Study on punch length of spade soil opener based on neural network

In this paper, on the basis of analyzing construction characteristics and working procedure of a spade soil opener, the profile of formed hole was obtained by investigating the moving traces of the two endpoints of spade since that only these two points of the spade played the determinant roles during the hole forming within the soil and theoretical formula for calculating the length of the formed soil holes were developed. Then according to quadratic general revolving experiment design for the punch length, a data processing method based on Back Propagation (BP) neural network has been introduced to take better advantage of experimental information. The results showed that the deviation of the fitted value of BP neural network was less than that of the regression model. So a new analysis method was provided for the experimental study of the punch quality of the spade soil opener. The study provided bases for the design of the revolving spade soil opener on precision sowing machinery and for the widely application of BP neural network.