Greenhouse cultivation has gained a special importance in recent years and become the basis of the economy in south-eastern Spain. The structures used are light and, due to weather events, often collapse completely or partially, which has generated interest in the study of these unique buildings. This study presents a load and displacement monitoring system that was designed, and full scale tested, in an Almería-type greenhouse with a tensioned wire structure. The loads and displacements measured under real load conditions were recorded for multiple time periods. The traction force on the roof cables decreased up to 22% for a temperature increase of 30 °C, and the compression force decreased up to 16.1% on the columns or pillars for a temperature and wind speed increase of 25.8 °C and 1.9 m/s respectively. The results show that the structure is susceptible to daily temperature changes and, to a lesser extent, wind throughout the test. The monitoring system, which uses load cells to measure loads and machine vision techniques to measure displacements, is appropriate for use in different types of greenhouses.

No abstract

No abstract

No abstract

The paper presents a technique to partition and sort data in a large training set for building models of environmental function approximation using RBFs networks. This process allows us to make very accurate approximations of the functions in a time fraction related to the RBF networks classic training proccess. Furthermore, this technique avoids problems of buffer overflow in the training algorithm execution. The results obtained proved similar accuracy to those obtained with a classical model in a time substantially less, opening, on the other hand, the way to the parallelization process using GPUs technology.