Browsing by Author "Huaquipaco Encinas, Saul"

Now showing 1 - 3 of 3

An RCM Implementation for Wind Turbine Maintenance using MFEA Method and NHPP Model
(LACCEI Inc., 2018-09) Condori Yucra, Reynaldo; Beltrán Castañón, Norman Jesús; Ramos Cutipa, Jose; Huaquipaco Encinas, Saul; Aquino Larico, Rodrigo; Pizarro Viveros, Henry; Shuta Lloclla, Henry
The implementation of wind power plants for the generation of energy is becoming increasingly popular, however the generation equipment may have failures due to factors of the equipment or operation, in this sense it is important to have a predictive maintenance strategy that allows to anticipate the possible faults that could arise. In this paper we propose the implementation of a Reliability-Centered Maintenance (RCM) scheme, applied to a wind turbine plant using Failure Mode Effect Analysis (FMEA) and Non-Homogeneous Poisson Process (NHPP), which require minimal use of advanced monitoring technologies and simple data acquisition systems. For this, the critical components of the wind system that may present failure are used as indicators to predict the general maintenance time of the system. First, these components to be used as indicators for predictive maintenance are chosen using the FMEA method, where the most critical components are chosen. Second, the fault information of the chosen components are analyzed using the NHPP model; Finally, the analysis of the results is carried out, especially calculating the average time of failure and thus deciding the time of general maintenance of the wind system. The present work demonstrates the validity of these known techniques applied to a wind generation plant, thus supporting the development of the implementation of more wind generator centers.
Modeling and prediction of a multivariate photovoltaic system, using the multiparametric regression model with Shrinkage regularization and eXtreme Gradient Boosting.
(LACCEI Inc., 2021-07) Huaquipaco Encinas, Saul; Cruz, Jose; Beltran Castañon, Norman Jesus; Pineda, Ferdinand; Romero, Christian; Chura Acero, Julio Fredy; Mamani Machaca, Wilson
Alternative energy systems have more frequently been acquiring a fundamental role in the generation of energy that promotes the development of countries in social, economic, and environmental terms. For the efficient operation of photovoltaic systems (SFV), it is necessary to make predictions about their operation, turning them into intelligent systems. The present work proposes the collection, modeling, and prediction of a multivariate SFV, using a multiparametric regression model, presenting five regression models with machine learning: three that use Shrinkage regularization and two that use eXtreme Gradient Boosting (XGBoost). Results obtained, we note that the five predictions have determination coefficients higher than 99.47%; being XGBoost with n_estimators = 500 which reduces the root mean square error by about 55%. Likewise, in all cases, the test times are less than 1 second. The results were validated so that they not only have mathematical significance, but are also real, showing that XGBoost with n_estimators = 10 does not meet the five validation conditions, so this prediction model should not be considered.
Photovoltaic charger system for mobile devices using quick charge 3.0 technology.
(LACCEI Inc., 2020-07) Huaquipaco Encinas, Saul; Beltran Castañon, Norman Jesus; Sarmiento Mamani, Vilma; Huanchi Mamani, Luz Elizabeth; Tito Paredes, Romel Isaias; Contreras Mamani, Richard John; Reyes Molero, Maria Rosa; Pacoricona Apaza, Alex
Mobile devices are becoming more popular, but along with their utility users have experienced autonomy problems, most of the companies have resolved this by increasing the capacity of the battery and the problem that this has generated is that the time of charging also has increased; photovoltaic systems have been presented as a way to supply power to these devices, but always using conventional charging systems. The present work implemented a fast charging system using quick charge 3.0 technology to achieve faster and more efficient loading of mobile devices. For this, we experimented with a mobile device charging it with a photovoltaic solar system with quick charge 3.0 technology and a photovoltaic solar system with a conventional charging method of 5V to 2A. The results showed differences of up to 100 minutes in the loading time between one and another technology. Concluding that photovoltaic systems with quick charge 3.0 technology are faster when loading mobile devices.