Computer Engineering and Applications ›› 2012, Vol. 48 ›› Issue (11): 229-232.

Previous Articles     Next Articles

EMD method and genetic neural network algorithm and its application to dynamic weighing system for loader

LIU Qinxian1, LV Wei2, BAO Weibing1   

  1. 1.College of Zhijiang, Zhejiang University of Technology, Hangzhou 310024, China
    2.Hangzhou Xiaoshan International Airport, Hangzhou 311207, China
  • Online:2012-04-11 Published:2012-04-16

EMD和遗传神经网络算法研究
—以装载机动态称重系统为例

刘勤贤1,吕  炜2,鲍卫兵1   

  1. 1.浙江工业大学 之江学院,杭州 310024
    2.杭州萧山国际机场,杭州 311207

Abstract: The output signal of pressure sensor installed in the dynamic weighing system for loader contains strong vibration, noise, nonlinear signal. The accuracy of the dynamic weighing system is closely related to the pressure signal. An Empirical Mode Decomposition(EMD) algorithm is proposed to preprocess the signal contaminated. The real weighing signal is filtered out. BP neural network is used to fit the nonlinear relationship between the weighing signal and the weights of the goods. The genetic algorithm is put forward to speed up the convergence. The suitable mathematical model of nonlinear measure weight is obtained. The emulation analysis and the results show that by using the above method, measure precision is efficacious.

Key words: loader, dynamic weighing system, Empirical Mode Decomposition(EMD), genetic neural network

摘要: 装载机压力传感器的输出信号是包含强振动、噪声的非线性信号,而装载机动态称重系统的测量精度与压力传感器的信号之间有极其密切的关系,采用经验模态分解对压力传感器的信号进行预处理,提取其有用称重信号,采用BP神经网络算法对称重信号与重物重量之间的非线性关系进行拟合,同时使用遗传算法加快收敛速度,得到适合的非线性测重数学模型,仿真和实验参数计算表明,该处理方法在装载机动态称重系统中的应用是有效的。

关键词: 装载机, 动态称重系统, 经验模态分解, 遗传神经网络