Water Resources Management, Год журнала: 2022, Номер 36(12), С. 4785 - 4797
Опубликована: Авг. 10, 2022
Язык: Английский
Water Resources Management, Год журнала: 2022, Номер 36(12), С. 4785 - 4797
Опубликована: Авг. 10, 2022
Язык: Английский
Energy Reports, Год журнала: 2022, Номер 9, С. 924 - 940
Опубликована: Дек. 20, 2022
Hybrid Energy Systems (HES) combine multiple energy sources to maximize efficiency. Due the unpredictability and dependence on weather, integrating renewable (RES) is a viable option for distributed distribution (DG). To minimize environmental impact meet increasing demand–supply gap, scientists need find alternative sources. Several studies have confirmed that HES economically in remote areas, particularly off-grid applications. Despite several improvements over past few years, existing control systems are complex, costly, less reliable, not sufficiently efficient. The purpose of this paper present most common challenges faced by stand-alone hybrid how artificial intelligence (AI) technique has improved them. AI techniques widely used HES, study addressed can solve classification, forecasting, networking, optimization, problems. This provides an overview recent history critical management, sizing, demand side storage management; additionally, we conceptual/theoretical problems, antecedents, consequences may be interest or require further research. Companies must ensure their perform effectively pay investments. Regardless system, failures defects should diagnosed repaired as soon possible. achieved system's efficiency preventing early-stage damage. Researchers project managers who work will invaluable resource.
Язык: Английский
Процитировано
38Computational Intelligence and Neuroscience, Год журнала: 2022, Номер 2022, С. 1 - 10
Опубликована: Авг. 10, 2022
Corn has great importance in terms of production the field agriculture and animal feed. Obtaining pure corn seeds is quite significant for seed quality. For this reason, distinction that have numerous varieties plays an essential role marketing. This study was conducted with 14,469 images BT6470, Calipso, Es_Armandi, Hiva types licensed by BIOTEK. The classification carried out three stages. At first stage, deep feature extraction four performed pretrained CNN model SqueezeNet 1000 features were obtained each image. In second order to reduce these from SqueezeNet, separate selection processes Bat Optimization (BA), Whale (WOA), Gray Wolf (GWO) algorithms among optimization algorithms. Finally, last stages classified using machine learning methods Decision Tree (DT), Naive Bayes (NB), multi-class Support Vector Machine (mSVM), k-Nearest Neighbor (KNN), Neural Network (NN). mSVM achieved highest success 89.40%. as a result classifications through active selected (BA, WOA, GWO), 88.82%, 88.72%, 88.95%, respectively. accuracies tested stage are close other success. However, used selection, successful been fewer shorter time. results study, which inexpensive, objective, time processing types, present different perspective performance.
Язык: Английский
Процитировано
33Materials Today Communications, Год журнала: 2024, Номер 39, С. 109150 - 109150
Опубликована: Май 8, 2024
Язык: Английский
Процитировано
8International Journal of Electrical Power & Energy Systems, Год журнала: 2025, Номер 165, С. 110445 - 110445
Опубликована: Янв. 12, 2025
Язык: Английский
Процитировано
1Energy and Buildings, Год журнала: 2025, Номер unknown, С. 115478 - 115478
Опубликована: Фев. 1, 2025
Язык: Английский
Процитировано
1Electric Power Systems Research, Год журнала: 2022, Номер 208, С. 107917 - 107917
Опубликована: Март 16, 2022
Язык: Английский
Процитировано
28Artificial Intelligence in Medicine, Год журнала: 2023, Номер 139, С. 102492 - 102492
Опубликована: Янв. 19, 2023
Язык: Английский
Процитировано
10International Journal of Systems Assurance Engineering and Management, Год журнала: 2025, Номер unknown
Опубликована: Янв. 8, 2025
Язык: Английский
Процитировано
0Journal of Energy Storage, Год журнала: 2025, Номер 114, С. 115719 - 115719
Опубликована: Фев. 10, 2025
Язык: Английский
Процитировано
0Water, Год журнала: 2025, Номер 17(7), С. 939 - 939
Опубликована: Март 24, 2025
The presence of oil slicks in the ocean presents significant environmental and regulatory challenges for offshore processing operations. During primary oil–water separation, produced water is discharged into ocean, carrying residual oil, which measured using total grease (TOG) method. formation spread are influenced by metoceanographic variables, including wind direction (WD), speed (WS), current (CD), (CS), wave (WWD), peak period (PP). In Brazil, limits impose sanctions on companies when exceed 500 m length, making accurate prediction their occurrence extent crucial operators. This study follows three main stages. First, performance five machine learning classification algorithms evaluated, selecting most efficient method based metrics from a Brazilian company’s slick database. Second, best-performing model used to analyze influence variables TOG levels detection probability. Finally, third stage examines detected identify key contributing factors. results enhance decision-support frameworks, improving monitoring mitigation strategies discharges.
Язык: Английский
Процитировано
0