Optimization of Operation Parameters and Performance Prediction of Paddy Field Grader Based on a GA-BP Neural Network

Abstract

Paddy field leveling is an essential step before rice transplanting. During the operation of a paddy field grader, a common issue is the wrapping of rice straw around the blades, resulting in a low rice straw burial rate. This study focused on analyzing the operating parameters of a disc spring–tooth-combined paddy field grader. A soil–straw mechanism simulation model was created using EDEM 2021 software to simulate the field operation status. Firstly, the single-factor test was carried out, with the working speed, the working depth of the disc cutter roller, and the rotation speed of the cutter roller as the factors and the straw-buried rate (SBR) and the machine forward resistance (MFR) as the test indexes, and the parameter range was optimized. The parameters were optimized by the response surface method (RSM) and machine learning algorithms. The results indicated that the genetic algorithm–back propagation (GA-BP) neural network outperformed other optimization models in terms of prediction accuracy and stability. By utilizing the GA-BP regression model and RSM model for regression fitting, two sets of optimal parameter combinations were obtained. Verification experiments were carried out using two sets of parameter combinations. Taking the average of the experimental results, the simulation results showed that the straw burial rate was 93.47% and the forward resistance was 6487 N for the parameter combinations of RSM, and the straw burial rate was 94.86% and the forward resistance was 6352 N for the parameter combinations of GA-BP; the field experiments showed that the straw burial rate was 92.86% and the forward resistance was 6518 N for the parameter combinations of RSM, and the straw burial rate was 95.17% and the forward resistance was 6249 N for the parameter combinations of GA-BP. The results demonstrated that the GA-BP prediction model exhibited better predictive capabilities compared to the traditional RSM, providing more accurate predictions of the paddy field grader’s field operation performance.