拖拉机作业载荷数据平台设计与旋耕作业质量预测  

Construction of Tractor Working Load Data Platform and Prediction of Rotary Tillage Quality

作　　者：温昌凯 谢斌[1,2] 李若晨 宋正河[1,2] 韩建刚 刘江辉 WEN Changkai;XIE Bin;LI Ruochen;SONG Zhenghe;HAN Jian gang;LIU Jianghui(College of Engineering,China Agricultural University,Beijing 100083,China;Beijing Key Laboratory of Optimized Design for Modern Agricultural Equipment,China Agricultural University,Beijing 100083,China;Luoyang Xiyuan Vehicle and Power Inspection Institute Co.,Ltd.,Luoyang 471000,China)

机构地区：[1]中国农业大学工学院,北京100083 [2]中国农业大学现代农业装备优化设计北京市重点实验室,北京100083 [3]洛阳西苑车辆与动力检验所有限公司,洛阳471000

出　　处：《农业机械学报》2020年第8期372-381,共10页Transactions of the Chinese Society for Agricultural Machinery

基　　金：国家重点研发计划项目(2017YFD0700300)。

摘　　要：针对拖拉机田间试验数据不足、机组作业质量无法实时评估与准确预测的问题,设计了涵盖多参数、多工况的车载测试终端,构建了全国范围的田间作业试验拖拉机作业载荷数据平台系统,以获取拖拉机各关键零部件的田间作业载荷数据。在此基础上,研究了准确预测、评价拖拉机田间旋耕作业质量的智能算法,为产品研发、性能预测以及作业评估提供全面的基础数据与可靠的预测结果。基于农业大数据,融合BP神经网络与遗传算法对数据平台基础作业载荷进行分类挖掘,预测评价了拖拉机田间旋耕作业质量,结果表明,基于遗传算法的神经网络预测精度高达96.77%,均方根误差(RMSE)小于0.01,说明拖拉机作业载荷数据平台的基于遗传算法的神经网络预测模型可准确预测评价拖拉机田间旋耕工况的作业质量。Aiming at the problems of insufficient field test data of tractors and inaccurate real-time evaluation and prediction of unit performance and agronomy,a vehicle-borne test terminal covering multi-parameters and multi-working conditions was built,and a data platform for tractor operation load was established to obtain field operation load data of key parts of tractors.Based on this platform,the field operation load data of key parts and key parts of tractors were obtained.On this basis,the intelligent algorithm for reliable real-time prediction and evaluation of tractor traction performance was studied,which provided comprehensive basic data and effective prediction algorithm for product development,performance prediction and operation evaluation.Firstly,the operation parameters and structure system of the vehicle test terminal were introduced.Then,the tractor operation load data platform based on the field operation test nationwide was designed and built.Finally,based on the large agricultural data,the BP neural network and genetic algorithm were combined to classify and mine the basic working load of the data platform.The traction performance of tractor rotary tillage was predicted and evaluated.The results showed that the prediction accuracy of the neural network based on genetic algorithm was as high as 96.77%,and the root mean square error(RMSE)was less than 0.01,which showed that the prediction accuracy of the neural network based on genetic algorithm was as high as 96.77%.Neural network algorithm based on genetic algorithm can accurately and reliably evaluate and predict traction performance of tractor rotary tillage operation.

关 键 词：拖拉机 作业载荷数据平台 作业质量 预测 

分 类 号：S24[农业科学—农业电气化与自动化] S219.1[农业科学—农业工程]