
handle: 10882/13797
Se desarrolla una red neuronal en Tensor Flow para la selección de métodos de recobro mejorado mediante microorganismos MEOR entre tres categorías CMR (Cyclic Microbial Recovery), MFR (Microbial Flooding Recovery) y MSFR (Microbial Selective Plugging Recovery). La red neuronal propuesta fue entrenada a partir de 45 datos de casos de éxito de aplicación de estos métodos disponibles en la literatura. El modelo brindó una precisión esperada de 67.5%, que al ser puesta a prueba clasificó correctamente el 73% de los datos. Los datos de entrada definidos para el análisis fueron el tipo de formación geológica, la profundidad del yacimiento, la permeabilidad efectiva, la temperatura, la gravedad API, la viscosidad y la porosidad.
A neural network is developed in Tensor Flow for the selection of enhanced recovery methods using MEOR microorganisms among three categories CMR (Cyclic Microbial Recovery), MFR (Microbial Flooding Recovery) and MSFR (Microbial Selective Plugging Recovery). The proposed neural network was trained from 45 case data of successful application of these methods available in the literature. The model provided an expected accuracy of 67.5%, which when tested correctly classified 73% of the data. The input data defined for the analysis were geological formation type, reservoir depth, effective permeability, temperature, API gravity, viscosity and porosity.
Ingeniero de Sistemas
Pregrado
Microorganismos, Neuronal, Recobro, Hidrocarburos, Microorganisms, Network, Mejoramiento de procesos, Red, Redes neuronales (Computadores), Hydrocarbons, Inteligencia artificial, Recovery, Neural
Microorganismos, Neuronal, Recobro, Hidrocarburos, Microorganisms, Network, Mejoramiento de procesos, Red, Redes neuronales (Computadores), Hydrocarbons, Inteligencia artificial, Recovery, Neural
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
