02168naa a2200253 a 450000100080000000500110000800800410001902200140006002400510007410000240012524501270014926000090027652013250028565300220161065300260163265300220165865300270168065300400170765300230174770000200177070000200179070000200181077300840183020782112018-07-18       2017    bl uuuu     u00u1 u    #d  a1793-351X7 ahttps://doi.org/10.1142/S1793351X174001042DOI1 aPEÑALOZA, E. A. G.  aA model approach to infer the quality in agricultural sprayers supported by knowledge bases and experimental measurements.  c2017  aThis paper presents a method to infer the quality of sprayers based on data collection of the drop spectra and their physical descriptors, which are used to generate a knowledge base to support decision-making in agriculture. The knowledge base is formed by collected experimental data, obtained in a controlled environment under specific operating conditions, and the semantics used in the spraying process to infer the quality in the application. The electro-hydraulic operating conditions of the sprayer system, which include speed and flow measurements, are used to define experimental tests, perform calibration of the spray booms and select the nozzle types. Using the Grubbs test and the quartile-quartile plot an exploratory analysis of the collected data was made in order to determine the data consistency, the deviation of atypical values, the independence between the data of each test, the repeatability and the normal representation of them. Therefore, integrating measurements to a knowledge base it was possible to improve the decision-making in relation to the quality of the spraying process defined in terms of a distribution function. Results shown that the use of advanced models and semantic interpretation improved the decision-making processes related to the quality of the agricultural sprayers.  aAdvanced modeling  aAgricultural sprayers  aAverage diameters  aDrop size distribution  aQuality of agricultural application  aSemantic computing1 aCRUVINEL, P. E.1 aOLIVEIRA, V. A.1 aCOSTA, A. G. F.  tIn: International Journal of Semantic Computinggv. 11, n. 3, p. 279-292, 2017.