This study aimed to develop artificial neural networks for the estimation of tractor fuel consumption during soil preparation, according to the adopted system. The multilayer perceptron network was chosen. As input data: the soil mechanical penetration resistance, the mobilized area by implements, the working gear and the tractor engine speed. The number of layers and neurons varied to form different architectures. The adjustment was verified based on various statistical criteria. The values estimated by the networks did not differ significantly from those obtained experimentally. The conclusion was that the networks showed adequate reliability and accuracy to predicting the fuel consumption in each tillage system, in function of the input data and this can be a useful tool for planning and management of agricultural operations.
RESUMOEste trabalho teve como objetivo avaliar a resistência do solo a penetração, por meio de um penetrógrafo eletrônico de velocidade constante, em dois solos: Latossolo Vermelho distrófico Típico, textura argilosa e Latossolo Vermelho Amarelo distrófico Típico, textura média, submetidos aos processos de mecanização e transporte na cultura de cana-de-açú-car, em função de diferentes números de corte e diferentes profundidades de trabalho. Os dados foram analisados estatisticamente sob dois formatos: (a) pela estatística convencional, comparando-se as médias dos tratamentos pelo teste de Tukey a 5% de probabilidade e (b) pela geoestatística, utilizando-se a semivariância para produzir modelos que representassem dependência espacial dos dados. Os resultados de resistência do solo a penetração, mostraram-se diferenciados nas profundidades estudadas, indicando que o peso dos veículos e máquinas e a pressão dos rodados provocaram alterações no perfil do solo. Palavras-chave: compactação do solo, mecanização, geoestatísticaUse of an electronic penetrometer to evaluate resistance of a soil cultivated with sugarcane 1 ABSTRACTThis work aimed to evaluate soil resistance to penetration by means of a constant-speed electronic penetrograph, in two soils: a clay-textured Rhodic Haplustox and a loamy-textured Typic Haplustox, under mechanization and transportation processes in a sugarcane crop as a function of different numbers of cuts and different working depths. The data were statistically analyzed under two formats: (a) by means of conventional statistics, in which the treatment means were compared by Tukey test at 5% probability level, and (b) by geostatistical analysis, in which semivariance was used to produce models that would represent the spatial dependence of the data. The resistance to penetration results showed distinct behaviors for the studied depths, indicating that the weight of vehicles and machinery and the rotating wheel pressure caused alterations in the soil profile.
RESUMO:No presente estudo, foram elaborados modelos empíricos para determinar a força de tração demandada por arados de discos, escarificadores e semeadoras adubadoras, em função da resistência mecânica do solo à penetração. A média da referida resistência, determinou-se até as profundidades de 25; 35 e 15 cm, em correspondência com as regulagens do arado de discos, escarificador e semeadora adubadora. O ajuste foi verificado de acordo com o coeficiente de determinação, gráficos de dispersão, análise residual e teste t (Student). Com base nessas análises, confirmou-se a normalidade dos resíduos, e foram estabelecidos intervalos de confiança com 95% de probabilidade. Os valores estimados e obtidos experimentalmente não discreparam significativamente. Concluiu-se que as funções exponenciais associadas apresentaram adequada precisão e confiabilidade para predizer a força de tração, considerando-se a resistência mecânica do solo à penetração e que os modelos podem ser uma ferramenta útil para o planejamento e gestão de operações agrícolas mecanizadas em solos com textura similar às desta pesquisa.PALAVRAS-CHAVE: desempenho de máquinas, modelos empíricos, modelos não lineares. TRACTIVE DEMAND AS FUNCTION OF SOIL MECHANICAL RESISTANCE TO PENETRATIONABSTRACT: In this study, empirical models were developed to determine the tensile force demanded by disc plows, harrows and planters fertilizers, as function of soil mechanical resistance to penetration. The mean of the referred resistance was determined until 25, 35 and 15 cm depths, according to the regulations for the disc plow, springs harrow and fertilizer seeder. The adjustment was verified based on the coefficient of determination, dispersion graphics, residual analysis and t test (Student). It was confirm the normality of the residuals and to establish intervals of confidence with 95% of probability. The estimated and experimentally obtained values did not differ significantly. It was concluded that the associated exponential functions presented appropriate precision and reliability to predict the traction force being considered the soil mechanical resistance to penetration and that the models can be a useful tool for planning and management of mechanized farming operations in soils with texture similar to those of this research.KEYWORDS: machine performance; empirical models; nonlinear models. INTRODUCCIÓNPara implantar una cultura agrícola, se puede preparar el terreno convencionalmente o adoptando métodos conservacionistas. En el preparo convencional existe elevada movilización del suelo causada por arados y gradas. Por otro lado, los métodos conservacionistas tienen por finalidad disminuir el número de operaciones, como es el sistema reducido utilizándose un escarificador o aún eliminar totalmente esas actividades como es en el plantío directo, realizado solamente con una sembradora abonadora apropiada. Sin embargo, independientemente del método de preparo, para Pedro H. M. Borges, Aloísio Bianchini, João C. S. Maia et al. Eng. Agríc., Jaboticabal, v.34, n.2, p....
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
334 Leonard St
Brooklyn, NY 11211
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.