The prognosis of wind turbine failures in real operating conditions is a significant gap in the academic literature and is essential for achieving viable performance parameters for the operation and maintenance of these machines, especially those located offshore. This paper presents a framework for estimating the remaining useful life (RUL) of the main bearing using regression models fed operational data (temperature, wind speed, and the active power of the network) collected by a supervisory control and data acquisition (SCADA) system. The framework begins with a careful data filtering process, followed by creating a degradation profile based on identifying the behavior of temperature time series. It also uses a cross-validation strategy to mitigate data scarcity and increase model robustness by combining subsets of data from different available turbines. Support vector, gradient boosting, random forest, and extra trees models were created, which, in the tests, showed an average of 20 days in estimating the remaining useful life and presented mean absolute error (MAE) values of 0.047 and mean squared errors (MSE) of 0.012. As its main contributions, this work proposes (i) a robust and effective regression modeling method for estimating RUL based on temperature and (ii) an approach for dealing with a lack of data, a common problem in wind turbine operation. The results demonstrate the potential of using these forecasts to support the decision making of the teams responsible for operating and maintaining wind farms.

This study investigates and compares the experimental heat transfer performance and simulation via computational fluid dynamics (CFD) of graphene nanoplatelets (GNP) and water nanofluids GNP/water in the double-tube-type heat exchanger (DTHE). Tests were conducted with water/water and GNP/water fluids, with the nanofluid for the hot-fluid circuit and water for the cold-fluid circuit, with counterflow direction, varying the nanofluid concentrations by weight (wt%) at 0.0125%, 0.025%, and 0.050%, the operating temperature at 50 and 60 °C, and Reynolds numbers between 2000–6000. The results showed that 0.025 wt% GNP presented better thermal performance, with a 28% increase in the temperature gain. The 0.025 wt% GNP had slightly better performance for the Nusselt number (Nu), and the 0.05 wt% GNP had a slightly better thermal effectiveness. The comparison between the experimental values showed good agreement with those calculated by empirical correlations and the CFD model, with maximum and minimum relative error values of 9% and 1%, respectively, when the Petukhov equation was used.

This paper presents a thermodynamic model developed for a prototype absorption chiller using NH₃/LiNO₃ with 10 kW of nominal capacity. The study was undertaken using thermodynamic modeling based on the mass and energy balance, takes the overall heat transfer coefficients into consideration and uses the characteristic equation method. First, the results obtained from the thermodynamic modeling developed were compared with those obtained from the characteristic equations of thermal power activation and the cooling capacity. These showed good agreement with the experimental data, there being maximum relative errors of around 5% for most of the operational conditions of the system. Secondly, a parametric analysis was made by altering the variables, such as temperature, mass flow rate, and configuring the heat dissipation that influences the overall performance of the prototype chiller.

Infections triggered by fungi of the genus Candida are widely known, although the high incidence and mortality factors are still unclear. The classic methods of identifying Candida species are subject to errors, requiring new techniques with faster and more accurate performance. We present a study for identifying fungi species by analyzing volatile organic compounds of cultures acquired and interpreted using Electronic Nose and Artificial Intelligence methods. The proposed approach contributes to establishing an agile and appropriate treatment, reducing the complications of the disease and the number of deaths. We perform experiments with three species of Candida obtaining accuracy above 90% in the fungi identification. Therefore, future works are encouraged to deal with more types of fungi to help create a new identification methodology faster and more reliable using artificial intelligence methods.