An adaptive neuro-fuzzy inference system (ANFIS) was implemented to evaluate different combinations of nozzle flow rates and boom heights in terms of liquid pesticide distribution uniformity from a ground field sprayer. In addition, the ANFIS was utilized to determine the optimum combination of the two principal factors (boom height and nozzle flow rate) that would result in the best distribution uniformity. In ANFIS, the two principal factors were selected as inputs, however, the Coefficient of Distribution Uniformity (CDU) was considered as the system output. For the tested set of data, the ANFIS analysis designated a boom height of 60 cm and a nozzle flow rate of 118 L/h as the optimum combination with a CDU value of 65.7%. Results of the study showed that the ANFIS technique was effective in evaluating and classifying the different possible combinations of the involved principal factors for best distribution uniformity. Moreover, results revealed that the utilized ANFIS was accurate in predicting the CDU. The R2 values for the relationship between calculated CDU and ANFIS predicted CDU were 0.992 and 0.988 for the training and testing stages, respectively.
Key words: Pesticides, nozzle flow rate, boom height, ground field sprayer, adaptive neuro-fuzzy inference system, coefficient of distribution uniformity.
Copyright © 2022 Author(s) retain the copyright of this article.
This article is published under the terms of the Creative Commons Attribution License 4.0