摘要
针对谷物收获时采用人工计算损失率不能实时得到谷物收获损失率的问题,在研究国内外对于谷物收获损失率计算方法的基础上,提出一种基于神经网络损失率计算方法.该方法合并4个变量为1个变量输入矩阵,采用神经网络实时计算变量输入矩阵并与真实损失率进行对比.仿真结果表明其计算精度达到工程要求.
The calculation of the loss rate at grain harvesting is manually calculated and the loss of grain harvest rate cannot be measured in real time. After the study on loss detection of grain harvest at home and abroad, this paper proposed a method based on the calculation of loss rate of neural network. With this method, the matrix was input by combining four variables into one variable. Then, neural network was used to calculate the variable input matrix in real time and compared with real loss rate. The simulation results show that the calculation accuracy and correct rate meet the engineering requirements.
作者
葛雨生
周冬冬
徐睿
GE Yu-sheng;ZHOU Dong-dong;XU Rui(School of Electric Power Engineering,Nanjing Institute of Technology,Nanjing 211167,China;School of Mechanical Engineering,Nanjing Institute of Technology,Nanjing 211167,China)
出处
《南京工程学院学报(自然科学版)》
2018年第2期57-61,共5页
Journal of Nanjing Institute of Technology(Natural Science Edition)
关键词
神经网络
变量输入矩阵
损失率计算
neural network
variable input matrix
loss rate calculation