Rafael Batres | Tecnológico de Monterrey (original) (raw)

Papers by Rafael Batres

Lecture Notes in Computer Science, 2011

Tokai Shibu Sokai Koenkai koen ronbunshu, 2011

Tokai Shibu Sokai Koenkai koen ronbunshu, 2011

Ingeniería Investigación y Tecnología, Oct 1, 2016

Journal of Japan Institute of Light Metals, 2014

Journal of Industrial Ecology, Jul 1, 2005

The need for more efficient online learning strategies surged due to the global pandemic, providi... more The need for more efficient online learning strategies surged due to the global pandemic, providing opportunities to use global classrooms such as the COIL (Collaborative Online International Learning) model. COIL facilitates faculty members' interactions at two different universities in different countries and creates virtual learning communities. Additionally, besides the pandemic, the advent of Industry 4.0 confronts graduates with the need to develop competencies in Machine Learning (ML), which are applied to resolve many industrial problems requiring prediction and classification and the availability and management of large amounts of data. This paper describes a global classroom in ML designed and implemented by professors at Tecnologico de Monterrey (Tec) in Mexico and the University of Applied Sciences Würzburg-Schweinfurt (FHWS) in Germany11The collaboration was funded by the German Academic Exchange Service (DAAD). The global classroom's goal was to implement a joint international experience to develop machine learning competencies among students working in teams to resolve real problems with data-driven methods using an online digital platform called Remote Virtual Lab 4.0 (vLab).

Computer-aided chemical engineering, 2002

Systems and Soft Computing

Advances in intelligent systems and computing, Aug 15, 2020

Representation of knowledge used by E-learning systems to modulate learning processes plays a key... more Representation of knowledge used by E-learning systems to modulate learning processes plays a key role in its effectiveness. In ill-defined domains where training is carried out using an apprenticeship model such as the area of Technical and Vocational Education and Training, building a Knowledge Model is not straightforward. In such areas the knowledge model heavily depends on the journeyman tacit expertise which is spread across text documents such as manuals, books, reports, competency descriptions, among others. Hence, in this work it is proposed to employ Learning Analytics for building a Knowledge Model from text documents used in lineworkers vocational education. The model is organized by declarative, procedural, and competency layers. Each of these contains a semantic networked built from extracted concepts, and the semantic relations between concepts is obtained using the Normalized Web Distance. Initial results shows that building knowledge models for ill-defined domains is promising, although more experimentation is required.

Nowadays, liberalized energy markets give priority to power generation using renewable energy sou... more Nowadays, liberalized energy markets give priority to power generation using renewable energy sources (RES) to minimize environmental impact and promote competitiveness. Demand changes and the variability caused by RES are two obstacles in achieving a stable electricity generation. In this context, operational strategies are the key to achieve a more stable and balanced energy generation. Such operational strategies are characterized by operation profiles which show valve operations that takes the plant from an initial state to a final state by means of a series of state variables transitions. Some work has been published in the literature that focuses on the coupling of simulation and optimization. However, this approach involves many iterations, demanding significant computation time. In this paper, a machine-learning approach is proposed that can be used to replace the rigorous simulation model with a surrogate model, which is obtained in short period of time and reduces dramatically the simulation time. The proposed approach has been initially tested in a case study that focuses on the generation of operation profiles of a hydraulic system composed of three interconnected tanks whose level changes are achieved by control valve manipulations and its operation is analogous to some power-plant components (e.g. drum boiler) in terms of valve manipulations.

International Journal of Smart Grid and Clean Energy, 2020

In competitive energy markets, the growing adoption of renewable energy sources such as wind ener... more In competitive energy markets, the growing adoption of renewable energy sources such as wind energy and photovoltaics causes power grid fluctuations due to the intermittency and variability in their power output. To balance the demand and generation by renewable sources conventional thermal power plants must operate with greater flexibility in the way they increase or decrease output. Furthermore, for a conventional plant to be competitive in the new energy market, it requires a balance between ramp rate and life consumption of the power-plant equipment. This paper proposes an approach to support the design of optimal operating profiles that minimize the ramp rate and maximizes the lifetime of critical equipment of conventional thermal power plants. The output of the methodology is the sequence of valve operations that achieve the operating profile.

International Journal of Smart Grid and Clean Energy, 2020

International Journal of Energy Research, 2020

Lecture Notes in Computer Science, 2011

Tokai Shibu Sokai Koenkai koen ronbunshu, 2011

Tokai Shibu Sokai Koenkai koen ronbunshu, 2011

Ingeniería Investigación y Tecnología, Oct 1, 2016

Journal of Japan Institute of Light Metals, 2014

Journal of Industrial Ecology, Jul 1, 2005

The need for more efficient online learning strategies surged due to the global pandemic, providi... more The need for more efficient online learning strategies surged due to the global pandemic, providing opportunities to use global classrooms such as the COIL (Collaborative Online International Learning) model. COIL facilitates faculty members' interactions at two different universities in different countries and creates virtual learning communities. Additionally, besides the pandemic, the advent of Industry 4.0 confronts graduates with the need to develop competencies in Machine Learning (ML), which are applied to resolve many industrial problems requiring prediction and classification and the availability and management of large amounts of data. This paper describes a global classroom in ML designed and implemented by professors at Tecnologico de Monterrey (Tec) in Mexico and the University of Applied Sciences Würzburg-Schweinfurt (FHWS) in Germany11The collaboration was funded by the German Academic Exchange Service (DAAD). The global classroom's goal was to implement a joint international experience to develop machine learning competencies among students working in teams to resolve real problems with data-driven methods using an online digital platform called Remote Virtual Lab 4.0 (vLab).

Computer-aided chemical engineering, 2002

Systems and Soft Computing

Advances in intelligent systems and computing, Aug 15, 2020

Representation of knowledge used by E-learning systems to modulate learning processes plays a key... more Representation of knowledge used by E-learning systems to modulate learning processes plays a key role in its effectiveness. In ill-defined domains where training is carried out using an apprenticeship model such as the area of Technical and Vocational Education and Training, building a Knowledge Model is not straightforward. In such areas the knowledge model heavily depends on the journeyman tacit expertise which is spread across text documents such as manuals, books, reports, competency descriptions, among others. Hence, in this work it is proposed to employ Learning Analytics for building a Knowledge Model from text documents used in lineworkers vocational education. The model is organized by declarative, procedural, and competency layers. Each of these contains a semantic networked built from extracted concepts, and the semantic relations between concepts is obtained using the Normalized Web Distance. Initial results shows that building knowledge models for ill-defined domains is promising, although more experimentation is required.

Nowadays, liberalized energy markets give priority to power generation using renewable energy sou... more Nowadays, liberalized energy markets give priority to power generation using renewable energy sources (RES) to minimize environmental impact and promote competitiveness. Demand changes and the variability caused by RES are two obstacles in achieving a stable electricity generation. In this context, operational strategies are the key to achieve a more stable and balanced energy generation. Such operational strategies are characterized by operation profiles which show valve operations that takes the plant from an initial state to a final state by means of a series of state variables transitions. Some work has been published in the literature that focuses on the coupling of simulation and optimization. However, this approach involves many iterations, demanding significant computation time. In this paper, a machine-learning approach is proposed that can be used to replace the rigorous simulation model with a surrogate model, which is obtained in short period of time and reduces dramatically the simulation time. The proposed approach has been initially tested in a case study that focuses on the generation of operation profiles of a hydraulic system composed of three interconnected tanks whose level changes are achieved by control valve manipulations and its operation is analogous to some power-plant components (e.g. drum boiler) in terms of valve manipulations.

International Journal of Smart Grid and Clean Energy, 2020

In competitive energy markets, the growing adoption of renewable energy sources such as wind ener... more In competitive energy markets, the growing adoption of renewable energy sources such as wind energy and photovoltaics causes power grid fluctuations due to the intermittency and variability in their power output. To balance the demand and generation by renewable sources conventional thermal power plants must operate with greater flexibility in the way they increase or decrease output. Furthermore, for a conventional plant to be competitive in the new energy market, it requires a balance between ramp rate and life consumption of the power-plant equipment. This paper proposes an approach to support the design of optimal operating profiles that minimize the ramp rate and maximizes the lifetime of critical equipment of conventional thermal power plants. The output of the methodology is the sequence of valve operations that achieve the operating profile.

International Journal of Smart Grid and Clean Energy, 2020

International Journal of Energy Research, 2020