This paper addresses the problem of developing a system to monitor the behavior of solar modules using a CAN network. It is desired to measure current, voltage, and temperature under different operating conditions of a photovoltaic installation, in order to obtain the necessary information to later use it to determine its energy efficiency. In this work, current, voltage and temperature data are transmitted over a CAN network based on devices from the Microchip® family of microcontrollers. The network design is made up of slave nodes in charge of carrying out data acquisition and leading them to a CAN Central master node. This master node receives them, oversees timing tasks and connects via serial port to a personal computer. The programming environment used is MikroC® for dsPIC®. The process of sending the data can be observed through the MikroC® USART terminal, these are saved in a .txt file for later analysis with a scientific software. Experimental tests carried out with a group of commercial panels are reported under two operating conditions: short circuit and open circuit. The graphs are shown, and to validate the information provided by the acquired data, the relationships between the monitored variables are verified considering the knowledge obtained from the literature.

Over time, the CAN (Controller Area Network) communication bus has been implemented in different technological sectors, within which, depending on the application, the bus implementation may change. On the other hand, the design and implementation of digital controls based on experimental data is a well-known topic in the automation industry where the acquisition system is of great importance. In this document, a heuristic study of the behavior of a Full CAN network is reported to implement digital controllers in two interconnected control loops. This study takes into account the access time to the bus and the amount of data sent when observing the response to disturbances. The design of two digital controllers is presented based on the parametric identification of two plants: a DC motor with an electromagnetic brake and a pneumatic levitator. Using PSoC® microcontrollers, a Full CAN network is implemented, where the digital controllers exchange data by randomly accessing the bus. A specially designed interface allows visualizing the speed and amount of data transferred under different operating conditions of the control loops. At the document end, the experimental data obtained are discussed.

This project describes the design process of an artificial neural network model to predict the risk of dropping out of engineering students throughout their socioeconomic, academic, and personal data sing CRISP-DM methodology. The neural network used in the project considers backpropagation functionality with one hidden layer on data from a context questionnaire and academic data from the students in its CENEVAL’s entrance exam and their academic status after one year in the institution. The data used to train the neural network it’s from 781 records of the last four generations of freshmen year students at the Technological Institute of Motul organized in 48 attributes out of the almost 120 included in the original instrument. The result is a predictive model with a significance level of 75.42% and an F index of 0.6027. This model will be included in the comprehensive tutoring system that is been develop within the organization to monitor the student’s academic performance.