ROBERTO NAVARRO DE MESQUITA

ROBERTO NAVARRO DE MESQUITA

(Fonte: Lattes)

Resumo

Possui graduação em Física pela Universidade Estadual de Campinas (1987), mestrado em Física pela Universidade Estadual de Campinas (1991) e doutorado em Engenharia Mecânica pela Universidade de São Paulo (2002). Atualmente é tecnologista pleno da Comissão Nacional de Energia Nuclear. Tem experiência na área de Ciência da Computação, com ênfase em Sistemas de Inteligência Artificial, atuando principalmente nos seguintes temas: inteligência artificial, diagnóstico de defeitos em tubos, correntes parasitas (ECT), reconhecimento de padrões em imagens. (Texto extraído do Currículo Lattes em 27 dez. 2021)

Página do item completo

Resultados de Busca

Agora exibindo 1 - 2 de 2

Characterization of polyacrylonitrile thermal stabilization process for carbon fiber production using intelligent algorithms
2021 - TERRA, BRUNA M.; ANDRADE, DELVONEI A. de; MESQUITA, ROBERTO N. de
Composite materials have widened their application range in recent years. The polymeric composite reinforced with carbon fibers can be described as a high-performance structural material which merges two important features: low weight and mechanical stability. Carbon fiber production which uses polyacrylonitrile as precursor is composed of many stages such as polymerization, spinning, thermal stabilization, carbonization, and surface treatment. Thermal stabilization is the critical stage of this production process, during which aromatic rings are generated, and therefore the main factor for the carbon fiber structure definition and thus for this material quality. A thermal stabilization model using intelligent algorithms was developed aiming a possible optimization of the production process and consequent cost reduction. This work was based on real experimental data obtained from a composite material production pilot plant. A qualitative analysis was initially performed using Self-Organizing Maps trained with variables of fiber production reagents and process. Thereafter, a supervised training with feedforward backpropagation neural network was used for a quantitative analysis. Based on this quantitative analysis, the carbon fiber thermal stabilization process was simulated, obtaining 2.98% and 2.48% mean errors relative to experimental results of Volumetric Density and FTIR Conversion index, respectively.
Nutritional evaluation of Brachiaria brizantha cv. marandu using convolutional neural networks
2020 - DAL PRÁ, BRUNO R.; MESQUITA, ROBERTO N. de; MENEZES, MARIO O. de; ANDRADE, DELVONEI A. de
The identification of plant nutritional stress based on visual symptoms is predominantly done manually and is performed by trained specialists to identify such anomalies. In addition, this process tends to be very time consuming, has a variability between crop areas and is often required for analysis at various points of the property. This work proposes an image recognition system that analyzes the nutritional status of the plant to help solve these problems. The methodology uses deep learning that automates the process of identifying and classifying nutritional stress of Brachiaria brizantha cv. marandu. An image recognition system was built and analyzes the nutritional status of the plant using the digital images of its leaves. The system identifies and classifies Nitrogen and Potassium deficiencies. Upon receiving the image of the pasture leaf, after a classification performed by a convolutional neural network (CNN), the system presents the result of the diagnosed nutritional status. Tests performed to identify the nutritional status of the leaves presented an accuracy of 96%. We are working to expand the data of the image database to obtain an increase in the accuracy levels, aiming at the training with a larger amount of information presented to CNN and, thus, obtaining results that are more expressive.