基于小波和BP神经网络的车载动态称重算法  

Vehicle Dynamic Weighing Algorithm Based on Wavelet and BP Neural Network

作　　者：郝晓娴 牛昱光[1] 韩芝星 蔡晓龙[3] 

机构地区：[1]太原理工大学信息工程学院,山西太原030024 [2]山西职业技术学院电气工程与自动化系,山西太原030006 [3]国网山西省电力公司检修公司,山西太原030032

出　　处：《仪表技术与传感器》2017年第8期110-113,121,共5页Instrument Technique and Sensor

摘　　要：针对车载动态称重系统测量精度较低问题,提出了基于小波和BP神经网络的车载动态称重算法。首先利用小波变换对车载称重信号进行噪声滤波预处理,然后将车辆速度信号、加速度信号和小波预处理之后的车载称重信号作为BP神经网络输入层构建网络模型,使车载动态称重误差控制在2%以内,满足车载动态称重精度要求。研究结果表明,该模型预测精度高、实用性强。Aiming at the problem that the measurement accuracy of on-board dynamic weighting system is low, vehicle dy- namic weighting algorithm was proposed based on wavelet and BP neural network. Firstly, the wavelet transform was used to pre- process noise of vehicle weighing signal.Then ,the vehicle speed signal, acceleration signal, and vehicle weighing signal were used as the input layers of BP neural network to build network model to make the vehicle dynamic weighing error less than 2% and meet the demand of vehicle weighing.The results showed that the model has high precision and strong practicability.

关 键 词：车载动态称重 小波变换 BP神经网络 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]