Pub Date : 2022-09-07DOI: 10.1109/ARGENCON55245.2022.9939998
José Aravena, D. Carrasco, Emilio Contreras Boulet, Matías Uriarte, M. Díaz
Several off-the-shelf real-time control systems are available for industrial and academic applications. These systems enable real-time control and prototyping of power electronic applications. However, most of these systems have a considerable cost and are inflexible, limiting their teaching and academic research usage. Consequently, this paper presents the design and implementation of a control platform based on a low-cost easy-to-program microcontroller from Texas Instruments. The proposed control platform is intended for rapid-control-prototyping, and it considers optic PWM outputs, isolated sensing of voltage/currents, multipurpose input-outputs, and hardware protections. Experimental results are presented to validate the usefulness of the proposed control platform.
{"title":"Design and Implementation of an off-the-shelf Controller for Power Electronics Research and Teaching","authors":"José Aravena, D. Carrasco, Emilio Contreras Boulet, Matías Uriarte, M. Díaz","doi":"10.1109/ARGENCON55245.2022.9939998","DOIUrl":"https://doi.org/10.1109/ARGENCON55245.2022.9939998","url":null,"abstract":"Several off-the-shelf real-time control systems are available for industrial and academic applications. These systems enable real-time control and prototyping of power electronic applications. However, most of these systems have a considerable cost and are inflexible, limiting their teaching and academic research usage. Consequently, this paper presents the design and implementation of a control platform based on a low-cost easy-to-program microcontroller from Texas Instruments. The proposed control platform is intended for rapid-control-prototyping, and it considers optic PWM outputs, isolated sensing of voltage/currents, multipurpose input-outputs, and hardware protections. Experimental results are presented to validate the usefulness of the proposed control platform.","PeriodicalId":318846,"journal":{"name":"2022 IEEE Biennial Congress of Argentina (ARGENCON)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124024712","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-07DOI: 10.1109/ARGENCON55245.2022.9939959
M. Meira, Guillermo R. Bossio, J. Bossio, C. Verucchi, C. Ruschetti
Reliable detection of broken rotor bars through the analysis of sidebands around the fundamental component of the stator current at steady state is difficult when the motor operates at no-load or low load. In this work it is proposed to monitor the time evolution of the high frequency sequence components associated with broken rotor bars during the starting transient. Through simulations, the behavior of these components is analyzed for balanced and unbalanced power supply conditions, with and without harmonic distortion. The strategy proved to be independent of these conditions.
{"title":"Broken rotor bar detection using the full spectrum applied to the induction motor starting currents","authors":"M. Meira, Guillermo R. Bossio, J. Bossio, C. Verucchi, C. Ruschetti","doi":"10.1109/ARGENCON55245.2022.9939959","DOIUrl":"https://doi.org/10.1109/ARGENCON55245.2022.9939959","url":null,"abstract":"Reliable detection of broken rotor bars through the analysis of sidebands around the fundamental component of the stator current at steady state is difficult when the motor operates at no-load or low load. In this work it is proposed to monitor the time evolution of the high frequency sequence components associated with broken rotor bars during the starting transient. Through simulations, the behavior of these components is analyzed for balanced and unbalanced power supply conditions, with and without harmonic distortion. The strategy proved to be independent of these conditions.","PeriodicalId":318846,"journal":{"name":"2022 IEEE Biennial Congress of Argentina (ARGENCON)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133769051","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-07DOI: 10.1109/ARGENCON55245.2022.9939758
Carla Rodriguez Gonzalez, C. Guzman, V. Andreo
Aedes aegypti is the main vector of dengue, chikungunya and zika viruses, which together have resulted in the highest rate of disease and mortality among emerging and/or re-emerging viruses in the Americas. Vector surveillance is a key tool for prevention and control of these diseases. In this context, a proper distribution of sensors within a city will provide timely and precise information to guide public health actions. Under the assumption that environmental variability will determine different probabilities of mosquito presence and activity, our objective was to characterise the urban coverage of Córdoba city at neighbourhood and census tracts levels in order to determine an optimal distribution for the ovitrap network based on the environmental variability. To this aim we first classified very high resolution (VHR) satellite imagery following an object based (GEOBIA) approach. Then, we estimated several landscape metrics for neighbourhood and census tracts polygons and performed a k-mean clustering to determine groups of environmentally similar polygons over the city. After different tests, we defined four environmental clusters for the census tracts and three for the neighbourhoods. Finally, we distributed 150 ovitraps over the city based on the environmental groups defined and compared this distribution with the one used by the Health Ministry, a random one and, a systematic one. It was observed that the arbitrary distribution is the least environmentally representative of the city both for neighbourhoods and census tracts. Instead, the ovitrap distribution stratified by clusters at census tracts level was the best option as it properly covers the environmental variability detected over the city.
{"title":"Environmental characterisation of an urban area to assess the distribution of Aedes aegypti monitoring system","authors":"Carla Rodriguez Gonzalez, C. Guzman, V. Andreo","doi":"10.1109/ARGENCON55245.2022.9939758","DOIUrl":"https://doi.org/10.1109/ARGENCON55245.2022.9939758","url":null,"abstract":"Aedes aegypti is the main vector of dengue, chikungunya and zika viruses, which together have resulted in the highest rate of disease and mortality among emerging and/or re-emerging viruses in the Americas. Vector surveillance is a key tool for prevention and control of these diseases. In this context, a proper distribution of sensors within a city will provide timely and precise information to guide public health actions. Under the assumption that environmental variability will determine different probabilities of mosquito presence and activity, our objective was to characterise the urban coverage of Córdoba city at neighbourhood and census tracts levels in order to determine an optimal distribution for the ovitrap network based on the environmental variability. To this aim we first classified very high resolution (VHR) satellite imagery following an object based (GEOBIA) approach. Then, we estimated several landscape metrics for neighbourhood and census tracts polygons and performed a k-mean clustering to determine groups of environmentally similar polygons over the city. After different tests, we defined four environmental clusters for the census tracts and three for the neighbourhoods. Finally, we distributed 150 ovitraps over the city based on the environmental groups defined and compared this distribution with the one used by the Health Ministry, a random one and, a systematic one. It was observed that the arbitrary distribution is the least environmentally representative of the city both for neighbourhoods and census tracts. Instead, the ovitrap distribution stratified by clusters at census tracts level was the best option as it properly covers the environmental variability detected over the city.","PeriodicalId":318846,"journal":{"name":"2022 IEEE Biennial Congress of Argentina (ARGENCON)","volume":"39 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133525229","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-07DOI: 10.1109/ARGENCON55245.2022.9939770
C. Pezzani, D. Aligia, C. D. De Angelo
Los resultados que se muestran en este trabajo surgieron a partir de un proyecto realizado por un grupo de investigación para una empresa privada que proyecta fabricar una aspiradora urbana autopropulsada en Argentina. La aspiradora tendrá tres motores de inducción de baja tensión de fabricación nacional, cuyos controladores electrónicos están siendo desarrollados en el grupo de investigación. El algoritmo de control es de campo orientado sin sensor de posición. Se realizaron ensayos que permitieron identificar los parámetros del motor y a partir de los cuales se determinó que el motor trabaja en la región de saturación cuando se lo alimenta en condiciones nominales. Es conocido en la bibliografía que es posible minimizar las pérdidas de un motor de inducción mediante el control de la corriente de magnetización y en diversos trabajos se analiza cómo se debe realizar para motores que operan en la región lineal de magnetización. Sin embargo, esto no se cumple cuando el motor trabaja en la región de saturación. En este trabajo se analiza en forma experimental cómo es posible minimizar las pérdidas en el motor controlando la corriente de magnetización para distintos niveles de carga. Estos resultados permitirán en un futuro controlar a los motores de la aspiradora minimizando las pérdidas en el motor.
{"title":"Minimización de pérdidas en accionamiento eléctrico de tracción para aspiradora urbana autopropulsada","authors":"C. Pezzani, D. Aligia, C. D. De Angelo","doi":"10.1109/ARGENCON55245.2022.9939770","DOIUrl":"https://doi.org/10.1109/ARGENCON55245.2022.9939770","url":null,"abstract":"Los resultados que se muestran en este trabajo surgieron a partir de un proyecto realizado por un grupo de investigación para una empresa privada que proyecta fabricar una aspiradora urbana autopropulsada en Argentina. La aspiradora tendrá tres motores de inducción de baja tensión de fabricación nacional, cuyos controladores electrónicos están siendo desarrollados en el grupo de investigación. El algoritmo de control es de campo orientado sin sensor de posición. Se realizaron ensayos que permitieron identificar los parámetros del motor y a partir de los cuales se determinó que el motor trabaja en la región de saturación cuando se lo alimenta en condiciones nominales. Es conocido en la bibliografía que es posible minimizar las pérdidas de un motor de inducción mediante el control de la corriente de magnetización y en diversos trabajos se analiza cómo se debe realizar para motores que operan en la región lineal de magnetización. Sin embargo, esto no se cumple cuando el motor trabaja en la región de saturación. En este trabajo se analiza en forma experimental cómo es posible minimizar las pérdidas en el motor controlando la corriente de magnetización para distintos niveles de carga. Estos resultados permitirán en un futuro controlar a los motores de la aspiradora minimizando las pérdidas en el motor.","PeriodicalId":318846,"journal":{"name":"2022 IEEE Biennial Congress of Argentina (ARGENCON)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131646666","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-07DOI: 10.1109/ARGENCON55245.2022.9939974
Lucas L. Martín Fernández, Federico M. Serra, C. D. De Angelo, Eduardo Maximiliano Asensio
En este trabajo se presenta una estrategia de control para un cargador de baterías trifásico para vehículos eléctricos que se conecta al sistema eléctrico de potencia mediante un filtro LCL. La estrategia propuesta consiste en un controlador basado en energía, usando la técnica basada en pasividad, combinado con una ponderación de las corrientes circundantes en el sistema, que permite reducir el orden del mismo, mientras se asegura la estabilidad en lazo cerrado. Los objetivos de control del cargador de baterías consisten en generar un perfil de carga, controlando corriente y tensión en el lado de continua y asegurar corriente sinusoidal balanceada y en fase con la tensión de red en el lado de alterna, manteniendo su distorsión armónica dentro de limites establecidos en las normativas. La estrategia de control propuesta es validada mediante resultados de simulación.
{"title":"Control IDA-WAC para cargador de baterías de vehículos eléctricos conectado a la red con filtro LCL","authors":"Lucas L. Martín Fernández, Federico M. Serra, C. D. De Angelo, Eduardo Maximiliano Asensio","doi":"10.1109/ARGENCON55245.2022.9939974","DOIUrl":"https://doi.org/10.1109/ARGENCON55245.2022.9939974","url":null,"abstract":"En este trabajo se presenta una estrategia de control para un cargador de baterías trifásico para vehículos eléctricos que se conecta al sistema eléctrico de potencia mediante un filtro LCL. La estrategia propuesta consiste en un controlador basado en energía, usando la técnica basada en pasividad, combinado con una ponderación de las corrientes circundantes en el sistema, que permite reducir el orden del mismo, mientras se asegura la estabilidad en lazo cerrado. Los objetivos de control del cargador de baterías consisten en generar un perfil de carga, controlando corriente y tensión en el lado de continua y asegurar corriente sinusoidal balanceada y en fase con la tensión de red en el lado de alterna, manteniendo su distorsión armónica dentro de limites establecidos en las normativas. La estrategia de control propuesta es validada mediante resultados de simulación.","PeriodicalId":318846,"journal":{"name":"2022 IEEE Biennial Congress of Argentina (ARGENCON)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131737170","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-07DOI: 10.1109/ARGENCON55245.2022.9940035
Ignacio Pérez Correa, Pablo D. Giunta, J. A. Francesconi, Fernando J. Mariño
En este trabajo proponemos la utilización de una red de tipo autoencoder para procesar compuestos orgánicos codificados en formato SMILES buscando evocar representaciones significativas en el espacio latente y utilizar estas representaciones para generar modelos de predicción de propiedades. Fueron utilizados 400.000 compuestos codificados mediante SMILES para el entrenamiento del autoencoder, dónde se encontró que una dimensión latente de 25 elementos logra reconstruir los datos adecuadamente. A partir de esto, se desarrollaron modelos de predicción para las 8 propiedades termodinámicas de interés (presión crítica, temperatura crítica, volumen crítico, temperatura de fusión, temperatura de ebullición y las entalpías de vaporización, fusión y formación). Para la regresión se utilizaron 1079 sustancias cuya capacidad de predicción también fue contrastada con el modelo de Joback y Reid, referencia en predicción de propiedades. El modelo propuesto presenta errores del 1% al 6% para las distintas propiedades (exceptuando el punto de fusión) que mejoran notablemente respecto del modelo de referencia que posee valores en el entorno de (3-9) % para las mismas propiedades. Respecto del punto de fusión, se observa que ambos modelos tienen dificultades en la estimación y que podría sugerir que se requieren otros indicadores para representar este fenómeno.
{"title":"Representación estructurada de compuestos orgánicos basada en autoencoders","authors":"Ignacio Pérez Correa, Pablo D. Giunta, J. A. Francesconi, Fernando J. Mariño","doi":"10.1109/ARGENCON55245.2022.9940035","DOIUrl":"https://doi.org/10.1109/ARGENCON55245.2022.9940035","url":null,"abstract":"En este trabajo proponemos la utilización de una red de tipo autoencoder para procesar compuestos orgánicos codificados en formato SMILES buscando evocar representaciones significativas en el espacio latente y utilizar estas representaciones para generar modelos de predicción de propiedades. Fueron utilizados 400.000 compuestos codificados mediante SMILES para el entrenamiento del autoencoder, dónde se encontró que una dimensión latente de 25 elementos logra reconstruir los datos adecuadamente. A partir de esto, se desarrollaron modelos de predicción para las 8 propiedades termodinámicas de interés (presión crítica, temperatura crítica, volumen crítico, temperatura de fusión, temperatura de ebullición y las entalpías de vaporización, fusión y formación). Para la regresión se utilizaron 1079 sustancias cuya capacidad de predicción también fue contrastada con el modelo de Joback y Reid, referencia en predicción de propiedades. El modelo propuesto presenta errores del 1% al 6% para las distintas propiedades (exceptuando el punto de fusión) que mejoran notablemente respecto del modelo de referencia que posee valores en el entorno de (3-9) % para las mismas propiedades. Respecto del punto de fusión, se observa que ambos modelos tienen dificultades en la estimación y que podría sugerir que se requieren otros indicadores para representar este fenómeno.","PeriodicalId":318846,"journal":{"name":"2022 IEEE Biennial Congress of Argentina (ARGENCON)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132145343","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-07DOI: 10.1109/ARGENCON55245.2022.9976397
M. G. Adán Faramiñán, Cristian Laino, Facundo Carmona, M. Holzman, R. Rivas
An important issue for agricultural planning is to estimate evapotranspiration accurately due to its fundamental role in sustainable use of water resources. It is essential to have reliable and precise evapotranspiration (ET) measurements to improve models or products. This work aims to evaluate a generalized linear model (GLM) in order to estimate actual evapotranspiration of barley crop with satellite (Landsat, Sentinel, and CERES) and reanalysis (MERRA-2) data. The results obtained were compared with water balance values from an agrometeorological station. The GLM with the combination of MERRA-2/CERES/Sentinel 2 as input was the best performance (R2 = 0.59). The results show the feasibility of applying machine learning algorithms for obtaining actual evapotranspiration values in agricultural plains without ground agro-meteorological data.
{"title":"Evaluation of a generalized linear model for the actual evapotranspiration using satellite and reanalysis data","authors":"M. G. Adán Faramiñán, Cristian Laino, Facundo Carmona, M. Holzman, R. Rivas","doi":"10.1109/ARGENCON55245.2022.9976397","DOIUrl":"https://doi.org/10.1109/ARGENCON55245.2022.9976397","url":null,"abstract":"An important issue for agricultural planning is to estimate evapotranspiration accurately due to its fundamental role in sustainable use of water resources. It is essential to have reliable and precise evapotranspiration (ET) measurements to improve models or products. This work aims to evaluate a generalized linear model (GLM) in order to estimate actual evapotranspiration of barley crop with satellite (Landsat, Sentinel, and CERES) and reanalysis (MERRA-2) data. The results obtained were compared with water balance values from an agrometeorological station. The GLM with the combination of MERRA-2/CERES/Sentinel 2 as input was the best performance (R2 = 0.59). The results show the feasibility of applying machine learning algorithms for obtaining actual evapotranspiration values in agricultural plains without ground agro-meteorological data.","PeriodicalId":318846,"journal":{"name":"2022 IEEE Biennial Congress of Argentina (ARGENCON)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133362525","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-07DOI: 10.1109/ARGENCON55245.2022.9976398
L. Cymberknop, Nicolas A. Aguirre, Eugenia Ipar, R. Armentano
Coronary Artery Calcium (CAC) constitutes a highly specific feature of ‘coronary’ atherosclerosis. The aim of this study is to explore the combination of arterial biomechanical parameters, used for general atherosclerosis evaluation, in CAC score assessment, stratified by year of age. Three hundred and fifty individuals participated in the study, with no history of cardiovascular disease. CAC score jointly with ascending aortic diameter (AAD) were determined through multislice computer tomography. Carotid intima-media thickness (cIMT) and presence of carotid and femoral plaques (PAB) were also assessed using B-mode ultrasound. Aortic stiffness was calculated by means of Pulse Wave Velocity (aPWV). Data were grouped by age, thus becoming a stratification factor. Univariate and multiple linear regression (MLR) analysis were applied for CAC score quantification. Univariate analysis evidenced a linear association between log-transformed levels of CACs stratified by age (LCACs) and aPWV (R2=0.43, P<0.05), cIMT (R2=0.52, P<0.05), AAD (R2=0.53, P<0.05), PAB (R2=0.46, P<0.05) and SBP (R2=0.10, P<0.05). An adjusted determination coefficient (adj. R2) of 0.89 was obtained for MLR, where AAD, cIMT, PAB, SBP and BMI were significantly correlated with LCACs (P<0.05). This analysis provides a holistic description in terms of the contribution of atherosclerosis/arteriosclerosis markers (such as cIMT and aortic diameters) that may suggest the existence of increased levels of age-stratified CAC.
{"title":"Age-Stratified Coronary Artery Calcium Levels Quantification Based on Arterial Biomechanical Parameters*","authors":"L. Cymberknop, Nicolas A. Aguirre, Eugenia Ipar, R. Armentano","doi":"10.1109/ARGENCON55245.2022.9976398","DOIUrl":"https://doi.org/10.1109/ARGENCON55245.2022.9976398","url":null,"abstract":"Coronary Artery Calcium (CAC) constitutes a highly specific feature of ‘coronary’ atherosclerosis. The aim of this study is to explore the combination of arterial biomechanical parameters, used for general atherosclerosis evaluation, in CAC score assessment, stratified by year of age. Three hundred and fifty individuals participated in the study, with no history of cardiovascular disease. CAC score jointly with ascending aortic diameter (AAD) were determined through multislice computer tomography. Carotid intima-media thickness (cIMT) and presence of carotid and femoral plaques (PAB) were also assessed using B-mode ultrasound. Aortic stiffness was calculated by means of Pulse Wave Velocity (aPWV). Data were grouped by age, thus becoming a stratification factor. Univariate and multiple linear regression (MLR) analysis were applied for CAC score quantification. Univariate analysis evidenced a linear association between log-transformed levels of CACs stratified by age (LCACs) and aPWV (R2=0.43, P<0.05), cIMT (R2=0.52, P<0.05), AAD (R2=0.53, P<0.05), PAB (R2=0.46, P<0.05) and SBP (R2=0.10, P<0.05). An adjusted determination coefficient (adj. R2) of 0.89 was obtained for MLR, where AAD, cIMT, PAB, SBP and BMI were significantly correlated with LCACs (P<0.05). This analysis provides a holistic description in terms of the contribution of atherosclerosis/arteriosclerosis markers (such as cIMT and aortic diameters) that may suggest the existence of increased levels of age-stratified CAC.","PeriodicalId":318846,"journal":{"name":"2022 IEEE Biennial Congress of Argentina (ARGENCON)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131943841","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-07DOI: 10.1109/ARGENCON55245.2022.9940083
A. Montenegro, M. Holzman, D. Fernández, Lucia Mañueco, Maira Guiñazu
The Irrigation and Drainage Consortium of Villa Regina, Río Negro is part of a vast, irrigated valley. Its main production is pears and apple crops. Throughout the years, water and drainage problems have been detected due to a water table raise. Studying the zone extensively becomes crucial in order to understand the groundwater and surface water sources interaction and remote sensing information may enable the analysis and understanding of the hydrological behavior of the basin. The aim of this study is to detect variations in the surface water area in the Río Negro in years with contrasting hydrological conditions by using spectral indexes and relate them to water table levels. Sentinel 2 images were used in order to analyze the surface water area. Spectral indexes NDWI and MNDWI were calculated for periods of different flows: 318.66 m3/s (August 2017) y 1157.18 m3/s (August 2018). Unconfined aquifer piezometers near to the river were selected to elaborate piezometric graphs and calculate water table average elevation. The NDWI and the MNDWI indexes were consistent with the river flood in 2018, showing an increase of the water covered area of 420,000 m2 with regard to 2017. The analysis of piezometric graphs during the specific period showed an average elevation of the water table level of 0.7 m. These results suggest the interaction between the river flood and the water table in the studied area. It is possible to conclude that the use of geographical information can contribute to analyze and understand this interaction and can be used as a complement to design proper integrated water management programs for the Alto Valle of Rio Negro and Neuquén.
{"title":"Detección de agua en superficie en el río Negro con índices espectrales y análisis del impacto sobre el acuífero freático","authors":"A. Montenegro, M. Holzman, D. Fernández, Lucia Mañueco, Maira Guiñazu","doi":"10.1109/ARGENCON55245.2022.9940083","DOIUrl":"https://doi.org/10.1109/ARGENCON55245.2022.9940083","url":null,"abstract":"The Irrigation and Drainage Consortium of Villa Regina, Río Negro is part of a vast, irrigated valley. Its main production is pears and apple crops. Throughout the years, water and drainage problems have been detected due to a water table raise. Studying the zone extensively becomes crucial in order to understand the groundwater and surface water sources interaction and remote sensing information may enable the analysis and understanding of the hydrological behavior of the basin. The aim of this study is to detect variations in the surface water area in the Río Negro in years with contrasting hydrological conditions by using spectral indexes and relate them to water table levels. Sentinel 2 images were used in order to analyze the surface water area. Spectral indexes NDWI and MNDWI were calculated for periods of different flows: 318.66 m3/s (August 2017) y 1157.18 m3/s (August 2018). Unconfined aquifer piezometers near to the river were selected to elaborate piezometric graphs and calculate water table average elevation. The NDWI and the MNDWI indexes were consistent with the river flood in 2018, showing an increase of the water covered area of 420,000 m2 with regard to 2017. The analysis of piezometric graphs during the specific period showed an average elevation of the water table level of 0.7 m. These results suggest the interaction between the river flood and the water table in the studied area. It is possible to conclude that the use of geographical information can contribute to analyze and understand this interaction and can be used as a complement to design proper integrated water management programs for the Alto Valle of Rio Negro and Neuquén.","PeriodicalId":318846,"journal":{"name":"2022 IEEE Biennial Congress of Argentina (ARGENCON)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122927649","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-07DOI: 10.1109/ARGENCON55245.2022.9940020
Carlos I. Sanseverinatti, Mariano M. Perdomo, Luis A. Clementi, J. R. Vega
En el presente trabajo se implementó un módulo para la detección de fallas en sensores de registro de variables en procesos continuos, el cual se desarrolló sobre la base de una máquina de soporte vectorial. Con el fin de obtener una arquitectura adecuada de la máquina, se estudió el desempeño del módulo para diversas implementaciones obtenidas a partir de diferentes técnicas de codificación múltiple y maquinas Kernel. En particular, se analizó el desempeño de las máquinas de soporte implementadas en términos de su capacidad para detectar y clasificar fallas típicas en sensores de procesos continuos. Para cada máquina implementada, se escogió el tamaño del conjunto de entrenamiento y los valores de los hiperparámetros correspondientes a cada una a partir de una búsqueda de tipo rejilla. Los resultados mostraron que el mejor desempeño en términos de exactitud en el testeo se obtuvo para una codificación de tipo One Vs Rest, utilizando un Kernel de tipo función de base radial, para la cual se alcanzó una exactitud superior al 98%.
{"title":"Máquina de Soporte Vectorial para la Detección y Clasificación de Fallas en Sensores de Registro de Datos en Procesos Continuos","authors":"Carlos I. Sanseverinatti, Mariano M. Perdomo, Luis A. Clementi, J. R. Vega","doi":"10.1109/ARGENCON55245.2022.9940020","DOIUrl":"https://doi.org/10.1109/ARGENCON55245.2022.9940020","url":null,"abstract":"En el presente trabajo se implementó un módulo para la detección de fallas en sensores de registro de variables en procesos continuos, el cual se desarrolló sobre la base de una máquina de soporte vectorial. Con el fin de obtener una arquitectura adecuada de la máquina, se estudió el desempeño del módulo para diversas implementaciones obtenidas a partir de diferentes técnicas de codificación múltiple y maquinas Kernel. En particular, se analizó el desempeño de las máquinas de soporte implementadas en términos de su capacidad para detectar y clasificar fallas típicas en sensores de procesos continuos. Para cada máquina implementada, se escogió el tamaño del conjunto de entrenamiento y los valores de los hiperparámetros correspondientes a cada una a partir de una búsqueda de tipo rejilla. Los resultados mostraron que el mejor desempeño en términos de exactitud en el testeo se obtuvo para una codificación de tipo One Vs Rest, utilizando un Kernel de tipo función de base radial, para la cual se alcanzó una exactitud superior al 98%.","PeriodicalId":318846,"journal":{"name":"2022 IEEE Biennial Congress of Argentina (ARGENCON)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127751127","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：