Artículo
Permanent URI for this collectionhttps://hdl.handle.net/11285/345284
Artículo científico o editorial en una publicación periódica académica sujeto a revisión de pares. Cumple con los índices internacionales o bases de datos de amplia cobertura, como el listado del Current Contents, ISI WEB of Knowledge (http://isiknowledge.com/) e índice de revistas mexicanas de CONACYT (www.conacyt.mx/dac/revistas). Éstos indizan y resumen los artículos de revistas seleccionadas, en todas las áreas del saber.
Browse
Search Results
- Comparative multi-objective optimization using neural networks for ejector refrigeration systems with LiBr and LiCl working agents(Science Direct, 2024-08) Khanmohammadi, Shoaib; Ahmadi, Pouria; Jahangiri, Ali; Izadi, Ali; Tariq, Rasikh; https://ror.org/05hkxne09; https://ror.org/05hkxne09; https://ror.org/05vf56z40; https://ror.org/0091vmj44; https://ror.org/03ayjn504Education's evolution in the context of energy systems is essential for addressing sustainable energy challenges and developing a workforce equipped for future innovations, emphasizing both formal curricula and informal lifelong learning through successful energy case studies. As the global energy sector transforms to reduce carbon emissions and reliance on fossil fuels, innovations in renewable technologies like solar thermal are pivotal for promoting energy security and economic stability, supported by an educational foundation that fosters awareness and technical skills for sustainable development. Exposure to successful renewable energy systems, such as solar-powered refrigeration, offers an informal educational experience that enhances understanding and supports global educational goals, initiating with the innovative design and optimization of these systems using artificial intelligence (neural networks). Based on this formulation, the current article developed two sustainable energy systems by comparing the refrigeration cycles with two different operating fluids and various arrangements, and multi-objective optimization with an evolutionary genetic algorithm is performed for the proposed systems. The studied systems are refrigeration cycles using an ejector and without an ejector with two working fluids of lithium bromide and lithium chloride. The present work's main aim is to examine the working fluid and refrigeration system arrangements. Energy and economic modeling were performed for the proposed systems, and then parametric analysis and two-objective optimization were extracted. Parameters such as generator temperature, condenser temperature, absorber temperature, and evaporator temperature, which significantly impact the proposed system's performance, have been selected as decision parameters, and parametric analysis has been extracted for them. In addition to the mentioned parameters, diffusion mixing efficiency, nozzle efficiency, and heat exchanger have also been studied in the ejector asset system. To find the best values of decision variables, multi-objective optimization for both arrangements is conducted, and results are presented. The results have indicated that the refrigeration system using lithium chloride working fluid without an ejector achieves a coefficient of performance of 0.766 and a cost of 0.922 $/h at the optimal point, while the system with an ejector yields a higher coefficient of performance (1.047) and a slightly lower cost rate (0.991 $/h). The outcomes of this work can play a critical role for higher education institutions in advancing innovative solutions to pressing energy challenges. Lifelong learning, at the heart of educational innovation, can benefit from the integration of sustainable energy systems as a core component of informal education through the optimization of ejector refrigeration systems.
- Predicting open education competency level: A machine learning approach(Science Direct, 2023-11) Ibarra Vázquez, Gerardo; Ramírez Montoya, María Soledad; Buenestado Fernández, Mariana; Olague, Gustavo; https://ror.org/03ayjn504; https://ror.org/046ffzj20; https://ror.org/04znhwb73This article aims to study open education competency data through machine learning models to determine whether models can be built on decision rules using the features from the students' perceptions and classify them by the level of competency. Data was collected from a convenience sample of 326 students from 26 countries using the eOpen instrument. Based on a quantitative research approach, we analyzed the eOpen data using two machine learning models considering these findings: 1) derivation of decision rules from students' perceptions of knowledge, skills, and attitudes or values related to open education to predict their competence level using Decision Trees and Random Forests models, 2) analysis of the prediction errors in the machine learning models to find bias, and 3) description of decision trees from the machine learning models to understand the choices that both models made to predict the competency levels. The results confirmed our hypothesis that the students' perceptions of their knowledge, skills, and attitudes or values related to open education and its sub-competencies produced satisfactory data for building machine learning models to predict the participants' competency levels.