Open AccessArduino data-logger and artificial neural network to data analysis
Author(s) -
Ghiordy Ferney Contreras Contreras,
Héctor Jaime Dulce-Moreno,
Rodrigo A. Melo
Publication year - 2019
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1386/1/012070
Subject(s) - data logger , arduino , artificial neural network , computer science , software , anemometer , work (physics) , process (computing) , electric potential energy , energy consumption , simulation , energy (signal processing) , real time computing , automotive engineering , electrical engineering , artificial intelligence , statistics , meteorology , engineering , embedded system , mechanical engineering , mathematics , operating system , geography , wind speed
This work takes thermodynamic modelling through computer science for incubation process at domestic birds, that has presented energy consumption significantly high than energy used in processes. Thus, a data analysis was applied upon variables of temperature and relative humidity for heating zones, trying to know how much energy supplied by source was used, as well as, voltage and current variables are measured in the same moment that temperature and relative humidity are acquired. Then, data analysis was done using artificial neural networks models with samples obtained from sensors, where real process is highly time- variant, fixing environment conditions at the moment required. Therefore, with this system has been obtained an air flow of 3.4375 10 −2 m 3 /J using a anemometer respect to electrical energy supplied by fans, giving 9.4818 W of average power using ceramics resistances, and testing an adaptive controller where its variables are fitted using equations obtained from data analysis. In contrast, colombian farmers have decreased economic conditions to maintain them productions due to free trade agreements implemented lastly, indeed this system was developed using open- source software and hardware to avoid costs in acquisition by licensing politicians or periodic subscription to a specific product developed by companies.