João Rodrigo Andrade

Establishing precise welding parameters is essential to achieving the desired bead geometry and ensuring consistent quality in manufacturing processes. However, determining the optimal configuration of parameters remains a challenge, particularly when relying on limited experimental data. This study proposes the use of artificial neural networks (ANNs), with their architecture optimized via differential evolution (DE), to predict key MAG welding parameters based on target bead geometry. To address data limitations, cross-validation and data augmentation techniques were employed to enhance model generalization. In addition to the ANN model, machine learning algorithms commonly recommended for small datasets, such as K-nearest neighbors (KNNs) and support vector machines (SVMs), were implemented for comparative evaluation. The results demonstrate that all models achieved good predictive performance, with SVM showing the highest accuracy among the techniques tested, reinforcing the value of integrating traditional ML models for benchmarking purposes in low-data scenarios.

Este artigo apresenta a caracterizac¸ ˜ao experimental e num´erica do controle de vaz˜ao em uma v´alvula proporcional de esfera utilizada em um sistema t´ermico pneum´atico composto por compressor, tanque de 5,7 litros, resistˆencia de aquecimento e sensores de press˜ao e temperatura. A metodologia envolveu a aquisic¸ ˜ao de dados experimentais, o c´alculo da abertura da v´alvula com base no balanc¸o de energia e a comparac¸ ˜ao com resultados num´ericos. Adicionalmente, foi proposta a aplicac¸ ˜ao de m´etodos de otimizac¸ ˜ao para ajustar a abertura experimental. Os resultados mostram que a abertura da v´alvula pode ser representada de forma consistente por meio do coeficiente de vaz˜ao (Cv) e a modelagem termodinˆamica, mas a falta de isolamento t´ermico do tanque aquecido pode gerar desvios em relac¸ ˜ao ao modelo ideal devido a troca de calor com o meio pelas paredes do tanque. O trabalho contribui com o estudo para caracterizac¸ ˜ao de v´alvulas em sistemas t´ermico hidr´aulicos e abre caminho para aplicac¸ ˜ao de t´ecnicas avanc¸adas de controle multivari´avel.

Este trabalho apresenta a análise energética de um compressor alternativo Vilter, integrado a um sistema de refrigeração utilizado na indústria de laticínios e operando com amônia (R717) como fluido refrigerante. O objetivo principal foi otimizar o desempenho do compressor em função das demandas reais da planta, adotando como estratégia o controle da abertura e fechamento das válvulas solenoides. A metodologia incluiu o levantamento da carga térmica nos diversos processos produtivos, a fim de identificar períodos de maior e menor estabilidade, além da aplicação de análises energética e exergética do ciclo de refrigeração em diferentes condições de operação. Para isso, foram coletados dados de pressão e temperatura em dias representativos, permitindo determinar propriedades termodinâmicas e indicadores de desempenho. Os resultados evidenciaram economias entre 33% e 66% no consumo de amônia e uma redução de aproximadamente 19% no consumo global de energia. O coeficiente de desempenho (COP) variou entre 4,4 e 5,7, com capacidade de refrigeração entre 184 e 301 kW, mostrando que a operação otimizada atende às demandas térmicas da planta, especialmente em períodos de baixa produção. Conclui-se que o uso de válvulas solenoides para modulação da capacidade é uma estratégia eficaz, garantindo eficiência operacional e redução de custos na indústria de laticínios.

The CFD simulation of cyclone separators has remarkably evolved over the past decades. Nowadays, computational models are essential for designing, analyzing, and optimizing these devices. Due to the intrinsic anisotropy of the flow inside these separators, the Reynolds stress model (RSM) has been mostly employed. However, RSM models fail to solve most time and space scales, including those relevant to particle behavior. Consequently, the prediction of the grade collection efficiency may be hindered, particularly for low-Stokes-number particles. For example, the precessing vortex core phenomenon (PVC), a well-known phenomenon that is relevant for particle motion, is not usually captured in Reynolds-averaged Navier–Stokes (RANS) simulations. Alternatively, the large-eddy simulation (LES) has been proven to be a superior approach since it captures many time and space scales that would have been otherwise dissipated, allowing for more accurate predictions of particle collection. However, this accuracy comes at a considerable computational cost. To combine the advantages of these two models, the main objective of this research was to evaluate a new hybrid RSM-LES model applied to the cyclone’s flow. The results were compared to experimental data and with RSM model results. It showed that, compared to a RANS model given by the RSM closure model, the grade collection efficiency curve obtained by the hybrid model is closer to the experimental one, even for the coarser mesh. Beyond that, the results showed that while the improvement in results was not proportional to mesh refinement for RANS modeling, the hybrid model showed significant improvement with mesh refinement.

Cyclone separators are widely used in fluid catalytic cracking (FCC) units due to their lack of moving parts and relatively low-pressure drop. However, cyclone separators are prone to erosion-related issues, which is a major drawback. In this paper, a large eddy simulation (LES) of the particle-gas flow in a cyclone separator is investigated using a four-way Euler-Lagrange approach to model inter-particle collisions and the exchange of momentum between particles and fluid. The effects of inter-particle and particle-wall collisions are characterized in terms of erosive wear. Additional effects involving the exchange of momentum between the fluid and the particles are also discussed. The results show that considering the interparticle collisions between solid particles may be the key to predicting erosion.