基于GA-BP神经网络的甘蔗收获质量预测

甘蔗联合收割机收获质量对制糖工艺有极大影响,但测量难度大,难以直接获得.针对上述问题,以甘蔗联合收割机切割机构、行走机构、切段机构、风机机构的负载压力信号和转速信号为输入变量,以含杂率和损失率为输出变量,建立了一种GA-BP神经网络预测模型.GA-BP神经网络预测模型对甘蔗收获质量的预测结果平均MSE为0.0937,平...

Sugarcane Harvest Quality Prediction Based on GA-BP Neural Network

The harvest quality of sugarcane combine harvester has great influence on sugar processing technology,but it is difficult to measure and obtain directly.Aiming at the above problems,a GA-BP neural network prediction model is established by taking the load pressure signal and rotate speed signal of the cutting mechanism,walking mechanism,chopper mechanism and fan mechanism of sugarcane combine harvester as the input variables,and the impurity rate and loss rate as the output variables.GA-BP neural network prediction model on the quality of the sugarcane harvest predicted results average MSE is 0.0937,the average R 2 is 0.8915.Compared with the BP neural network model,MSE reduced by 18.17%,the R 2 reduced by 2.59%.These resulits further illustrates prediction accuracy of the GA-BP model is better than the traditional BP neural network.This article provide a new way to measure the sugarcane harvest quality,and a theoretical basis for t-he coordinated linkage control strategy of each subsystem to improve the sugarcane harvest quality under different working conditions of the sugarcane harvester.