摘要
就深松铲作业阻力及功率消耗预测问题,提出了一种基于神经网络的预测方法,建立了基于BP神经网络和径向基神经网络的两种预测模型,并对两种模型的预测误差及预测效果进行对比,最后得出,径向基函数神经网络对深松铲作业阻力及功耗的预测误差较小、预测效果较好,可以用于深松铲作业阻力及功耗的预测。
In view of sub-soiling shovel operation resistance and power consumption issue,a prediction method based on neural networks is proposed,with two prediction models based on BP neural network and radial basis function neural network established,the prediction errors and effects of the two models compared. The final conclusion is that the radial basis function neural network has smaller sub-soiling shovel operation resistance and power consumption prediction errors and better prediction effects and can be sued for prediction of operation resistance and power consumption of sub-soiling shovels.
引文
[1]齐关宇.深松铲牵引阻力及土壤扰动量研究[D].哈尔滨:东北农业大学,2015.
[2]陈明. MATLAB神经网络原理与实例精解[M].北京:清华大学出版社,2017.
[3]张璐.深松铲减阻技术研究[D].长春:吉林大学,2013.
[4]王志强. GA-BP柴油机NOx排放预测模型的建立及实船应用研究[D].大连:大连海事大学,2014.
[5]白利波.基于BP神经网络的船用柴油机NOx排放特性预测[D].大连:大连海事大学,2010.
[6]张连滨,葛浙东,鞠明远,等.改进型神经网络在木件打磨机器人中的应用[J].林业机械与木工设备,2017,45(4):19-22.
[7]牟洪波,王世伟,戚大伟,等.基于灰度共生矩阵和模糊BP神经网络的木材缺陷识别[J].森林工程,2017,33(4):40-43.