BP神经网络信息融合的汽车载重测量方案  

Carload Measuring Project Based on BP Neural Network Information Fusion

作　　者：赵桂清[1] 

机构地区：[1]聊城大学东昌学院,山东聊城252000

出　　处：《机械设计与制造》2017年第12期134-137,共4页Machinery Design & Manufacture

基　　金：山东省高等学校科技计划项目(J15LN77)

摘　　要：针对当前汽车载重量测量精度低的问题,;提出了基于BP神经网络信息融合算法的汽车载重测量方案。首先分析了现有的两种载重测量方法,即叠板弹簧形变量测量法和胎压变化量测量法,并分别建立了汽车载重量与叠板弹簧变化量、轮胎气压变化量的数学模型;然后提出了使用BP神经网络算法将这两种测量方法的测量信息进行融合;通过样本数据的训练,确立了BP神经网络三层网络拓扑结构和参数。设计了10组载重试验对此算法进行验证,结果表明基于BP神经网络信息融合的汽车载重测量方法可以有效地测量汽车载重,最大测量误差为0.91%。A imed at solving the problem of low measuring accuracy of carload, this paper proposes a measuring method based on BP neural network information fusion. Two existing methods, spring deformation measurement and tire pressure measurement, are analyzed. Mathematical model between carload and spring defomation, tire pressure is set up respectively. BP neural network algorithm is put forward to fuse the two existing methods. Through the training of sample data, structure and parameter of neural network is established. Carlaod experiment is designed to verify the BP neural network information fusion algorithm. The results show that the algorithm designed in this paper can measure carload validly, and maximum measurement error is 0.91%.

关 键 词：汽车载重测量 BP神经网络 信息融合 胎压 叠板弹簧形变 

分 类 号：TH16[机械工程—机械制造及自动化] U491[交通运输工程—交通运输规划与管理]