hybrid systems
Recently Published Documents


TOTAL DOCUMENTS

5018
(FIVE YEARS 750)

H-INDEX

101
(FIVE YEARS 12)

2022 ◽  
Vol 44 ◽  
pp. 101137
Author(s):  
Constantinos Heracleous ◽  
Christodoulos Keliris ◽  
Christos G. Panayiotou ◽  
Marios M. Polycarpou

Author(s):  
Roberto Outa ◽  
Fabio Roberto Chavarette ◽  
Vishnu Narayan Mishra ◽  
Aparecido Carlos Gonçalves ◽  
Adriana Garcia ◽  
...  

This work is of multidisciplinary concept, whose development is difficult to perform. Considering also that, in one of the steps, the similarity between the FRF of the vibration and acoustic signal is demonstrated. The objective of this work is the analysis and prognosis of the progression of failures of a pair of gears using the artificial immune system (AIS) of negative selection. In order to have this condition met, during the development of this work, the Wiener filter technique, the vibration and acoustic signal analysis (FRF), the application of negative selection AIS techniques for classification and grouping of signals were applied. The final result successfully demonstrates the effectiveness of the development process of this work and the robustness of the negative selection AIS algorithm.


2022 ◽  
Vol 12 (1) ◽  
Author(s):  
Paulo S. G. de Mattos Neto ◽  
George D. C. Cavalcanti ◽  
Domingos S. de O. Santos Júnior ◽  
Eraylson G. Silva

AbstractThe sea surface temperature (SST) is an environmental indicator closely related to climate, weather, and atmospheric events worldwide. Its forecasting is essential for supporting the decision of governments and environmental organizations. Literature has shown that single machine learning (ML) models are generally more accurate than traditional statistical models for SST time series modeling. However, the parameters tuning of these ML models is a challenging task, mainly when complex phenomena, such as SST forecasting, are addressed. Issues related to misspecification, overfitting, or underfitting of the ML models can lead to underperforming forecasts. This work proposes using hybrid systems (HS) that combine (ML) models using residual forecasting as an alternative to enhance the performance of SST forecasting. In this context, two types of combinations are evaluated using two ML models: support vector regression (SVR) and long short-term memory (LSTM). The experimental evaluation was performed on three datasets from different regions of the Atlantic Ocean using three well-known measures: mean square error (MSE), mean absolute percentage error (MAPE), and mean absolute error (MAE). The best HS based on SVR improved the MSE value for each analyzed series by $$82.26\%$$ 82.26 % , $$98.93\%$$ 98.93 % , and $$65.03\%$$ 65.03 % compared to its respective single model. The HS employing the LSTM improved $$92.15\%$$ 92.15 % , $$98.69\%$$ 98.69 % , and $$32.41\%$$ 32.41 % concerning the single LSTM model. Compared to literature approaches, at least one version of HS attained higher accuracy than statistical and ML models in all study cases. In particular, the nonlinear combination of the ML models obtained the best performance among the proposed HS versions.


Energies ◽  
2022 ◽  
Vol 15 (2) ◽  
pp. 468
Author(s):  
Jorge Olmedo-González ◽  
Guadalupe Ramos-Sánchez ◽  
Erika Paola Garduño-Ruiz ◽  
Rosa de Guadalupe González-Huerta

Stand-alone systems in remote regions require the utilization of renewable resources; however, their natural intermittence requires the implementation of energy-storage systems that allow a continuous power supply. More than one renewable source is usually available at the same site. Thus, the choice of a hybrid system seems viable. It is relevant to study hybrid systems as they could reduce energy storage; however, sizing the hybrid system might have several implications, not only for the available daily energy, but also for the required daily energy storage and surplus seasonal energy. In this work, we present a case study of a stand-alone, conventional household powered by photovoltaic and marine-current-energy systems in Cozumel, Mexico. The analysis of different hybridization degrees serves as a guidance tool to decide whether hybrid systems are required for a specific situation; in contrast to previous approaches, where ideal consumption and generation profiles have been utilized, yearlong profiles were utilized here. The renewable potential data were obtained on site at an hourly resolution; requirements such as size of and cycles in the daily and seasonal energy storage were analyzed according to the degree of participation or hybridization of the proposed renewable systems through an algorithm that evaluates power generation and daily consumption throughout the year. A further analysis indicated that marine-current-energy implementation reduces the size of the daily energy-storage system by 79% in comparison to the use of only a photovoltaic system due to the similarity between the energy-demand profile and the marine-current-energy production profile. The results indicate that a greater participation of marine currents can help decrease daily storage while increasing seasonal storage by 16% compared to using only solar energy. On the other hand, hybridization enabled a reduction in the number of daily charge and discharge cycles at 0.2 hybridization degrees. It also allowed us to reduce the seasonal energy storage by 38% at 0.6 hybridization degrees with respect to only using energy from marine currents. Afterwards, energy-storage technologies were evaluated using the TOPSIS Multi-Criteria Decision Analysis to validate the best-suited technology for the energy-storage system. The evaluation considered the characteristics of the technology and the periods of energy storage. In this work, hybrid storage systems were mandatory since, for daily storage, lithium-ion batteries are better suited, while for seasonal storage, hydrogen-producing systems are more suitable to manage the amount of energy and the storage duration due to the high seasonal renewable-energy variations.


2022 ◽  
pp. 67-82
Author(s):  
Nadia Obrownick Okamoto-Schalch ◽  
Natalia Cristina da Silva ◽  
Rafael Belasque Canedo da Silva ◽  
Milena Martelli Tosi

Sign in / Sign up

Export Citation Format

Share Document