANI et al. 2001 e ROSS, 1994). Estes dois modelos foram aplicados em duas áreasteste, com resultados bastante divergentes. Neste contexto de incertezas, este trabalho testou a viabilidade e a confiabilidade de uma nova ferramenta a ser aplicada na elaboração de modelos de fragilidade ambiental, as redes neurais artificiais (RNAs). Empregando os conhecimentos e experiências de especialistas na área em questão, extraídos das respostas dadas por estes durante a comparação de variáveis e cenários aplicados através dos programas adaptados para esta finalidade: Pesquisa de Calibração, Pesquisa de Escalonamento de Variáveis e Pesquisa de Avaliação de Cenários. Estes programas geraram uma base de dados referente ao modo de avaliação de cada especialista quanto à fragilidade ambiental, sendo aplicada no treinamento das RNAs, para que a rede assimilasse o padrão de avaliação deste especialista. Os resultados comprovam de que é possível emular, com razoável confiabilidade, o padrão de avaliação de especialistas na definição da fragilidade dos sistemas ambientais, eliminando assim, a arbitrariedade e a subjetividade do processo de elaboração de modelos de fragilidade ambiental. Este trabalho não propõe um novo modelo, mas uma metodologia para a construção de modelos, utilizando redes neurais artificiais, dando um primeiro passo em busca de novas técnicas, temidas pelos geógrafos, mas necessárias para a evolução da ciência geográfica. / This paper deals with the challenge in modeling environmental fragility, which implies not only the understanding of the intrinsic and dynamic relationship that exists between the physical, biotic and socio-economic components of environmental systems, but also in translating this knowledge in a mathematical model. In order to shed light on this difficulty, the results generated by two empirical models of environmental fragility were presented and compared, models that are widely used in Brazilian physical-territorial planning. (CREPANI et al. 2001 and ROSS, 1994). These two models were applied in two thesis-areas with very diverging results. Within this context of uncertainties, this paper tested the feasibility and reliability of a new tool to be applied in the elaboration of environmental fragility models, the artificial neural networks (ANN). Tapping on the knowledge and experience of specialists in this area, extracted from the answers given by them during the comparison of variables and scenarios applied in programs adapted for this objective: Gauging Research, Scheduling of Variables Research and Scenario Evaluation Research. These programs generated a databank related to the evaluation format of each specialist regarding environmental fragility applied in the training of ANNs, so that the network would assimilate the evaluation standard of that specialist. The results proved that it is possible to emulate, with reasonable reliability, the evaluation standard of specialists in the definition of environmental systems fragility, eliminating in this way, arbitrariness and subjectivity in the elaboration process of environmental fragility models. This work does not presuppose a new model, rather a methodology for the construction of models, using artificial neural networks, taking the first step in the search of new techniques, albeit feared by the geographers, however, necessary for the evolution of geographic science.
134

Classificação e localização de faltas em linhas de transmissão usando diferentes arquiteturas de redes neurais artificiais. / Classification and location faults in transmission lines, using different artificial neural networks architectures.

Menezes, Marlim Pereira 19 August 2008 (has links)
Este trabalho apresenta o desenvolvimento de algoritmos para determinação da estimativa da distância de ocorrência de falta em uma linha de transmissão de alta tensão, em relação a um terminal local, e também a classificação do tipo de falta, utilizando técnicas baseadas em redes neurais artificiais. Os testes e a validação dos algoritmos propostos são feitos a partir de dados simulados para os fasores de tensão e corrente, em regime permanente, com uso da linguagem MATLAB. Os fasores são obtidos com uso de cálculo tradicional de curto e parâmetros reais de uma linha de transmissão conhecida. Em casos reais os fasores seriam obtidos de amostras de tensões e correntes detectadas por dispositivos de proteção localizados nos terminais local e remoto da linha de transmissão em análise. As simulações das redes neurais para a classificação do tipo de falta e para a obtenção da estimativa da distância de falta foram feitas com duas rotinas escritas em MATLAB levando em consideração erros de medição dos fasores. Os resultados obtidos permitem avaliar a eficiência e a precisão dos algoritmos propostos em relação aos já existentes e conhecidos na literatura, e que usam somente equacionamento elétrico. / This work presents the development of algorithms for determination of the estimate of the distance of occurrence of fault in a high voltage transmission line, in relation to a local terminal, and also the classification of the fault type, using techniques based on artificial neural networks. The tests and the validation of the proposed algorithms are made using simulated data for the voltage and current phasors, in steady state, with use of the MATLAB language. The phasors are obtained with use of traditional calculation of short-circuit and real parameters of a known transmission line. In real cases the phasors would be obtained with samples of voltages and currents detected by protection devices located in the local and remote terminals of the transmission line in analysis. The simulations of the neural networks for the classification of the fault type and for the obtaining the estimate of the fault distance were done with two routines written in MATLAB taking into account measurement errors of the phasors. The obtained results allow to evaluate the efficiency and the accuracy of the proposed algorithms in relation to the already existent and known in the literature, and that use only electric equations.
135

Um sistema de localização robótica para ambientes internos baseado em redes neurais. / An indoor robot localization system based on neural networks.

Sanches, Vitor Luiz Martinez 15 April 2009 (has links)
Nesta pesquisa são estudados aspectos relacionados à problemática da localização robótica, e um sistema de localização robótica é construído. Para determinação da localização de um robô móvel em relação a um mapa topológico do ambiente, é proposta uma solução determinística. Esta solução é empregada a fim de prover localização para problemas de rastreamento de posição, embora seja de interesse também a observação da eficácia, do método proposto, frente a problemas de localização global. O sistema proposto baseia-se no uso de vetores de atributos, compostos de medições momentâneas extraídas do ambiente através de sensoriamentos pertencentes à percepção do robô. Estimativas feitas a partir da odometria e leitura de sensores de ultra-som são utilizadas em conjunto nestes vetores de atributos, de forma a caracterizar as observações feitas pelo robô. Uma bússola magnética também é empregada na solução. O problema de localização é então resolvido como um problema de reconhecimento de padrões. A topologia do ambiente é conhecida, e a correlação entre cada local neste ambiente e seus atributos são armazenados através do uso de redes neurais artificiais. O sistema de localização foi avaliado de maneira experimental, em campo, em uma plataforma robótica real, e resultados promissores foram obtidos e são apresentados. / In this research aspects related to the robot localization problem have been studied. In order to determine the localization of a mobile robot in relation to a topological map of its environment, a deterministic solution has been proposed. This solution is applied to provide localization for position tracking problems, although it is also of interest to observe the performance of the proposed method applied to global localization problems. The proposed system is based on feature vectors, which are composed of momentaneous measures extracted from sensory data of the robots perception. Estimative made from odometry, sonars and magnetic compass readings are used together in these feature vectors, in order to characterize observed scenes by the robot. Thus, the localization problem is solved as a pattern recognition problem. The topology of the environment is known, and the correlation between each place of this environment and its features is stored using an artificial neural network. The localization system was experimentally evaluated, in a real robotic platform. The results obtained allow validation of the methodology.
136

Analysis of the voltage stability problem in electric power systems using artificial neural networks

Schmidt, Hernan Prieto January 1994 (has links)
The voltage stability problem in electric power systems is concerned with the analysis of events and mechanisms that can lead a system into inadmissible operating conditions from the voltage viewpoint. In the worst case, total collapse of the system may result, with disastrous consequences for both electricity utilities and customers. The analysis of this problem has become an important area of research over the past decade due to some instances of voltage collapse that have occurred in electric systems throughout the world. This work addresses the voltage stability problem within the framework of artificial neural networks. Although the field of neural networks was established during the late 1940s, only in the past few years has it experienced rapid development. The neural network approach offers some potential advantages to the solution of problems for which an analytical solution is difficult. Also, efficient and accurate computation may be achieved through neural networks. The first contribution of this work refers to the development of an artificial neural network capable of computing a static voltage stability index, which provides information on the stability of a given operating state in the power system. This analytical tool was implemented as a self-contained computational system which exhibited good accuracy and extremely low processing times when applied to some study cases. Dynamic characteristics of the electrical system in the voltage stability problem are very important. Therefore, in a second stage of the present work, the scope of the research was extended so as to take into account these new aspects. Another neural network-based computational system was developed and implemented with the purpose of providing some information on the behaviour of the electrical system in the immediate future. Examples and case studies are presented throughout the thesis in order to illustrate the most relevant aspects of both artificial neural networks and the computational models developed. A general discussion summarises the main contributions of the present work and topics for further research are outlined.
137

Applications of Artificial Neural Networks (ANNs) in exploring materials property-property correlations

Cheng, Xiaoyu January 2014 (has links)
The discoveries of materials property-property correlations usually require prior knowledge or serendipity, the process of which can be time-consuming, costly, and labour-intensive. On the other hand, artificial neural networks (ANNs) are intelligent and scalable modelling techniques that have been used extensively to predict properties from materials’ composition or processing parameters, but are seldom used in exploring materials property-property correlations. The work presented in this thesis has employed ANNs combinatorial searches to explore the correlations of different materials properties, through which, ‘known’ correlations are verified, and ‘unknown’ correlations are revealed. An evaluation criterion is proposed and demonstrated to be useful in identifying nontrivial correlations. The work has also extended the application of ANNs in the fields of data corrections, property predictions and identifications of variables’ contributions. A systematic ANN protocol has been developed and tested against the known correlating equations of elastic properties and the experimental data, and is found to be reliable and effective to correct suspect data in a complicated situation where no prior knowledge exists. Moreover, the hardness increments of pure metals due to HPT are accurately predicted from shear modulus, melting temperature and Burgers vector. The first two variables are identified to have the largest impacts on hardening. Finally, a combined ANN-SR (symbolic regression) method is proposed to yield parsimonious correlating equations by ruling out redundant variables through the partial derivatives method and the connection weight approach, which are based on the analysis of the ANNs weight vectors. By applying this method, two simple equations that are at least as accurate as other models in providing a rapid estimation of the enthalpies of vaporization for compounds are obtained.
138

Signal processing for advanced neural recording systems

Al-Shueli, Assad January 2013 (has links)
Many people around the world suffer from neurological injuries of various sorts that cause serious difficulties in their lives, due to the loss of important sensory and motor functions. Functional electrical stimulation (FES) provides a possible solution to these difficulties by means of a feedback connection allowing the target organ (or organs) to be controlled by electrical stimulation. The control signals can be provided using recorded data extracted from the nerves (electroneurogram, ENG). The most common and safe approaches for interfacing with nerves is called cuff electrodes which deliver the required feedback path for the implantable system with minimum risk. The amount of recorded information can be improved by increasing the number of electrodes within a single cuff known as multi-electrode cuffs (MECs) configuration. This strategy can increase the signal to noise ratio for the recorded signals which have typically very low amplitude (less than 5μV). Consequently multiple high gain amplifiers are used in order to amplify the signals and supply a multi-channel recorded data stream for signal processing or monitoring applications. The signal processing unit within the implantable system or outside the body is employed for classification and sorting the action potential signals (APs) depending on their conduction velocities. This method is called velocity selective recording (VSR). Basically, the idea of this approach is that the conduction velocity of AP can be determined by timing the appearance of the signal at two or more points along the nerve and then dividing the distance between the points by the delay. The purpose of this thesis to investigate an alternative approach using artificial network for APs detection and extraction in neural recording applications to increase the velocity selectivity based on VSR using MECs. The prototype systems impose four major requirements which are high velocity selectivity, small size, low power consumption and high reliability. The proposed method has been developed for applications which require online AP classification. A novel time delay neural network (TDNN) approach is used to decompose the recorded data into several matched velocity bands to allow for individual velocity selectivity at each band to be increased. Increasing the velocity selectivity leads to more accurate recording from the target fibre (or fibres) within the nerve bundle which can be used for applications that require AP classification such as bladder control and the adjustment of foot drop. The TDNN method was developed to obtain more information from an individual cuff without increasing the number of electrodes or the sampling rate. Moreover, the optimization of the hardware implementation for the proposed signal processing method permits savings in power consumption and silicon area. Finally, a nerve signal synthesiser and noise generator for the evaluation of the VSRmethod is described. This system generates multiple artificial AP signals with a time offset between the channels with additive white Gaussian noise (AWGN) to simulate the MEC and hence reduce the cost and the number of the animals required for experimental tests.
139

Previsão de venda de produtos em uma indústria de telecomunicação utilizando redes neurais artificiais

Silva, Rafael Schardosin 29 September 2010 (has links)
Made available in DSpace on 2015-03-05T14:01:49Z (GMT). No. of bitstreams: 0 Previous issue date: 29 / Nenhuma / Este trabalho tem por objetivo apresentar uma proposta para a previsão de vendas de produtos, com fundamentação teórica, por meio da utilização de Redes Neurais Artificiais, utilizando como estudo de caso uma indústria que desenvolve produtos para o ramo de telecomunicação. Atualmente, realizar previsões de venda nas empresas é fundamental para reduzir seus custos com gastos desnecessários em recursos humanos e materiais e aumentar sua liquidez, sem perder a qualidade que os clientes estão acostumados, no sentido de evitar atrasos nos prazos de entrega dos produtos. O problema abordado nesta dissertação é importante para quase todas as áreas das indústrias, uma vez que a correta previsão de vendas permite às indústrias uma melhor organização de seu setor produtivo, permitindo a antecipação da quantidade ideal de matéria-prima a ser adquirida, o alinhamento de sua linha de produção, de modo a não ocorrerem alterações bruscas em seus layouts de fábrica, e um maior controle de seus níveis de estoque, reduzindo e / This work has the objective to present a methodology to predict product sales using artificial neural networks, as a study case was treated the periodic sales volume of an industry which develops products to the telecommunication area. Nowadays, realize sales prediction in the companies is crucial to reduce the costs with human resources, materials and increase the liquidity, without loose the quality which the clients are familiarized, avoiding delays in the products deliveries. The problem which this dissertation tackles is important to several kinds of industries, once a precise sales prediction allow the industries to organize themselves in a better way. It allows the company to know anticipated the material to be acquired, align their productions lines, avoiding an abrupt change in the factory layouts and offers a better control of their stocks. The study realized and the solution proposed are based on Artificial Neural Networks, applied to predict product sales using the sales history and the insertion
140

Estimação da rugosidade gerada no processo de fresamento frontal via redes neurais artificiais

Hübner, Henrique Butzlaff January 2016 (has links)
A rugosidade é um parâmetro de acabamento importante nos processos de fabricação por usinagem e é determinado de acordo com a aplicação técnica da superfície usinada. A rugosidade afeta atributos funcionais dos produtos como desgaste, atrito, reflexão da luz, capacidade de manter e espalhar um lubrificante, etc.. Como a inspeção da superfície é normalmente feita com rugosímetros após a operação de usinagem, essa tarefa consome tempo e demanda trabalho, gerando custo adicional ao produto. Assim, este trabalho tem como objetivo estimar os valores das rugosidades média (Ra) e total (Rt) geradas no processo de fresamento frontal a seco do aço SAE 1045 com fresa de topo reto via redes neurais artificiais (RNA). Dessa forma, os valores de rugosidade Ra e Rt podem ser obtidos somente informando os parâmetros do processo ao modelo. Foram considerados como variáveis de entrada do processo a velocidade de corte (vc), o avanço por dente (fz) e o raio de ponta da ferramenta (r). Após uma análise estatística, constatou-se que as variáveis de saída que melhor se correlacionavam com os valores de rugosidade foram a força média no eixo x (Fx) (direção de avanço) e a variação da força no eixo z (Fz) (direção axial). Os dados de força foram obtidos usando um sistema sensório constituído de plataforma piezelétrica, placa de aquisição de dados e computador com software apropriado. Portanto, os cinco parâmetros de entrada utilizados nos 16 modelos testados foram vc, fz, r, Fx e Fz. O algoritmo de treinamento usado foi o de Levemberg-Marquardt. Dentre os testados, os modelos com topologia 5-10-10-1 (cinco entradas e uma saída) apresentaram as melhores capacidade de estimação para os valores de Ra e Rt, mostrando a eficiência da técnica de modelagem da rugosidade por RNA. / The surface roughness is an important finishing parameter in the machining manufacturing processes and it is determined according with the technical application of the machined surface. The surface roughness affects functional attributes of parts such as wear, friction, light reflection, ability to spreading and retaining a lubricant etc. As the surface inspection is usually done with the rugosimeter after the machining operation, this task is time consuming and labor demand, generating additional cost to the product. Thus, this work aims to estimate the values of average roughness (Ra) and total roughness (Rt) generated in the dry end milling process of the SAE 1045 steel via artificial neural networks (ANN). Thus, the roughness values of Ra and Rt may be obtained only by informing the process parameters to the model. Cutting speed (vc), feed per tooth (fz) and tool nose radius (r) were considered as input variables. After statistical analysis, it was found that output variables that best correlate with roughness values were the average force on the x axis (Fx) (feed direction) and the force variation in the z-axis (Fz) (axial direction). The cutting force data signals were obtained using a sensory system composed by piezoelectric platform, data acquisition board and personal computer with appropriate software. Therefore, the five input parameters applied in the 16 models tested were vc, fz, r, Fx and Fz and the training algorithm used was the Levemberg-Marquardt. Among the models tested, those with 5-10-10-1 topology (five inputs and one output) showed the best capacity for estimation of the Ra and Rt values that can demonstrate the modeling technique effectiveness of the surface roughness using ANN.

Page generated in 0.0819 seconds