| 01-06-2022 |
Predicción de contactos termo-elasto-hidrodinámicos por medio de métodos de aprendizaje automático
La reducción de las pérdidas por fricción y desgaste en los tribo-contactos lubricados de elementos de máquinas o componentes mecánicos sometidos a grandes cargas es esencial para desarrollar sistemas energéticamente eficientes y fiables. En particular, la modelización de los contactos concentrados y termo-elasto-hidrodinámicamente lubricados (TEHL), en los que se superponen la deformación elástica local de las superficies de fricción y la formación de una lámina de fluido hidrodinámico, es comparativamente compleja y computacionalmente costosa. Basado en resultados previos, este proyecto estudiantil se basará en la hipótesis de que los métodos de aprendizaje automático predicen las características de los contactos con gran exactitud y más rápidamente que los complejos modelos de simulación. Los datos de las simulaciones de contacto se utilizarán para entrenar enfoques de aprendizaje automático, como Artificial Neural Networks.
Prerequisitos:
no tiene.
Tiene un método de evaluación Nota 1-7, con 10 créditos y tiene 2/2 vacantes disponibles |
Mentor(es): Ver en la plataforma |
| 01-06-2022 |
Prediction of Thermo-elastohydrodynamic contacts by machine learning approaches
Reducing friction and wear losses in the lubricated tribo-contacts of heavily loaded machine elements or mechanical components is essential for developing energy-efficient and reliable systems. In particular, the modeling of concentrated and thermo-elasto-hydrodynamically lubricated (TEHL) contacts, in which local elastic deformation of friction surfaces and the formation of a hydrodynamic fluid film are superimposed, is comparatively complex and computationally expensive. Based on previous results, this student project will be based on the hypothesis that machine learning methods predict contact characteristics with high accuracy and faster than complex simulation models. Data from contact simulations will be used to train machine learning approaches, such as Artificial Neural Networks.
Prerequisites:
None.
Evaluation method: Nota 1-7, with 2/2 available vacants |
Mentor(s): Open in the plataform |
| 14-12-2021 |
Modeling of the atmospheric signal and other contaminants in cosmological data
The measurements of the cosmic microwave background radiation done from the ground suffer from atmospheric contamination, as well as other contaminants. This justifies the development of new models to identify and treat these contaminants, aiming to produce clean maps of the background signal. Our group is an active collaborator of several CMB experiments installed in Chile, contributing among other things to the analysis and reduction of raw data, including the modeling of contamination and systematic effects contained in the data. In this IPRE the student will develop computational and mathematical methods to model and extract the atmospheric signal from real raw data obtained by the ACT telescope. His/her results will be potentially implemented in the real pipeline for the production of better CMB maps.
Keywords:
telescopios
microondas
análisis de datos
computación
programación
Astronomia
radioastronomía
Atmosfera
Prerequisites:
IIC1222
Evaluation method: Nota 1-7, with 0/1 available vacants |
Mentor(s): Open in the plataform |
| 30-01-2020 |
Prerequisites:
None.
Evaluation method: Nota 1-7, with 0/3 available vacants |
Mentor(s): Open in the plataform |
| 13-11-2017 |
Keywords:
computación
complejidad comp.
Prerequisites:
None.
Evaluation method: Nota 1-7, with 0/1 available vacants |
Mentor(s): Open in the plataform |
| 13-11-2017 |
Keywords:
computación
complejidad comp.
Prerequisites:
None.
Evaluation method: Nota 1-7, with 0/1 available vacants |
Mentor(s): Open in the plataform |